From ce7019345c0c5d7a071d9b7d5a94e1b19056080e Mon Sep 17 00:00:00 2001
From: Lu Nelson <ln@hash.ai>
Date: Wed, 26 Aug 2026 15:43:15 +0200
Subject: [PATCH 1/9] Scope plugin patterns to failing slots

Optional slot predicates keep kind-indexed prompts live only for the missing fact they address, while load-time checks reject predicates outside the plugin contract.

Co-authored-by: Cursor <cursoragent@cursor.com>
---
 .../packages/core/schema/CHANGELOG.md         |  7 ++++
 .../packages/core/schema/plugin.schema.json   |  4 +++
 .../brunch-agent/packages/core/src/cue.ts     | 10 +++++-
 .../packages/core/src/plugin-definition.ts    | 24 ++++++++++++-
 .../packages/core/test/cue.test.ts            | 13 +++++++
 .../core/test/plugin-definition.test.ts       | 36 +++++++++++++++++++
 .../packages/core/test/slot-fixtures.ts       |  2 +-
 .../packages/plugin-gherkin/plugin.yaml       |  4 ++-
 .../packages/plugin-sdcpn/plugin.yaml         |  4 ++-
 .../packages/plugin-sdcpn/test/plugin.test.ts |  2 +-
 10 files changed, 100 insertions(+), 6 deletions(-)

diff --git a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
index f505e8fa76d..c0043d9bede 100644
--- a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
+++ b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
@@ -151,3 +151,10 @@ written against.
 - `movements` fixed to `{slice, sweep}` — every formalism examined fits the
   pair; a single-walkthrough formalism would leave `sweep` empty, which the
   schema allows for plugins.
+
+## Cycle 2 — implementation, 2026-08-26
+
+- Added optional `patterns.items[*].slot`. The reader rejects a slot that an
+  explicitly indexed kind does not demand; the cue surfaces a slot-scoped
+  pattern only for a failure on that slot. SDCPN P01/P02 and Gherkin P01/P03
+  now declare the predicates identified by the cycle-1 pressure review.
diff --git a/libs/@hashintel/brunch-agent/packages/core/schema/plugin.schema.json b/libs/@hashintel/brunch-agent/packages/core/schema/plugin.schema.json
index 8e062817933..ec346959a22 100644
--- a/libs/@hashintel/brunch-agent/packages/core/schema/plugin.schema.json
+++ b/libs/@hashintel/brunch-agent/packages/core/schema/plugin.schema.json
@@ -246,6 +246,10 @@
                   "minLength": 1
                 }
               },
+              "slot": {
+                "type": "string",
+                "minLength": 1
+              },
               "when": {
                 "type": "string",
                 "minLength": 1
diff --git a/libs/@hashintel/brunch-agent/packages/core/src/cue.ts b/libs/@hashintel/brunch-agent/packages/core/src/cue.ts
index 07e073a29b3..3d555127051 100644
--- a/libs/@hashintel/brunch-agent/packages/core/src/cue.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/src/cue.ts
@@ -38,7 +38,15 @@ export const buildSweepList = (
   for (const node of model.nodes) {
     if (!failingNodeIds.has(node.id)) continue;
     for (const pattern of patterns) {
-      if (pattern.kinds.length === 0 || pattern.kinds.includes(node.kind)) {
+      const kindMatches =
+        pattern.kinds.length === 0 || pattern.kinds.includes(node.kind);
+      const slotMatches =
+        pattern.slot === undefined ||
+        report.failures.some(
+          (failure) =>
+            failure.nodeId === node.id && failure.slot === pattern.slot,
+        );
+      if (kindMatches && slotMatches) {
         cues.push({ id: pattern.id, nodeId: node.id, ask: pattern.ask });
       }
     }
diff --git a/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts b/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
index dcd26555a53..385c3d97a25 100644
--- a/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
@@ -81,6 +81,8 @@ export interface PatternRow {
   readonly ask: string;
   /** The kinds whose nodes can trigger it; empty means any node. */
   readonly kinds: readonly string[];
+  /** When present, the pattern applies only while this demanded slot fails. */
+  readonly slot?: string;
 }
 
 /** The completion anchor, declared: the kind whose dependency slot is the slice. */
@@ -265,6 +267,7 @@ export const PluginDefinitionSchema = v.strictObject({
       v.strictObject({
         id: v.pipe(v.string(), v.regex(/^P\d{2}$/u)),
         on: v.array(text),
+        slot: v.optional(text),
         when: text,
         ask: text,
       }),
@@ -395,7 +398,26 @@ export function readPluginDefinition(yamlText: string): PluginDefinition {
   }
   const patterns: PatternRow[] = input.patterns.items.map((row) => {
     for (const kind of row.on) knownKind(kind, `pattern ${row.id}`);
-    return { id: row.id, when: row.when, ask: row.ask, kinds: row.on };
+    if (row.slot !== undefined) {
+      const kindWithoutSlot = row.on.find(
+        (kind) =>
+          !mustKnow.some(
+            (demand) => demand.kind === kind && demand.slot === row.slot,
+          ),
+      );
+      if (kindWithoutSlot !== undefined) {
+        fail(
+          `pattern ${row.id} names slot \`${row.slot}\`, which \`${kindWithoutSlot}\` does not demand`,
+        );
+      }
+    }
+    return {
+      id: row.id,
+      when: row.when,
+      ask: row.ask,
+      kinds: row.on,
+      ...(row.slot === undefined ? {} : { slot: row.slot }),
+    };
   });
 
   const jobs = input.plugin.jobs;
diff --git a/libs/@hashintel/brunch-agent/packages/core/test/cue.test.ts b/libs/@hashintel/brunch-agent/packages/core/test/cue.test.ts
index 79b0978d080..19df700239c 100644
--- a/libs/@hashintel/brunch-agent/packages/core/test/cue.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/test/cue.test.ts
@@ -50,6 +50,19 @@ describe("the sweep list", () => {
     ]);
   });
 
+  test("a slot-scoped pattern does not fire for another failure on the same node", () => {
+    const model = foldElicitedModel(
+      snapshotOf(completeCaptures().filter((c) => c.id !== "c-stamp-actor")),
+      definition,
+    );
+    const report = evaluateCompletion(model, demands);
+    const list = buildSweepList(model, report, definition.patterns);
+    expect(list.unsatisfied.map((failure) => failure.slot)).toEqual([
+      "who performs it",
+    ]);
+    expect(list.patterns.map((cue) => cue.id)).toEqual(["P03"]);
+  });
+
   test("surfaces nothing for a complete model", () => {
     const model = foldElicitedModel(snapshotOf(completeCaptures()), definition);
     const list = buildSweepList(
diff --git a/libs/@hashintel/brunch-agent/packages/core/test/plugin-definition.test.ts b/libs/@hashintel/brunch-agent/packages/core/test/plugin-definition.test.ts
index 81b6ab99883..50952d86e45 100644
--- a/libs/@hashintel/brunch-agent/packages/core/test/plugin-definition.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/test/plugin-definition.test.ts
@@ -78,6 +78,13 @@ describe("the synthetic fixture definition", () => {
     ]);
   });
 
+  test("reads a pattern predicate on one of its kinds' demanded slots", () => {
+    expect(definition.patterns[0]).toMatchObject({
+      id: "P01",
+      slot: "how long it takes",
+    });
+  });
+
   test("flattens guidance and runbook cells with their key paths", () => {
     expect(
       guidanceEntries(definition.guidance).map((entry) => entry.path),
@@ -144,6 +151,14 @@ describe("contract violations fail to load", () => {
       FIXTURE_PLUGIN_YAML.replace("on: [step]", "on: [queue]"),
       /pattern P01 names kind `queue`/u,
     ],
+    [
+      "a pattern predicate on a slot its kind does not demand",
+      FIXTURE_PLUGIN_YAML.replace(
+        "on: [step], slot: how long it takes",
+        "on: [step], slot: queue capacity",
+      ),
+      /pattern P01 names slot `queue capacity`, which `step` does not demand/u,
+    ],
     [
       "a runbook for an undeclared job",
       FIXTURE_PLUGIN_YAML.replace(
@@ -213,4 +228,25 @@ describe.skipIf(!contextRootPresent)("the shipped plugin definitions", () => {
     expect(sdcpn.anchor.kind).not.toBe(gherkin.anchor.kind);
     expect(sdcpn.proposals.map((p) => p.type)).toEqual(["slot-asserted"]);
   });
+
+  test("ambiguous kind-indexed patterns declare the slot that keeps them live", () => {
+    const sdcpn = readShipped("plugin-sdcpn");
+    const gherkin = readShipped("plugin-gherkin");
+    expect(
+      sdcpn.patterns
+        .filter((pattern) => ["P01", "P02"].includes(pattern.id))
+        .map((pattern) => [pattern.id, pattern.slot]),
+    ).toEqual([
+      ["P01", "how often it occurs, if it is an event rather than a step"],
+      ["P02", "what is lost when it changes the system's mode"],
+    ]);
+    expect(
+      gherkin.patterns
+        .filter((pattern) => ["P01", "P03"].includes(pattern.id))
+        .map((pattern) => [pattern.id, pattern.slot]),
+    ).toEqual([
+      ["P01", "the examples that illustrate it"],
+      ["P03", "the observable outcome"],
+    ]);
+  });
 });
diff --git a/libs/@hashintel/brunch-agent/packages/core/test/slot-fixtures.ts b/libs/@hashintel/brunch-agent/packages/core/test/slot-fixtures.ts
index 64925ed5892..39c5f4b170a 100644
--- a/libs/@hashintel/brunch-agent/packages/core/test/slot-fixtures.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/test/slot-fixtures.ts
@@ -61,7 +61,7 @@ schema:
 patterns:
   preamble: Patterns fire on nodes.
   items:
-    - { id: P01, on: [step], when: a step is an event, ask: ask how often }
+    - { id: P01, on: [step], slot: how long it takes, when: a step is an event, ask: ask how often }
     - { id: P02, on: [thing], when: more than one thing competes, ask: ask which wins }
     - { id: P03, on: [], when: the expert says they do not know, ask: ask for a source }
 
diff --git a/libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml b/libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml
index fb7ffdbb545..a775500e984 100644
--- a/libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml
+++ b/libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml
@@ -10,7 +10,7 @@
 
 plugin:
   id: gherkin
-  version: gherkin/2026-08-25.1
+  version: gherkin/2026-08-26.1
   formalism: Gherkin — executable specifications as features, rules, and examples
   jobs: [construct, review-and-revise]
   purpose: |
@@ -125,6 +125,7 @@ patterns:
   items:
     - id: P01
       on: [rule]
+      slot: the examples that illustrate it
       when: a rule has a statement but no example.
       ask: Ask for the last time this rule mattered — what was the situation, what happened, what was seen.
     - id: P02
@@ -133,6 +134,7 @@ patterns:
       ask: Ask what distinguishes the two situations; the difference is a missing part of the context or a missing rule.
     - id: P03
       on: [example]
+      slot: the observable outcome
       when: an outcome is stated as an intention ("should work", "is handled") rather than something observable.
       ask: Ask what someone watching would see, and where.
     - id: P04
diff --git a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml
index c8db0f5338b..ffd6fa48590 100644
--- a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml
+++ b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml
@@ -13,7 +13,7 @@
 
 plugin:
   id: sdcpn
-  version: sdcpn/2026-08-25.2
+  version: sdcpn/2026-08-26.1
   formalism: stochastic dynamic coloured Petri nets (Petrinaut)
   jobs: [construct, review-and-revise]
   purpose: |
@@ -257,6 +257,7 @@ patterns:
   items:
     - id: P01
       on: [activity]
+      slot: "how often it occurs, if it is an event rather than a step"
       when: >-
         an `activity` is an event that can befall the system — a failure, an interruption, an
         unplanned arrival — rather than a step in the flow
@@ -266,6 +267,7 @@ patterns:
         round a range up to a spread.
     - id: P02
       on: [activity]
+      slot: "what is lost when it changes the system's mode"
       when: >-
         an `activity` changes the system's mode — a setup, changeover, restart, warm-up,
         reconfiguration, handover
diff --git a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/test/plugin.test.ts b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/test/plugin.test.ts
index e591f4094d5..970a42c1140 100644
--- a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/test/plugin.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/test/plugin.test.ts
@@ -70,7 +70,7 @@ describe("the SDCPN plugin", () => {
   test("is the parsed file plus one slot-assertion proposal type", () => {
     expect(sdcpn.targetFormalism).toBe("sdcpn");
     expect(sdcpn.definition).toBe(sdcpnDefinition);
-    expect(sdcpnDefinition.version).toBe("sdcpn/2026-08-25.2");
+    expect(sdcpnDefinition.version).toBe("sdcpn/2026-08-26.1");
     expect(sdcpn.proposalCatalog.map((proposal) => proposal.name)).toEqual([
       "slot-asserted",
     ]);

From d7e72cd6e688a0beb57cb03030ffc66fe247af62 Mon Sep 17 00:00:00 2001
From: Lu Nelson <ln@hash.ai>
Date: Wed, 26 Aug 2026 15:47:26 +0200
Subject: [PATCH 2/9] Validate wildcard pattern slots

Reject dead predicates that no plugin kind can demand and resolve review findings in the adjacent tests.

Co-authored-by: Cursor <cursoragent@cursor.com>
---
 .../packages/core/src/plugin-definition.ts             |  8 ++++++++
 .../brunch-agent/packages/core/test/cue.test.ts        |  4 +++-
 .../packages/core/test/plugin-definition.test.ts       | 10 +++++++++-
 3 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts b/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
index 385c3d97a25..9948c374d6a 100644
--- a/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
@@ -399,6 +399,14 @@ export function readPluginDefinition(yamlText: string): PluginDefinition {
   const patterns: PatternRow[] = input.patterns.items.map((row) => {
     for (const kind of row.on) knownKind(kind, `pattern ${row.id}`);
     if (row.slot !== undefined) {
+      if (
+        row.on.length === 0 &&
+        !mustKnow.some((demand) => demand.slot === row.slot)
+      ) {
+        fail(
+          `pattern ${row.id} names slot \`${row.slot}\`, which no kind demands`,
+        );
+      }
       const kindWithoutSlot = row.on.find(
         (kind) =>
           !mustKnow.some(
diff --git a/libs/@hashintel/brunch-agent/packages/core/test/cue.test.ts b/libs/@hashintel/brunch-agent/packages/core/test/cue.test.ts
index 19df700239c..8f4e554819b 100644
--- a/libs/@hashintel/brunch-agent/packages/core/test/cue.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/test/cue.test.ts
@@ -52,7 +52,9 @@ describe("the sweep list", () => {
 
   test("a slot-scoped pattern does not fire for another failure on the same node", () => {
     const model = foldElicitedModel(
-      snapshotOf(completeCaptures().filter((c) => c.id !== "c-stamp-actor")),
+      snapshotOf(
+        completeCaptures().filter((capture) => capture.id !== "c-stamp-actor"),
+      ),
       definition,
     );
     const report = evaluateCompletion(model, demands);
diff --git a/libs/@hashintel/brunch-agent/packages/core/test/plugin-definition.test.ts b/libs/@hashintel/brunch-agent/packages/core/test/plugin-definition.test.ts
index 50952d86e45..8b432272115 100644
--- a/libs/@hashintel/brunch-agent/packages/core/test/plugin-definition.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/test/plugin-definition.test.ts
@@ -79,7 +79,7 @@ describe("the synthetic fixture definition", () => {
   });
 
   test("reads a pattern predicate on one of its kinds' demanded slots", () => {
-    expect(definition.patterns[0]).toMatchObject({
+    expect(definition.patterns.at(0)).toMatchObject({
       id: "P01",
       slot: "how long it takes",
     });
@@ -159,6 +159,14 @@ describe("contract violations fail to load", () => {
       ),
       /pattern P01 names slot `queue capacity`, which `step` does not demand/u,
     ],
+    [
+      "a wildcard pattern predicate on a slot no kind demands",
+      FIXTURE_PLUGIN_YAML.replace(
+        "id: P03, on: [], when:",
+        "id: P03, on: [], slot: queue capacity, when:",
+      ),
+      /pattern P03 names slot `queue capacity`, which no kind demands/u,
+    ],
     [
       "a runbook for an undeclared job",
       FIXTURE_PLUGIN_YAML.replace(

From 1740fde8e0efde19ecefba80b40eaffc36e44af1 Mon Sep 17 00:00:00 2001
From: Lu Nelson <ln@hash.ai>
Date: Wed, 26 Aug 2026 16:28:26 +0200
Subject: [PATCH 3/9] Accept alternative plugin precision demands

One semantic slot can now accept either a numeric grade or a spelled-out structure, preserving calendars and qualitative objective rules without duplicate rows.

Co-authored-by: Cursor <cursoragent@cursor.com>
---
 .../docs/specs/plugin-contract.md             | 13 +++---
 .../packages/core/schema/CHANGELOG.md         |  6 +++
 .../packages/core/schema/plugin.schema.json   | 14 ++++++
 .../packages/core/src/completion.ts           | 23 ++++++++--
 .../packages/core/src/instructions.ts         | 12 ++++-
 .../packages/core/src/plugin-definition.ts    | 18 +++++---
 .../packages/core/test/completion.test.ts     | 45 +++++++++++++++++++
 .../packages/core/test/instructions.test.ts   | 12 +++++
 .../core/test/plugin-definition.test.ts       | 40 +++++++++++++++++
 .../packages/plugin-sdcpn/plugin.yaml         |  4 +-
 10 files changed, 169 insertions(+), 18 deletions(-)

diff --git a/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md b/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md
index c6848777f36..957fe42165a 100644
--- a/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md
+++ b/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md
@@ -68,21 +68,24 @@ Shapes are fixed by the schema; the exemplars are normative for value vocabulari
 | `ontology.attributes` | `name`, `on`, `values?`, `text`                                          | cross-kind attributes (`quantity`, `source-regime`, `rationale`, `status`); a plugin may not scope them to some kinds |
 | `schema.anchor`     | `kind`, `depends_on`                                                       | the completion anchor, declared: the kind whose named slot is the dependency slice (was `objective` by convention) |
 | `schema.floor`      | `kind`, `at_least`                                                         | the static floor as counts                                                                                       |
-| `schema.must_know`  | `kind`, `slot`, `precision`, `not_applicable`, `why`                       | one demand row per (kind, slot); `precision` is a harness precision word or `at least N`                          |
+| `schema.must_know`  | `kind`, `slot`, `precision`, `not_applicable`, `why`                       | one demand row per (kind, slot); `precision` is one harness precision word, a non-empty any-of list, or `at least N` |
 | `schema.proposals`  | `type`, `payload`                                                          | the proposal types the plugin's code declares (`slot-asserted`/`slot-assertion` for a kind-and-slot plugin)        |
-| `patterns.items`    | `id`, `on`, `when`, `ask`                                                  | discretionary interviewing patterns indexed by the kinds in `on`; surfaced when a node matches and a slot is unsatisfied |
+| `patterns.items`    | `id`, `on`, `slot?`, `when`, `ask`                                         | discretionary interviewing patterns indexed by the kinds in `on`; a slot-scoped pattern surfaces only while that slot is unsatisfied |
 
 Rules the reader enforces beyond the schema:
 
 - Every `must_know` row names a kind present in `kinds`; every kind has at least one row.
 - The anchor's `depends_on` is a `must_know` row on the anchor kind demanding `at least N`.
 - `precision` is harness vocabulary (`named`, `number`, `range`, `spread`, `spelled out`,
-  `at least N`; `PRECISION_LADDER` in core), rendered for every plugin. Grade means narrowing of
-  interpretation space, never claim strength. A plugin no longer declares its own precision table.
+  `at least N`; `PRECISION_LADDER` in core), rendered for every plugin. A non-empty list accepts
+  any listed word for one semantic slot. Grade means narrowing of interpretation space, never
+  claim strength. A plugin no longer declares its own precision table.
 - The completion rule itself is fixed by [`elicitation-completion.md`](elicitation-completion.md);
   the plugin supplies only the floor and the anchor.
 - Runbooks may be given only for jobs the identity block declares.
-- Patterns are never mandates. The harness surfaces; the interviewer decides.
+- A pattern's optional `slot` must be demanded by every explicitly indexed kind, or by at least
+  one kind when `on` is empty. Patterns are never mandates. The harness surfaces; the interviewer
+  decides.
 
 ## Version binding
 
diff --git a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
index c0043d9bede..d54abb1ea89 100644
--- a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
+++ b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
@@ -158,3 +158,9 @@ written against.
   explicitly indexed kind does not demand; the cue surfaces a slot-scoped
   pattern only for a failure on that slot. SDCPN P01/P02 and Gherkin P01/P03
   now declare the predicates identified by the cycle-1 pressure review.
+- Extended `schema.must_know[*].precision` to accept a non-empty list of
+  alternative precision words. Completion accepts a value that satisfies any
+  listed word and renders the alternatives explicitly. SDCPN's objective
+  metric accepts `range` or `spelled out`; its arrival pattern accepts `spread`
+  or `spelled out`, covering numeric distributions and structural rules without
+  splitting either semantic slot.
diff --git a/libs/@hashintel/brunch-agent/packages/core/schema/plugin.schema.json b/libs/@hashintel/brunch-agent/packages/core/schema/plugin.schema.json
index ec346959a22..eb09fcc881d 100644
--- a/libs/@hashintel/brunch-agent/packages/core/schema/plugin.schema.json
+++ b/libs/@hashintel/brunch-agent/packages/core/schema/plugin.schema.json
@@ -181,6 +181,20 @@
                     ],
                     "type": "string"
                   },
+                  {
+                    "type": "array",
+                    "items": {
+                      "enum": [
+                        "named",
+                        "number",
+                        "range",
+                        "spread",
+                        "spelled out"
+                      ],
+                      "type": "string"
+                    },
+                    "minItems": 1
+                  },
                   {
                     "type": "string",
                     "pattern": "^at least [1-9]\\d*$"
diff --git a/libs/@hashintel/brunch-agent/packages/core/src/completion.ts b/libs/@hashintel/brunch-agent/packages/core/src/completion.ts
index 2e882d62557..82a304b6b37 100644
--- a/libs/@hashintel/brunch-agent/packages/core/src/completion.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/src/completion.ts
@@ -141,8 +141,16 @@ export const precisionSatisfies = (
   return LADDER[given]! >= LADDER[demanded]!;
 };
 
-const describeDemand = (precision: PrecisionDemand): string =>
-  precision.kind === "word" ? precision.word : `at least ${precision.count}`;
+const describeDemand = (precision: PrecisionDemand): string => {
+  switch (precision.kind) {
+    case "word":
+      return precision.word;
+    case "any-of":
+      return precision.words.join(" or ");
+    case "at-least":
+      return `at least ${precision.count}`;
+  }
+};
 
 const isEmptySelection = (value: JsonValue): boolean =>
   value === null ||
@@ -251,10 +259,17 @@ const evaluateRow = (
           `"${row.slot}" on ${node.id} lists ${count}; at least ${row.precision.count} needed.`,
         );
   }
-  if (!precisionSatisfies(slot.precision, row.precision.word)) {
+  const demandedWords =
+    row.precision.kind === "word" ? [row.precision.word] : row.precision.words;
+  if (
+    !demandedWords.some((demanded) =>
+      precisionSatisfies(slot.precision, demanded),
+    )
+  ) {
+    const requirement = describeDemand(row.precision);
     return fail(
       "below-required-precision",
-      `"${row.slot}" on ${node.id} is known as a ${slot.precision}; the model needs ${row.precision.word}. Smallest delta: move it from ${slot.precision} to ${row.precision.word}.`,
+      `"${row.slot}" on ${node.id} is known as a ${slot.precision}; the model needs ${requirement}. Smallest delta: move it from ${slot.precision} to ${row.precision.kind === "word" ? row.precision.word : `one of ${requirement}`}.`,
     );
   }
   return null;
diff --git a/libs/@hashintel/brunch-agent/packages/core/src/instructions.ts b/libs/@hashintel/brunch-agent/packages/core/src/instructions.ts
index 1c132859ac5..551be1bc22c 100644
--- a/libs/@hashintel/brunch-agent/packages/core/src/instructions.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/src/instructions.ts
@@ -47,8 +47,16 @@ const renderItems = (items: readonly GuidanceItem[]): string[] =>
     return `- **${item.name}** — ${item.text.trim()}${signature}`;
   });
 
-const renderDemand = (demand: PrecisionDemand): string =>
-  demand.kind === "word" ? demand.word : `at least ${demand.count}`;
+const renderDemand = (demand: PrecisionDemand): string => {
+  switch (demand.kind) {
+    case "word":
+      return demand.word;
+    case "any-of":
+      return demand.words.join(" or ");
+    case "at-least":
+      return `at least ${demand.count}`;
+  }
+};
 
 const paragraphs = (...parts: (string | undefined)[]): string[] =>
   parts.flatMap((part) =>
diff --git a/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts b/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
index 9948c374d6a..5a5a63fbc67 100644
--- a/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
@@ -37,9 +37,10 @@ export const PRECISION_WORDS = [
 ] as const;
 export type PrecisionWord = (typeof PRECISION_WORDS)[number];
 
-/** What a row demands: a precision word, or a count of nodes present. */
+/** What a row demands: one or more alternative precision words, or a node count. */
 export type PrecisionDemand =
   | { readonly kind: "word"; readonly word: PrecisionWord }
+  | { readonly kind: "any-of"; readonly words: readonly PrecisionWord[] }
   | { readonly kind: "at-least"; readonly count: number };
 
 /** What each precision word means; harness vocabulary, rendered for every plugin. */
@@ -177,8 +178,10 @@ const version = v.pipe(
     "expected `<id>/<yyyy-mm-dd>.<n>`",
   ),
 );
+const precisionWord = v.picklist(PRECISION_WORDS);
 const precision = v.union([
-  v.picklist(PRECISION_WORDS),
+  precisionWord,
+  v.pipe(v.array(precisionWord), v.minLength(1)),
   v.pipe(v.string(), v.regex(/^at least [1-9]\d*$/u)),
 ]);
 
@@ -288,12 +291,17 @@ export type PluginDefinitionInput = v.InferInput<typeof PluginDefinitionSchema>;
 
 // ── The reader ──────────────────────────────────────────────────────────────
 
-const parsePrecision = (word: string): PrecisionDemand => {
-  const atLeast = /^at least (\d+)$/u.exec(word);
+const parsePrecision = (
+  input: v.InferOutput<typeof precision>,
+): PrecisionDemand => {
+  if (Array.isArray(input)) {
+    return { kind: "any-of", words: input };
+  }
+  const atLeast = /^at least (\d+)$/u.exec(input);
   if (atLeast?.[1] !== undefined) {
     return { kind: "at-least", count: Number(atLeast[1]) };
   }
-  return { kind: "word", word: word as PrecisionWord };
+  return { kind: "word", word: input as PrecisionWord };
 };
 
 const fail = (message: string): never => {
diff --git a/libs/@hashintel/brunch-agent/packages/core/test/completion.test.ts b/libs/@hashintel/brunch-agent/packages/core/test/completion.test.ts
index 1d64a425a57..2e82204cc97 100644
--- a/libs/@hashintel/brunch-agent/packages/core/test/completion.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/test/completion.test.ts
@@ -15,7 +15,9 @@ import {
   type CompletionDemands,
 } from "../src/completion";
 import { foldElicitedModel, type ElicitedModel } from "../src/elicited-model";
+import { readPluginDefinition } from "../src/plugin-definition";
 import {
+  FIXTURE_PLUGIN_YAML,
   absence,
   assertionCapture,
   completeCaptures,
@@ -337,6 +339,49 @@ describe("what counts as a value (8–14)", () => {
     expect(precisionSatisfies("spelled out", "named")).toBe(true);
   });
 
+  test("12. any listed precision satisfies one semantic slot", () => {
+    const anyOfDefinition = readPluginDefinition(
+      FIXTURE_PLUGIN_YAML.replace(
+        "precision: spread",
+        "precision: [spread, spelled out]",
+      ),
+    );
+    const anyOfDemands = completionDemands(anyOfDefinition);
+    const reportAt = (precision: "range" | "spread" | "spelled out") =>
+      evaluateCompletion(
+        foldElicitedModel(
+          snapshotOf(
+            replacing(
+              "c-stamp-duration",
+              assertionCapture(
+                "c-stamp-duration",
+                value(
+                  "step",
+                  "stamp",
+                  "how long it takes",
+                  precision,
+                  precision === "spelled out"
+                    ? { calendar: "weekday shift" }
+                    : { low: 2, high: 5 },
+                ),
+              ),
+            ),
+          ),
+          anyOfDefinition,
+        ),
+        anyOfDemands,
+      );
+
+    expect(reportAt("spread").complete).toBe(true);
+    expect(reportAt("spelled out").complete).toBe(true);
+    expect(reportAt("range").failures).toEqual([
+      expect.objectContaining({
+        diagnostic: "below-required-precision",
+        requirement: "spread or spelled out",
+      }),
+    ]);
+  });
+
   test("13. conflict and divergence fail conservatively", () => {
     expect(
       diagnosticsOf([
diff --git a/libs/@hashintel/brunch-agent/packages/core/test/instructions.test.ts b/libs/@hashintel/brunch-agent/packages/core/test/instructions.test.ts
index 42330cfe9b5..94efe95019c 100644
--- a/libs/@hashintel/brunch-agent/packages/core/test/instructions.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/test/instructions.test.ts
@@ -169,6 +169,18 @@ describe("renderInstructions", () => {
     expect(rendered).not.toContain("objective-relative");
   });
 
+  test("renders alternative demanded precisions as any-of", () => {
+    const withAlternatives = readPluginDefinition(
+      FIXTURE_PLUGIN_YAML.replace(
+        "precision: spread",
+        "precision: [spread, spelled out]",
+      ),
+    );
+    expect(renderInstructions(repertoire, withAlternatives)).toContain(
+      "how long it takes — spread or spelled out",
+    );
+  });
+
   test("contains no template residue", () => {
     expect(text).not.toMatch(/\$\{|undefined|\[object Object\]/u);
   });
diff --git a/libs/@hashintel/brunch-agent/packages/core/test/plugin-definition.test.ts b/libs/@hashintel/brunch-agent/packages/core/test/plugin-definition.test.ts
index 8b432272115..dd95a90349b 100644
--- a/libs/@hashintel/brunch-agent/packages/core/test/plugin-definition.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/test/plugin-definition.test.ts
@@ -58,6 +58,23 @@ describe("the synthetic fixture definition", () => {
     );
   });
 
+  test("reads a list of alternative demanded precision words", () => {
+    const withAlternatives = readPluginDefinition(
+      FIXTURE_PLUGIN_YAML.replace(
+        "precision: spread",
+        "precision: [spread, spelled out]",
+      ),
+    );
+    expect(
+      mustKnowRowsFor(withAlternatives, "step").find(
+        (row) => row.slot === "how long it takes",
+      )?.precision,
+    ).toEqual({
+      kind: "any-of",
+      words: ["spread", "spelled out"],
+    });
+  });
+
   test("reads the anchor as a declaration, not a convention", () => {
     expect(definition.anchor).toEqual({
       kind: "objective",
@@ -237,6 +254,29 @@ describe.skipIf(!contextRootPresent)("the shipped plugin definitions", () => {
     expect(sdcpn.proposals.map((p) => p.type)).toEqual(["slot-asserted"]);
   });
 
+  test("SDCPN accepts structural alternatives to numeric precision where the slot permits either", () => {
+    const sdcpn = readShipped("plugin-sdcpn");
+    expect(
+      sdcpn.mustKnow
+        .filter((row) =>
+          [
+            'what "better" means, and trade-off weights',
+            "the arrival or availability pattern",
+          ].includes(row.slot),
+        )
+        .map((row) => [row.slot, row.precision]),
+    ).toEqual([
+      [
+        'what "better" means, and trade-off weights',
+        { kind: "any-of", words: ["range", "spelled out"] },
+      ],
+      [
+        "the arrival or availability pattern",
+        { kind: "any-of", words: ["spread", "spelled out"] },
+      ],
+    ]);
+  });
+
   test("ambiguous kind-indexed patterns declare the slot that keeps them live", () => {
     const sdcpn = readShipped("plugin-sdcpn");
     const gherkin = readShipped("plugin-gherkin");
diff --git a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml
index ffd6fa48590..ec49df6f14e 100644
--- a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml
+++ b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml
@@ -136,7 +136,7 @@ schema:
       why: "an objective that depends on nothing is unsupported by the model"
     - kind: objective
       slot: 'what "better" means, and trade-off weights'
-      precision: range
+      precision: [range, spelled out]
       not_applicable: true
       why: "quantified objectives need a metric; some are qualitative"
     - kind: entity-type
@@ -161,7 +161,7 @@ schema:
       why: "scenario initial state"
     - kind: boundary-condition
       slot: "the arrival or availability pattern"
-      precision: spread
+      precision: [spread, spelled out]
       not_applicable: false
       why: "source rates and calendars; a single average hides the shape"
     - kind: activity

From 0cd67ae6e18e72cc330188e00b87bef2f0409578 Mon Sep 17 00:00:00 2001
From: Lu Nelson <ln@hash.ai>
Date: Wed, 26 Aug 2026 16:32:48 +0200
Subject: [PATCH 4/9] Condition repertoire teaching on plugin precision

Generic quantity and observed-practice methods now render only for plugin contracts that demand compatible precision, keeping shared defaults relevant without plugin overrides.

Co-authored-by: Cursor <cursoragent@cursor.com>
---
 .../docs/specs/plugin-contract.md             |  5 ++
 .../packages/core/schema/CHANGELOG.md         |  5 ++
 .../packages/core/src/instructions.ts         | 49 +++++++++--
 .../packages/core/src/plugin-definition.ts    |  2 +
 .../packages/core/src/repertoire.ts           | 88 +++++++++++++++++--
 .../packages/core/test/instructions.test.ts   | 31 +++++++
 .../packages/repertoire/README.md             |  3 +
 .../packages/repertoire/repertoire.yaml       |  9 +-
 .../repertoire/test/repertoire.test.ts        | 20 +++++
 9 files changed, 199 insertions(+), 13 deletions(-)

diff --git a/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md b/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md
index 957fe42165a..22acac52996 100644
--- a/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md
+++ b/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md
@@ -43,6 +43,11 @@ interviewer reads above each, lives in `packages/core/src/keys.ts`; the catalogu
 until a co-authoring cycle changes no key (ADR-0007 decision 9), with changes recorded in
 `packages/core/schema/CHANGELOG.md`.
 
+The repertoire may additionally give an item `for_precision`, a non-empty list of harness
+precision words. Such an item is rendered only when at least one plugin demand names a listed
+word. This conditions generic teaching on the plugin contract without allowing a plugin to
+override the repertoire.
+
 Domain-neutrality rule: nothing in the definition may name a domain. A new case that seems to
 need a new row is a finding about the abstraction, decided by review, never content added to a
 plugin.
diff --git a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
index d54abb1ea89..f5d3793f249 100644
--- a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
+++ b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
@@ -164,3 +164,8 @@ written against.
   metric accepts `range` or `spelled out`; its arrival pattern accepts `spread`
   or `spelled out`, covering numeric distributions and structural rules without
   splitting either semantic slot.
+- Added repertoire-item `for_precision`, a non-empty list of precision words.
+  Rendering now omits an annotated default unless the plugin demands at least
+  one listed word. The seven quantity and observed-practice entries identified
+  by the cycle review use the facet, so Gherkin is no longer taught numeric or
+  retrospective elicitation merely because it shares the fixed key catalogue.
diff --git a/libs/@hashintel/brunch-agent/packages/core/src/instructions.ts b/libs/@hashintel/brunch-agent/packages/core/src/instructions.ts
index 551be1bc22c..379e95673da 100644
--- a/libs/@hashintel/brunch-agent/packages/core/src/instructions.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/src/instructions.ts
@@ -25,6 +25,7 @@ import {
   type GuidanceItem,
   type PluginDefinition,
   type PrecisionDemand,
+  type PrecisionWord,
 } from "./plugin-definition";
 import { type Repertoire } from "./repertoire";
 
@@ -47,6 +48,32 @@ const renderItems = (items: readonly GuidanceItem[]): string[] =>
     return `- **${item.name}** — ${item.text.trim()}${signature}`;
   });
 
+const demandedPrecisions = (
+  definition: PluginDefinition,
+): ReadonlySet<PrecisionWord> => {
+  const words = new Set<PrecisionWord>();
+  for (const row of definition.mustKnow) {
+    if (row.precision.kind === "word") {
+      words.add(row.precision.word);
+    } else if (row.precision.kind === "any-of") {
+      for (const word of row.precision.words) {
+        words.add(word);
+      }
+    }
+  }
+  return words;
+};
+
+const applicableRepertoireItems = (
+  items: readonly GuidanceItem[],
+  precisions: ReadonlySet<PrecisionWord>,
+): GuidanceItem[] =>
+  items.filter(
+    (item) =>
+      item.forPrecision === undefined ||
+      item.forPrecision.some((precision) => precisions.has(precision)),
+  );
+
 const renderDemand = (demand: PrecisionDemand): string => {
   switch (demand.kind) {
     case "word":
@@ -137,21 +164,29 @@ export const renderContract = (definition: PluginDefinition): string[] => {
 export const renderGuidance = (
   repertoire: Repertoire,
   definition: PluginDefinition,
-): string[] =>
-  GUIDANCE_KEYS.map((key) => {
+): string[] => {
+  const precisions = demandedPrecisions(definition);
+  return GUIDANCE_KEYS.map((key) => {
     const description = GUIDANCE_KEY_DESCRIPTIONS[key];
     const body =
       key === "movements"
         ? MOVEMENTS.flatMap((movement) => [
             `### ${movement === "slice" ? "Slice" : "Sweep"}`,
             [
-              ...renderItems(repertoire.guidance.movements[movement]),
+              ...renderItems(
+                applicableRepertoireItems(
+                  repertoire.guidance.movements[movement],
+                  precisions,
+                ),
+              ),
               ...renderItems(definition.guidance.movements[movement]),
             ].join("\n"),
           ])
         : [
             [
-              ...renderItems(repertoire.guidance[key]),
+              ...renderItems(
+                applicableRepertoireItems(repertoire.guidance[key], precisions),
+              ),
               ...renderItems(definition.guidance[key]),
             ].join("\n"),
           ];
@@ -159,6 +194,7 @@ export const renderGuidance = (
       .filter((part) => part !== "")
       .join("\n\n");
   });
+};
 
 /** One job's runbook: each runbook key's definition, default, and plugin cell. */
 export const renderRunbook = (
@@ -167,13 +203,16 @@ export const renderRunbook = (
   job: Job,
 ): string => {
   const cells = definition.runbooks[job];
+  const precisions = demandedPrecisions(definition);
   const sections = RUNBOOK_KEYS.map((key) => {
     const description = RUNBOOK_KEY_DESCRIPTIONS[key];
     return [
       `### ${description.title}`,
       `_${description.definition}_`,
       [
-        ...renderItems(repertoire.runbooks[job][key]),
+        ...renderItems(
+          applicableRepertoireItems(repertoire.runbooks[job][key], precisions),
+        ),
         ...renderItems(cells?.[key] ?? []),
       ].join("\n"),
     ].join("\n\n");
diff --git a/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts b/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
index 5a5a63fbc67..c1b9a1b6b8b 100644
--- a/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
@@ -96,6 +96,8 @@ export interface Anchor {
 export interface GuidanceItem {
   readonly name: string;
   readonly text: string;
+  /** Repertoire-only applicability; omitted entries apply to every plugin. */
+  readonly forPrecision?: readonly PrecisionWord[];
   /** For failure modes: how the failure is detected. */
   readonly signature?: string;
   /** Where the entry comes from; required of the repertoire, optional for a plugin. */
diff --git a/libs/@hashintel/brunch-agent/packages/core/src/repertoire.ts b/libs/@hashintel/brunch-agent/packages/core/src/repertoire.ts
index 5c17828c6fc..7b91f737a5d 100644
--- a/libs/@hashintel/brunch-agent/packages/core/src/repertoire.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/src/repertoire.ts
@@ -13,11 +13,11 @@ import * as v from "valibot";
 
 import { GUIDANCE_KEYS, JOBS, MOVEMENTS, RUNBOOK_KEYS, type Job } from "./keys";
 import {
-  GuidanceCellsSchema,
+  PRECISION_WORDS,
   PluginDefinitionError,
   readYamlAs,
-  RunbookCellsSchema,
   type GuidanceCells,
+  type GuidanceItem,
   type RunbookCells,
 } from "./plugin-definition";
 
@@ -28,6 +28,36 @@ export interface Repertoire {
   readonly runbooks: Readonly<Record<Job, RunbookCells>>;
 }
 
+const text = v.pipe(v.string(), v.nonEmpty());
+const RepertoireItemSchema = v.strictObject({
+  name: text,
+  text,
+  signature: v.optional(text),
+  source: v.optional(text),
+  for_precision: v.optional(
+    v.pipe(v.array(v.picklist(PRECISION_WORDS)), v.minLength(1)),
+  ),
+});
+const items = v.array(RepertoireItemSchema);
+const RepertoireGuidanceCellsSchema = v.strictObject({
+  lenses: items,
+  techniques: items,
+  movements: v.strictObject({
+    slice: items,
+    sweep: items,
+  }),
+  licenses: items,
+  motifs: items,
+  smells: items,
+  rabbit_holes: items,
+  failure_modes: items,
+});
+const RepertoireRunbookCellsSchema = v.strictObject({
+  kickoff: items,
+  trajectory: items,
+  close: items,
+});
+
 export const RepertoireSchema = v.strictObject({
   repertoire: v.strictObject({
     version: v.pipe(
@@ -36,13 +66,54 @@ export const RepertoireSchema = v.strictObject({
     ),
     purpose: v.pipe(v.string(), v.nonEmpty()),
   }),
-  guidance: GuidanceCellsSchema,
+  guidance: RepertoireGuidanceCellsSchema,
   runbooks: v.strictObject({
-    construct: RunbookCellsSchema,
-    "review-and-revise": RunbookCellsSchema,
+    construct: RepertoireRunbookCellsSchema,
+    "review-and-revise": RepertoireRunbookCellsSchema,
   }),
 });
 
+type RepertoireItemInput = v.InferOutput<typeof RepertoireItemSchema>;
+type RepertoireGuidanceCellsInput = v.InferOutput<
+  typeof RepertoireGuidanceCellsSchema
+>;
+type RepertoireRunbookCellsInput = v.InferOutput<
+  typeof RepertoireRunbookCellsSchema
+>;
+
+const readItem = (input: RepertoireItemInput): GuidanceItem => ({
+  name: input.name,
+  text: input.text,
+  ...(input.for_precision === undefined
+    ? {}
+    : { forPrecision: input.for_precision }),
+  ...(input.signature === undefined ? {} : { signature: input.signature }),
+  ...(input.source === undefined ? {} : { source: input.source }),
+});
+
+const readItems = (inputs: readonly RepertoireItemInput[]): GuidanceItem[] =>
+  inputs.map(readItem);
+
+const readGuidance = (input: RepertoireGuidanceCellsInput): GuidanceCells => ({
+  lenses: readItems(input.lenses),
+  techniques: readItems(input.techniques),
+  movements: {
+    slice: readItems(input.movements.slice),
+    sweep: readItems(input.movements.sweep),
+  },
+  licenses: readItems(input.licenses),
+  motifs: readItems(input.motifs),
+  smells: readItems(input.smells),
+  rabbit_holes: readItems(input.rabbit_holes),
+  failure_modes: readItems(input.failure_modes),
+});
+
+const readRunbook = (input: RepertoireRunbookCellsInput): RunbookCells => ({
+  kickoff: readItems(input.kickoff),
+  trajectory: readItems(input.trajectory),
+  close: readItems(input.close),
+});
+
 const fail = (message: string): never => {
   throw new PluginDefinitionError(message);
 };
@@ -85,7 +156,10 @@ export function readRepertoire(yamlText: string): Repertoire {
   return {
     version: input.repertoire.version,
     purpose: input.repertoire.purpose,
-    guidance: input.guidance,
-    runbooks: input.runbooks,
+    guidance: readGuidance(input.guidance),
+    runbooks: {
+      construct: readRunbook(input.runbooks.construct),
+      "review-and-revise": readRunbook(input.runbooks["review-and-revise"]),
+    },
   };
 }
diff --git a/libs/@hashintel/brunch-agent/packages/core/test/instructions.test.ts b/libs/@hashintel/brunch-agent/packages/core/test/instructions.test.ts
index 94efe95019c..a5f26055583 100644
--- a/libs/@hashintel/brunch-agent/packages/core/test/instructions.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/test/instructions.test.ts
@@ -116,6 +116,37 @@ describe("renderInstructions", () => {
     expect(section).not.toMatch(/\n\n$/u);
   });
 
+  test("renders a repertoire item only when the plugin demands an applicable precision", () => {
+    const conditionalRepertoire = readRepertoire(
+      REPERTOIRE_YAML.replace(
+        item("techniques default"),
+        "      - { name: techniques default, text: default techniques default., source: test, for_precision: [range, spread] }",
+      ).replace(
+        item("kickoff default"),
+        "      - { name: kickoff default, text: default kickoff default., source: test, for_precision: [range, spread] }",
+      ),
+    );
+    const nonNumericDefinition = readPluginDefinition(
+      FIXTURE_PLUGIN_YAML.replace(
+        "precision: range",
+        "precision: named",
+      ).replace("precision: spread", "precision: spelled out"),
+    );
+
+    expect(
+      renderGuidance(conditionalRepertoire, definition).join("\n"),
+    ).toContain("**techniques default**");
+    expect(
+      renderGuidance(conditionalRepertoire, nonNumericDefinition).join("\n"),
+    ).not.toContain("**techniques default**");
+    expect(
+      renderRunbook(conditionalRepertoire, definition, "construct"),
+    ).toContain("**kickoff default**");
+    expect(
+      renderRunbook(conditionalRepertoire, nonNumericDefinition, "construct"),
+    ).not.toContain("**kickoff default**");
+  });
+
   test("splits movements into slice and sweep", () => {
     expect(
       ascending(
diff --git a/libs/@hashintel/brunch-agent/packages/repertoire/README.md b/libs/@hashintel/brunch-agent/packages/repertoire/README.md
index d40ce188a47..03551827e57 100644
--- a/libs/@hashintel/brunch-agent/packages/repertoire/README.md
+++ b/libs/@hashintel/brunch-agent/packages/repertoire/README.md
@@ -12,6 +12,9 @@ Two rules the reader enforces here and not on a plugin: every key is filled,
 and every entry names its `source` — a run, a replay, a verified literature
 finding, or an accepted decision. Admission is by evidence (ADR-0007
 decision 7). Entries name no formalism and no domain; the test checks.
+An entry may declare `for_precision`, a non-empty list of harness precision
+words. The renderer includes it only for plugins that demand at least one of
+those words.
 
 ## Topology
 
diff --git a/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml b/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml
index cfc2a709b1a..54d072cfab9 100644
--- a/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml
+++ b/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml
@@ -10,7 +10,7 @@
 # Paths are relative to the Brunch context root.
 
 repertoire:
-  version: repertoire/2026-08-25.1
+  version: repertoire/2026-08-26.1
   purpose: |
     Teach the interviewer how an expert-knowledge interview goes right and
     wrong, independent of what is being modelled: what to attend to, how to
@@ -26,6 +26,7 @@ guidance:
     - name: Policy versus practice
       text: 'An answer in normative language — "we would", "the rule is", "you are supposed to" — reports a policy, not what happens. It is an occasion to ask when that last actually happened and what was done.'
       source: docs/reference/research/elicitation/elicitation-strategy-literature.md §2.3 (policy-vs-practice detector); docs/archive/specs/cps-interview-guidance-2026-08-25.md CPS-Q05
+      for_precision: [range, spread]
     - name: Two answers in tension
       text: When something just said does not fit something said earlier, the tension is evidence — of a distinction not yet drawn, a condition not yet named, or an error. Say so and ask; do not pick one silently.
       source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (check consistency); docs/reference/research/elicitation/elicitation-strategy-literature.md §5.1 (consistency probe)
@@ -45,18 +46,22 @@ guidance:
     - name: Mean or tail
       text: Before eliciting any quantity, ask whether what matters is the typical case or the bad one — a mean or a tail. The answer decides whether a single figure, a range, or a spread is being asked for.
       source: docs/reference/research/elicitation/elicitation-strategy-literature.md §1.3 (mean-or-tail router)
+      for_precision: [number, range, spread]
     - name: Quantiles, never three points
       text: 'For anything that varies, ask "typically?", then "one time in ten, worse than?", then "one time in ten, better than?". Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. If a min/mode/max triple arrives unprompted, ask the confidence question and record whether the middle value is a mode or a mean.'
       source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (category 4); docs/reference/research/elicitation/elicitation-strategy-literature.md §1.4 (IDEA four-step interval, anti-triangular guard)
+      for_precision: [spread]
     - name: The clairvoyant test
       text: A quantity is well enough defined only when someone who could see everything could report it without asking a clarifying question. If the slot's name would need one, ask the clarifying question first.
       source: docs/reference/research/elicitation/elicitation-strategy-literature.md §1.4 (Howard's clairvoyant test)
+      for_precision: [number, range, spread]
     - name: Consistency probe
       text: '"You said earlier that ___, but then you told me ___. How do you explain that?" — stated plainly, without choosing between the two.'
       source: docs/reference/research/elicitation/elicitation-strategy-literature.md §5.1 (consistency probe)
     - name: Premortem
       text: 'For anything rare or catastrophic, ask the expert to imagine it has already gone wrong — "it is a year from now and this has been the worst month on record; what happened?" — and demand mechanism and sequence, not sentiment.'
       source: docs/reference/research/elicitation/elicitation-strategy-literature.md §2.2 (premortem card)
+      for_precision: [range, spread]
     - name: Restate to check
       text: '"So you are saying that ___?" — a restatement in your own words, offered for correction. Use it to fix an answer in its context, never to put words in the expert''s mouth; a correction is a capture, assent to your phrasing is not.'
       source: docs/reference/research/elicitation/elicitation-strategy-literature.md §5.1 (check-reflect / restatement); docs/reference/research/elicitation/frontier-model-elicitor-failure-catalogue.md FM-15
@@ -72,6 +77,7 @@ guidance:
       - name: One property across one stratum
         text: A sweep makes one property hold across one class of node the slice revealed — every step has a duration, every resource has a count. Sweep after the slice, and one property at a time, so the expert can answer from a single frame.
         source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (Slice, then sweep); docs/control/SPEC-LEDGER.md §11.5
+        for_precision: [number, range, spread]
       - name: Ask for absences
         text: 'Near the end of each topic ask "is there anything that never happens?" and "what have I not asked about that matters here?". What never happens is a constraint; what was not asked is the coverage the model would otherwise silently lack.'
         source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (Ask for absences); docs/reference/research/elicitation/frontier-model-elicitor-failure-catalogue.md FM-08
@@ -161,6 +167,7 @@ runbooks:
       - name: Objectives first
         text: Establish what the model must be able to answer, and for whom, before anything else; then let it prioritise the rest. What "better" means, numerically where possible, is almost never written down — expect to co-construct it.
         source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (Objectives first, category 1)
+        for_precision: [number, range, spread]
       - name: The posture
         text: "From the first exchanges, take the expert's time available, what the model is for, how confident it must be, and how far they will tolerate you proposing assumptions. These set the interview's stance; they are not asked as a form."
         source: docs/adr/0007-harness-teaching-meets-plugin-content-at-fixed-keys.md (decision 4)
diff --git a/libs/@hashintel/brunch-agent/packages/repertoire/test/repertoire.test.ts b/libs/@hashintel/brunch-agent/packages/repertoire/test/repertoire.test.ts
index ad697c7bf30..8bd572f7011 100644
--- a/libs/@hashintel/brunch-agent/packages/repertoire/test/repertoire.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/repertoire/test/repertoire.test.ts
@@ -66,4 +66,24 @@ describe("the shipped repertoire", () => {
       .join("\n");
     expect(text).not.toMatch(FORMALISM_OR_DOMAIN);
   });
+
+  test("conditions quantity and observed-practice methods on compatible precision demands", () => {
+    const entries = [
+      ...guidanceEntries(repertoire.guidance),
+      ...runbookEntries(repertoire.runbooks),
+    ];
+    expect(
+      entries
+        .filter(({ item }) => item.forPrecision !== undefined)
+        .map(({ item }) => [item.name, item.forPrecision]),
+    ).toEqual([
+      ["Policy versus practice", ["range", "spread"]],
+      ["Mean or tail", ["number", "range", "spread"]],
+      ["Quantiles, never three points", ["spread"]],
+      ["The clairvoyant test", ["number", "range", "spread"]],
+      ["Premortem", ["range", "spread"]],
+      ["One property across one stratum", ["number", "range", "spread"]],
+      ["Objectives first", ["number", "range", "spread"]],
+    ]);
+  });
 });

From 5fdbe604979c457a5f819259a51f7f4b7100befe Mon Sep 17 00:00:00 2001
From: Lu Nelson <ln@hash.ai>
Date: Wed, 26 Aug 2026 16:41:21 +0200
Subject: [PATCH 5/9] Complete the cycle-two plugin content pass

Fill the ADR's missing selection and guidance, resolve the pressure-review contradictions, and make both plugin cells add specific content without repeating repertoire defaults.

Co-authored-by: Cursor <cursoragent@cursor.com>
---
 .../docs/specs/plugin-contract.md             |   5 +-
 .../packages/core/schema/CHANGELOG.md         |  10 ++
 .../packages/plugin-gherkin/plugin.yaml       |   7 +-
 .../test/statement-noted.test.ts              |  10 +-
 .../packages/plugin-sdcpn/plugin.yaml         | 111 +++++++++++++-----
 .../packages/plugin-sdcpn/test/plugin.test.ts |  28 ++++-
 .../packages/repertoire/repertoire.yaml       |  74 ++++++++++--
 .../repertoire/test/repertoire.test.ts        |  87 +++++++++++++-
 8 files changed, 284 insertions(+), 48 deletions(-)

diff --git a/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md b/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md
index 22acac52996..3365e5931c8 100644
--- a/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md
+++ b/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md
@@ -36,8 +36,9 @@ The keys fall in four groups (ADR-0007 decision 2), under an identity block `plu
 | machinery   | `checks` · `tools`                                                                                | identifiers of harness or plugin machinery; unconsumed in cycle one |
 
 Every guidance and runbook cell is a list of `{name, text, signature?, source?}` items. A cell
-adds to the default; it never overrides it and never restates what the harness enforces. A plugin
-may leave any cell blank — the default is then the whole of the key — and may add no key: an
+adds to the default; it never overrides or repeats it and never restates what the harness
+enforces. A plugin may leave any cell blank — the default is then the whole of the key — and may
+add no key: an
 unknown key anywhere fails to load. The catalogue of keys, and the one-paragraph definition the
 interviewer reads above each, lives in `packages/core/src/keys.ts`; the catalogue is a working set
 until a co-authoring cycle changes no key (ADR-0007 decision 9), with changes recorded in
diff --git a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
index f5d3793f249..93de419c083 100644
--- a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
+++ b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
@@ -169,3 +169,13 @@ written against.
   one listed word. The seven quantity and observed-practice entries identified
   by the cycle review use the facet, so Gherkin is no longer taught numeric or
   retrospective elicitation merely because it shares the fixed key catalogue.
+- Completed the cycle-two content pass without adding or removing a key. The
+  repertoire now consumes posture in trajectory selection; fills the ADR's
+  missing licenses, smells, rabbit holes, kickoff scope, and stopping outcomes;
+  and states its choices on clearinghouse probes, quantile order, batching,
+  hypotheticals, confirmed restatements, and structure after kickoff. SDCPN
+  motifs now name their variant axes, its cells no longer repeat generic
+  quantile teaching, and its demand rows, sweep, and anti-guidance cover
+  dynamics noise and the missed edge material. Gherkin's duplicate
+  rule-without-example failure mode was removed. A gate now rejects exact
+  sentence repetition between repertoire defaults and plugin cells.
diff --git a/libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml b/libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml
index a775500e984..fe98164d35c 100644
--- a/libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml
+++ b/libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml
@@ -10,7 +10,7 @@
 
 plugin:
   id: gherkin
-  version: gherkin/2026-08-26.1
+  version: gherkin/2026-08-26.2
   formalism: Gherkin — executable specifications as features, rules, and examples
   jobs: [construct, review-and-revise]
   purpose: |
@@ -114,7 +114,7 @@ schema:
       slot: the known step it binds to
       precision: named
       not_applicable: true
-      why: A phrase the team already automates needs no new code; a new phrase is a cost the person should know about.
+      why: Ask the person to name the known team step; without an available lexicon, record the phrase as new rather than inventing a binding.
   proposals:
     - { type: statement-noted, payload: statement }
 
@@ -183,9 +183,6 @@ guidance:
     - name: Organising the suite
       text: Tags, file layout, and naming conventions are not behaviour.
   failure_modes:
-    - name: Rule without example
-      text: A general statement is recorded as if it were checkable.
-      signature: A rule node whose examples slot is unsatisfied at close.
     - name: Untethered example
       text: An example illustrates no stated rule and no one knows what it proves.
       signature: An example whose rule slot is neither named nor marked not applicable.
diff --git a/libs/@hashintel/brunch-agent/packages/plugin-gherkin/test/statement-noted.test.ts b/libs/@hashintel/brunch-agent/packages/plugin-gherkin/test/statement-noted.test.ts
index 548b646d061..c1223cca7da 100644
--- a/libs/@hashintel/brunch-agent/packages/plugin-gherkin/test/statement-noted.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/plugin-gherkin/test/statement-noted.test.ts
@@ -3,7 +3,7 @@ import { describe, expect, test } from "vitest";
 
 import { createSweepExtractionResultSchema } from "@hashintel/brunch-agent";
 
-import { gherkin } from "../src/index";
+import { gherkin, gherkinDefinition } from "../src/index";
 
 const quote = "Payment is authorized before fulfillment.";
 const statementNoted = {
@@ -19,6 +19,14 @@ const statementNoted = {
 };
 
 describe("the Gherkin verbatim-grade proposal floor", () => {
+  test("leaves rule coverage to the sweep, pattern, and check without a duplicate failure mode", () => {
+    expect(
+      gherkinDefinition.guidance.failure_modes.map(
+        (failureMode) => failureMode.name,
+      ),
+    ).not.toContain("Rule without example");
+  });
+
   test("declares exactly one statement proposal and compiles it into sweep extraction", () => {
     expect(gherkin.proposalCatalog.map((proposal) => proposal.name)).toEqual([
       "statement-noted",
diff --git a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml
index ec49df6f14e..6ea5cafdf41 100644
--- a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml
+++ b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml
@@ -13,7 +13,7 @@
 
 plugin:
   id: sdcpn
-  version: sdcpn/2026-08-26.1
+  version: sdcpn/2026-08-26.2
   formalism: stochastic dynamic coloured Petri nets (Petrinaut)
   jobs: [construct, review-and-revise]
   purpose: |
@@ -96,9 +96,8 @@ ontology:
     - name: quantity
       on: any kind
       text: >-
-        Any duration, rate, probability, count, or capacity. Elicited by quantiles — "typical?",
-        "one time in ten, worse than?", "one time in ten, better than?" — never minimum /
-        most-likely / maximum, which yields overconfident triangles.
+        Any duration, rate, probability, count, or capacity. Preserve the precision the expert
+        reached; the row's demand says what further narrowing completion requires.
     - name: source-regime
       on: any kind
       values: [prescribed, practiced]
@@ -224,6 +223,11 @@ schema:
       precision: range
       not_applicable: false
       why: "the differential law; a direction with no rate cannot be simulated"
+    - kind: dynamics
+      slot: "how it varies around that change"
+      precision: spread
+      not_applicable: true
+      why: "noise can dominate threshold timing; deterministic change may explicitly have none"
     - kind: dynamics
       slot: "what happens at a threshold"
       precision: spelled out
@@ -274,7 +278,8 @@ patterns:
       ask: >-
         ask what is lost in the transition, as a range, after a *named* transition. If the expert
         does not know, ask what they would treat as an authoritative source — never convert
-        "unknown" into a value.
+        "unknown" into a value. Ask before recording an explicit "not applicable"; an ordinary
+        activity with no mode change is a useful negative answer, not a reason to skip the slot.
     - id: P03
       on: [ordering/flow]
       when: an `ordering/flow` moves things in groups — batches, runs, lots, loads
@@ -335,49 +340,88 @@ guidance:
         A `dynamics` node — something changing continuously while nothing discrete happens — or a
         mode change with a loss. The expert rarely volunteers the rate; the model cannot run
         without it.
-  techniques:
-    - name: quantiles, never triangles
+    - name: '"always" and "never"'
+      text: >-
+        A `constraint` or a `policy` stated in passing. Ask what enforces it, what it limits, and
+        whether an exception has ever overridden it.
+    - name: duration that depends on the clock
       text: >-
-        For any quantity, ask "typical?", then "one time in ten, worse than?", then "one time in
-        ten, better than?" — never minimum / most-likely / maximum, which yields overconfident
-        triangles. A `spread` is exactly this.
+        An `activity` duration whose elapsed time crosses a calendar boundary depends on a
+        `boundary-condition`, not only on the work itself. Ask for both the work time and the
+        availability rule.
+  techniques:
     - name: precision is about the value, not its source
       text: >-
         "About three hours" from the expert is an honest `number` at the wrong precision; "three
         hours" supplied by the interviewer is at the right precision and is not evidence at all.
         Track both and let neither substitute for the other.
+    - name: stress the binding resource
+      text: >-
+        Before deepening every duration into a distribution, ask which `entity-type` actually
+        constrains the objective and whether its utilisation or variability makes stochastic detail
+        consequential.
+    - name: turn an unknown into an observable threshold
+      text: >-
+        When the expert cannot give an exact quantity, ask what boundary would change a decision or
+        become visibly unacceptable. Record the threshold they can judge; do not invent the value
+        beyond it.
+    - name: ask what is conserved
+      text: >-
+        When quantities enter and leave a process, ask what total should remain constant and where
+        loss is possible. A conservation answer belongs as a `constraint`, in the expert's units.
   movements:
     slice:
       - name: one instance, arriving to leaving
         text: >-
           One case in this formalism is one instance of the `entity-type` that flows, followed from
-          the moment it reaches the system to the moment it leaves. Create nodes as they appear; as
-          each `objective` becomes clearer, link it to the nodes it depends on. An `objective` that
-          depends on nothing yet is unsupported — say so and go find its structure.
+          the moment it reaches the system to the moment it leaves. If several things flow, first
+          ask which unit defines one case — order, batch, item, or another named unit. Create nodes
+          as they appear; as each `objective` becomes clearer, link it to the nodes it depends on.
+          An `objective` that depends on nothing yet is unsupported — say so and go find its
+          structure.
     sweep:
       - name: strata are kinds, net-bearing first
         text: >-
-          A stratum is one kind. Sweep in kind order, `entity-type` through `dynamics` (net-bearing)
-          before `objective` through `validation-criterion` (partly or wholly IR-only).
+          After kickoff has established each `objective` and its `validation-criterion`, a stratum
+          is one kind. Sweep `entity-type` through `dynamics` first because they bear the net, then
+          complete the remaining IR-only rows.
       - name: the unwritten constraints
         text: >-
           Close the `constraint` stratum with the unwritten rules: "what would a newcomer get wrong
           in the first week?", "what do you always or never do that is written nowhere?", "which rule
           exists because something once went wrong?"
+      - name: what can befall each activity
+        text: >-
+          Close the `activity` stratum by asking across exception types: work-item failure, deadline
+          expiry, resource unavailability, external trigger, and constraint violation. For each
+          named exception, ask what happens to the work, the case, and the recovery.
   licenses: []
   motifs:
     - name: shared resource
-      text: several activities want one `entity-type`'s instances — ask which wins and what overrides.
+      text: >-
+        Several activities want one `entity-type`'s instances. Ask whether the server is indivisible
+        or splittable by role, how many instances act together, which activity wins, and what
+        overrides that rule.
     - name: batch, lot, load
-      text: an `ordering/flow` that moves things in groups — ask what the group is and what a split costs.
+      text: >-
+        An `ordering/flow` that moves things in groups. Ask whether formation fires by count, by a
+        clock, or by either; whether the group must stay together; and what a split costs.
     - name: gate or release
-      text: a `policy` or `boundary-condition` that lets things proceed — ask for the practiced event, not the approximate time.
+      text: >-
+        A `policy` or `boundary-condition` that lets things proceed. Ask whether the gate is a state,
+        an event, or a person's decision; where it is observed; and what overrides it.
     - name: mode change
-      text: a setup, changeover, restart, or warm-up — ask what is lost, after a named transition.
+      text: >-
+        A setup, changeover, restart, or warm-up. Ask whether loss depends on direction, whether the
+        change is local or cascading, and which time, material, or capacity components are lost.
     - name: event, not step
-      text: a failure or interruption that befalls the system — ask rate and duration separately.
+      text: >-
+        A failure or interruption that befalls the system. Ask occurrence and duration separately,
+        then whether the rate is independent or changes with a named state.
     - name: threshold on a continuous quantity
-      text: a `dynamics` node — ask what it triggers and which `activity` resets it.
+      text: >-
+        A `dynamics` node. Ask what it triggers, which `activity` resets it, and — when several
+        components evolve — whether they combine additively or the weakest component decides.
   smells:
     - name: a quantity for one type and no other
       text: given for one `entity-type` when others exist and never asked whether it varies (P07).
@@ -402,8 +446,17 @@ guidance:
         from `boundary-condition` nodes at simulation time.
     - name: depth on IR-only kinds
       text: >-
-        `data-binding` and `validation-criterion` project to nothing today; name them and record
-        them for the loss report, do not elaborate them.
+        Establish the `validation-criterion` and accuracy bar at kickoff even though they do not
+        project today. For `data-binding`, stop after the variable, source, and any evidence gap;
+        implementation detail belongs in the loss report.
+    - name: precision below what the expert observes
+      text: >-
+        Do not decompose a quantity below the granularity the expert can observe. Record the coarser
+        value and a deposit naming where finer evidence could come from.
+    - name: eliciting the objective's answer
+      text: >-
+        The interview builds what the model needs to answer an `objective`; it does not ask the
+        expert to predict that answer and store the prediction as model structure.
   failure_modes:
     - name: dead net
       signature: no `ordering/flow` with its order spelled out; activities exist but nothing connects them
@@ -411,9 +464,6 @@ guidance:
     - name: unsupported objective
       signature: an `objective` whose dependency slot names no node in the model
       text: the model cannot answer the question it was built for; the slice never reached it.
-    - name: overconfident triangle
-      signature: a duration or rate captured as minimum / most-likely / maximum
-      text: the expert was asked the wrong three questions; re-ask as quantiles.
 
 # ─── Runbooks ─────────────────────────────────────────────────────────────────────────────────────
 # One cell set per job this plugin supports. The harness default runbook for each job comes first;
@@ -425,8 +475,9 @@ runbooks:
       - name: what "no model exists" means here
         text: >-
           The user knows the system; the interviewer knows the kinds. Capture each thing the user
-          wants the model to answer or decide as an `objective` node. Expect to co-construct: these
-          are almost never written down. Ask what "better" means and whether it can be quantified.
+          wants the model to answer or decide as an `objective` node. Recast an optimisation request
+          as a comparison among candidate policies, and name the time resolution over which the
+          answer must remain useful.
     trajectory:
       - name: kind order
         text: >-
@@ -446,6 +497,10 @@ runbooks:
           The SDCPN scaffold, the code-obligation sidecar, and the typed loss report are derived by
           the plugin's projection. The interviewer does not write them and must not claim the model
           is loadable, compiled, or simulated.
+      - name: stopping outcomes
+        text: >-
+          Named and distinct: `complete-under-declared-demands`, `partial-with-open-slots`,
+          `unsupported-objective`, `data-deposit-required`, `expert-stopped`.
   review-and-revise:
     kickoff:
       - name: what "a model exists" means here
diff --git a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/test/plugin.test.ts b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/test/plugin.test.ts
index 970a42c1140..936d7d374dd 100644
--- a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/test/plugin.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/test/plugin.test.ts
@@ -70,12 +70,38 @@ describe("the SDCPN plugin", () => {
   test("is the parsed file plus one slot-assertion proposal type", () => {
     expect(sdcpn.targetFormalism).toBe("sdcpn");
     expect(sdcpn.definition).toBe(sdcpnDefinition);
-    expect(sdcpnDefinition.version).toBe("sdcpn/2026-08-26.1");
+    expect(sdcpnDefinition.version).toBe("sdcpn/2026-08-26.2");
     expect(sdcpn.proposalCatalog.map((proposal) => proposal.name)).toEqual([
       "slot-asserted",
     ]);
   });
 
+  test("keeps motif variants specific without repeating generic quantile teaching", () => {
+    const motifs = new Map(
+      sdcpnDefinition.guidance.motifs.map((motif) => [motif.name, motif.text]),
+    );
+    expect(motifs.get("shared resource")).toMatch(/indivisible.*splittable/iu);
+    expect(motifs.get("batch, lot, load")).toMatch(/count.*clock/iu);
+    expect(motifs.get("threshold on a continuous quantity")).toMatch(
+      /weakest|combine/iu,
+    );
+    expect(
+      sdcpnDefinition.guidance.techniques.map((technique) => technique.name),
+    ).not.toContain("quantiles, never triangles");
+    expect(
+      sdcpnDefinition.guidance.failure_modes.map(
+        (failureMode) => failureMode.name,
+      ),
+    ).not.toContain("overconfident triangle");
+    expect(
+      sdcpnDefinition.mustKnow.find(
+        (row) =>
+          row.kind === "dynamics" &&
+          row.slot === "how it varies around that change",
+      )?.precision,
+    ).toEqual({ kind: "word", word: "spread" });
+  });
+
   test("accepts an assertion addressed to a kind and slot the file names", () => {
     const schema = createSweepExtractionResultSchema(sdcpn);
     const proposal = proposalOf(
diff --git a/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml b/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml
index 54d072cfab9..a99be2ca006 100644
--- a/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml
+++ b/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml
@@ -10,7 +10,7 @@
 # Paths are relative to the Brunch context root.
 
 repertoire:
-  version: repertoire/2026-08-26.1
+  version: repertoire/2026-08-26.2
   purpose: |
     Teach the interviewer how an expert-knowledge interview goes right and
     wrong, independent of what is being modelled: what to attend to, how to
@@ -33,6 +33,12 @@ guidance:
     - name: Cues the expert relies on
       text: 'After any substantive answer, the expert''s basis is worth more than the answer: "how would you know that — what are you actually looking at?" and "how would this be hard for someone less experienced?" surface what the expert did not think to say.'
       source: docs/reference/research/elicitation/elicitation-strategy-literature.md §2.2 (universal cue follow-up rule, ACTA)
+    - name: Sources that disagree
+      text: When two people or records disagree, preserve both claims and ask what observation would distinguish them. Do not average a contested fact or silently choose an authority.
+      source: docs/reference/research/elicitation/elicitation-strategy-literature.md §5.3 (reconciliation loop); evaluations/protocols/process-model-elicitation/baseline/condition-1.md (scheduler versus engineering)
+    - name: Unexplained terms and documents
+      text: A local term must be explained in the expert's own words. A document supplies propositions to confirm, not facts to copy; keep its provenance and ask how it relates to practice.
+      source: docs/reference/research/elicitation/elicitation-strategy-literature.md §1.1; docs/reference/research/elicitation/frontier-model-elicitor-failure-catalogue.md FM-14
     - name: Burden and impatience
       text: A cue that the expert is pressed, bored, or burdened is a fact about the interview, not a permission to stop. Notice it, name what is still missing, and let the expert choose; never let it end the interview by itself.
       source: docs/reference/research/elicitation/frontier-model-elicitor-failure-catalogue.md FM-04; evaluations/protocols/process-model-elicitation/baseline/condition-3-prompt.md HINT-RESPECTFUL-CLOSE
@@ -48,8 +54,8 @@ guidance:
       source: docs/reference/research/elicitation/elicitation-strategy-literature.md §1.3 (mean-or-tail router)
       for_precision: [number, range, spread]
     - name: Quantiles, never three points
-      text: 'For anything that varies, ask "typically?", then "one time in ten, worse than?", then "one time in ten, better than?". Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. If a min/mode/max triple arrives unprompted, ask the confidence question and record whether the middle value is a mode or a mean.'
-      source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (category 4); docs/reference/research/elicitation/elicitation-strategy-literature.md §1.4 (IDEA four-step interval, anti-triangular guard)
+      text: Ask first for a lower and upper plausible value, then a typical value, then how confident the expert is that reality falls inside the interval. Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. Record which protocol was used rather than silently mixing interval-first and typical-first answers.
+      source: docs/reference/research/elicitation/elicitation-strategy-literature.md §1.4 (IDEA four-step interval, anti-triangular guard); docs/archive/specs/cps-interview-guidance-2026-08-25.md CPS-Q01
       for_precision: [spread]
     - name: The clairvoyant test
       text: A quantity is well enough defined only when someone who could see everything could report it without asking a clarifying question. If the slot's name would need one, ask the clarifying question first.
@@ -63,15 +69,21 @@ guidance:
       source: docs/reference/research/elicitation/elicitation-strategy-literature.md §2.2 (premortem card)
       for_precision: [range, spread]
     - name: Restate to check
-      text: '"So you are saying that ___?" — a restatement in your own words, offered for correction. Use it to fix an answer in its context, never to put words in the expert''s mouth; a correction is a capture, assent to your phrasing is not.'
+      text: '"So you are saying that ___?" — a restatement in your own words, offered for correction. When the expert confirms or corrects it, ask them for the settled wording and capture that wording; bare assent to your phrasing is not their statement.'
       source: docs/reference/research/elicitation/elicitation-strategy-literature.md §5.1 (check-reflect / restatement); docs/reference/research/elicitation/frontier-model-elicitor-failure-catalogue.md FM-15
+    - name: Trade weights through choices
+      text: When the expert cannot name an exchange rate between objectives, offer two concrete outcomes that trade one against the other and ask which they would choose. Vary the pair until the boundary is visible; do not ask for an abstract weight.
+      source: evaluations/protocols/process-model-elicitation/baseline/condition-2.md (cliff and slope objective); docs/reference/research/elicitation/elicitation-strategy-literature.md §2.1 (swing weighting)
+    - name: One incident is not a rate
+      text: A memorable incident gives consequence and mechanism, not frequency. Ask how many opportunities there were, what period the expert is recalling, and whether the incident was ordinary or exceptional before recording a rate.
+      source: evaluations/protocols/process-model-elicitation/baseline/condition-1.md (outage frequency); docs/archive/specs/cps-interview-guidance-2026-08-25.md CPS-Q01
   movements:
     slice:
       - name: One concrete case end to end
         text: 'Before sweeping anything, walk one real case from beginning to end — "walk me through one, from when it arrives to when it leaves". The slice exposes the structure and the vocabulary; everything the sweeps later ask about, they ask about because the slice revealed it.'
         source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (Slice, then sweep); docs/reference/research/elicitation/elicitation-strategy-literature.md §1.2 (bounded task-diagram opener)
       - name: Escalate hypotheticals only from a real case
-        text: A what-if is useful only when anchored to an incident already on record; vary the real case. A free-floating hypothetical returns the expert's policy, not their practice.
+        text: Anchor a what-if to a real case when one is available. A constructed contrast may still test a suspected rule, but state that its parameters are yours and capture only what the expert confirms or corrects.
         source: docs/reference/research/elicitation/elicitation-strategy-literature.md §2.3 (hypothetical-escalation card)
     sweep:
       - name: One property across one stratum
@@ -79,14 +91,14 @@ guidance:
         source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (Slice, then sweep); docs/control/SPEC-LEDGER.md §11.5
         for_precision: [number, range, spread]
       - name: Ask for absences
-        text: 'Near the end of each topic ask "is there anything that never happens?" and "what have I not asked about that matters here?". What never happens is a constraint; what was not asked is the coverage the model would otherwise silently lack.'
+        text: 'Near the end of each topic ask for cases that never happen and for exceptions or constraints not yet discussed. This offers one cheap correction opportunity; it does not prove coverage or replace the completion report.'
         source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (Ask for absences); docs/reference/research/elicitation/frontier-model-elicitor-failure-catalogue.md FM-08
       - name: Exceptions as a sweep
         text: For each kind of thing that can go wrong, ask what happens to the work in hand, what happens to the case as a whole, and what the recovery is — three questions, asked across the exceptions the expert names.
         source: docs/reference/research/elicitation/elicitation-strategy-literature.md §3.1 (exception sweep card)
   licenses:
     - name: Batch breadth, sequence depth
-      text: You may group two to four related survey questions in one turn when they share a frame; probe one thread at a time when deepening. Five items is a warning; an opening battery is a failure.
+      text: You may group two to four related survey questions in one turn when they share a frame; probe one thread at a time when deepening. This is a one-run-vindicated departure from strict one-question guidance, not a universal optimum. Five items is a warning; an opening battery is a failure.
       source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (Batch breadth, sequence depth); docs/archive/specs/cps-interview-guidance-2026-08-25.md GEN-Q02; docs/reference/research/elicitation/frontier-model-elicitor-failure-catalogue.md FM-12
     - name: Name the grade
       text: You may tell the expert what an answer has reached and what is still needed — "I have the typical figure; I do not yet have how bad it gets" — and ask for the smallest thing that would close the gap.
@@ -97,6 +109,15 @@ guidance:
     - name: Defer with a deposit
       text: You may leave a topic unfinished when the expert cannot answer now — but only by recording what is missing, why, and where it would come from. A deferral without a deposit is a promise, and promises are the failure.
       source: docs/reference/research/elicitation/frontier-model-elicitor-failure-catalogue.md (Licensed deferral is a deposit, not a promise; FM-02, FM-03)
+    - name: Press without trapping
+      text: When the expert is busy, you may name the smallest load-bearing gap and ask whether to spend the remaining time on it or stop. Pressure licenses a clear choice, never pretending the gap is closed.
+      source: evaluations/protocols/process-model-elicitation/baseline/condition-2.md (huddle time pressure); docs/adr/0007-harness-teaching-meets-plugin-content-at-fixed-keys.md (decision 2)
+    - name: Decline a sweep
+      text: You may decline to sweep a stratum when no active objective depends on it. Say why it is outside the current slice and leave it available for a later objective.
+      source: docs/adr/0007-harness-teaching-meets-plugin-content-at-fixed-keys.md (decision 2); evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (Objectives first)
+    - name: Propose structure for correction
+      text: You may offer a low-risk structure as your suggestion when it is faster to correct than to elicit from nothing. Mark it as yours, invite correction, and capture only the expert's settled wording.
+      source: evaluations/protocols/process-model-elicitation/baseline/condition-2.md (corrected model skeleton); docs/reference/research/elicitation/frontier-model-elicitor-failure-catalogue.md FM-15
   motifs:
     - name: Ask whether, never assemble
       text: A motif is a question — "is there something here that works like ___?" — asked with its parameters. The expert's account is where structure comes from; the motif catalogue drives questions and gap-detection, never the model.
@@ -117,6 +138,12 @@ guidance:
     - name: Assent taken as origin
       text: The expert agreed to a phrasing that was yours. Their agreement is evidence that they did not object, not that they said it; the capture must quote them, not you.
       source: docs/reference/research/elicitation/frontier-model-elicitor-failure-catalogue.md FM-15
+    - name: Schema-shaped questioning
+      text: Your questions follow the model's headings or fields instead of the thread the expert is answering. The resulting coverage looks orderly while concrete structure and tacit distinctions remain hidden.
+      source: evaluations/protocols/process-model-elicitation/baseline/condition-1.md (opening questionnaire); docs/adr/0007-harness-teaching-meets-plugin-content-at-fixed-keys.md (decision 2)
+    - name: Correction recorded twice
+      text: A corrected or sharpened statement is about to be appended beside its earlier form instead of superseding it. The model will treat a correction as two competing facts.
+      source: docs/adr/0007-harness-teaching-meets-plugin-content-at-fixed-keys.md (decision 2); evaluations/protocols/process-model-elicitation/baseline/condition-1.md (confirmed inference)
   rabbit_holes:
     - name: Structure before responses
       text: Asking about how the system is built before knowing what question it must answer produces detail nobody needs. Refuse a structural thread until at least one objective or response is on record.
@@ -127,6 +154,15 @@ guidance:
     - name: Depth where nothing depends on it
       text: A fact earns probing when something the model must answer depends on it. Depth on a node outside every anchor's slice is effort the expert pays for and the model does not use.
       source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (Objectives first — depth is objective-relative); docs/adr/0006-plugins-per-target-formalism.md
+    - name: Clearinghouse as coverage
+      text: Asking what you failed to ask may offer a final correction, but it cannot discover an omission the expert also does not notice. Never use a clearinghouse answer as evidence that coverage is complete.
+      source: docs/archive/specs/cps-interview-guidance-2026-08-25.md; evaluations/protocols/process-model-elicitation/baseline/condition-3-prompt.md
+    - name: Whole-model restatement as progress
+      text: Repeatedly summarising the whole model during elicitation consumes time without deepening the active thread. Reserve one complete read-back for close; use local restatement for correction.
+      source: docs/adr/0007-harness-teaching-meets-plugin-content-at-fixed-keys.md (decision 2); docs/reference/research/elicitation/elicitation-strategy-literature.md §4.4
+    - name: Document treated as practice
+      text: A schedule, procedure, or spreadsheet states one source's claim. Do not take it for the practised rule; confirm when it holds, when it does not, and whose observation would distinguish the two.
+      source: evaluations/protocols/process-model-elicitation/baseline/condition-2.md (schedule versus practice); docs/reference/research/elicitation/elicitation-strategy-literature.md §1.1
   failure_modes:
     - name: Silent hardening
       text: A vague or hedged answer becomes a precise value in the model without a clarification turn.
@@ -165,14 +201,23 @@ runbooks:
   construct:
     kickoff:
       - name: Objectives first
-        text: Establish what the model must be able to answer, and for whom, before anything else; then let it prioritise the rest. What "better" means, numerically where possible, is almost never written down — expect to co-construct it.
+        text: Establish what the model must be able to answer, and for whom, before anything else; then let it prioritise the rest.
         source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (Objectives first, category 1)
+      - name: Quantify better when relevant
+        text: Where the plugin demands a numeric objective, ask what "better" means and expect to co-construct the comparison rather than receive a ready-made metric.
+        source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (Objectives first, category 1); evaluations/protocols/process-model-elicitation/baseline/condition-2.md (cliff and slope objective)
         for_precision: [number, range, spread]
       - name: The posture
         text: "From the first exchanges, take the expert's time available, what the model is for, how confident it must be, and how far they will tolerate you proposing assumptions. These set the interview's stance; they are not asked as a form."
         source: docs/adr/0007-harness-teaching-meets-plugin-content-at-fixed-keys.md (decision 4)
-      - name: No structure in the first exchange
-        text: Do not ask how the system is built until an objective is on record. The bounded opener is a three-to-six-step account of what happens, not a diagram.
+      - name: Define the boundary and horizon
+        text: Establish what is inside, what is outside, why that boundary serves the objective, and how far in time the model must remain useful before asking for structure.
+        source: evaluations/protocols/process-model-elicitation/baseline/condition-2.md (scope and horizon); docs/reference/research/elicitation/elicitation-strategy-literature.md §4.1
+      - name: Name factors and the accuracy bar
+        text: Ask what the expert may vary, what response decides success, and what observation or replay would make the result accurate enough for its intended use.
+        source: docs/reference/research/elicitation/elicitation-strategy-literature.md §1.2, §4.3; evaluations/protocols/process-model-elicitation/baseline/condition-1.md (validation target)
+      - name: Purpose before structure
+        text: Do not ask how the system is built until an objective, boundary, and accuracy bar are on record. After that kickoff, use a bounded three-to-six-step account to begin the slice rather than requesting a diagram.
         source: docs/reference/research/elicitation/elicitation-strategy-literature.md §1.2 (opening-five card)
     trajectory:
       - name: Slice, then sweep
@@ -187,6 +232,9 @@ runbooks:
       - name: Change technique when yield drops
         text: When several turns produce nothing new, change technique — a story, a contrast, a sweep of absences — rather than asking more of the same open questions.
         source: docs/reference/research/elicitation/elicitation-strategy-literature.md §2.4 (yield monitor)
+      - name: Select by posture
+        text: When appetite is high, explore openly and follow a concrete slice. When time is constrained, synthesise what is known and invite correction. In a mixed posture, propose low-risk structure and spend questions on high-impact uncertainty. These are biases for choosing among available moves, not a state machine.
+        source: docs/adr/0007-harness-teaching-meets-plugin-content-at-fixed-keys.md (decision 2)
     close:
       - name: End properly
         text: Before delivering, summarise what you have, state what is missing or assumed, and give the expert one chance to correct you. Do not end because the expert seems busy; if pressed for time, say what is still missing and let them choose. Do not keep going once the demanded slots are satisfied.
@@ -200,6 +248,12 @@ runbooks:
       - name: Deliver the losses
         text: The deliverable includes the assumption ledger and a short account of what the model deliberately leaves out and why.
         source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (The deliverable)
+      - name: Name the stopping outcome
+        text: State whether the model completed its demanded slice, the expert stopped, the time budget ended, or a partial result was delivered for another reason. A smooth conversation or a document in hand is not completion.
+        source: docs/adr/0007-harness-teaching-meets-plugin-content-at-fixed-keys.md (decision 2)
+      - name: Separate assumptions from simplifications
+        text: List unknown claims supplied provisionally as assumptions separately from deliberate exclusions or collapsed detail. For each simplification, say what is lost and why the objective permits it.
+        source: evaluations/protocols/process-model-elicitation/baseline/condition-1.md (assumptions versus simplifications); docs/reference/research/elicitation/elicitation-strategy-literature.md §4.1
   review-and-revise:
     kickoff:
       - name: Locate the change
diff --git a/libs/@hashintel/brunch-agent/packages/repertoire/test/repertoire.test.ts b/libs/@hashintel/brunch-agent/packages/repertoire/test/repertoire.test.ts
index 8bd572f7011..500e61cf2d7 100644
--- a/libs/@hashintel/brunch-agent/packages/repertoire/test/repertoire.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/repertoire/test/repertoire.test.ts
@@ -1,3 +1,5 @@
+import { readFileSync } from "node:fs";
+
 import { describe, expect, test } from "vitest";
 
 import {
@@ -5,6 +7,7 @@ import {
   guidanceEntries,
   JOBS,
   MOVEMENTS,
+  readPluginDefinition,
   RUNBOOK_KEYS,
   runbookEntries,
 } from "@hashintel/brunch-agent";
@@ -15,6 +18,12 @@ import { repertoire } from "../src/index";
 const FORMALISM_OR_DOMAIN =
   /\b(petri|transition|place|token|sdcpn|gherkin|scenario|feature|hospital|coating|truck|packaging)\b/iu;
 
+const sentences = (text: string): string[] =>
+  text
+    .split(/(?<=[.!?])\s+/u)
+    .map((sentence) => sentence.toLowerCase().replace(/\s+/gu, " ").trim())
+    .filter((sentence) => sentence.length >= 40);
+
 describe("the shipped repertoire", () => {
   test("fills every guidance key, both movements, and every runbook key of every job", () => {
     const guidancePaths = new Set(
@@ -83,7 +92,83 @@ describe("the shipped repertoire", () => {
       ["The clairvoyant test", ["number", "range", "spread"]],
       ["Premortem", ["range", "spread"]],
       ["One property across one stratum", ["number", "range", "spread"]],
-      ["Objectives first", ["number", "range", "spread"]],
+      ["Quantify better when relevant", ["number", "range", "spread"]],
     ]);
   });
+
+  test("fills the selection, permission, warning, scope, and stopping guidance decided by the ADR", () => {
+    const entries = [
+      ...guidanceEntries(repertoire.guidance),
+      ...runbookEntries(repertoire.runbooks),
+    ];
+    const namesAt = (path: string) =>
+      entries
+        .filter((entry) => entry.path === path)
+        .map((entry) => entry.item.name);
+
+    expect(namesAt("licenses")).toEqual(
+      expect.arrayContaining([
+        "Press without trapping",
+        "Decline a sweep",
+        "Propose structure for correction",
+      ]),
+    );
+    expect(namesAt("smells")).toEqual(
+      expect.arrayContaining([
+        "Schema-shaped questioning",
+        "Correction recorded twice",
+      ]),
+    );
+    expect(namesAt("rabbit_holes")).toEqual(
+      expect.arrayContaining([
+        "Clearinghouse as coverage",
+        "Whole-model restatement as progress",
+        "Document treated as practice",
+      ]),
+    );
+    expect(namesAt("construct.kickoff")).toEqual(
+      expect.arrayContaining([
+        "Define the boundary and horizon",
+        "Name factors and the accuracy bar",
+      ]),
+    );
+    expect(namesAt("construct.trajectory")).toContain("Select by posture");
+    expect(namesAt("construct.close")).toEqual(
+      expect.arrayContaining([
+        "Name the stopping outcome",
+        "Separate assumptions from simplifications",
+      ]),
+    );
+  });
+
+  test("plugin cells add to the repertoire without repeating its sentences", () => {
+    const repertoireSentences = new Set(
+      [
+        ...guidanceEntries(repertoire.guidance),
+        ...runbookEntries(repertoire.runbooks),
+      ].flatMap(({ item }) => sentences(item.text)),
+    );
+    const repeated = ["plugin-sdcpn", "plugin-gherkin"].flatMap(
+      (packageName) => {
+        const definition = readPluginDefinition(
+          readFileSync(
+            new URL(`../../${packageName}/plugin.yaml`, import.meta.url),
+            "utf8",
+          ),
+        );
+        return [
+          ...guidanceEntries(definition.guidance),
+          ...runbookEntries(definition.runbooks),
+        ].flatMap(({ path, item }) =>
+          sentences(item.text)
+            .filter((sentence) => repertoireSentences.has(sentence))
+            .map(
+              (sentence) => `${packageName}:${path}:${item.name}:${sentence}`,
+            ),
+        );
+      },
+    );
+
+    expect(repeated).toEqual([]);
+  });
 });

From 0e581f3852280ea79f23bc0c64e5ec0a8f0f5e10 Mon Sep 17 00:00:00 2001
From: Lu Nelson <ln@hash.ai>
Date: Wed, 26 Aug 2026 16:52:28 +0200
Subject: [PATCH 6/9] Resolve cycle-two plugin review findings

Co-authored-by: Cursor <cursoragent@cursor.com>
---
 libs/@hashintel/brunch-agent/CONTEXT.md       |  4 +--
 .../docs/specs/plugin-contract.md             |  3 ++-
 .../packages/core/schema/CHANGELOG.md         | 25 ++++++++++++++++++-
 .../packages/core/src/completion.ts           | 17 +++----------
 .../packages/core/src/instructions.ts         | 15 ++---------
 .../packages/core/src/plugin-definition.ts    | 11 ++++++++
 .../packages/plugin-gherkin/plugin.yaml       |  2 +-
 .../packages/plugin-sdcpn/plugin.yaml         | 19 ++++++--------
 .../packages/plugin-sdcpn/test/plugin.test.ts |  6 +++++
 .../packages/repertoire/repertoire.yaml       |  3 ++-
 .../repertoire/test/repertoire.test.ts        |  1 +
 11 files changed, 62 insertions(+), 44 deletions(-)

diff --git a/libs/@hashintel/brunch-agent/CONTEXT.md b/libs/@hashintel/brunch-agent/CONTEXT.md
index 8134009a737..30ead60e188 100644
--- a/libs/@hashintel/brunch-agent/CONTEXT.md
+++ b/libs/@hashintel/brunch-agent/CONTEXT.md
@@ -121,7 +121,7 @@ One row of a plugin's `schema` key (the `Must know` table under ADR-0006): a slo
 _Avoid_: demand clause, scope expression, objective row
 
 **Pattern**:
-A discretionary, kind-indexed heuristic under a plugin's `patterns` key with a **machine-matchable trigger on node state**: the model situation that triggers it and the question that resolves it. A trigger the harness cannot match against node state (a vague quantifier, an expert who does not know) is guidance — a technique or a movement — not a pattern (ADR-0007). Surfaced by the harness when a node matches the trigger and the relevant slot is unsatisfied; the interviewer decides whether to use it. Never names a domain.
+A discretionary, kind-indexed heuristic under a plugin's `patterns` key. Its machine trigger is the declared kind plus, when present, one unsatisfied demanded slot; its `when` text explains when the surfaced candidate applies and its `ask` text gives the resolving question. A trigger the harness cannot narrow to node kind and slot state (a vague quantifier, an expert who does not know) is guidance — a technique or a movement — not a pattern (ADR-0007). The interviewer decides whether to use a surfaced candidate. Never names a domain.
 _Avoid_: card, kernel card (retired — ADR-0006 replaced Detects/Goal/Questions/Artifacts cards with pattern rows), technique card
 
 **Runbook**:
@@ -133,7 +133,7 @@ One of the fixed, harness-owned headings of plugin authoring (ADR-0007): the har
 _Avoid_: heading (for the authoring unit), section, property (unqualified)
 
 **Repertoire**:
-The harness's own filling of every guidance and runbook key — what it teaches every plugin about interviewing — shipped as `packages/repertoire`, rendered by bindings, never imported by a plugin. Admitted by evidence, not by plausibility; never rescoped without run evidence.
+The harness's own filling of every guidance and runbook key — what it can teach any plugin about interviewing — shipped as `packages/repertoire`, rendered by bindings, never imported by a plugin. An entry may declare the value grades it applies to; the harness derives applicability from the plugin's demand rows. Admitted by evidence, not by plausibility; never rescoped without run evidence.
 _Avoid_: quiver (retired name), strategy library, kernel
 
 **Mechanism type**:
diff --git a/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md b/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md
index 3365e5931c8..2df77b1d097 100644
--- a/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md
+++ b/libs/@hashintel/brunch-agent/docs/specs/plugin-contract.md
@@ -191,7 +191,8 @@ Full text survives in the
 - **Typed `ScopeExpr` / `where` / `inSupport` algebra:** demands are now per (kind, slot), and
   the anchor's dependency slice replaces `inSupport`; the algebra had nothing left to select.
 - **`ProposalType.affordance.firesWhen` (closed 7-value enum):** patterns are surfaced by a
-  node matching `when` with an unsatisfied slot, which needs no per-proposal predicate.
+  matching kind plus an optional unsatisfied demanded slot; `when` remains explanatory prose for
+  interviewer judgment, so no per-proposal predicate is needed.
 - **`NodeKind.completionAnchor`:** replaced first by rule, then by the declared `schema.anchor`.
 - **Typed `foldTable` / `demandTable` / `variantDimension` / `lossCategories` declaration:** the
   fold derives from the `must_know` rows, the demand list *is* that key, `source-regime` is a
diff --git a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
index 93de419c083..8f7572ec9ae 100644
--- a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
+++ b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
@@ -166,7 +166,7 @@ written against.
   splitting either semantic slot.
 - Added repertoire-item `for_precision`, a non-empty list of precision words.
   Rendering now omits an annotated default unless the plugin demands at least
-  one listed word. The seven quantity and observed-practice entries identified
+  one listed word. The eight quantity and observed-practice entries identified
   by the cycle review use the facet, so Gherkin is no longer taught numeric or
   retrospective elicitation merely because it shares the fixed key catalogue.
 - Completed the cycle-two content pass without adding or removing a key. The
@@ -179,3 +179,26 @@ written against.
   dynamics noise and the missed edge material. Gherkin's duplicate
   rule-without-example failure mode was removed. A gate now rejects exact
   sentence repetition between repertoire defaults and plugin cells.
+
+### Cycle-two review dispositions
+
+- Objective identity and deduplication do not change the key catalogue. They are
+  register semantics: plugins name the `objective` kind and its slots, while the
+  harness must decide whether a later statement refers to an existing objective
+  or creates another one.
+- Removed the SDCPN `rationale` attribute. The cycle found no evidence that
+  rationale should be collected on every kind, so a universal plugin facet
+  would create noise; targeted "why" questions remain available in patterns and
+  guidance where they resolve a known model gap.
+- Recounted the cycle-one condition-five evidence before considering finer
+  `must_know` rows. Its 267 captures use 22 unique slot names, all exact names
+  declared by the plugin; the larger observed count was slot instances across
+  nodes, not undeclared slot vocabulary. The catalogue therefore keeps the
+  current slot granularity until a run demonstrates a recurring unresolved
+  sub-slot.
+- Clarified that pattern matching is kind plus optional unsatisfied demanded
+  slot. Pattern prose explains why the surfaced candidate applies; it does not
+  add a hidden machine predicate.
+- Restricted "One incident is not a rate" to plugins demanding `range` or
+  `spread`, removed unqualified grade terminology from SDCPN prose, and shared
+  demand formatting between completion diagnostics and rendered instructions.
diff --git a/libs/@hashintel/brunch-agent/packages/core/src/completion.ts b/libs/@hashintel/brunch-agent/packages/core/src/completion.ts
index 82a304b6b37..1d3047100d3 100644
--- a/libs/@hashintel/brunch-agent/packages/core/src/completion.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/src/completion.ts
@@ -16,10 +16,10 @@ import {
   type SlotState,
 } from "./elicited-model";
 import {
+  formatPrecisionDemand,
   type FloorRow,
   type MustKnowRow,
   type PluginDefinition,
-  type PrecisionDemand,
   type PrecisionWord,
 } from "./plugin-definition";
 
@@ -141,17 +141,6 @@ export const precisionSatisfies = (
   return LADDER[given]! >= LADDER[demanded]!;
 };
 
-const describeDemand = (precision: PrecisionDemand): string => {
-  switch (precision.kind) {
-    case "word":
-      return precision.word;
-    case "any-of":
-      return precision.words.join(" or ");
-    case "at-least":
-      return `at least ${precision.count}`;
-  }
-};
-
 const isEmptySelection = (value: JsonValue): boolean =>
   value === null ||
   value === "" ||
@@ -187,7 +176,7 @@ const evaluateRow = (
     nodeId: node.id,
     kind: node.kind,
     slot: row.slot,
-    requirement: describeDemand(row.precision),
+    requirement: formatPrecisionDemand(row.precision),
     actual: describeSlot(slot),
     captureIds: slot?.captureIds ?? [],
   };
@@ -266,7 +255,7 @@ const evaluateRow = (
       precisionSatisfies(slot.precision, demanded),
     )
   ) {
-    const requirement = describeDemand(row.precision);
+    const requirement = formatPrecisionDemand(row.precision);
     return fail(
       "below-required-precision",
       `"${row.slot}" on ${node.id} is known as a ${slot.precision}; the model needs ${requirement}. Smallest delta: move it from ${slot.precision} to ${row.precision.kind === "word" ? row.precision.word : `one of ${requirement}`}.`,
diff --git a/libs/@hashintel/brunch-agent/packages/core/src/instructions.ts b/libs/@hashintel/brunch-agent/packages/core/src/instructions.ts
index 379e95673da..933da83684e 100644
--- a/libs/@hashintel/brunch-agent/packages/core/src/instructions.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/src/instructions.ts
@@ -21,10 +21,10 @@ import {
   type Job,
 } from "./keys";
 import {
+  formatPrecisionDemand,
   PRECISION_LADDER,
   type GuidanceItem,
   type PluginDefinition,
-  type PrecisionDemand,
   type PrecisionWord,
 } from "./plugin-definition";
 import { type Repertoire } from "./repertoire";
@@ -74,17 +74,6 @@ const applicableRepertoireItems = (
       item.forPrecision.some((precision) => precisions.has(precision)),
   );
 
-const renderDemand = (demand: PrecisionDemand): string => {
-  switch (demand.kind) {
-    case "word":
-      return demand.word;
-    case "any-of":
-      return demand.words.join(" or ");
-    case "at-least":
-      return `at least ${demand.count}`;
-  }
-};
-
 const paragraphs = (...parts: (string | undefined)[]): string[] =>
   parts.flatMap((part) =>
     part === undefined || part.trim() === "" ? [] : [part.trim()],
@@ -111,7 +100,7 @@ export const renderContract = (definition: PluginDefinition): string[] => {
       .filter((row) => row.kind === kindRow.kind)
       .map(
         (row) =>
-          `  - ${row.slot} — ${renderDemand(row.precision)}${row.notApplicableAllowed ? '; "not applicable" is accepted' : ""}. _Why:_ ${row.why}`,
+          `  - ${row.slot} — ${formatPrecisionDemand(row.precision)}${row.notApplicableAllowed ? '; "not applicable" is accepted' : ""}. _Why:_ ${row.why}`,
       );
     return [`- \`${kindRow.kind}\``, ...own].join("\n");
   });
diff --git a/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts b/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
index c1b9a1b6b8b..e1a8b8ec3e8 100644
--- a/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
+++ b/libs/@hashintel/brunch-agent/packages/core/src/plugin-definition.ts
@@ -43,6 +43,17 @@ export type PrecisionDemand =
   | { readonly kind: "any-of"; readonly words: readonly PrecisionWord[] }
   | { readonly kind: "at-least"; readonly count: number };
 
+export const formatPrecisionDemand = (demand: PrecisionDemand): string => {
+  switch (demand.kind) {
+    case "word":
+      return demand.word;
+    case "any-of":
+      return demand.words.join(" or ");
+    case "at-least":
+      return `at least ${demand.count}`;
+  }
+};
+
 /** What each precision word means; harness vocabulary, rendered for every plugin. */
 export const PRECISION_LADDER: Readonly<
   Record<PrecisionWord | "at least N", string>
diff --git a/libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml b/libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml
index fe98164d35c..1cdabc2ac61 100644
--- a/libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml
+++ b/libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml
@@ -135,7 +135,7 @@ patterns:
     - id: P03
       on: [example]
       slot: the observable outcome
-      when: an outcome is stated as an intention ("should work", "is handled") rather than something observable.
+      when: the observable-outcome slot is unsatisfied; intentions such as "should work" and "is handled" are common below-grade forms.
       ask: Ask what someone watching would see, and where.
     - id: P04
       on: [step]
diff --git a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml
index 6ea5cafdf41..12f826e9cf9 100644
--- a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml
+++ b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml
@@ -96,7 +96,7 @@ ontology:
     - name: quantity
       on: any kind
       text: >-
-        Any duration, rate, probability, count, or capacity. Preserve the precision the expert
+        Any duration, rate, probability, count, or capacity. Preserve the value grade the expert
         reached; the row's demand says what further narrowing completion requires.
     - name: source-regime
       on: any kind
@@ -105,9 +105,6 @@ ontology:
         One model, not two: when the manual and the floor disagree, both are recorded on the same
         node and the divergence is an ordinary typed conflict for the expert to resolve —
         elicitation gold, not an error.
-    - name: rationale
-      on: any kind
-      text: Why the expert says it is so — on any kind, never only on objectives.
 
 schema:
   preamble: |
@@ -267,7 +264,7 @@ patterns:
         unplanned arrival — rather than a step in the flow
       ask: >-
         occurrence and duration are two slots. Ask how often, as a range, for each named event
-        separately; then how long, as a spread. Keep the precision the expert actually gave; never
+        separately; then how long, as a spread. Keep the value grade the expert actually gave; never
         round a range up to a spread.
     - id: P02
       on: [activity]
@@ -350,11 +347,11 @@ guidance:
         `boundary-condition`, not only on the work itself. Ask for both the work time and the
         availability rule.
   techniques:
-    - name: precision is about the value, not its source
+    - name: value grade is not evidence
       text: >-
-        "About three hours" from the expert is an honest `number` at the wrong precision; "three
-        hours" supplied by the interviewer is at the right precision and is not evidence at all.
-        Track both and let neither substitute for the other.
+        "About three hours" from the expert is an honest `number` below the demanded grade; "three
+        hours" supplied by the interviewer may look narrow enough and is not evidence at all. Track
+        grade and evidence separately and let neither substitute for the other.
     - name: stress the binding resource
       text: >-
         Before deepening every duration into a distribution, ask which `entity-type` actually
@@ -449,7 +446,7 @@ guidance:
         Establish the `validation-criterion` and accuracy bar at kickoff even though they do not
         project today. For `data-binding`, stop after the variable, source, and any evidence gap;
         implementation detail belongs in the loss report.
-    - name: precision below what the expert observes
+    - name: grade finer than what the expert observes
       text: >-
         Do not decompose a quantity below the granularity the expert can observe. Record the coarser
         value and a deposit naming where finer evidence could come from.
@@ -488,7 +485,7 @@ runbooks:
       - name: the deliverable
         text: >-
           Summarise per kind. Deliver the model with every node in the expert's own vocabulary,
-          each slot's value and precision as actually obtained and its source-regime where both were
+          each slot's value grade as actually obtained and its source-regime where both were
           given; the assumption ledger; and a loss section — what the model deliberately leaves
           out, which slots are open and why, which objectives are unsupported, and which kinds the
           net cannot carry.
diff --git a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/test/plugin.test.ts b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/test/plugin.test.ts
index 936d7d374dd..7a345a2ac20 100644
--- a/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/test/plugin.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/plugin-sdcpn/test/plugin.test.ts
@@ -102,6 +102,12 @@ describe("the SDCPN plugin", () => {
     ).toEqual({ kind: "word", word: "spread" });
   });
 
+  test("does not collect unsupported rationale on every kind", () => {
+    expect(
+      sdcpnDefinition.ontology.attributes.map((attribute) => attribute.name),
+    ).not.toContain("rationale");
+  });
+
   test("accepts an assertion addressed to a kind and slot the file names", () => {
     const schema = createSweepExtractionResultSchema(sdcpn);
     const proposal = proposalOf(
diff --git a/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml b/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml
index a99be2ca006..f4f5fae667a 100644
--- a/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml
+++ b/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml
@@ -77,6 +77,7 @@ guidance:
     - name: One incident is not a rate
       text: A memorable incident gives consequence and mechanism, not frequency. Ask how many opportunities there were, what period the expert is recalling, and whether the incident was ordinary or exceptional before recording a rate.
       source: evaluations/protocols/process-model-elicitation/baseline/condition-1.md (outage frequency); docs/archive/specs/cps-interview-guidance-2026-08-25.md CPS-Q01
+      for_precision: [range, spread]
   movements:
     slice:
       - name: One concrete case end to end
@@ -91,7 +92,7 @@ guidance:
         source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (Slice, then sweep); docs/control/SPEC-LEDGER.md §11.5
         for_precision: [number, range, spread]
       - name: Ask for absences
-        text: 'Near the end of each topic ask for cases that never happen and for exceptions or constraints not yet discussed. This offers one cheap correction opportunity; it does not prove coverage or replace the completion report.'
+        text: "Near the end of each topic ask for cases that never happen and for exceptions or constraints not yet discussed. This offers one cheap correction opportunity; it does not prove coverage or replace the completion report."
         source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (Ask for absences); docs/reference/research/elicitation/frontier-model-elicitor-failure-catalogue.md FM-08
       - name: Exceptions as a sweep
         text: For each kind of thing that can go wrong, ask what happens to the work in hand, what happens to the case as a whole, and what the recovery is — three questions, asked across the exceptions the expert names.
diff --git a/libs/@hashintel/brunch-agent/packages/repertoire/test/repertoire.test.ts b/libs/@hashintel/brunch-agent/packages/repertoire/test/repertoire.test.ts
index 500e61cf2d7..923b897701b 100644
--- a/libs/@hashintel/brunch-agent/packages/repertoire/test/repertoire.test.ts
+++ b/libs/@hashintel/brunch-agent/packages/repertoire/test/repertoire.test.ts
@@ -91,6 +91,7 @@ describe("the shipped repertoire", () => {
       ["Quantiles, never three points", ["spread"]],
       ["The clairvoyant test", ["number", "range", "spread"]],
       ["Premortem", ["range", "spread"]],
+      ["One incident is not a rate", ["range", "spread"]],
       ["One property across one stratum", ["number", "range", "spread"]],
       ["Quantify better when relevant", ["number", "range", "spread"]],
     ]);

From 3dc4beb268f77b6d30be11eea0c63f871304047e Mon Sep 17 00:00:00 2001
From: Lu Nelson <ln@hash.ai>
Date: Wed, 26 Aug 2026 17:40:07 +0200
Subject: [PATCH 7/9] Freeze the plugin key catalogue

Co-authored-by: Cursor <cursoragent@cursor.com>
---
 .../baseline/readout.md                       |    80 +-
 .../transcripts/condition-4-system.md         |    79 +-
 .../baseline/transcripts/condition-4.md       |  1472 +-
 .../baseline/transcripts/condition-4.raw.json |   372 +-
 .../transcripts/condition-5-captures.json     |  9084 ++++-----
 .../baseline/transcripts/condition-5-model.md |   637 +-
 .../transcripts/condition-5-system.md         |    79 +-
 .../baseline/transcripts/condition-5.md       |   341 +-
 .../baseline/transcripts/condition-5.raw.json | 15507 ++++++----------
 .../{ => cycle-1}/condition-4-model.txt       |     0
 .../transcripts/cycle-1/condition-4-system.md |   286 +
 .../transcripts/cycle-1/condition-4.md        |  1229 ++
 .../transcripts/cycle-1/condition-4.raw.json  |   825 +
 .../cycle-1/condition-5-captures.json         |  9292 +++++++++
 .../transcripts/cycle-1/condition-5-model.md  |   444 +
 .../transcripts/cycle-1/condition-5-system.md |   316 +
 .../transcripts/cycle-1/condition-5.md        |   375 +
 .../transcripts/cycle-1/condition-5.raw.json  | 14345 ++++++++++++++
 .../packages/core/schema/CHANGELOG.md         |    13 +
 19 files changed, 37354 insertions(+), 17422 deletions(-)
 rename libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/{ => cycle-1}/condition-4-model.txt (100%)
 create mode 100644 libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4-system.md
 create mode 100644 libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4.md
 create mode 100644 libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4.raw.json
 create mode 100644 libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5-captures.json
 create mode 100644 libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5-model.md
 create mode 100644 libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5-system.md
 create mode 100644 libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5.md
 create mode 100644 libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5.raw.json

diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/readout.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/readout.md
index 8ff8eebb2da..2475d2b0291 100644
--- a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/readout.md
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/readout.md
@@ -1,17 +1,14 @@
 # Baseline control — read-out (FE-1361)
 
 Scored 2026-08-13, against the transcripts in [`transcripts/`](transcripts/). Design and
-mechanics in the executable
+mechanics are in the executable
 [protocol](../../../../../evaluations/protocols/process-model-elicitation/baseline/protocol.md).
-Both conditions ran `claude-opus-5` as interviewer
-against the same simulated master scheduler, single-shot each — every claim below is existence
-evidence from one run per condition, not a rate estimate. Condition 4 (the ADR-0007 teaching
-layer rendered as a prompt only, run and scored 2026-08-25) is appended at the end under its own
-heading; the sections between are the 2026-08-13 read-out of conditions 1 and 2, unchanged.
-Condition 5 (the shipped harness in the loop) ran on 2026-08-25; its transcript, raw record, and
-folded store are in [`transcripts/`](transcripts/) and its
-[turn latency assessment](condition-5-turn-latency.md) is written, but its read-out on the
-dimensions below is **pending review** and not part of this document yet.
+All conditions ran `claude-opus-5` as interviewer against the same simulated master scheduler,
+single-shot each — every claim below is existence evidence, not a rate estimate. The sections
+through the first condition-4 review are the 2026-08-13 / 2026-08-25 read-out unchanged.
+Cycle-one live-arm artifacts are archived under [`transcripts/cycle-1/`](transcripts/cycle-1/);
+the current condition-4 and condition-5 artifacts are the cycle-two runs from 2026-08-26. Their
+catalogue verdict is appended at the end.
 
 ## Headline findings
 
@@ -264,13 +261,13 @@ What one page of guidance demonstrably cannot fix, each observed in the stronges
 
 ## Condition 4 — the teaching layer as prompt only (scored 2026-08-25)
 
-Scored against [`transcripts/condition-4.md`](transcripts/condition-4.md) (22 interviewer
+Scored against [`transcripts/cycle-1/condition-4.md`](transcripts/cycle-1/condition-4.md) (22 interviewer
 turns, stop reason `delivered-after-forced-wrap`), the assembled system prompt
-[`transcripts/condition-4-system.md`](transcripts/condition-4-system.md) (the condition-4
+[`transcripts/cycle-1/condition-4-system.md`](transcripts/cycle-1/condition-4-system.md) (the condition-4
 framing + the rendered `repertoire.yaml` + `plugin-sdcpn/plugin.yaml`, ≈280 lines), and the
-delivered model [`transcripts/condition-4-model.txt`](transcripts/condition-4-model.txt).
+delivered model [`transcripts/cycle-1/condition-4-model.txt`](transcripts/cycle-1/condition-4-model.txt).
 Interviewer `claude-opus-5`, same simulated master scheduler, single shot — existence evidence
-from one run, not a rate. Line references are `condition-4.md:LINE`; interviewer turns are
+from one run, not a rate. Line references are `cycle-1/condition-4.md:LINE`; interviewer turns are
 numbered T1–T22 (T1 at line 22, T9 at 202, T10 at 236, T11–T20 at 462–598, T21 at 610, T22 at
 958). The impatience probe was appended to the expert's T8 reply (line 198); the forced-wrap
 line was appended after T20 (line 606) and again after T21 (line 954), as the runner also did in
@@ -281,7 +278,7 @@ that is not visible in the Markdown transcript and is taken from the run record.
 
 **1. The teaching layer produced the best-disciplined nine questioning turns of any condition,
 and the thinnest model.** Objectives first with a demand for a real case ("Give me a real one
-you've argued about recently, not a general category" — `condition-4.md:28`), a bounded
+you've argued about recently, not a general category" — `cycle-1/condition-4.md:28`), a bounded
 five-or-six-step slice (`:68`), one to three questions per turn, quantile elicitation on all four
 changeover types, a resource-in-passing lens that caught the changeover crew (`:188`), a
 last-time probe that got the practiced contention rule with its borderline case and its override
@@ -584,7 +581,7 @@ strain; the last group lists what fired as designed, so the next cycle does not
 - `plugin.schema.must_know[activity]."what is lost when it changes the system's mode"` +
   `plugin.patterns.P02` + `plugin.guidance.motifs."mode change"` — three restatements of one
   ask; none fired. Ramp scrap never asked in T1–T10; the slot closed by redefinition
-  (`condition-4.md:1054`, `:723`). P02's second sentence ("If the expert does not know, ask what
+  (`cycle-1/condition-4.md:1054`, `:723`). P02's second sentence ("If the expert does not know, ask what
   they would treat as an authoritative source") is exactly the pack's situation (quality tracks
   scrap monthly) and was the right move at T5–T7; it did not occur. The row's phrasing "what is
   lost" reads as time lost when the neighbouring row is "how long it takes"; say "material,
@@ -673,7 +670,7 @@ strain; the last group lists what fired as designed, so the next cycle does not
   classifier prompt must accept a deliverable with declared gaps, or the harness's computed
   completion (absent in a prompt-only condition) must be the stop signal — which is the
   ADR-0007 position anyway.
-- **The raw record keeps the classifier's usage but not its verdicts.** `condition-4.raw.json`
+- **The raw record keeps the classifier's usage but not its verdicts.** `cycle-1/condition-4.raw.json`
   has 22 classifier calls with token counts and no text; the per-turn verdicts above had to be
   replayed. `run.ts` should record the verdict per turn.
 - **The forced-wrap line was injected twice** (`:606`, `:954`), as in condition 2, producing
@@ -681,3 +678,52 @@ strain; the last group lists what fired as designed, so the next cycle does not
 - **The condition-4 framing asked for "the most faithful representation the target formalism
   allows"** while the plugin says the interviewer does not build the net; the plugin won. A
   rerun should either drop that clause or run the projector on the deliverable.
+
+## Cycle 2 live-arm review and catalogue verdict (2026-08-26)
+
+Cycle two reran both live arms against `sdcpn/2026-08-26.2` and
+`repertoire/2026-08-26.2`.
+
+### What the runs established
+
+- **Condition 4 exercised the revised teaching but retained the known prompt-only stop defect.**
+  It ran all 24 turns and stopped at the hard limit
+  ([transcript](transcripts/condition-4.md):1–8), despite delivering a gap-declaring model more
+  than once. Its 1,006,344 input and 57,851 output tokens across 67 calls make the cost of that
+  classifier false negative material, but do not identify a missing plugin key.
+- **Condition 5 stopped honestly with an incomplete engagement.** The expert left after ten
+  turns; the interviewer delivered `expert-stopped, partial-with-open-slots`, named the source
+  for each deferred item, and did not claim to have built a net
+  ([transcript](transcripts/condition-5.md):275–316). The folded store contains 166 active
+  captures, 51 nodes, 0 unmapped captures, and 93 unsatisfied demands
+  ([model](transcripts/condition-5-model.md):7–10). The unsatisfied rows are visible rather than
+  silently filled.
+- **The evidence boundary held.** Five sweep attempts were refused when quotations were not
+  verbatim or occurred only in non-user entries; a later sweep admitted only deposits grounded
+  in the expert's words ([transcript](transcripts/condition-5.md):379–406). This cost turns, but
+  it did not corrupt the store.
+- **Node identity remains the dominant harness defect.** One wash-versus-idle question became
+  six near-duplicate objective nodes plus a separate exchange-rate objective
+  ([model](transcripts/condition-5-model.md):163–196); entity types, policies, constraints, and
+  activities show the same naming drift. The interviewer itself identified duplicate
+  changeover nodes ([transcript](transcripts/condition-5.md):369–373). This is register
+  identity/deduplication in the sweep/fold path, not vocabulary a plugin key can supply.
+- **Session termination remains harness control.** After the expert accepted the handover, the
+  runner dispatched two more non-question turns and classified the result as `stalled`
+  ([transcript](transcripts/condition-5.md):318–422). Guidance correctly described the stopping
+  outcome; the runtime lacks a terminal act for an incomplete, expert-stopped engagement.
+
+### Catalogue decision
+
+**The fixed key catalogue freezes at cycle two.** The cycle added, merged, and dropped no key.
+The revised surface expressed the evidence the runs needed: structural or numeric objective and
+arrival demands, explicit absences with deposits, mode-change loss, dynamics noise, validation
+criteria, source bindings, and a typed partial close. No observed fact required a new guidance,
+runbook, ontology, schema, pattern, or machinery key. Missing model content is represented by
+existing unsatisfied rows; adding keys would not repair it.
+
+Freeze means the authoring interface is stable, not that the harness is finished. Node
+identity/deduplication, quote-repair efficiency, the condition-4 delivery classifier, and the
+condition-5 terminal act remain follow-up evidence for the FE-1383 harness work. They do not
+reopen FE-1431's key catalogue unless a later target formalism proves that an existing key cannot
+express required authoring content.
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4-system.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4-system.md
index b382c4e3930..0823f42a47e 100644
--- a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4-system.md
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4-system.md
@@ -66,9 +66,8 @@ Things that look like kinds and are not:
 
 Attributes on every kind:
 
-- **quantity**, on any kind — Any duration, rate, probability, count, or capacity. Elicited by quantiles — "typical?", "one time in ten, worse than?", "one time in ten, better than?" — never minimum / most-likely / maximum, which yields overconfident triangles.
+- **quantity**, on any kind — Any duration, rate, probability, count, or capacity. Preserve the value grade the expert reached; the row's demand says what further narrowing completion requires.
 - **source-regime** (`prescribed` | `practiced`), on any kind — One model, not two: when the manual and the floor disagree, both are recorded on the same node and the divergence is an ordinary typed conflict for the expert to resolve — elicitation gold, not an error.
-- **rationale**, on any kind — Why the expert says it is so — on any kind, never only on objectives.
 
 ## Must know
 
@@ -82,7 +81,7 @@ a repair on another are the same rows instantiated on different nodes.
   - how many there are, or the population's shape — range; "not applicable" is accepted. _Why:_ initial populations for contended resources; unbounded is an allowed answer
 - `boundary-condition`
   - the starting state — spelled out. _Why:_ scenario initial state
-  - the arrival or availability pattern — spread. _Why:_ source rates and calendars; a single average hides the shape
+  - the arrival or availability pattern — spread or spelled out. _Why:_ source rates and calendars; a single average hides the shape
 - `activity`
   - what it needs before it can start — spelled out. _Why:_ transition preconditions
   - what it produces or changes — spelled out. _Why:_ transition outcomes
@@ -99,11 +98,12 @@ a repair on another are the same rows instantiated on different nodes.
   - what overrides it — spelled out; "not applicable" is accepted. _Why:_ exceptions are where the simulation and reality diverge
 - `dynamics`
   - what changes, in which direction, at what rate — range. _Why:_ the differential law; a direction with no rate cannot be simulated
+  - how it varies around that change — spread; "not applicable" is accepted. _Why:_ noise can dominate threshold timing; deterministic change may explicitly have none
   - what happens at a threshold — spelled out; "not applicable" is accepted. _Why:_ most continuous quantities exist to trigger something
 - `objective`
   - the question, in the expert's words — spelled out. _Why:_ everything else is elicited relative to it
   - the nodes it depends on — at least 1. _Why:_ an objective that depends on nothing is unsupported by the model
-  - what "better" means, and trade-off weights — range; "not applicable" is accepted. _Why:_ quantified objectives need a metric; some are qualitative
+  - what "better" means, and trade-off weights — range or spelled out; "not applicable" is accepted. _Why:_ quantified objectives need a metric; some are qualitative
 - `constraint`
   - the limit and what happens when it is hit — spelled out. _Why:_ a capacity without a consequence cannot be simulated
 - `data-binding`
@@ -133,8 +133,8 @@ that resolves it. None names a domain; each applies wherever its trigger appears
 surfaces a pattern when a node matches its trigger and the relevant slot is unsatisfied; the
 interviewer decides whether and how to use it.
 
-- **P01** — _when_ an `activity` is an event that can befall the system — a failure, an interruption, an unplanned arrival — rather than a step in the flow — _ask_ occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.
-- **P02** — _when_ an `activity` changes the system's mode — a setup, changeover, restart, warm-up, reconfiguration, handover — _ask_ ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert "unknown" into a value.
+- **P01** — _when_ an `activity` is an event that can befall the system — a failure, an interruption, an unplanned arrival — rather than a step in the flow — _ask_ occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.
+- **P02** — _when_ an `activity` changes the system's mode — a setup, changeover, restart, warm-up, reconfiguration, handover — _ask_ ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert "unknown" into a value. Ask before recording an explicit "not applicable"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.
 - **P03** — _when_ an `ordering/flow` moves things in groups — batches, runs, lots, loads — _ask_ ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.
 - **P04** — _when_ a `policy` or `boundary-condition` gates when something may proceed — a release, a start, an admission — _ask_ replace any time-shaped approximation ("about two days before") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.
 - **P05** — _when_ more than one thing can want the same `entity-type` instance at once — _ask_ ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.
@@ -150,11 +150,15 @@ _What to attend to in the expert's talk: the interview situations the harness ca
 - **Policy versus practice** — An answer in normative language — "we would", "the rule is", "you are supposed to" — reports a policy, not what happens. It is an occasion to ask when that last actually happened and what was done.
 - **Two answers in tension** — When something just said does not fit something said earlier, the tension is evidence — of a distinction not yet drawn, a condition not yet named, or an error. Say so and ask; do not pick one silently.
 - **Cues the expert relies on** — After any substantive answer, the expert's basis is worth more than the answer: "how would you know that — what are you actually looking at?" and "how would this be hard for someone less experienced?" surface what the expert did not think to say.
+- **Sources that disagree** — When two people or records disagree, preserve both claims and ask what observation would distinguish them. Do not average a contested fact or silently choose an authority.
+- **Unexplained terms and documents** — A local term must be explained in the expert's own words. A document supplies propositions to confirm, not facts to copy; keep its provenance and ask how it relates to practice.
 - **Burden and impatience** — A cue that the expert is pressed, bored, or burdened is a fact about the interview, not a permission to stop. Notice it, name what is still missing, and let the expert choose; never let it end the interview by itself.
 - **a resource named in passing** — A machine, team, vehicle, or bay mentioned as an aside is an `entity-type` whose instances are contended for; the contention rule it implies is a `policy`, and it is usually the expert's least-examined knowledge.
 - **"it depends"** — Hides either a branch in the `ordering/flow`, a `policy` deciding it, or a quantity that varies by `entity-type`. Ask which before moving on.
 - **"sometimes it breaks", "we have to wait for"** — An event-shaped `activity` with a rate and a duration, or a `boundary-condition` the system does not control. Both are routinely left out of a first account of the flow.
 - **warming up, wearing down, filling** — A `dynamics` node — something changing continuously while nothing discrete happens — or a mode change with a loss. The expert rarely volunteers the rate; the model cannot run without it.
+- **"always" and "never"** — A `constraint` or a `policy` stated in passing. Ask what enforces it, what it limits, and whether an exception has ever overridden it.
+- **duration that depends on the clock** — An `activity` duration whose elapsed time crosses a calendar boundary depends on a `boundary-condition`, not only on the work itself. Ask for both the work time and the availability rule.
 
 ## Techniques
 
@@ -163,13 +167,17 @@ _Question forms that deepen one answer already given. A technique is applied to
 - **Ask for the last time** — Prefer "when did that last happen, and what did you do?" to any generalisation. A story yields the sequence, the cues, and the exception; a generalisation yields the policy.
 - **No bare why** — Never ask "why do you do it this way?" as the primary probe; experts cannot report the basis of practised judgment on demand. Ask for an occasion and for what was attended to.
 - **Mean or tail** — Before eliciting any quantity, ask whether what matters is the typical case or the bad one — a mean or a tail. The answer decides whether a single figure, a range, or a spread is being asked for.
-- **Quantiles, never three points** — For anything that varies, ask "typically?", then "one time in ten, worse than?", then "one time in ten, better than?". Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. If a min/mode/max triple arrives unprompted, ask the confidence question and record whether the middle value is a mode or a mean.
+- **Quantiles, never three points** — Ask first for a lower and upper plausible value, then a typical value, then how confident the expert is that reality falls inside the interval. Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. Record which protocol was used rather than silently mixing interval-first and typical-first answers.
 - **The clairvoyant test** — A quantity is well enough defined only when someone who could see everything could report it without asking a clarifying question. If the slot's name would need one, ask the clarifying question first.
 - **Consistency probe** — "You said earlier that ___, but then you told me ___. How do you explain that?" — stated plainly, without choosing between the two.
 - **Premortem** — For anything rare or catastrophic, ask the expert to imagine it has already gone wrong — "it is a year from now and this has been the worst month on record; what happened?" — and demand mechanism and sequence, not sentiment.
-- **Restate to check** — "So you are saying that ___?" — a restatement in your own words, offered for correction. Use it to fix an answer in its context, never to put words in the expert's mouth; a correction is a capture, assent to your phrasing is not.
-- **quantiles, never triangles** — For any quantity, ask "typical?", then "one time in ten, worse than?", then "one time in ten, better than?" — never minimum / most-likely / maximum, which yields overconfident triangles. A `spread` is exactly this.
-- **precision is about the value, not its source** — "About three hours" from the expert is an honest `number` at the wrong precision; "three hours" supplied by the interviewer is at the right precision and is not evidence at all. Track both and let neither substitute for the other.
+- **Restate to check** — "So you are saying that ___?" — a restatement in your own words, offered for correction. When the expert confirms or corrects it, ask them for the settled wording and capture that wording; bare assent to your phrasing is not their statement.
+- **Trade weights through choices** — When the expert cannot name an exchange rate between objectives, offer two concrete outcomes that trade one against the other and ask which they would choose. Vary the pair until the boundary is visible; do not ask for an abstract weight.
+- **One incident is not a rate** — A memorable incident gives consequence and mechanism, not frequency. Ask how many opportunities there were, what period the expert is recalling, and whether the incident was ordinary or exceptional before recording a rate.
+- **value grade is not evidence** — "About three hours" from the expert is an honest `number` below the demanded grade; "three hours" supplied by the interviewer may look narrow enough and is not evidence at all. Track grade and evidence separately and let neither substitute for the other.
+- **stress the binding resource** — Before deepening every duration into a distribution, ask which `entity-type` actually constrains the objective and whether its utilisation or variability makes stochastic detail consequential.
+- **turn an unknown into an observable threshold** — When the expert cannot give an exact quantity, ask what boundary would change a decision or become visibly unacceptable. Record the threshold they can judge; do not invent the value beyond it.
+- **ask what is conserved** — When quantities enter and leave a process, ask what total should remain constant and where loss is possible. A conservation answer belongs as a `constraint`, in the expert's units.
 
 ## Movements
 
@@ -178,25 +186,29 @@ _The two shapes a stretch of interview takes. A slice walks one concrete case en
 ### Slice
 
 - **One concrete case end to end** — Before sweeping anything, walk one real case from beginning to end — "walk me through one, from when it arrives to when it leaves". The slice exposes the structure and the vocabulary; everything the sweeps later ask about, they ask about because the slice revealed it.
-- **Escalate hypotheticals only from a real case** — A what-if is useful only when anchored to an incident already on record; vary the real case. A free-floating hypothetical returns the expert's policy, not their practice.
-- **one instance, arriving to leaving** — One case in this formalism is one instance of the `entity-type` that flows, followed from the moment it reaches the system to the moment it leaves. Create nodes as they appear; as each `objective` becomes clearer, link it to the nodes it depends on. An `objective` that depends on nothing yet is unsupported — say so and go find its structure.
+- **Escalate hypotheticals only from a real case** — Anchor a what-if to a real case when one is available. A constructed contrast may still test a suspected rule, but state that its parameters are yours and capture only what the expert confirms or corrects.
+- **one instance, arriving to leaving** — One case in this formalism is one instance of the `entity-type` that flows, followed from the moment it reaches the system to the moment it leaves. If several things flow, first ask which unit defines one case — order, batch, item, or another named unit. Create nodes as they appear; as each `objective` becomes clearer, link it to the nodes it depends on. An `objective` that depends on nothing yet is unsupported — say so and go find its structure.
 
 ### Sweep
 
 - **One property across one stratum** — A sweep makes one property hold across one class of node the slice revealed — every step has a duration, every resource has a count. Sweep after the slice, and one property at a time, so the expert can answer from a single frame.
-- **Ask for absences** — Near the end of each topic ask "is there anything that never happens?" and "what have I not asked about that matters here?". What never happens is a constraint; what was not asked is the coverage the model would otherwise silently lack.
+- **Ask for absences** — Near the end of each topic ask for cases that never happen and for exceptions or constraints not yet discussed. This offers one cheap correction opportunity; it does not prove coverage or replace the completion report.
 - **Exceptions as a sweep** — For each kind of thing that can go wrong, ask what happens to the work in hand, what happens to the case as a whole, and what the recovery is — three questions, asked across the exceptions the expert names.
-- **strata are kinds, net-bearing first** — A stratum is one kind. Sweep in kind order, `entity-type` through `dynamics` (net-bearing) before `objective` through `validation-criterion` (partly or wholly IR-only).
+- **strata are kinds, net-bearing first** — After kickoff has established each `objective` and its `validation-criterion`, a stratum is one kind. Sweep `entity-type` through `dynamics` first because they bear the net, then complete the remaining IR-only rows.
 - **the unwritten constraints** — Close the `constraint` stratum with the unwritten rules: "what would a newcomer get wrong in the first week?", "what do you always or never do that is written nowhere?", "which rule exists because something once went wrong?"
+- **what can befall each activity** — Close the `activity` stratum by asking across exception types: work-item failure, deadline expiry, resource unavailability, external trigger, and constraint violation. For each named exception, ask what happens to the work, the case, and the recovery.
 
 ## Licenses
 
 _Moves the interviewer is permitted to make that a cooperative model would otherwise suppress. A license says what is allowed and the limit of the allowance; it never obliges._
 
-- **Batch breadth, sequence depth** — You may group two to four related survey questions in one turn when they share a frame; probe one thread at a time when deepening. Five items is a warning; an opening battery is a failure.
+- **Batch breadth, sequence depth** — You may group two to four related survey questions in one turn when they share a frame; probe one thread at a time when deepening. This is a one-run-vindicated departure from strict one-question guidance, not a universal optimum. Five items is a warning; an opening battery is a failure.
 - **Name the grade** — You may tell the expert what an answer has reached and what is still needed — "I have the typical figure; I do not yet have how bad it gets" — and ask for the smallest thing that would close the gap.
 - **Say what you would assume** — You may propose an assumption to unblock the interview, provided it is stated as yours, entered in the assumption ledger with why and how to check it, and the expert is asked. You may never let it pass into the model as theirs.
 - **Defer with a deposit** — You may leave a topic unfinished when the expert cannot answer now — but only by recording what is missing, why, and where it would come from. A deferral without a deposit is a promise, and promises are the failure.
+- **Press without trapping** — When the expert is busy, you may name the smallest load-bearing gap and ask whether to spend the remaining time on it or stop. Pressure licenses a clear choice, never pretending the gap is closed.
+- **Decline a sweep** — You may decline to sweep a stratum when no active objective depends on it. Say why it is outside the current slice and leave it available for a later objective.
+- **Propose structure for correction** — You may offer a low-risk structure as your suggestion when it is faster to correct than to elicit from nothing. Mark it as yours, invite correction, and capture only the expert's settled wording.
 
 ## Motifs
 
@@ -204,12 +216,12 @@ _Recurring shapes the formalism knows — offered as scaffolds for a question, n
 
 - **Ask whether, never assemble** — A motif is a question — "is there something here that works like ___?" — asked with its parameters. The expert's account is where structure comes from; the motif catalogue drives questions and gap-detection, never the model.
 - **Name plus variant** — Never record a motif by name alone; record the name and the axis on which it varies, in the expert's words. Names are stable across the literature and semantics are not.
-- **shared resource** — several activities want one `entity-type`'s instances — ask which wins and what overrides.
-- **batch, lot, load** — an `ordering/flow` that moves things in groups — ask what the group is and what a split costs.
-- **gate or release** — a `policy` or `boundary-condition` that lets things proceed — ask for the practiced event, not the approximate time.
-- **mode change** — a setup, changeover, restart, or warm-up — ask what is lost, after a named transition.
-- **event, not step** — a failure or interruption that befalls the system — ask rate and duration separately.
-- **threshold on a continuous quantity** — a `dynamics` node — ask what it triggers and which `activity` resets it.
+- **shared resource** — Several activities want one `entity-type`'s instances. Ask whether the server is indivisible or splittable by role, how many instances act together, which activity wins, and what overrides that rule.
+- **batch, lot, load** — An `ordering/flow` that moves things in groups. Ask whether formation fires by count, by a clock, or by either; whether the group must stay together; and what a split costs.
+- **gate or release** — A `policy` or `boundary-condition` that lets things proceed. Ask whether the gate is a state, an event, or a person's decision; where it is observed; and what overrides it.
+- **mode change** — A setup, changeover, restart, or warm-up. Ask whether loss depends on direction, whether the change is local or cascading, and which time, material, or capacity components are lost.
+- **event, not step** — A failure or interruption that befalls the system. Ask occurrence and duration separately, then whether the rate is independent or changes with a named state.
+- **threshold on a continuous quantity** — A `dynamics` node. Ask what it triggers, which `activity` resets it, and — when several components evolve — whether they combine additively or the weakest component decides.
 
 ## Smells
 
@@ -219,6 +231,8 @@ _Signs in the interviewer's own output — not the expert's — that the intervi
 - **Many questions in one turn** — You are about to ask more than four things at once, or anything at all before the first answer has landed. The expert will choose which to answer and silently drop the rest.
 - **Fluent and empty** — The conversation reads well and the completion report still lists the same unsatisfied slots it did three turns ago. Fluency is not progress.
 - **Assent taken as origin** — The expert agreed to a phrasing that was yours. Their agreement is evidence that they did not object, not that they said it; the capture must quote them, not you.
+- **Schema-shaped questioning** — Your questions follow the model's headings or fields instead of the thread the expert is answering. The resulting coverage looks orderly while concrete structure and tacit distinctions remain hidden.
+- **Correction recorded twice** — A corrected or sharpened statement is about to be appended beside its earlier form instead of superseding it. The model will treat a correction as two competing facts.
 - **a quantity for one type and no other** — given for one `entity-type` when others exist and never asked whether it varies (P07).
 - **a continuous quantity that triggers nothing** — a `dynamics` node with no threshold and no consequence usually does not belong in the model.
 - **a queue as a node** — a buffer or waiting state elicited as if it were an activity; it is implied and emerges in projection.
@@ -233,9 +247,14 @@ _Where not to dig, and what looks like progress and is not. Anti-guidance, kept
 - **Structure before responses** — Asking about how the system is built before knowing what question it must answer produces detail nobody needs. Refuse a structural thread until at least one objective or response is on record.
 - **The representation stopped changing** — That the model has stopped growing is not evidence it is complete; it is evidence you have stopped asking. Stop on the demanded slots, never on stability.
 - **Depth where nothing depends on it** — A fact earns probing when something the model must answer depends on it. Depth on a node outside every anchor's slice is effort the expert pays for and the model does not use.
+- **Clearinghouse as coverage** — Asking what you failed to ask may offer a final correction, but it cannot discover an omission the expert also does not notice. Never use a clearinghouse answer as evidence that coverage is complete.
+- **Whole-model restatement as progress** — Repeatedly summarising the whole model during elicitation consumes time without deepening the active thread. Reserve one complete read-back for close; use local restatement for correction.
+- **Document treated as practice** — A schedule, procedure, or spreadsheet states one source's claim. Do not take it for the practised rule; confirm when it holds, when it does not, and whose observation would distinguish the two.
 - **building the net in conversation** — Places, transitions, arcs, and colours are projection output. Naming them to the expert buys nothing and costs the expert's vocabulary.
 - **eliciting queues or scenarios** — Neither is a node. Ask about the activities on either side of a wait; assemble scenarios from `boundary-condition` nodes at simulation time.
-- **depth on IR-only kinds** — `data-binding` and `validation-criterion` project to nothing today; name them and record them for the loss report, do not elaborate them.
+- **depth on IR-only kinds** — Establish the `validation-criterion` and accuracy bar at kickoff even though they do not project today. For `data-binding`, stop after the variable, source, and any evidence gap; implementation detail belongs in the loss report.
+- **grade finer than what the expert observes** — Do not decompose a quantity below the granularity the expert can observe. Record the coarser value and a deposit naming where finer evidence could come from.
+- **eliciting the objective's answer** — The interview builds what the model needs to answer an `objective`; it does not ask the expert to predict that answer and store the prediction as model structure.
 
 ## Failure modes
 
@@ -251,7 +270,6 @@ _Named ways an interview of this kind fails, each with the signature by which it
 - **Deferral without deposit** — The interviewer names future work or external data as a prerequisite and records nothing. _Signature:_ A promise of later work with no durable record of what is missing and where it would come from.
 - **dead net** — the floor catches presence; only the sweep catches an order that was never actually stated. _Signature:_ no `ordering/flow` with its order spelled out; activities exist but nothing connects them
 - **unsupported objective** — the model cannot answer the question it was built for; the slice never reached it. _Signature:_ an `objective` whose dependency slot names no node in the model
-- **overconfident triangle** — the expert was asked the wrong three questions; re-ask as quantiles. _Signature:_ a duration or rate captured as minimum / most-likely / maximum
 
 ## Job: construct — no model exists
 
@@ -259,10 +277,13 @@ _Named ways an interview of this kind fails, each with the signature by which it
 
 _What to establish before any structure, and how. Kickoff produces a posture — the stance the rest of the interview takes from the expert's time, intended use, required confidence, and tolerance for proposed assumptions. It is a form the interviewer fills implicitly, never an opening battery of questions._
 
-- **Objectives first** — Establish what the model must be able to answer, and for whom, before anything else; then let it prioritise the rest. What "better" means, numerically where possible, is almost never written down — expect to co-construct it.
+- **Objectives first** — Establish what the model must be able to answer, and for whom, before anything else; then let it prioritise the rest.
+- **Quantify better when relevant** — Where the plugin demands a numeric objective, ask what "better" means and expect to co-construct the comparison rather than receive a ready-made metric.
 - **The posture** — From the first exchanges, take the expert's time available, what the model is for, how confident it must be, and how far they will tolerate you proposing assumptions. These set the interview's stance; they are not asked as a form.
-- **No structure in the first exchange** — Do not ask how the system is built until an objective is on record. The bounded opener is a three-to-six-step account of what happens, not a diagram.
-- **what "no model exists" means here** — The user knows the system; the interviewer knows the kinds. Capture each thing the user wants the model to answer or decide as an `objective` node. Expect to co-construct: these are almost never written down. Ask what "better" means and whether it can be quantified.
+- **Define the boundary and horizon** — Establish what is inside, what is outside, why that boundary serves the objective, and how far in time the model must remain useful before asking for structure.
+- **Name factors and the accuracy bar** — Ask what the expert may vary, what response decides success, and what observation or replay would make the result accurate enough for its intended use.
+- **Purpose before structure** — Do not ask how the system is built until an objective, boundary, and accuracy bar are on record. After that kickoff, use a bounded three-to-six-step account to begin the slice rather than requesting a diagram.
+- **what "no model exists" means here** — The user knows the system; the interviewer knows the kinds. Capture each thing the user wants the model to answer or decide as an `objective` node. Recast an optimisation request as a comparison among candidate policies, and name the time resolution over which the answer must remain useful.
 
 ### Trajectory
 
@@ -272,6 +293,7 @@ _Which movements in which bias, varied by posture. Stated as postures the interv
 - **Deepen before recording** — When an answer is not yet usable — vague, normative, or in tension with an earlier one — apply a technique to it before moving on. One thread at a time.
 - **Keep the assumption ledger** — Any value or rule you supply that the expert did not state goes in a numbered list with why it was assumed and how to check it. Never let one pass silently into the model.
 - **Change technique when yield drops** — When several turns produce nothing new, change technique — a story, a contrast, a sweep of absences — rather than asking more of the same open questions.
+- **Select by posture** — When appetite is high, explore openly and follow a concrete slice. When time is constrained, synthesise what is known and invite correction. In a mixed posture, propose low-risk structure and spend questions on high-impact uncertainty. These are biases for choosing among available moves, not a state machine.
 - **kind order** — Slice one instance end to end first; the shape of the model comes from the slice. Then sweep the nodes the slice revealed in kind order, net-bearing kinds before IR-only ones, checking each node's rows and every pattern its state matches.
 
 ### Close
@@ -282,5 +304,8 @@ _How to end honestly. Completion is computed by the harness from the model, neve
 - **Read it back** — The close is a walkthrough — the model read back item by item for sign-off — not a document handed over for silent review.
 - **Honour a stop** — When the expert stops, open no new topic. State the best useful result, the gaps, and the assumptions, and deliver what exists.
 - **Deliver the losses** — The deliverable includes the assumption ledger and a short account of what the model deliberately leaves out and why.
-- **the deliverable** — Summarise per kind. Deliver the model with every node in the expert's own vocabulary, each slot's value and precision as actually obtained and its source-regime where both were given; the assumption ledger; and a loss section — what the model deliberately leaves out, which slots are open and why, which objectives are unsupported, and which kinds the net cannot carry.
+- **Name the stopping outcome** — State whether the model completed its demanded slice, the expert stopped, the time budget ended, or a partial result was delivered for another reason. A smooth conversation or a document in hand is not completion.
+- **Separate assumptions from simplifications** — List unknown claims supplied provisionally as assumptions separately from deliberate exclusions or collapsed detail. For each simplification, say what is lost and why the objective permits it.
+- **the deliverable** — Summarise per kind. Deliver the model with every node in the expert's own vocabulary, each slot's value grade as actually obtained and its source-regime where both were given; the assumption ledger; and a loss section — what the model deliberately leaves out, which slots are open and why, which objectives are unsupported, and which kinds the net cannot carry.
 - **what the interviewer does not claim** — The SDCPN scaffold, the code-obligation sidecar, and the typed loss report are derived by the plugin's projection. The interviewer does not write them and must not claim the model is loadable, compiled, or simulated.
+- **stopping outcomes** — Named and distinct: `complete-under-declared-demands`, `partial-with-open-slots`, `unsupported-objective`, `data-deposit-required`, `expert-stopped`.
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4.md
index 365e008f246..74d032e041a 100644
--- a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4.md
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4.md
@@ -1,11 +1,11 @@
 # Baseline control — condition 4 (rendered repertoire + plugin definition, prompt only)
 
-- Run started: 2026-08-25T15:14:42.641Z
+- Run started: 2026-08-26T15:00:21.375Z
 - Interviewer: claude-opus-5 + condition-4-prompt.md + rendered repertoire.yaml + plugin-sdcpn/plugin.yaml (see condition-4-system.md)
 - Simulated expert: claude-sonnet-5 + situation-pack.md
-- Interviewer turns: 22 (impatience probe at 8, forced wrap at 20)
-- Stop reason: delivered-after-forced-wrap
-- Tokens: 720412 in (+0 cache write, +0 cache read) / 40823 out across 64 calls
+- Interviewer turns: 24 (impatience probe at 8, forced wrap at 20)
+- Stop reason: hard-stop
+- Tokens: 1006344 in (+0 cache write, +0 cache read) / 57851 out across 67 calls
 
 ---
 **Opening message**:
@@ -21,179 +21,223 @@ Please interview me about how our operation works, and then produce the model.
 
 **Interviewer**:
 
-Good — that's enough for me to start. I'll ask you about your operation in your own words; the format side is my problem, not yours.
+Good — that's enough for me to know what I'm building toward. I'll interview you in your own words about how the plant actually runs, keep a running note of what I've got and what I still need, and hand you back a structured model at the end. I won't invent numbers; anything I have to assume I'll list separately so you can check it.
 
-Before anything about how the plant is built, I want to know what the model has to be *for*. Two things to start:
+Let me start with what the model is *for*, because everything else gets prioritised against that.
 
-1. When your boss says "test scheduling decisions before making them" — what's a decision you'd actually want to test? Give me a real one you've argued about recently, not a general category.
+**When your boss says "test scheduling decisions before making them" — what's a decision you've actually had to make recently where you'd have wanted to try it in a model first?** Tell me the specific situation if you can.
 
-2. And when you compare two schedules today, what makes one better than the other in your eyes? I'm after the thing you'd actually point at — a number, a complaint you'd avoid, whatever it is.
+And alongside that: **when a schedule turns out to have been a bad one, how do you find out — what's the thing that goes wrong that you notice?**
 
 ---
 
 **Expert (Marta)**:
 
-Okay, real one: two weeks ago I had a Meridian white order finishing on Line 2 Thursday afternoon, and then a batch of tint waiting behind it. My instinct was to let Line 2 sit idle for maybe an hour because I had a heads-up another same-family white order was about to drop in from a distributor, and doing them back to back would save us a full washdown. My boss's question was basically "are you sure that's worth it, or are you just guessing?" And honestly — I was guessing. That's the kind of thing I'd love to test: hold the line versus wash it down now, which one actually costs less over the week.
+Okay, good question. Let me think of a real one.
 
-As for what makes one schedule better than another — first thing I look at is whether Meridian shipped on time, full stop, that's non-negotiable. After that it's changeover hours, because every hour the crew spends washing down is an hour not filling anything. And honestly I also just glance at how ugly the sheet looks — like, are there gaps where a line's sitting idle for no good reason. That last one's not a number, it's more a gut check, but it's real.
+A couple weeks back Line 1's mill motor hiccuped — not the four-day disaster, just a few hours down — right when I had a specialty batch and a Meridian white order both needing to move. I had to decide on the spot whether to shift the specialty over to Line 3 and eat the requalification headache, or hold it and let the white slip behind on Line 2 instead. I did it by gut at the huddle — moved the specialty, kept the white going — but I genuinely don't know if that was the right call or if I just got lucky. That's the kind of thing I'd love to run twice and see which one bites me less.
+
+The other recurring one is the idle-line-versus-washdown thing — do I sit Line 2 empty for an hour waiting on a same-family order, or just pay the three-hour washdown now. I make that call almost weekly and it's pure feel.
+
+As for how I find out a schedule was bad — honestly, it's usually the huddle two days later, or a call from Meridian's account rep. Late orders are the loudest signal — someone above me hears about it before I do sometimes. Quieter version is the changeover crew looking wrecked by Thursday because I stacked too many family switches back to back. And every so often quality flags a scrap spike and I go "oh, right, that was the week I rushed the ramp after a washdown."
 
 ---
 
 **Interviewer**:
 
-That's a good, concrete decision — hold the line for a possible same-family order versus wash down now. I'll build the model so that's testable.
+That's exactly the right kind of answer — two concrete recurring decisions, and three different ways badness shows up.
+
+Let me pin the purpose down before I ask about the plant itself.
 
-Two things about "better", then I'll get you to walk me through a job:
+1. I'm hearing **two questions the model must answer**: *"when a line goes down mid-run, do I reroute the affected job to another line and eat requalification, or hold it and let something else slip?"* and *"do I hold a line idle waiting for a same-family order, or pay the washdown now?"* Is that a fair statement of both, in your words? And is there a third recurring call of that type that you'd want to test — anything around sequencing, or order acceptance, or overtime?
 
-1. Meridian on-time is non-negotiable — what does "on time" actually mean in practice? A ship date on the order, a truck appointment, a promised week? And what happens when one *does* go late — who feels it and how?
+2. You said you'd want to see "which one bites me less." If I ran both versions of that Line 1 decision and handed you two sets of results — **what would you look at to say one was better?** Late orders, scrap, crew load, something else — and if one option gave you one late order and the other gave you a scrap spike, do you already know which way you'd lean, or does that depend?
 
-2. Changeover hours versus a late non-Meridian order: if a schedule saved you, say, four changeover hours but made one distributor order two days late, would you take it? I'm trying to find out whether these trade against each other at all, or whether lateness for everyone else is just soft.
+3. **How far ahead do you schedule, and at what resolution?** I want to know whether the model needs to be useful over a shift, a week, or a quarter.
 
 ---
 
 **Expert (Marta)**:
 
-Good questions, let me take them separately.
+Let me take those one at a time.
 
-On "on time" for Meridian — it's a ship date they give us via the order, usually with a delivery window attached, like a specific dock appointment on their end. So it's not just "shipped this week," it's "shipped in time to hit that appointment," which usually means it needs to leave our dock a day ahead for freight. If we miss it, first thing is a fine — I don't see the number, that's commercial's problem, but I hear about it. Second thing, worse honestly, is they track our on-time percentage and if it drops too far they threaten to delist SKUs. That's happened to a competitor of ours, so it's not an empty threat, and it's why the rule is absolute — we don't even try to be clever about it.
+**On the two decisions** — yes, that's fair, that's the two big ones. A third I'd add: **run-size / sequencing** — whether to split a big order into two runs to slot in a rush job, or batch several small orders of the same family together even if it means one of them ships a bit early and sits in the warehouse. I do that juggling every week on the sheet and I've never had a way to check if I'm leaving hours on the table.
 
-On the trade-off — honestly, yes, I'd take that trade most of the time, four hours of changeover is real money and crew time, and a distributor slipping two days is usually just an annoyed phone call from our sales rep, not a fine. But "most of the time" is doing a lot of work in that sentence — if it's the same distributor slipping late for the third week running, that's different, they'll start asking for a discount. So it's soft, but it's not infinitely soft. I couldn't put a number on it though — that's genuinely a "sit down with commercial" conversation, nobody's ever made me quantify it.
+I wouldn't say overtime approval is mine to test — that's the ops director's call, though I do feed him the "we'll miss X without it" argument, so maybe that's a variant of the same question rather than a fourth one.
+
+**On what I'd look at to judge the two options** — first thing, always, is: did anything ship late, and to whom. A late order to Meridian is worse than three late orders to a small distributor, so it's not just a count, it matters *who*. After that, changeover hours lost and scrap. If one path gives me a late Meridian order and the other gives me a scrap spike — I'll take the scrap spike every time, no contest. Scrap costs money, a late Meridian order costs a relationship and a fine. So there is a rough pecking order in my head, I just don't have it written down as numbers — that's the bit I said I'd need to sit down with commercial for.
+
+**On horizon** — the sheet is a rolling weekly thing, built fresh every Monday against that week's demand book, but I'm constantly re-juggling it day to day as breakdowns and rush orders land. So really it needs to be useful at two grains: a full week, so I can see the whole book, but responsive enough to redo at shift-level when something breaks at 6am. A quarter's too far out — I don't plan that far, ERP just doesn't give me visibility past a few weeks anyway.
 
 ---
 
 **Interviewer**:
 
-That's clear, and I'll record the trade-off as deliberately unquantified rather than invent a weight — I'll flag it as needing commercial, since you've told me exactly where the number would come from.
+Good. I've got three objectives now, a rough pecking order (late Meridian ≫ late small distributor > changeover hours ≈ scrap; and scrap spike beats a late Meridian order every time), and a two-grain horizon — a full week, re-runnable at shift level. The exchange rate in numbers is parked as needing commercial; I'll flag it rather than invent it.
+
+Two more framing questions and then I want you to walk me through an actual order.
 
-Now let's get the structure. Take that Meridian white order from two weeks ago and walk me through it as a sequence — from the moment it lands on your desk to the moment it's off the dock. Keep it to the main steps, five or six; I'll dig into each one after.
+1. **What's inside the model and what's outside?** Specifically: does it start when an order lands in your demand book, or earlier? Does it end when the batch is filled off the line, or does it follow through QC, packing, warehouse, shipping? And is raw material supply something you ever wait on, or is it always just there?
+
+2. **The accuracy bar.** If I gave you the model loaded with last week's demand book and it produced a schedule, **what would you look at to decide "yes, that's basically our plant" versus "no, that's a toy"?** Is there a week you could replay from memory or from the sheet?
 
 ---
 
 **Expert (Marta)**:
 
-Sure, let me walk it through.
+**On scope:**
+
+Starting point — order lands in the demand book, that's the natural start, ERP hands it to me and it becomes a line on my sheet. I don't need the model reasoning about how orders get generated upstream, sales does whatever it does.
+
+End point — I'd say it ends when the batch clears QC hold and is released to the warehouse. What happens after that — trucks, warehouse slotting — isn't my problem, that's logistics' sheet, not mine. But QC hold has to be in there, because that four-hours-typical wait genuinely ties up my thinking about whether an order will make its due date, especially for specialty where it can be a full day. If a model ignored QC hold it would look like orders finish the moment they're filled, and that's just wrong — I've had orders filled on time and *still* gone late because the lab backed up on a Friday.
+
+Materials — mostly it's just there, I don't sit and calculate feedstock. But it's not *never* an issue — resin slips maybe once a month and when it does it stalls the run and I have to shuffle around it. So I'd say: outside the model most of the time, but there needs to be some way for "oh, the resin didn't show up" to occasionally throw a wrench in, otherwise you're modelling a plant that never has a bad Tuesday.
+
+**On the accuracy bar:**
+
+Honestly, the first thing I'd check is boring but telling: does it get the *unwritten rules* right — does Meridian white actually land on Line 2, does it never send specialty to Line 2, does it respect that Line 3 isn't qualified for those two tint SKUs. If it violates any of that, I'll dismiss it in about ten seconds, doesn't matter how clever the maths is.
 
-1. **It lands in the demand book** — comes over from ERP on the weekly pull, SKU, quantity, due date, flagged Meridian so it jumps to the top of my attention.
-2. **I allocate it to Line 2** — that's not really a decision, Meridian whites always go to Line 2, that's just how it's done here.
-3. **It sits in the queue behind whatever's running** — depending what's ahead of it, sometimes I'll reorder things a bit so it doesn't get stuck behind a big changeover.
-4. **Changeover if needed, then it runs** — mix, mill, tint or straight through if it's a plain white, then fill and pack. For a white that's usually the more straightforward path.
-5. **It goes into QA hold** — every batch does, typically a few hours before it's released.
-6. **Once released, it's staged for shipping** — and that's when the truck appointment matters, because if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line.
+Second — does the changeover pattern look like our week, not a fantasy week. If it shows tint-to-white as quick and white-to-tint as the long one, I'll know someone got the plant backwards.
 
-That's the whole arc, really — desk to dock. The QA step is the one people don't think about when they're mad at scheduling; half the time a "late" order was actually sitting done in QA hold waiting for the lab to get to it.
+Third, and this is the real test — I could take last week's actual book, run it through, and see whether the late orders it predicts are roughly the ones that *actually* went late. I remember last week pretty well: we had a Meridian order squeak through by a few hours, and a distributor order slid four days with a phone call and nobody blinked. If the model's version of last week says something wildly different — says Meridian went late, say, or doesn't flag the Line 1 tank issue that actually bit us — I'd say it's a toy. I can probably reconstruct two or three weeks like that from memory and the sheet if you want a real test case.
 
 ---
 
 **Interviewer**:
 
-That QA point is exactly the kind of thing that gets left out of a first account — I'll come back to it properly.
+That accuracy bar is unusually useful — the unwritten rules first, then the changeover asymmetry, then a replay of last week. I'm noting all three as the acceptance test, and I'm noting the direction-dependence you just gave away: **tint→white quick, white→tint long**. I'll come back and check I've got that the right way round.
 
-First let me pin down what you're actually scheduling. You said "Meridian white order", "a batch of tint", "same-family white". Three things:
+Now let me walk one real case end to end.
 
-1. Is the thing you schedule the *order*, or does an order get broken into batches that could run at different times? What's the relationship?
+1. First, so I follow the right thing: **what's "one" for you — an order, a batch, a run?** If a customer order can be split across two runs, or several orders can go down as one run, I need to know which unit you actually track on the sheet.
 
-2. What are the families? You used "same-family white" as if it's a defined grouping — is that a formal thing on the SKU, or your judgment?
-
-3. And how many lines are there, besides Line 2?
+2. Then: **take that Meridian white order from last week — the one that squeaked through — and walk me through it.** From the moment it lands in your book to the moment it's released to the warehouse. Just tell it as it happened, including the boring steps; I'll stop you where I need detail.
 
 ---
 
 **Expert (Marta)**:
 
-1. Mostly the order *is* the batch, if it fits a reasonable run size — a lot of our orders are big enough that we just run the whole thing as one batch. But sometimes I'll split one: if a distributor orders more than makes sense in a single run, or if I need to interleave it with something more urgent, I'll chop it into two batches and run them at different times. So it's order-to-batch most of the time, but not a strict one-to-one — I have the freedom to split if I need to.
+Ha — good catch, let me actually correct myself before we go further: I said it that way round out of habit, but hang on, let me think it through properly. Pigment carryover into a white is the disaster — a speck of tint ruins a batch of white. So it's **white → tint that's the quick one** (a bit of white residue in a tinted batch, who cares, it's getting colour anyway) and **tint → white that needs the full three-hour washdown**, because you cannot have any tint carryover into white. I had it backwards just now. Sorry — glad you flagged it instead of writing it down.
+
+**On the unit:** the sheet tracks at the **run** level, not the order. An order is a line in the demand book — SKU, quantity, due date — but what actually sits on the sheet as a block of time on a line is a run, and a run can be one order's worth or several small orders of the same SKU lumped together to clear the minimum-run-size bar. Occasionally a big order gets split into two runs if I need to interleave a rush job — that's the sequencing juggling I mentioned. So: orders are what demand gives me, runs are what I actually schedule, and I'm the one deciding the mapping between them week to week.
+
+**Walking the Meridian order:**
 
-2. The families are real, they're on the SKU — every product's either a base white, a tinted colour, or a specialty clear. That's not my judgment, that's how the SKU's classified in the system, it drives what changeover you need going in and out. "Same-family" just means two SKUs both being whites, or both being tints, so the changeover between them is the cheap quick-rinse kind instead of the expensive family-switch kind.
+It landed in Monday's demand book — a decent-sized white order, due Friday close of business, which for Meridian really means Friday, no wiggle. I put it on Line 2, because Meridian white always goes there. On the sheet I slotted it Wednesday, because Line 2 had a tint run booked Tuesday and I didn't want back-to-back — tint before white means I'm looking at the long washdown, and I wanted that overnight rather than eating into the day.
 
-3. Three lines total. Line 1's the old workhorse — slower but it's qualified for everything, including specialty. Line 2's the fast one, that's your big-volume runner. Line 3's the newest and quickest, but it's still being qualified product by product, so it can't run everything yet.
+Tuesday afternoon the tint run overran a bit — nothing dramatic, maybe an hour past what the sheet said — so the crew didn't get the washdown started until early evening instead of mid-afternoon. That's a three-hour job, so it ran into the night shift. Wednesday morning, line's clean, but we lost the ramp-up scrap at start of shift, and then the filler jammed for about forty minutes mid-morning — one of the routine jams, nothing scary. So the run itself finished later Wednesday than planned.
+
+It went to QC hold Wednesday evening. Normally that's four-ish hours and it'd be released overnight, but the lab had a backlog from earlier in the week, so it didn't actually get signed off until Thursday midday. Released to the warehouse Thursday afternoon — comfortably ahead of the Friday deadline in the end, but it "squeaked" in my head because if the filler jam had been the four-hour kind instead of the forty-minute kind, or if QC's Thursday had been as backed up as Friday usually is, it wouldn't have made it.
 
 ---
 
 **Interviewer**:
 
-Changeover is at the heart of the decision you want to test, so let's do it properly.
+Thank you for correcting the direction — tint→white is the three-hour washdown, white→tint is the quick one. That's now recorded that way round, and I've thrown away my earlier note.
+
+That walkthrough gave me the spine. Let me fill in the machinery inside it — three related things:
 
-You've named two kinds: the quick rinse between same-family SKUs, and the full washdown on a family switch. For the **quick rinse between two whites on Line 2** — the exact case from two weeks ago:
+1. **Within a run, does your sheet treat it as one block of time on the line, or are there distinct stages you track separately?** You mentioned a mill motor and a filler, which sounds like at least two things happening — is making the batch and filling it one continuous occupation of the line, or can one order be mixing while a different one is filling?
 
-1. Typically, how long does it take, start to finish, before the next batch is filling?
-2. One time in ten it goes worse than — what?
-3. And one time in ten it's better than — what?
+2. **Who does the washdown?** Is there a dedicated changeover crew, how many of them, and can two lines be washing at the same time — or does one line's washdown block another's?
 
-Give me the crew time too if it differs from line downtime.
+3. **The QC lab** — is it one lab serving all three lines? Can it work on several batches at once, or is it one at a time, and is it staffed around the clock or only on shifts?
 
 ---
 
 **Expert (Marta)**:
 
-For a straight white-to-white rinse on Line 2:
+Good questions, and honestly the answers get at things I only half-think about because the sheet flattens them.
+
+**1. Within a run:** On the sheet it's one block of time — I put down "Meridian order, Line 2, Wed 06:00–18:00" and that's it, I don't sub-divide it. But physically, no, it's not one continuous thing happening in one spot. There's mix, then mill, then tint/letdown, then fill — four stages, and they're at different points on the line with small holding tanks between them. So in principle, while the back end of a batch is filling, the front end of the *next* batch could already be mixing, if there's product to feed it — it's a bit of a flow, not a single monolithic block. My sheet doesn't capture that at all, it just says "Line 2 busy 06:00–18:00" and moves on. Whether that's actually true — whether the line is fully occupied that whole window or there's slack — I genuinely couldn't tell you without going and watching it, which is part of why I said the sheet flatters reality.
 
-1. Typically? Call it 25 minutes, start to finish, before the fill head's actually running clean product again.
-2. Worse case — one time in ten it drags to maybe 45 minutes, usually because the tech's tied up finishing something on another line first and there's a wait before they even start on Line 2.
-3. Better case — one time in ten, if the tech's standing right there and it's a genuinely easy one, 15 minutes and you're rolling again.
+The tanks between stages are exactly why I keep grumbling about Line 1's mill-to-fill tank — if fill is slow and the tank's small, mill has to stop and wait, and that's dead time my sheet never sees.
 
-Crew time and line downtime are basically the same thing here — it's quick enough that the tech's on it start to finish, no gap between "crew starts" and "line stops." That's different from the big washdowns, where the line's down way longer than the crew's actually hands-on, because there's soak time and QA checks in between.
+**2. The changeover crew:** One crew, two techs, day shift, covers all three lines. So no, two lines can't wash down at once — if Line 1 and Line 3 both want a washdown Tuesday morning, one of them waits its turn. That's the thing I mentioned with Line 3 sitting clean but idle waiting on the crew — it happens more than I'd like. Outside day shift, if a changeover's needed on night shift... honestly that's rare, we try to schedule washdowns for when the crew's on, but I couldn't tell you what happens if one gets forced onto nights. Might be we call someone in. Might be it waits till morning. I'd have to check with the crew lead.
+
+**3. QC lab:** One lab, serves all three lines, two people. I don't know the mechanics of whether they can run two batches' tests in parallel or whether it's strictly one-at-a-time per person — I just know that by Thursday/Friday there's a queue and things that should take four hours take longer. They're day-shift as far as I know, maybe with someone covering into evening, but I don't think there's a night presence. That's another one I'm going on impression, not fact — worth you asking them directly if it matters to the model.
 
 ---
 
 **Interviewer**:
 
-That distinction — line down longer than crew hands-on — matters, so let's get the washdown with both.
+Two deposits noted, both yours to check later: (a) what happens when a washdown is forced onto night shift — crew lead; (b) whether the lab runs batches in parallel and how far into the evening they cover — lab. I'll model something provisional and flag it.
+
+Now the thing you said you'd dismiss the model in ten seconds over: the lines and what may run where.
+
+1. **Give me the three lines and what distinguishes them** — capacity or speed, what each is qualified for, what physically differs. You've mentioned Line 1's mill motor and its small mill-to-fill tank, Line 2 as Meridian white's home, Line 3 as not qualified for two tint SKUs.
 
-For a **family switch on Line 2**, say white to tint: typically how long is the line down, one time in ten worse than, one time in ten better than? And roughly how much of that is the tech actually hands-on?
+2. **Give me the product families as you'd group them for scheduling.** You've said white, tint, specialty — is that the right cut, and are there others? What makes two things "same family" for the purposes of "I could run these back to back without a washdown"?
 
-Also: does it depend on direction — is tint-to-white the same as white-to-tint?
+3. **"Meridian white always goes on Line 2"** — is that a hard qualification, a customer requirement, or a habit? I want to know whether the model should treat it as a rule that can never break, or one you'd break under pressure.
 
 ---
 
 **Expert (Marta)**:
 
-It absolutely depends on direction — that's the thing people forget.
+**1. The three lines:**
+
+- **Line 1** — the old workhorse. Slower overall, but the most flexible: it's qualified for everything, whites, tints, specialty, all of it. It's the one you send something to when nowhere else can take it. Its weak point is the mill-to-fill tank being small — if fill lags, mill backs up and stalls. Also home to the scary mill motor that occasionally takes days to fix.
+- **Line 2** — the fast line. Built for volume. Roughly twice Line 1's speed on whites, though — and I only realised this when you pushed me on it earlier — that gap seems to shrink for tints, I don't actually know why. Not piped for the clear specialty resins at all, so specialty simply cannot run there, full stop, that's physical not a preference.
+- **Line 3** — newest, quick, but still being qualified SKU by SKU. Two tint SKUs specifically aren't signed off yet — I couldn't tell you technically why, that's a QA/engineering decision from before my time on this role, I just know not to put them there.
+
+**2. Product families:**
 
-**White to tint**, the easier direction: line's down typically about 45 minutes. Worse case, maybe an hour and a bit if the tech gets pulled away partway through. Better case, if everything's staged, maybe half an hour. Of that, the tech's hands-on for most of it — this one doesn't have much soak-and-wait, it's mostly just doing the work.
+Whites, tints, specialty — that's the cut I use, and it's really about what a washdown has to deal with, not the product itself. "Same family, no washdown" for whites means any white after any white is just a quick rinse. Same for tint-after-tint, more or less, though I think some tint-to-tint switches (light to light) are gentler than others (light to dark, or vice versa) — I've never separated that out on the sheet, it's all just "tint changeover, 20–30 min" to me, but I wouldn't swear every tint-to-tint pair is really equal.
 
-**Tint to white** is the ugly one, because any pigment left behind ruins a white batch, so it's a full washdown. Typically about 3 hours, line down the whole time. Worse case — if it doesn't pass the visual check first time and they have to redo part of it — could stretch to 4, maybe a bit more. Better case, a clean fast one, maybe 2 hours if the crew's good and nothing complicates it. Hands-on time for the crew is actually less than the 3 hours suggests — there's real soak and rinse-cycle time where the tech's not standing there, they might duck off to start something on another line. I'd guess they're actually working maybe half of that, the rest is the line just being down waiting on the process.
+**3. Meridian white on Line 2:**
 
-So no, it is absolutely not symmetric, and it trips people up if they assume it is.
+It's not written down anywhere as a hard qualification like the specialty-can't-run-on-Line-2 thing. It's a habit that calcified into a rule — Line 2's fill area got audited by Meridian's people years back for a supplier qualification, and ever since, if a Meridian order ran anywhere else, and they ever found out, it'd be a whole conversation nobody wants to have. So it's soft in the sense that physically Line 1 could make that batch. But in practice I have never once put a Meridian order on Line 1, even under real pressure — the one time Line 2 was going to be down most of a day, I held the order and let it run late-ish rather than move it, because breaking that rule felt riskier than a few hours' delay. So: treat it as effectively hard. If the model wants to explore breaking it, that's a "what if" experiment, not something I'd sanction as a live scheduling option.
 
 ---
 
 **Interviewer**:
 
-Good — asymmetric, and I've got both directions.
+Good — and I'll record the Meridian rule as effectively hard, breakable only as an explicit what-if.
 
-Two things to close out changeover:
+Now durations, which I need as ranges rather than single figures. Before I ask for numbers:
 
-1. Specialty clear is the third family — what does going into and out of clear cost, on Line 1 since that's the one qualified for it? Same shape of answer: typical, one-in-ten worse, one-in-ten better, either direction if they differ.
+1. **Is a run's length driven mainly by the quantity ordered, or do runs come in fairly standard sizes?** I want to know whether to ask you "how fast is Line 2 in litres per hour" or "how long is a typical white run on Line 2."
 
-2. Do the white/tint numbers you just gave me hold on Line 1 and Line 3, or are they line-specific?
+2. Whichever way you answer — **for the decisions you care about, is it the typical run length that matters, or the bad one?** You said the Meridian order "squeaked" because a jam could have been the four-hour kind. That suggests the tail is what bites you. Is that generally true?
+
+3. And a nag from your last answer: **you said Line 2 is roughly twice Line 1's speed on whites but the gap seems to shrink for tints.** Is there anyone who'd know why, or a place that would show it? I don't want to write "twice as fast" across the board if it's only true for whites.
 
 ---
 
 **Expert (Marta)**:
 
-1. Specialty is roughly the same both directions, unlike white/tint — call it 2 hours typical, either going in or coming out. Worse case, maybe 3 hours if it's coming out of clear and they're being extra careful about residue, since clear can be sneaky — you don't always see it the way you'd see pigment. Better case, maybe an hour and a half if it's a quick swap and the line was already fairly clean. Hands-on for the crew is most of that — specialty doesn't have the long soak cycles the tint-to-white washdown has, it's more just physically thorough cleaning because the product's thick and clingy.
+**1. Quantity vs. standard size:** It's driven by quantity, not standard batch sizes — the demand book gives me an order quantity in whatever units (drums, usually, sometimes bulk litres for the big Meridian stuff), and I convert that to run length using the rate for that product on that line. So it really is "quantity divided by rate, plus fill-up time" — which is why I'd answer "how fast is Line 2" more naturally than "how long is a typical run," except that in conversation I usually think in run-hours because that's what goes on the sheet. If you want the raw rate, I'd have to go dig for it — I keep the sheet in run-hours already converted.
+
+**2. Typical vs. tail:** Yeah, you've got it right. For deciding *how much to promise* — whether an order fits in the week — I use typical, because if I planned for worst-case every time I'd never fit anything on the sheet and everyone would think I was hoarding capacity. But for deciding whether something's actually going to be *late*, it's always the tail that gets me: the jam that runs long, the washdown that overruns, the QC backlog on a Friday. The plan is built on typical; the disasters come from the tail. So if the model's going to be useful for the "will this ship on time" question, it needs the tail, not just an average — that Meridian order was fine on a typical week and nearly wasn't.
 
-2. Honestly, I've mostly been quoting you Line 2 numbers because that's where the argument happened. I *think* the same rough shape holds on Line 1 — quick rinse cheap, tint-to-white expensive and slow, white-to-tint quicker — but I couldn't swear the minutes are identical. Line 1's older, the crew sometimes says it's fussier to get properly clean. Line 3 I genuinely don't have a good feel for, because it hasn't run enough different products yet to have built up war stories — it's still mostly running whatever it's been qualified for, which so far is mostly one or two SKUs. So if you need Line 3 numbers, that might be one where you're stuck assuming it's like Line 1 or Line 2 until we've got more history.
+**3. The Line 2 speed gap:** Honestly, no, I don't have a good answer, and I said "funny, never thought about why" earlier because I meant it — I've just always used "2x on whites" as my mental shorthand and never checked whether it holds for tints because tints don't move through Line 2 as often. If I had to guess who'd know, it'd be **process engineering** — they set the line rates originally and would know if something about tint viscosity or the letdown stage behaves differently machine to machine. Or possibly it's sitting in the historian data if someone actually pulled cycle times apart by product and stage, which — as I said — nobody's done. I wouldn't trust my own instinct on this one; flag it as something to verify, don't take "twice as fast" as gospel outside whites.
 
 ---
 
 **Interviewer**:
 
-That's the right answer — I'd rather have "I don't know" than invented minutes. Here's what I'd assume unless you tell me otherwise, and I'll mark it as mine, not yours:
+Understood — I'll carry "2× on whites, unverified for tints" as a flagged assumption with process engineering as the source to check.
+
+Now let me get actual numbers. You think in run-hours, so let's use those, and I'll ask each one as a low/high first, then typical.
 
-- **Line 1**: same shape as Line 2, with all changeover durations scaled up — say 20% longer — on the strength of the crew's "fussier to get properly clean".
-- **Line 3**: same as Line 2 until history exists.
+Think of a **white run on Line 2 of the size you'd typically see in the book** — say a Meridian-sized one like last week's:
 
-Both would be checked against the changeover logs, if the techs record start and finish. Does 20% sound like the right order of magnitude for Line 1, or is it more like double?
+1. **What's the shortest and longest that run could plausibly take, from starting the line to the last drum filled?** Then: what's the typical? I'm after the whole occupation of the line, including the ramp-up scrap period you mentioned, but *not* including the washdown before it or QC after.
 
-Separately — you just said something important in passing. The tech "gets pulled away partway through", "might duck off to start something on another line". How many changeover techs are there across the three lines?
+2. **Roughly how many run-hours does a typical week's book add up to across all three lines** — and how many hours of line time do you actually have in a week? I want to know how tight you normally are, because that tells me how much the tails actually matter.
 
 ---
 
 **Expert (Marta)**:
 
-20% sounds about right, not double — it's more "takes a bit longer to satisfy the visual check" than "fundamentally slower." Double would be if we were talking about the mill motor issue or something structurally different. So yeah, 20% longer on Line 1 feels like the right order of magnitude, not a multiplier like 2x.
+Okay, let's do the Meridian-sized white run on Line 2 first.
 
-On the crew — there's two techs on day shift covering all three lines between them. That's it. No dedicated tech per line. So if Line 1 and Line 3 both want a washdown at the same time, one of them waits, and that's the bit that actually causes grief at the huddle — it's not that the changeover itself is unpredictable, it's that the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line.
+**1. Run duration:** On a good day, that size order — call it the volume that took roughly a shift and a half on the sheet — runs about **10-11 hours** if nothing goes wrong, that's the number that's actually on the sheet for it. Shortest it's ever been, maybe 9 hours if the line just behaves and there's no jam at all — line's fast, it doesn't take much to knock a few hours off. Longest — if the filler has one of its worse jams, or there's more than one, I've seen that same-sized run stretch to 16, 18 hours. I did have one, maybe a year ago, that went nearly 24 because we had a jam *and* a short material stall on top of it, but I'd call that a genuine outlier, not "the bad day," more "the terrible day." So: typical **10-11**, shortest realistically **9**, and a bad-but-not-freak day is more like **14-16**. The 24-hour one I'd treat as a once-a-year tail, not the normal worst case.
+
+**2. Weekly book vs weekly capacity:** This one I can give you better because it's exactly the tension I live with every Monday. A typical week's book runs somewhere around **380-420 run-hours** total demand across the three lines, once I've converted everything. Capacity — Line 1 and Line 2 both run two shifts, so each is about 112 hours a week if fully utilised (16 hours a day times 7, though we don't always run weekends flat out — more like five and a half, six days realistically). Line 3's day-shift-only unless overtime's approved, so call it 56 hours normally. So total available is somewhere in the **270-300 run-hour** range in a normal week if I'm honest about weekends, versus a book that wants 380-420.
+
+Which tells you immediately: I am *always* over capacity on paper, which is exactly why changeover hours and scrap matter so much — every hour lost to a washdown or a jam is an hour I don't have to spare, and why late orders happen at all. It's also why weekend and overtime running is a live lever, not a nice-to-have — Line 3 running an extra day, or Line 1/2 pushing into Sunday, is often the difference between the week working or not.
 
 (Sorry — I've just seen the time, I have the floor huddle in ten minutes. How much more do you need?)
 
@@ -201,403 +245,432 @@ On the crew — there's two techs on day shift covering all three lines between
 
 **Interviewer**:
 
-Ten minutes is enough for one thing, so let me tell you where we are and then ask the one that matters most.
-
-**What I have:** the two objectives, the six-step arc, three lines, three families, all the changeover numbers for Line 2 with spreads, the asymmetry, the two techs as a shared resource.
+Ten minutes is useful — let me name what's still missing so you can choose, rather than pretend we're done.
 
-**What's still missing** — roughly six or seven things, and two of them are load-bearing for the exact decision you want to test:
+**Still open and load-bearing:**
+- **How often things go wrong** — I have durations for the filler jam, mill motor, resin slip, QC backlog, but almost no *rates*. You told me the tail is what makes orders late; without frequencies I can't produce tails.
+- **The two decision rules as you actually practice them** — the reroute-vs-hold rule and the idle-vs-washdown rule. I have the situations, not the rule you apply.
+- **Requalification** — "eat the requalification headache" is a cost I have no size for.
+- **How orders arrive** — rush orders, due-date patterns, which customers are Meridian-tier.
+- Run rates for Lines 1 and 3, and washdowns involving specialty.
 
-- how long a batch actually *runs* (I have changeovers but no run times at all)
-- how the "heads-up another order was about to drop" actually reaches you — that's the trigger your whole hold-the-line decision hangs on
-- QA hold as a spread, and whether the lab is a shared resource like the techs
-- the order arrival pattern off the ERP weekly pull
-- run sizes and what splitting a batch costs
-- which SKUs Line 3 is actually qualified for
-- what breaks, and how often
+If I get one thing now, I'd take the frequencies, because they're quick and nothing else substitutes for them. Three, same frame:
 
-None of that needs to happen now. My question for the remaining minutes, because it's the one I can't guess and it's the one that made you say "grief at the huddle":
+1. **In a typical week, how many filler jams do you get across the plant** — and roughly what's the split between the forty-minute kind and the four-hour kind?
+2. **How often does Line 1's mill motor take the line down** — the multi-day sort, not the few-hour hiccup? Once a quarter, twice a year?
+3. **How often is QC actually backed up** enough that a four-hour hold becomes a day-plus — is it genuinely a Friday thing, or any day?
 
-**When both lines want a washdown at once and one tech has to pick — what actually decides it?** Not the rule as posted. Think of the last time it happened: which line got the tech, and what was the reason?
+Answer what you can in the time; then tell me when we can pick up the rest.
 
 ---
 
 **Expert (Marta)**:
 
-Honestly, there's no posted rule at all — it's whoever's louder at the huddle, or whoever's about to actually run dry.
+Quick ones, then I have to run.
 
-Last time it happened, off the top of my head — Line 1 and Line 3 both wanted a washdown same morning. Line 3 got the tech first, not because it was more important, but because Line 3's changeover was the quick one and Line 1's was going to be the long tint-to-white slog anyway, so the thinking was "knock out the fast one, get that line moving, then commit the tech to the long one." Line 1 sat clean-but-waiting for almost 40 minutes past when it could've started.
+1. **Filler jams:** Most weeks, one or two. Almost all of them are the short kind, half hour to an hour, that's the bulk of them — I'd say four out of five. The multi-hour kind, the real headache, is more like once a month, maybe every six weeks. It's Line 2's filler mostly, that's the one I'd flag as jam-prone.
 
-If you push me on the actual logic — it's mostly gut triage: whichever line has the more time-sensitive order behind it wins, and if that's a tie, whichever changeover is faster wins so you get a line moving sooner. Nobody writes this down, it's literally whoever's standing at the huddle table making the case loudest. I've been overruled by the ops director once when he wanted his pet SKU out the door.
+2. **Mill motor, the multi-day sort:** Rare — I've seen it maybe three, four times in the years I've been doing this job. So call it once, maybe twice a year. When it happens it's ugly, but it's genuinely not a weekly worry the way the filler is.
 
-I do need to run — but this was useful, come back to the QA and run-time stuff next time, those are real gaps.
+3. **QC backlog:** Mostly a Friday thing, yes — book's heaviest early week, orders queue up at the lab by Thursday/Friday, so nine times out of ten if I'm going to see a hold stretch past a day it's end of week. Early week it's rare, maybe one bad Monday or Tuesday a month if something upstream bunched up.
+
+That's what I've got off the top of my head — day-to-day impression, not a logged rate, so treat it as roughly-right rather than exact.
+
+I've got to get to the huddle — same time tomorrow, or whenever suits you, we can pick up the decision rules and the requalification cost. That's probably the meatier half anyway.
 
 ---
 
 **Interviewer**:
 
-You've stopped, so I'm not opening anything new. Here's the model as it stands, read back item by item, with the gaps named honestly. The two things you flagged — QA and run times — are the first things on the list when you're back.
+Understood — go to your huddle. I won't open anything new. Here's where we got to, read back so you can correct it, plus exactly what I'll ask tomorrow.
+
+**Stopping outcome: `expert-stopped` — partial model with open slots.** The structural floor is met (objectives, entity types, activities, flow all present), but none of the three objectives has a complete dependency slice yet. The biggest holes are the two decision rules themselves — which is the meatiest half, as you said.
 
 ---
 
-# 1. The model
+# 1. The model as it stands
 
-Vocabulary is yours throughout. Each slot shows the value **and** the precision actually obtained. `⚠` marks a slot the model demands and does not yet have.
+Every value below is at the grade you actually gave it. Where I asked interval-first (low/high, then typical) I've said so.
 
 ## Objectives
 
-**O1 — "Hold the line versus wash it down now, which one actually costs less over the week"**
-- *The question, in your words:* whether letting Line 2 sit idle for ~1 hour waiting on an anticipated same-family white order is cheaper over a week than washing down to the tint batch now. — **spelled out**
-- *Depends on:* E1 Order, E2 Batch, E3 Line, E4 Changeover tech, B1 ERP weekly pull, B2 mid-week order drop-in, A4/A5/A6 changeovers, A8 run batch, A9 QA hold, F1 main arc, P1, P3, P5, C2, C4.
-- *What "better" means:* changeover hours consumed over the week, subject to O2 holding absolutely. — **named, not quantified against O4** ⚠
-
-**O2 — "Meridian shipped on time, full stop, that's non-negotiable"**
-- *The question:* does every Meridian order leave the dock in time for its dock appointment. — **spelled out**
-- *"On time" =* ship date + delivery window given on the order, resolving to a specific dock appointment their end; must leave our dock **one day ahead** for freight. — **spelled out**
-- *Consequence of a miss:* a fine (amount not visible to you — commercial's) and a hit to the tracked on-time percentage; if that drops far enough, threatened SKU delisting — a competitor has been delisted, so it's treated as real. — **spelled out, unquantified** ⚠
-- *Depends on:* A9 QA hold, A10 stage & ship, C4, P1, P2, B3.
-
-**O3 — Changeover hours**
-- *The question:* how many crew-hours go into washdowns rather than filling. "Every hour the crew spends washing down is an hour not filling anything." — **spelled out**
-- *Depends on:* A4, A5, A6, A7, E4, C2, P3.
-
-**O4 — "How ugly the sheet looks" — idle gaps with no good reason**
-- *The question:* are lines sitting idle for no good reason. — **spelled out**
-- *"Better" =* explicitly a gut check, not a number, "but it's real". — **your words: not quantified** ⚠ (IR-only; see §3)
+| ID | The question, in your words | Depends on | "Better" |
+|---|---|---|---|
+| **OBJ-1 Reroute or hold** | *"whether to shift the specialty over to Line 3 and eat the requalification headache, or hold it and let the white slip behind on Line 2"* — run it twice and see which one bites me less | ET-Line, ET-Order, A-Mill-motor-failure, A-Requalification, POL-Reroute-or-hold, C-Line-qualifications, POL-Meridian-Line-2 | Ranked, not numeric — see below |
+| **OBJ-2 Idle or washdown** | *"do I sit Line 2 empty for an hour waiting on a same-family order, or just pay the three-hour washdown now"* — a call *"almost weekly and it's pure feel"* | A-Washdown-tint-to-white, A-Ramp-up-scrap, ET-Changeover-crew, POL-Idle-vs-washdown, BC-Demand-book | Ranked, not numeric |
+| **OBJ-3 Run size & sequencing** | *"whether to split a big order into two runs to slot in a rush job, or batch several small orders of the same family together even if it means one of them ships a bit early and sits in the warehouse"* — *"I've never had a way to check if I'm leaving hours on the table"* | OF-Order-to-run-mapping, C-Minimum-run-size, A-Washdown-*, A-Ramp-up-scrap, BC-Demand-book | Ranked, not numeric |
 
-**Trade-off between O2, O3 and lateness for non-Meridian:** you would take 4 changeover hours saved against one distributor order two days late "most of the time" — a distributor slip is "an annoyed phone call from our sales rep, not a fine" — but the same distributor slipping three weeks running turns into a discount demand. So: soft, not infinitely soft, **and deliberately unquantified**. Deposit: you named the source — "sit down with commercial". Nobody has ever made you quantify it. ⚠
+Noted but **not** an objective you own: overtime approval — *"that's the ops director's call, though I do feed him the 'we'll miss X without it' argument… maybe that's a variant of the same question rather than a fourth one."*
 
-## Entity types
+**What "better" means** — grade: *spelled out as a ranking, numeric weights absent.*
+1. Did anything ship late, **and to whom** — *"a late order to Meridian is worse than three late orders to a small distributor, so it's not just a count, it matters who."*
+2. Changeover hours lost.
+3. Scrap.
+- Stated trade: *"a late Meridian order and… a scrap spike — I'll take the scrap spike every time, no contest. Scrap costs money, a late Meridian order costs a relationship and a fine."*
+- Exchange rate in currency: **open**, deposit = *"sit down with commercial."*
 
-**E1 — Order (from the demand book)**
-- *Distinctions the process treats apart:* Meridian vs. non-Meridian (Meridian "jumps to the top of my attention", on-time absolute); family classification on the SKU. — **spelled out**
-- *State riding along:* SKU, quantity, due date + delivery window, Meridian flag, family (base white / tinted colour / specialty clear — a real field in the system, not your judgment). — **spelled out**
-- *How many / population shape:* ⚠ not obtained — arrival volume per weekly pull unknown.
+**Horizon** (grade: spelled out): rolling week built fresh Monday against that week's demand book, re-runnable at shift grain when something breaks at 6am. *"A quarter's too far out."*
 
-**E2 — Batch**
-- *Distinctions:* same three families as the order it came from. — **spelled out**
-- *Relationship to order:* "mostly the order *is* the batch, if it fits a reasonable run size"; you may split into two batches run at different times when a distributor orders more than makes sense in one run, or to interleave something more urgent. Not a strict one-to-one; the split is your discretion. — **spelled out**
-- *Population shape:* ⚠ run sizes not obtained; cost of a split not obtained.
+**Boundary** (grade: spelled out): starts when an order lands in the demand book from ERP; ends when the batch **clears QC hold and is released to the warehouse**. Trucks/warehouse slotting excluded (*"logistics' sheet, not mine"*). QC hold is explicitly **in** scope — *"I've had orders filled on time and still gone late because the lab backed up on a Friday."* Feedstock excluded except that resin slips must be representable — *"otherwise you're modelling a plant that never has a bad Tuesday."*
 
-**E3 — Line** — a contended resource
-- *Distinctions:* **Line 1** — "the old workhorse", slower, qualified for everything including specialty, crew say it's "fussier to get properly clean". **Line 2** — the fast one, big-volume runner. **Line 3** — newest and quickest, still being qualified product by product, "can't run everything yet", so far mostly one or two SKUs. — **spelled out**
-- *State riding along:* which family the line is currently dirty with (this is what selects the changeover); qualification set. — **spelled out**
-- *How many:* 3. — **number**
+## Validation criteria
 
-**E4 — Changeover tech** — a contended resource
-- *Distinctions:* none stated between the two techs. — **named**
-- *State riding along:* which line they're currently committed to; can be "pulled away partway through". — **spelled out**
-- *How many:* 2 on day shift, covering all three lines, no dedicated tech per line. — **number**
+| ID | Criterion | Grade |
+|---|---|---|
+| VC-1 | The unwritten rules hold: Meridian white lands on Line 2; specialty never on Line 2; Line 3 never gets the two unqualified tint SKUs. *"If it violates any of that, I'll dismiss it in about ten seconds."* | spelled out |
+| VC-2 | Changeover asymmetry the right way round: **tint→white is the long one, white→tint is quick.** *"If it shows tint-to-white as quick… someone got the plant backwards."* | spelled out |
+| VC-3 | Replay last week's book; predicted late orders roughly match actual — Meridian squeaked through by a few hours, a distributor order slid four days with a phone call and nobody blinked, and the Line 1 tank issue bit us. You can reconstruct two or three such weeks. | spelled out |
 
-**E5 — QA lab**
-- *Distinctions / state / population:* ⚠ nothing obtained beyond its existence and that it can be "backed up on a Friday afternoon". Whether it's a shared resource like the techs is an open question you and I both flagged.
+## Entity types
 
-## Boundary conditions
+| ID | Type | Distinctions that matter | State it carries | How many |
+|---|---|---|---|---|
+| ET-1 | **Order** (a line in the demand book) | SKU; quantity (drums, or bulk litres for big Meridian); due date; customer — Meridian-tier vs small distributor | family (white / tint / specialty); due date hardness | ~380–420 run-hours of demand per week *(range)* |
+| ET-2 | **Run** (a block on the sheet) | the unit you actually schedule; one order's worth, or several small same-SKU orders lumped to clear minimum run size; a big order can be split into two runs | line assignment; family; scheduled window | derived from ET-1 by your weekly mapping |
+| ET-3 | **Line** | see below | current/last family (sets changeover); qualification set; up/down | 3 |
+| ET-4 | **Changeover crew** | one crew, two techs, day shift, all three lines | busy/free | 1 crew *(contended)* |
+| ET-5 | **QC lab** | one lab, two people, all three lines | queue depth | 1 lab, 2 people *(contended; parallelism unknown)* |
+| ET-6 | **Stage within a line** | mix → mill → tint/letdown → fill, with small holding tanks between | tank level (see D-1) | 4 stages per line |
 
-**B1 — ERP weekly pull into the demand book**
-- *Starting state:* orders arrive over from ERP on the weekly pull, carrying SKU, quantity, due date, Meridian flag. — **spelled out**
-- *Arrival pattern:* ⚠ **not obtained** — no volume, no spread, no within-week shape. Demanded as a spread.
+**The three lines** (grade: spelled out qualitatively; rates only partly numeric)
 
-**B2 — Mid-week order drop-in ("another same-family white order was about to drop in from a distributor")**
-- *Starting state / pattern:* ⚠ **not obtained.** This is the trigger the whole of O1 hangs on and I have only the one anecdote: you had "a heads-up". How that heads-up reaches you, from whom, how far ahead, and how often it turns out to be right are all unknown. Demanded as a spread; currently zero.
+- **Line 1** — *"the old workhorse… slower overall, but the most flexible: qualified for everything."* The one you send something to when nowhere else can take it. Weak point: small mill-to-fill tank — if fill lags, mill backs up and stalls. Home of the mill motor. Two shifts.
+- **Line 2** — *"the fast line. Built for volume."* Roughly 2× Line 1 on whites; **that gap "seems to shrink for tints" and you explicitly asked me not to take 2× as gospel outside whites.** Not piped for clear specialty resins — *"specialty simply cannot run there, full stop, that's physical not a preference."* Jam-prone filler. Two shifts.
+- **Line 3** — *"newest, quick, but still being qualified SKU by SKU."* Two tint SKUs not signed off. Day shift only unless overtime approved.
 
-**B3 — Meridian dock appointment**
-- *Pattern:* ship date with a delivery window on the order, resolving to a specific dock appointment their end. — **spelled out**
-- *Distribution of lead time:* ⚠ not obtained.
+**Families** (grade: spelled out, with a flagged sub-distinction): whites / tints / specialty — *"it's really about what a washdown has to deal with, not the product itself."* Caveat you gave: *"I wouldn't swear every tint-to-tint pair is really equal"* — light-to-light may be gentler than light-to-dark. Never separated on the sheet.
 
-**B4 — Tech availability calendar**
-- ⚠ only "two techs on day shift" obtained. Whether there is any night/weekend changeover coverage was never asked.
+## Boundary conditions
 
-**B5 — Line 3 qualification set at start of run**
-- ⚠ "mostly one or two SKUs" — **not spelled out**; which SKUs is unknown.
+| ID | What | Value | Grade |
+|---|---|---|---|
+| BC-1 | Demand book | Built fresh Monday from ERP; ~380–420 run-hours/week; rush orders land mid-week | range for volume; **arrival shape for rush orders open** |
+| BC-2 | Line calendar | L1 & L2 two shifts = 16h/day nominal ≈ 112h/wk, *"though we don't always run weekends flat out — more like five and a half, six days realistically"*; L3 day shift ≈ 56h unless OT. Total realistic **270–300 run-hours** | range |
+| BC-3 | Changeover crew calendar | Day shift only. Night behaviour: **unknown** — *"Might be we call someone in. Might be it waits till morning."* | open, deposit = crew lead |
+| BC-4 | QC lab calendar | Day shift, *"maybe with someone covering into evening,"* believed no night presence — *"impression, not fact"* | open, deposit = the lab |
+| BC-5 | Resin supply | *"mostly it's just there"*; slips **~once a month**, stalls the run | rate: range; stall duration: open |
+| BC-6 | Structural over-commitment | Book (380–420) always exceeds capacity (270–300). *"I am always over capacity on paper, which is exactly why changeover hours and scrap matter so much."* | spelled out |
 
 ## Activities
 
-**A1 — Lands in the demand book** — *needs:* the weekly ERP pull. *Produces:* an Order in the book, Meridian-flagged or not. *Performed by:* ERP / not attended. *Duration:* n/a (instantaneous receipt). **spelled out**
+| ID | Activity | Duration | Rate | Mode-change loss | Grade / notes |
+|---|---|---|---|---|---|
+| A-1 | **Run — Line 2, white, Meridian-sized** (start of line to last drum filled, incl. ramp-up, excl. washdown and QC) | shortest realistically **9h**; typical **10–11h**; bad-but-not-freak **14–16h**; freak ~**24h** (jam + material stall), *"once-a-year tail, not the normal worst case"* | n/a (step) | — | **spread-equivalent**, interval-first protocol. Deciles not explicitly stated. **Varies by line/product: not yet asked (P07 open)** |
+| A-2 | **Washdown, tint→white** | **3 hours** | n/a | — | **number**, not spread. You mention *"the washdown that overruns"* as a tail source — overrun spread **open** |
+| A-3 | **Changeover, white→tint** | *"a bit of white residue in a tinted batch, who cares"* — quick | n/a | — | **named only, no number** |
+| A-4 | **Changeover, tint→tint** | **20–30 min** | n/a | — | range. Light/dark sub-split suspected, never measured |
+| A-5 | **Changeover involving specialty** | — | — | — | **entirely open** |
+| A-6 | **Ramp-up after washdown** | — | — | scrap; *"that was the week I rushed the ramp after a washdown"* → scrap spike | **named as a real loss, magnitude open (P02)** |
+| A-7 | **QC hold** | typical **~4h**; specialty *"can be a full day"*; with backlog, a day-plus (last week: Wed evening → Thursday midday) | — | — | typical + qualitative tail |
+| A-8 | **Filler jam** | short kind **0.5–1h** (*"four out of five"*); long kind **multi-hour**, e.g. the 4-hour kind | **1–2 per week plant-wide**; long kind **once a month to every 6 weeks**; *"Line 2's filler mostly"* | — | rate: range; duration: range. Your caveat: *"day-to-day impression, not a logged rate"* |
+| A-9 | **Line 1 mill motor failure, multi-day** | *"the four-day disaster"* — days | **1–2 per year** (*"three, four times in the years I've been doing this job"*) | — | rate: range; duration: single anecdote |
+| A-10 | **Line 1 mill motor hiccup, hours** | *"a few hours"* | **open** | — | the recent one that triggered OBJ-1 |
+| A-11 | **Resin stall** | open | ~once a month | — | see BC-5 |
+| A-12 | **Requalification** (moving specialty to a line) | **open** | n/a | *"eat the requalification headache"* | **load-bearing for OBJ-1, entirely unsized** |
+| A-13 | **Release to warehouse** | end of scope | — | — | terminal |
 
-**A2 — Allocate to a line** — *needs:* an order in the book. *Produces:* order assigned to a line. *Performed by:* you. *Duration:* not a scheduling constraint; "not really a decision" for Meridian whites. **spelled out** (rule in P1)
+## Ordering / flow
 
-**A3 — Reorder the queue** — *needs:* an order sitting behind others. *Produces:* changed run sequence. *Performed by:* you. *Rule:* P4. — **spelled out**
+- **OF-1 (spelled out):** Order lands in demand book → scheduler maps orders to runs → run placed on a line in a week slot → *if incoming family ≠ line's current family, changeover first* → run executes (mix → mill → tint/letdown → fill, flowing, with holding tanks between; next batch's front end can start while this batch's back end fills) → QC hold → release to warehouse.
+- **OF-2 order↔run mapping (spelled out qualitatively):** lump several small same-SKU orders to clear the minimum run size; split a big order into two runs to interleave a rush job. Split cost = an extra changeover + extra ramp-up scrap. Minimum run size: **unquantified**.
+- **OF-3 line-choice branch (partly spelled out):** decided by qualification constraints C-1/C-2 plus POL-1; the residual discretion is exactly OBJ-1 and is **open**.
+- **OF-4 blocking (spelled out, unquantified):** on Line 1, if fill is slow and the mill-to-fill tank is small, *"mill has to stop and wait, and that's dead time my sheet never sees."*
+- **Known model/reality gap you volunteered:** the sheet records "Line 2 busy 06:00–18:00" and *"doesn't capture that at all"* — whether the line is genuinely occupied the whole window *"I genuinely couldn't tell you without going and watching it."*
 
-**A4 — Quick rinse (same family, e.g. white → white) on Line 2**
-- *Needs:* line free, previous batch off, a tech available, next SKU same family. *Produces:* line clean for next batch, fill head running clean product.
-- *Performed by:* 1 changeover tech. — **named**
-- *Duration (line down):* typical **25 min**; one-in-ten worse **45 min** (tech tied up finishing on another line, so a wait before they even start); one-in-ten better **15 min** (tech standing right there, genuinely easy one). — **spread**
-- *Crew hands-on:* same as line down — "no gap between crew starts and line stops". — **spelled out**
-- *Varies by type?* Family pair, yes (that's what selects A4 vs A5/A6/A7). By line: ⚠ see ledger #1, #2.
+## Policies
 
-**A5 — Changeover white → tint on Line 2** ("the easier direction")
-- *Duration (line down):* typical **45 min**; worse **"an hour and a bit"**; better **~30 min** if everything's staged. — **spread** (see ledger #3 for my numeric reading of "an hour and a bit")
-- *Crew hands-on:* "most of it — doesn't have much soak-and-wait, it's mostly just doing the work". — **spelled out qualitatively**, ledger #4 for the fraction
-- *Cause of the worse tail:* tech gets pulled away partway through. — **spelled out**
+| ID | Policy | As practiced | Overrides |
+|---|---|---|---|
+| POL-1 | **Meridian white runs on Line 2** | Habit calcified into a rule after Meridian audited Line 2's fill area for supplier qualification. *"I have never once put a Meridian order on Line 1, even under real pressure"* — when Line 2 was down most of a day you **held the order and let it run late-ish**. Physically Line 1 could do it. | *"Treat it as effectively hard."* Breakable only as an explicit what-if experiment, *"not something I'd sanction as a live scheduling option."* |
+| POL-2 | **Long washdown scheduled overnight** | *"tint before white means I'm looking at the long washdown, and I wanted that overnight rather than eating into the day"* | not asked |
+| POL-3 | **Washdowns scheduled to when the crew is on** | *"we try to schedule washdowns for when the crew's on"* | night case unknown (BC-3) |
+| POL-4 | **Avoid stacking family switches** | signalled by *"the changeover crew looking wrecked by Thursday because I stacked too many family switches back to back"* | not asked |
+| POL-5 | **Reroute vs hold** | **OPEN — the core of OBJ-1** | |
+| POL-6 | **Idle vs washdown** | **OPEN — the core of OBJ-2** | |
+| POL-7 | **Changeover crew contention** — who wins when two lines want a washdown | **OPEN.** Observed symptom only: *"Line 3 sitting clean but idle waiting on the crew — it happens more than I'd like"* | |
+| POL-8 | **QC lab queue discipline** | **OPEN** | |
+| POL-9 | **Overtime / weekend running** | Ops director's call; you feed the *"we'll miss X without it"* argument. *"A live lever, not a nice-to-have."* | |
 
-**A6 — Changeover tint → white on Line 2 — the full washdown** ("the ugly one")
-- *Needs:* as A4, plus a passing visual check before release to production.
-- *Duration (line down):* typical **~3 h**; worse **4 h, "maybe a bit more"** — when it doesn't pass the visual check first time and they redo part of it; better **~2 h** with a good crew and nothing complicating. — **spread**
-- *Crew hands-on:* "maybe half of that" — real soak and rinse-cycle time where the tech isn't standing there and "might duck off to start something on another line". — **spelled out qualitatively**, ledger #4
-- *Rationale:* "any pigment left behind ruins a white batch". — **spelled out**
-- **Asymmetry is load-bearing:** white→tint ≠ tint→white, "it trips people up if they assume it is". — **spelled out**
+## Constraints
 
-**A7 — Changeover into / out of specialty clear, on Line 1**
-- *Duration (line down):* typical **2 h**, roughly the same both directions "unlike white/tint"; worse **3 h**, especially coming out of clear, "clear can be sneaky — you don't always see it the way you'd see pigment"; better **1.5 h** on a quick swap with the line already fairly clean. — **spread**
-- *Crew hands-on:* "most of that" — no long soak cycles; it's physically thorough cleaning because the product's thick and clingy. — **spelled out qualitatively**, ledger #4
+| ID | Limit | Consequence when hit |
+|---|---|---|
+| C-1 | Specialty cannot run on Line 2 — not piped for clear specialty resins | infeasible; must go Line 1 or Line 3 |
+| C-2 | Two tint SKUs not qualified on Line 3 (QA/engineering decision, reason not known to you) | cannot be scheduled there |
+| C-3 | Line 1 qualified for everything | fallback line of last resort |
+| C-4 | Minimum run size | small orders must be lumped — **threshold unquantified** |
+| C-5 | One changeover crew → **one washdown at a time across all three lines** | the other line waits |
+| C-6 | One QC lab, two people | queue forms; **parallelism unknown** |
+| C-7 | Demand 380–420 vs capacity 270–300 run-hours | *"every hour lost to a washdown or a jam is an hour I don't have to spare"* |
+| C-8 | Meridian due date | *"due Friday close of business, which for Meridian really means Friday, no wiggle"* |
 
-**A8 — Run the batch** — mix, mill, tint (or straight through if it's a plain white), fill, pack. "For a white that's usually the more straightforward path."
-- *Needs:* clean line, batch released to run. *Produces:* filled and packed batch. — **spelled out**
-- *Performed by:* ⚠ line operators not elicited.
-- *Duration:* ⚠ **nothing obtained.** Demanded as a spread, per family and per line. This is the largest single hole in the model — O1 is a question about a *week*, and without run times there is no week.
+## Dynamics
 
-**A9 — QA hold and release** — every batch goes through it.
-- *Needs:* packed batch. *Produces:* released batch, or (presumably) something else on failure — ⚠ failure path never asked.
-- *Performed by:* the lab. *Duration:* **"typically a few hours"** — an honest figure at the wrong precision; demanded as a spread. ⚠
-- *Known failure mode:* "if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line"; "half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it." — **spelled out qualitatively**; the rate and the queueing mechanism are ⚠.
+| ID | Quantity | Direction & rate | Threshold |
+|---|---|---|---|
+| D-1 | **Line 1 mill-to-fill tank level** | rises when mill outpaces fill — **rate open** | at full, **mill stops and waits**; drains as fill proceeds; reset by fill catching up |
 
-**A10 — Stage for shipping / ship** — *needs:* QA release. *Produces:* order off the dock. *Timing constraint:* C4. — **spelled out**; duration ⚠.
+## Data bindings
 
-**A11 — Tech pulled away mid-changeover** (event, not step) — named by you as the cause of the worse tail on A4 and A5. *Rate:* ⚠ not obtained separately — currently only implicit in the one-in-ten tails.
+| ID | Variable | Feed |
+|---|---|---|
+| DB-1 | order arrivals, quantities, due dates | ERP demand book |
+| DB-2 | run durations in run-hours | your weekly sheet (already converted from rates) |
+| DB-3 | per-stage cycle times by product and line | the historian — *"if someone actually pulled cycle times apart by product and stage, which — as I said — nobody's done"* |
 
-**A12 — Washdown fails the visual check, part redone** (event, not step) — named as the cause of the 4 h tail on A6. *Rate:* ⚠ not obtained separately.
+---
 
-## Ordering / flow
+# 2. Assumption ledger
 
-**F1 — The main arc, desk to dock** — **spelled out**, your six steps:
-demand book → allocate to line → queue behind what's running (reorderable) → changeover if needed → run (mix, mill, tint-or-straight-through, fill, pack) → QA hold → release → stage → ship.
+Nothing below came from you. Each is mine, provisional, and needs your yes/no.
 
-**F2 — Order-to-batch split** — an order may become two batches run at different times. *Decided by:* you, on run size or urgency-interleaving. — **spelled out as a rule**; the *cost* of a split (extra changeovers, extra loss) ⚠ never asked.
+| # | Assumption | Why I'd need it | How to check |
+|---|---|---|---|
+| A1 | Changeover crew serves waiting lines **first-come-first-served** | C-5 makes the crew a contended resource; without a rule the model can't pick | Ask you (POL-7) — you may have a real priority rule |
+| A2 | QC lab works **FIFO** on arriving batches | Same reason for C-6 | Ask the lab; also ask you whether you ever expedite a batch |
+| A3 | A washdown falling outside day shift **waits until morning** | BC-3 is unknown and the model must do *something* | Crew lead — you flagged this yourself |
+| A4 | QC lab has **no night presence** | Your stated impression, not fact | The lab |
+| A5 | Line 2's ~2× speed advantage over Line 1 applies to **whites only**; I will not extend it to tints or specialty without evidence | You explicitly said don't take it as gospel outside whites | Process engineering, or historian cycle times (DB-3) |
+| A6 | Ramp-up scrap occurs after a **washdown**, not after every run | Inferred from *"the week I rushed the ramp after a washdown"* — you never said it happens after short changeovers | Ask you; ask quality |
+| A7 | The 24-hour Meridian run is modelled as a **rare tail, ~annual**, not part of the normal bad day | Your words *"once-a-year tail"* — but "once a year" as a rate is my reading of an anecdote | You, next session |
+| A8 | Filler jams are **plant-wide 1–2/week concentrated on Line 2** rather than 1–2 per line | *"It's Line 2's filler mostly"* is directional, not a split | You, next session |
 
-**F3 — Which changeover applies** — selected by (family currently on the line, family of the next batch, line). Same family → A4. White→tint → A5. Tint→white → A6. Into/out of specialty → A7. — **spelled out**
+---
 
-## Policies
+# 3. What's deliberately left out, and what's simply unknown
 
-**P1 — "Meridian whites always go to Line 2, that's just how it's done here"** — *practiced.* Overrides: ⚠ none asked. — **spelled out**
+**Deliberately out of scope** (your boundary, and I think it's right for these three questions):
+- Order generation upstream of the demand book.
+- Trucking, warehouse slotting, shipping — logistics' sheet.
+- Feedstock planning generally, except as the resin-slip disruption.
+- Quarter-scale planning — you don't do it and ERP doesn't support it.
 
-**P2 — Meridian on-time is absolute** — "we don't even try to be clever about it". *Rationale:* fine, plus tracked on-time % and a delisting threat that has been carried out on a competitor. *Overrides:* none — that's the point. — **spelled out**
+**Deliberately simplified, with what's lost:**
+- **Stage-level detail inside a run.** You schedule in whole-run blocks; the model will too, *except* on Line 1 where you told me the mill-to-fill tank causes real dead time. Lost: any pipelining benefit from overlapping the next batch's mix with this batch's fill. Justified for now because your sheet doesn't see it either — but flagged, because you said the sheet *flatters* reality, and OBJ-3 (are you leaving hours on the table?) is exactly the question where flattery misleads.
+- **Tint-to-tint sub-families.** Collapsed to one 20–30 min changeover. Lost: any light→dark penalty. Justified because you've never separated it; revisit if the model over-favours tint batching.
 
-**P3 — Who gets the tech when two lines want one** — *practiced, and there is no prescribed form:* "there's no posted rule at all."
-- The rule as practiced: whichever line has the **more time-sensitive order behind it** wins; if that's a tie, **whichever changeover is faster** wins, "so you get a line moving sooner". In the room it resolves as "whoever's louder at the huddle, or whoever's about to actually run dry".
-- *Borderline case on record:* Line 1 and Line 3 both wanted a washdown the same morning. Line 3 got the tech first because Line 3's was the quick one and Line 1's was the long tint→white slog anyway — knock out the fast one, get that line moving, then commit the tech to the long one. Line 1 sat clean-but-waiting ~40 minutes past when it could have started.
-- *What overrides it:* the ops director, who has overruled you once, wanting "his pet SKU out the door". — **spelled out**
-- *Rationale:* two techs, three lines, so "the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line" — that's the grief at the huddle, not changeover variability.
+**Unknown and load-bearing — these are what stop the model running honestly today:**
 
-**P4 — Reorder the queue so a job doesn't get stuck behind a big changeover** — *practiced, yours.* — **spelled out**; overrides ⚠ not asked.
+1. **POL-5 and POL-6** — the two rules the whole exercise exists to test. Without your practiced rule I have no baseline to compare a candidate policy against.
+2. **A-12 requalification cost** — OBJ-1 is a trade between requalification and a slipped white. One side of the trade is unsized.
+3. **POL-7 changeover-crew priority** — C-5 is a hard bottleneck and you named its symptom (Line 3 idle). Currently on assumption A1.
+4. **A-3, A-5, A-6** — the quick changeover, all specialty changeovers, and ramp-up scrap magnitude. OBJ-2 is *literally* "idle hour vs three-hour washdown plus ramp loss," and the ramp loss has no number.
+5. **P07 across the board** — I have one duration spread, for one product on one line. I do not know how run duration varies by line, family, or size.
+6. **BC-1 rush orders** — you say they land and force re-juggling; I have no arrival pattern, and OBJ-3 is about splitting runs to accommodate them.
+7. **Numeric trade weights** — the Meridian-vs-distributor-vs-scrap exchange rate. Deposit: commercial.
 
-**P5 — Hold the line for an anticipated same-family order** — the decision under test. As practiced two weeks ago: on a heads-up that a same-family white was about to drop, let Line 2 sit idle ~1 h rather than wash down to the waiting tint, to save a full washdown. Your own account: "I was guessing." — **spelled out as an instance**; the trigger condition (B2) and the decision threshold are ⚠.
+---
 
-**P6 — Batch split discretion** — "I have the freedom to split if I need to." — **spelled out**
+# 4. Agenda for tomorrow
 
-## Constraints
+In the order I'd spend the time, biggest gap first:
 
-**C1 — Line qualification** — Line 1 qualified for everything including specialty; Line 3 qualified product-by-product, "can't run everything yet"; Line 2 ⚠ never stated. *Consequence when hit:* the batch can't go on that line. — **partially spelled out** ⚠
+1. The **reroute-or-hold** rule and the **idle-or-washdown** rule, each via the last time you actually faced it and what you looked at.
+2. **Requalification** — what it actually involves and how long it takes.
+3. **Changeover crew priority** when two lines want them at once, plus a recent borderline case.
+4. **Ramp-up scrap** magnitude, and whether it follows every changeover or only washdowns.
+5. **Rates for the other lines and families** — enough to stop me extrapolating from one Meridian white run.
+6. **Rush order arrivals**, and who counts as Meridian-tier.
+7. Whichever of the three deposits (crew lead / lab / process engineering) you can chase.
 
-**C2 — Two techs, three lines** — *consequence when hit:* one line waits, clean-but-idle (40 min in the case on record). — **spelled out**
+One correction I'd like at the top of tomorrow: **have I got any of the above wrong or in the wrong words?** Particularly the objectives table and the "better" ranking — those drive what I ask everything else about.
 
-**C3 — Tint → white requires a full washdown with a passing visual check** — *consequence:* pigment left behind ruins a white batch. — **spelled out**
+---
 
-**C4 — Meridian must leave our dock a day ahead of the dock appointment** — *consequence:* fine + on-time % + delisting exposure. — **spelled out**
+**Expert (Marta)**:
 
-**C5 — Every batch goes through QA hold before release** — *consequence:* no batch ships unreleased. — **spelled out**
+This is a lot to take in on a screen before a huddle, but let me flag what jumps out at me now rather than wait.
 
-## Dynamics
+Mostly this reads right. A couple of things I want to correct or sharpen before you build on them:
 
-**None.** Nothing you described evolves continuously while nothing discrete happens. Soak time inside A6 is dead time within an activity, not a state variable that crosses a threshold. I am deliberately not inventing one.
+**The "better" ranking** — close but not quite. You've got scrap and changeover hours as roughly equal-weight, third and fourth. I don't think that's right. Re-reading what I actually said: I'd take a scrap spike over a late Meridian order, sure, but I never compared scrap to changeover hours directly. My gut says changeover hours lost matter *more* than scrap, because lost hours cascade into more lateness, whereas scrap is just money — annoying, contained, doesn't ripple. So the order should probably be: late-and-who > changeover hours lost > scrap. But flag that as me thinking out loud just now, not something I'd already settled — ask me again tomorrow once I've slept on it, I might change my mind.
 
-## Data bindings *(named only — these project to nothing today)*
+**A-7, the QC hold table** — you've written "with backlog, a day-plus (last week: Wed evening → Thursday midday)." That's about 18 hours, which is bad-Friday territory but it was actually a Wednesday-into-Thursday case, not the classic Friday backlog. I gave you that example as the "how it can still go wrong on a decent week" case, not as my definition of the tail. Don't let that example become your number for "the Friday case" — Friday's usually worse than that, I just don't have a clean anecdote for it yet.
 
-Changeover logs (tech start/finish per changeover — the check on ledger #1 and #2); ERP demand book (B1 arrival pattern); QA release timestamps (A9); Meridian on-time percentage (O2). — **named**
+**One thing missing entirely: BC-1, rush orders.** You've noted it as open, correctly, but I want to flag it's not a small gap — it might be as big as the two decision rules. Rush orders are *why* the reroute-or-hold and idle-or-washdown calls happen in the first place half the time. If you only ask me about the steady-state rules tomorrow and not about how rush orders actually arrive, you'll have modelled the calm week and missed the reason I lose sleep.
 
-## Validation criteria
+**Small correction on A-9/A-10**: you've split the mill motor into "hiccup" and "multi-day disaster" as two separate activities, which is fair, but don't assume everything between those two is smoothly distributed — in my experience it's bimodal, either a nuisance under half a day or a genuine disaster, rarely something in the middle. Worth being careful the model doesn't invent a smooth continuum where the real thing is two lumps.
 
-⚠ **None obtained.** I never asked how you'd know the model was right. It belongs at the top of the next session, next to run times.
+Otherwise — yes, that's my plant. See you tomorrow, same time. Lead with the two rules.
 
 ---
 
-# 2. Assumption ledger
+**Interviewer**:
 
-Everything here is mine, not yours.
+Recorded — all four as corrections that **supersede** what I'd written, not additions beside it.
 
-| # | Assumption | Why | How to check |
-|---|---|---|---|
-| 1 | Line 1 changeover durations = Line 2 × 1.2, all types | You said Line 1 is "fussier to get properly clean" and, when I proposed 20%, that it "sounds about right, not double" — but you explicitly could not swear the minutes. The 1.2 factor is mine. | Changeover logs, if techs record start and finish; compare Line 1 vs Line 2 for the same family pair. |
-| 2 | Line 3 changeover durations = Line 2 | You said Line 3 has no war stories and "you're stuck assuming it's like Line 1 or Line 2 until we've got more history". Choosing Line 2 rather than Line 1 is mine. | As #1, once Line 3 has run enough different products. |
-| 3 | "An hour and a bit" (A5 worse) = 70 min; "4, maybe a bit more" (A6 worse) = 4.5 h | Numeric reading of your words so the spread is usable. | Ask you to confirm or correct the two figures. |
-| 4 | Crew hands-on fractions: A4 = 1.0 (yours, stated); A5 = 0.8; A6 = 0.5; A7 = 0.8 | You said "most of it", "maybe half of that", "most of that". A6's 0.5 is close to your words; the two 0.8s are mine. | Changeover logs vs. tech time records; or ask the techs directly. |
-| 5 | No changeover happens outside day shift | You said "two techs on day shift covering all three lines". Whether there's any other coverage was never asked. | One question to you. |
-| 6 | Every batch's changeover requires exactly one tech (not two) | You always spoke of "the tech" singular. | One question to you. |
-| 7 | A6's redo-after-failed-visual-check is inside the 4 h tail rather than a separate event with its own rate | Simplification so the spread stands alone; you described it as the *cause* of the tail. | Ask how often the visual check fails first time. |
+1. **"Better" ranking** — now reads: *late orders and to whom* > *changeover hours lost* > *scrap*. Your reason on the record: *"lost hours cascade into more lateness, whereas scrap is just money — annoying, contained, doesn't ripple."* Marked **provisional — thought aloud, not settled**; I'll re-ask tomorrow before anything depends on it, and I won't build the metric on it in the meantime. The one firm ordering stays as you first gave it: scrap spike beats a late Meridian order, no contest.
 
----
+2. **A-7** — the Wed evening → Thursday midday case is now labelled as your *"how it can still go wrong on a decent week"* example. It is **not** the Friday tail and I've deleted it from that slot. The Friday tail is now explicitly open: *"Friday's usually worse than that, I just don't have a clean anecdote for it yet."*
 
-# 3. What this model leaves out, and what's still unknown
+3. **BC-1 rush orders** — promoted out of the general open list into the top tier, alongside POL-5 and POL-6, with your framing attached: *"rush orders are why the reroute-or-hold and idle-or-washdown calls happen in the first place half the time… you'll have modelled the calm week and missed the reason I lose sleep."*
 
-**Deliberately left out.**
-- **Queues and waiting states** are not modelled as things in their own right — the wait behind a running batch, the wait for a tech, the wait in QA hold. They fall out of the activities either side of them. The 40-minute clean-but-waiting on Line 1 is a *result* the model should produce, not an input.
-- **The commercial layer** — the fine, the on-time percentage, the delisting mechanism. C4 and O2 encode the hard deadline; the money behind it is out of scope because it's out of your sight.
-- **Who ran which changeover** — the two techs are interchangeable, since you drew no distinction between them.
+4. **A-9/A-10** — flagged as **bimodal, not a continuum**: nuisance under half a day, or genuine disaster, *"rarely something in the middle."* Noted as a modelling instruction, so nobody fits a single smooth distribution across the gap.
 
-**Things the model cannot carry, that I'm keeping in words so they aren't lost.**
-- **O4, "how ugly the sheet looks."** A real criterion you use, explicitly not a number. It can be approximated as line idle hours, but that approximation is mine, not yours, and I haven't made it.
-- **The O2/O3/lateness trade-off weight.** Genuinely unquantified, with the source named: commercial. Without it, the model can report changeover hours and lateness separately but cannot rank two schedules that trade one for the other.
-- **The huddle.** "Whoever's louder at the huddle" and the ops director's pet-SKU override are the real P3 in the room. The triage logic you gave me — time-sensitivity first, faster-changeover as tiebreak — is compilable; loudness and the override are not, and any run of this model will be *quieter and more rational* than your plant. That gap is worth remembering when the results look tidy.
-- **Ledger #1–#4** are load-bearing for any result involving Line 1 or Line 3. Right now O1 is only genuinely answerable for Line 2.
+Tomorrow, in this order: the reroute-or-hold rule, the idle-or-washdown rule, then rush orders — each via the last time it actually happened. Requalification and crew priority after that.
 
-**Open slots, in the order I'd close them.**
-1. **A8 run duration** — nothing at all, per family and per line, as a spread. O1 asks about a week; run time is most of a week.
-2. **B2, the drop-in and the heads-up** — how the warning reaches you, how far ahead, and how often it's right. P5 is the decision under test and its trigger is currently an anecdote.
-3. **A9 QA hold** — "a few hours" is a figure at the wrong precision. And whether the lab is a shared resource with a queue, like the techs — because by your own account that's where lateness actually comes from.
-4. **B1** — orders per weekly pull, and the within-week shape.
-5. **E2 / F2** — typical run sizes, and what a split actually costs in extra changeovers.
-6. **B5 / C1** — which SKUs Line 3 is qualified for, and whether Line 2 has restrictions.
-7. **Breakage and interruptions** — you mentioned "the mill motor issue" in passing as an example of something structurally different. I never asked what breaks, how often, or for how long.
-8. **Validation** — how you'd know the model is right.
-
-**One caution on the format.** I've built the model; the Petri-net scaffold and the code obligations are derived from it by the tooling, not written by me. I'm not claiming this loads or runs as-is — the run-duration hole alone would stop it.
+Enjoy the huddle.
 
 ---
 
 **Expert (Marta)**:
 
-*(No dialogue — Marta has left for the huddle. This turn is a silent acknowledgment beat only if the interviewer expects a reply; otherwise nothing further is added.)*
+Thanks — that all lands right. See you tomorrow.
 
 ---
 
 **Interviewer**:
 
-Nothing further from me — you've stopped, and the read-back above is the deliverable as it stands.
+See you tomorrow.
 
-For when you're back, the first three questions in one place, so you can answer them in five minutes if that's all you have:
+For the record, so nothing depends on memory overnight:
 
-1. **How long does a batch run?** Typical, one-in-ten worse, one-in-ten better — for a plain white on Line 2 first; I'll ask about the other families and lines after.
-2. **The heads-up.** Two weeks ago, who told you that white order was about to drop, how far ahead, and how often does that kind of warning turn out to be right?
-3. **QA hold.** "A few hours" — typical, one-in-ten worse, one-in-ten better. And is there a queue for the lab like there is for the techs?
+**Stopping outcome: `expert-stopped` — partial model with open slots.** The structural floor holds; none of the three objectives has a complete dependency slice. The model as read back stands, with the four corrections you just gave superseding what they replace:
 
-Enjoy the huddle.
+- **Better** = late-and-to-whom > changeover hours lost > scrap — *provisional, thought aloud, to be re-confirmed before any metric is built on it*. The settled part remains: scrap spike over a late Meridian order, no contest.
+- **A-7** — Wed→Thu ~18h is your *decent-week* example, not the Friday tail. Friday tail: open, no anecdote yet.
+- **BC-1 rush orders** — top-tier gap, level with the two decision rules.
+- **A-9/A-10** — bimodal by instruction: nuisance under half a day, or disaster. No smooth continuum across the middle.
+
+Three deposits still sitting with other people when you get a chance: the crew lead (what happens to a washdown forced onto nights), the lab (parallel testing and evening cover), and process engineering (whether Line 2's 2× holds outside whites).
+
+Tomorrow: the two rules first, then rush orders — each via the last time it actually happened.
 
 ---
 
 **Expert (Marta)**:
 
-*(Marta has stepped away to the huddle — no further reply expected this turn. The three questions are noted for the next session.)*
+Sounds right. Talk tomorrow.
 
 ---
 
 **Interviewer**:
 
-Noted — session closed. The model, the seven-item assumption ledger, and the eight open slots stand as delivered above; the three questions are queued for next time.
+Talk tomorrow. The record's in the read-back above — nothing further from me until we pick up the two rules.
 
 ---
 
 **Expert (Marta)**:
 
-Understood — nothing further needed from me here. Session closed, deliverables stand as written, and I'll pick up run times, the heads-up mechanism, and QA hold as the first order of business next time we talk.
+Good — I'll be ready to walk through the reroute and idle calls when we start. Nothing more from me either until then.
 
 ---
 
 **Interviewer**:
 
-Acknowledged. Session closed on your terms.
-
-For the record, so nothing depends on memory next time:
-
-- **Delivered:** the model (4 objectives, 5 entity types, 5 boundary conditions, 12 activities, 3 ordering/flow rules, 6 policies, 5 constraints, no dynamics, 4 named data bindings), the 7-entry assumption ledger, and the loss account.
-- **Queued, in order:** A8 run duration → B2 the heads-up mechanism → A9 QA hold and whether the lab queues.
-- **Standing caveat:** O1 — hold versus wash down — is currently answerable only for Line 2, and only once run times exist. Ledger #1–#4 are the assumptions to attack first if a result involving Line 1 or Line 3 ever looks decisive.
-
-Thanks for the time, Marta — the changeover asymmetry and the tech-contention story were the two things I'd never have got from a document.
+Understood. Standing by — we resume with the reroute-or-hold call, the idle-or-washdown call, then rush orders, each from the last time it happened.
 
 ---
 
 **Expert (Marta)**:
 
-Anytime. Glad the changeover asymmetry landed — that one catches everybody, including people who've been on the floor a lot longer than me. Come find me at the huddle when you're ready to go through run times, I'll have my head in the sheet anyway.
+Sounds good — I'll have the specific instances in mind. Talk then.
 
 ---
 
 **Interviewer**:
 
-Will do — I'll come to the huddle rather than pull you out of it. If your head's in the sheet anyway, that's the best possible place to ask about run times: I'd rather hear "that one took nine hours and it was a bad one" off the actual sheet than a remembered average.
-
-One small ask for whenever it's convenient, no work required now: if the changeover logs do have tech start and finish times on them, that's the single thing that would let me retire ledger entries #1 and #4 — the Line 1 scaling factor and the crew hands-on fractions — and swap my guesses for your history.
-
-See you at the huddle.
+Perfect — a specific instance for each is exactly what I need. Talk then.
 
 ---
 
 **Expert (Marta)**:
 
-Sounds good — I'll flag it to the two techs to make sure they're actually filling in start/finish consistently, because I'll be honest, I've never audited that field myself, I mostly just glance at duration. If it's patchy for Line 1 and Line 3 specifically, that itself would be useful for you to know, not just an inconvenience. See you at the huddle.
+Confirmed — same plan, same order. Talk then.
 
 ---
 
 **Interviewer**:
 
-That's a genuinely useful thing to have said, and I'm recording it rather than just noting it — it changes the status of a data binding I'd been leaning on.
-
-**Amendment to the delivered model:**
-
-- **Data binding "changeover logs (tech start/finish)"** — provenance qualified: the start/finish field has never been audited; you read duration only. Coverage is unknown and may be patchy, and you've flagged Line 1 and Line 3 as the places to look. Your words: "I've never audited that field myself, I mostly just glance at duration."
-- **Consequence for the ledger:** entries #1 (Line 1 × 1.2) and #4 (crew hands-on fractions) each carry a second-order dependency — their check depends on a feed of unverified coverage. If the field turns out patchy exactly where the assumptions bite, those two stay assumptions and the honest move is to widen them rather than to fill them in.
-- **Recorded as a finding in its own right:** patchy logging on Line 1 and Line 3 is itself evidence about the plant, not just an obstacle to the model.
-
-Nothing else changes. See you at the huddle.
+Confirmed. Ending here.
 
 ---
 
 **Expert (Marta)**:
 
-Fair enough — that's a better way to put it than I would have. Talk soon.
+Alright — ending here. Talk soon.
 
 ---
 
 **Interviewer**:
 
-Talk soon, Marta.
+Talk soon. The model, assumption ledger, and loss account are in the read-back above, with your four corrections applied; we resume at the two rules.
 
 ---
 
 **Expert (Marta)**:
 
-See you at the huddle.
+Understood — that's the record. Whenever you're ready to pick up the reroute-or-hold rule, I'll walk you through the actual case.
 
 ---
 
 **Interviewer**:
 
-See you there.
+Then let's pick it up now — no reason to wait.
+
+**Take that Line 1 mill motor morning.** Not the general rule yet, just what happened. You're at the huddle, the motor's down for a few hours, you've got the specialty batch and the Meridian white both needing to move.
+
+1. **Walk me through the minutes.** What did you look at first, what did you look at next, and what did you say out loud when you made the call? I want the sequence of your attention, not the justification.
+
+2. **What would have had to be different for you to call it the other way** — held the specialty on Line 1 and let the white slip? Give me the version of that morning where you make the opposite call.
 
 ---
 
 **Expert (Marta)**:
 
-*(end of session — nothing further to add.)*
+Okay, let me actually put myself back there.
 
----
+**1. The sequence.**
 
-**Interviewer**:
+First thing I looked at wasn't the specialty or the white at all — it was the motor. I wanted to know from maintenance, right then, "is this the twenty-minute reset kind or do I need to be worried," because that answer changes everything downstream. They said a few hours, looked routine, not the scary failure — that's the first fact I need before I can even think about rerouting anything.
 
-Session ended. Deliverables stand as written above.
+Second thing: I looked at the specialty batch's due date. It wasn't screaming — a few days out — so my first instinct was actually "can it just wait for Line 1 to come back," not "move it." That's my default, moving specialty is a pain, I don't want to do it.
 
----
+Third: I looked at what Line 2 was doing and what it was about to do. Line 2 had capacity coming up because the tint run ahead of the Meridian order was tracking fine — so the Meridian white had a clear path if Line 1's problem didn't spill into it. That's when the real tension showed up: if I *don't* move the specialty, it sits and waits for Line 1, fine, no drama — but the thing that actually made me move was that Line 1's queue that day wasn't just the specialty, it also had a knock-on tint job stacked behind it, and if the specialty sat there blocking the queue, that tint job gets delayed too, and *that* tint job was the one that fed into the Meridian white's changeover on Line 2 later in the week. So it wasn't "specialty vs white" directly — it was "if I don't clear Line 1's queue now, it back up onto something that touches the white two days later."
 
-**Expert (Marta)**:
+So what I actually said out loud at the huddle was something like "Line 1's down a few hours, let's shift the specialty to Three and keep the queue moving, I don't want this backing into Thursday." The white wasn't really the thing I was staring at — it was collateral reasoning, the domino two steps down.
 
-Confirmed — nothing further from this end. Session closed.
+**2. The opposite call.**
+
+I'd have held the specialty on Line 1 if: the motor fix had been quick — say under an hour, not "a few" — because then it's not worth the requalification hassle for such a short wait. Or if Line 3 had been tied up with something of its own that day, because then rerouting isn't even a real option, it's theoretical. Or — and this is probably the biggest one — if that tint job hadn't been sitting behind the specialty in Line 1's queue. If Line 1's queue that day was *just* the specialty and nothing behind it, I'd have shrugged and let it wait for the motor, because a few hours' hold on a not-urgent specialty order is cheap and a requalification isn't.
+
+So the honest rule buried in there isn't really "reroute vs hold based on the white" — it's more like: **I hold by default, and I only reroute if leaving it in place would jam something else behind it that I care about more.** The Meridian white in this story was three steps removed, not the thing I was directly weighing.
 
 ---
 
 **Interviewer**:
 
-Closed. Nothing further.
+That's a different rule than the one I was about to write down, and much more useful — thank you. Let me check I've got it.
+
+**So you're saying: your default is hold. You only reroute when leaving the job in place would block something behind it in that line's queue that you care about more than the requalification cost — and the thing you care about may be several steps removed, like a tint job that later feeds a changeover on another line.** Is that right, and would you word it differently?
+
+Two things I need to make that runnable:
+
+1. **How far down the queue do you actually look?** In that story you saw a tint job behind the specialty, and then saw that the tint job touched the white two days later — that's two hops. Is two hops typical, or did you go further that morning than you usually do? And is there a point where you stop tracing?
+
+2. **What makes a downstream job one you "care about more"?** In that case the chain ended at Meridian. Would a chain ending at a small distributor's order have moved you, or would you have shrugged and held?
 
 ---
 
 **Expert (Marta)**:
 
-Closed.
+Good questions, and honestly they make me realise I don't do this as cleanly as the story makes it sound.
+
+**On the wording** — yes, that's right, that's a better statement of it than I'd have managed myself. "Hold by default, reroute only if staying put jams something you care about more" — that's the shape of it. I'd maybe add: it's not just that requalification is costly, it's that requalification is a *known, bounded* cost and blocking the queue is an *unknown, possibly-cascading* one. So there's an asymmetry — I'll pay a known cost to avoid an unknown one, especially when I'm short on time to think it through properly, which at a 07:30 huddle I always am.
+
+**1. How far I look:** Honestly, two hops is probably close to my ceiling, and that morning I only got there because the tint job was the very next thing in queue and I happened to remember what it fed. I don't systematically trace the whole week's dependency chain every time something breaks — I don't have time, and frankly I don't think I *could* hold that whole picture in my head reliably. Normally it's one hop: "what's sitting right behind this in the queue, does it matter." The second hop only happens when the first hop is itself something time-pressured — if the tint job behind the specialty had had a slack due date, I probably wouldn't have bothered chasing where it went next. So: **one hop routinely, two hops only when hop one is already urgent-looking.** Past that I'm guessing, not tracing.
+
+**2. What makes it "care about more":** Yeah — if that chain had ended at a small distributor instead of Meridian, I don't think I'd have moved the specialty. I'd have shrugged, let Line 1's queue sit, and told the distributor's order it might run a day later, which is exactly the kind of slip that "nobody notices." The whole reason I bothered chasing the second hop that morning is that Meridian was at the end of it — if I hadn't recognized where the tint job fed, I wouldn't have rerouted at all. So the customer tier at the *end* of the chain is doing real work here, not just the immediate next job. Put bluntly: I trace further and act more readily when I suspect Meridian's at the other end of it than when I don't.
 
 ---
 
 **Interviewer**:
 
-Closed.
+Two more on this rule, then I'll size the cost side of it.
+
+1. **What overrides it?** I'm looking for the case that breaks the pattern — a time you rerouted even though nothing was stacked behind, or a time something urgent *was* blocked and you still held. If one comes to mind, tell me what was different about it.
+
+2. **Requalification** — you've called it a headache and a known bounded cost, but I have no size for it. When you moved that specialty to Line 3, **what actually had to happen before it could run?** Who did what, and how long did it hold the batch up?
 
 ---
 
@@ -609,343 +682,398 @@ I really do have to stop here. Please produce the model now with everything you
 
 **Interviewer**:
 
-# Coatings Plant Scheduling Model
-**Elicited from:** Marta, master scheduler
-**Job:** construct (no prior model)
-**Status at close:** floor satisfied; O1's dependency slice **incomplete** — see §3.
-**Vocabulary:** the expert's throughout. `⚠` = a slot the method demands and the interview did not obtain.
+Stopping now. Nothing new opened; the last two questions I asked are recorded as unanswered.
 
 ---
 
-## 1. The model
+# Coatings Plant Scheduling Model
 
-### 1.1 Objectives
+**Stopping outcome: `expert-stopped` — partial model with open slots.**
 
-**O1 — "Hold the line versus wash it down now, which one actually costs less over the week"**
-- **The question, in her words** *(spelled out)*: whether letting Line 2 sit idle for about an hour, on a heads-up that another same-family white order is about to drop in from a distributor, is cheaper over a week than washing down now to run the tint batch waiting behind it. Origin: a real Thursday-afternoon decision two weeks before the interview. Her own verdict on how she made it: *"I was guessing."*
-- **Depends on** *(≥1 satisfied)*: E1, E2, E3, E4, B1, B2, A4, A5, A6, A8, A9, F1, F2, P3, P4, P5, C1, C2, C3.
-- **What "better" means** *(named; not quantified)*: changeover hours consumed over the week, subject to O2 holding absolutely. ⚠ no trade-off weight against lateness — see the trade-off note below.
-- **Source-regime**: practiced.
+The structural floor holds (3 objectives, 6 entity-types, 13 activities, 4 ordering/flow nodes). **No objective's dependency slice is complete.** OBJ-1 is now substantially supported on its policy side and unsupported on its cost side; OBJ-2 and OBJ-3 remain unsupported at their cores. Details in §4.
 
-**O2 — "Whether Meridian shipped on time, full stop, that's non-negotiable"**
-- **The question** *(spelled out)*: does every Meridian order leave the dock in time for its dock appointment.
-- **"On time" defined** *(spelled out)*: a ship date given on the order, usually with a delivery window attached — a specific dock appointment at Meridian's end. In practice the batch must leave our dock **one day ahead** to allow for freight. Not "shipped this week."
-- **Consequence of a miss** *(spelled out, unquantified)*: a fine — *"I don't see the number, that's commercial's problem, but I hear about it"* — and, worse, Meridian tracks our on-time percentage and threatens to delist SKUs if it drops too far. A competitor has been delisted, *"so it's not an empty threat, and it's why the rule is absolute — we don't even try to be clever about it."* ⚠ fine amount and delisting threshold both outside her sight.
-- **Depends on**: A8, A9, A10, B3, C4, C5, P1, P2.
-- **Source-regime**: prescribed and practiced coincide — she reports no divergence, which is itself the finding.
+Every value below is at the grade you actually gave it, in your words where I have them. I have not promoted anything.
 
-**O3 — Changeover hours**
-- **The question** *(spelled out)*: how many crew-hours go into washing down rather than filling. *"Every hour the crew spends washing down is an hour not filling anything."*
-- **Depends on**: A4, A5, A6, A7, E4, C2, P3.
-- **What "better" means** *(named)*: fewer changeover hours. Directionally clear, no target value. ⚠
+---
 
-**O4 — "How ugly the sheet looks"**
-- **The question** *(spelled out)*: *"are there gaps where a line's sitting idle for no good reason."*
-- **What "better" means** *(her words; explicitly not a number)*: *"that last one's not a number, it's more a gut check, but it's real."*
-- **Depends on**: E3, C2, P3, P4, A4–A7.
-- **Status**: recorded, IR-only. Approximating it as line idle hours would be my move, not hers; I have not made it. See §3.
+## 1. Objectives
 
-**The trade-off between O2, O3 and non-Meridian lateness** *(spelled out as a rule; deliberately unquantified)*
-Four changeover hours saved against one distributor order two days late: *"honestly, yes, I'd take that trade most of the time"* — a distributor slip is *"usually just an annoyed phone call from our sales rep, not a fine."* But *"'most of the time' is doing a lot of work in that sentence"*: the same distributor slipping three weeks running starts asking for a discount. So lateness for non-Meridian is soft but not infinitely soft, and the softness decays with repetition on the same customer.
-**Deposit for the missing number**: *"that's genuinely a 'sit down with commercial' conversation, nobody's ever made me quantify it."* Source named; not obtainable from the scheduler. ⚠
+| ID | The question, in your words | Depends on | Slice status |
+|---|---|---|---|
+| **OBJ-1** **Reroute or hold** | *"whether to shift the specialty over to Line 3 and eat the requalification headache, or hold it and let the white slip behind on Line 2"* — *"I'd love to run twice and see which one bites me less"* | POL-5, A-12, ET-3, ET-1, C-1, C-2, C-3, POL-1, A-9, A-10, OF-3 | **Partial** — rule captured, requalification cost absent |
+| **OBJ-2** **Idle or washdown** | *"do I sit Line 2 empty for an hour waiting on a same-family order, or just pay the three-hour washdown now"* — a call *"almost weekly and it's pure feel"* | POL-6, A-2, A-3, A-4, A-6, ET-4, C-5, BC-1 | **Unsupported** — the deciding rule is absent |
+| **OBJ-3** **Run size & sequencing** | *"whether to split a big order into two runs to slot in a rush job, or batch several small orders of the same family together even if it means one of them ships a bit early and sits in the warehouse"* — *"I've never had a way to check if I'm leaving hours on the table"* | OF-2, C-4, A-6, A-2/3/4, BC-1, ET-2 | **Unsupported** — rush-order arrivals and minimum run size absent |
 
----
+Noted, **not** an objective you own — overtime approval: *"that's the ops director's call, though I do feed him the 'we'll miss X without it' argument… maybe that's a variant of the same question rather than a fourth one."*
 
-### 1.2 Entity types
+**What "better" means** — grade: *spelled out as a ranking; numeric weights absent.*
 
-**E1 — Order (in the demand book)**
-- **Distinctions the process treats apart** *(spelled out)*: Meridian vs. non-Meridian — a Meridian flag arrives on the order and it *"jumps to the top of my attention"*; family classification (see below), which drives allocation and changeover.
-- **State riding along** *(spelled out)*: SKU; quantity; due date with delivery window; Meridian flag; family — **base white / tinted colour / specialty clear**. The family is a real field: *"that's not my judgment, that's how the SKU's classified in the system, it drives what changeover you need going in and out."*
-- **How many / population shape**: ⚠ not obtained. Orders per weekly pull and within-week shape unknown.
+- **Settled:** ordering is by lateness **and to whom** — *"a late order to Meridian is worse than three late orders to a small distributor, so it's not just a count, it matters who."*
+- **Settled trade:** *"a late Meridian order and… a scrap spike — I'll take the scrap spike every time, no contest. Scrap costs money, a late Meridian order costs a relationship and a fine."*
+- **Provisional, thought aloud, explicitly not settled:** late-and-to-whom > changeover hours lost > scrap, because *"lost hours cascade into more lateness, whereas scrap is just money — annoying, contained, doesn't ripple."* You asked to be re-asked after sleeping on it. **No metric should be built on this ordering until you confirm it.**
+- Currency exchange rate between the three: **open.** Deposit: *"sit down with commercial."*
 
-**E2 — Batch**
-- **Distinctions** *(spelled out)*: inherits the family of the order it came from.
-- **Relationship to E1** *(spelled out)*: *"mostly the order is the batch, if it fits a reasonable run size."* Split into two batches run at different times when a distributor orders more than makes sense in a single run, or to interleave something more urgent. *"Order-to-batch most of the time, but not a strict one-to-one — I have the freedom to split if I need to."*
-- **How many / population shape**: ⚠ not obtained. Run sizes, "reasonable run size" threshold, and the cost of a split all unelicited.
+**Horizon** (spelled out): rolling week, built fresh Monday against that week's demand book, re-runnable at shift grain when something breaks at 06:00. *"A quarter's too far out — I don't plan that far, ERP just doesn't give me visibility past a few weeks anyway."*
 
-**E3 — Line** *(a contended resource: capacity in C1, contention in P1/P3, availability in B4)*
-- **Distinctions** *(spelled out)*:
- - **Line 1** — *"the old workhorse — slower but it's qualified for everything, including specialty."* Crew report it is *"fussier to get properly clean."*
- - **Line 2** — *"the fast one, that's your big-volume runner."* Meridian whites always go here (P1).
- - **Line 3** — *"the newest and quickest, but it's still being qualified product by product, so it can't run everything yet"*; so far *"mostly one or two SKUs."*
-- **State riding along** *(spelled out)*: the family the line is currently dirty with — this selects which changeover applies (F3); the line's qualification set.
-- **How many** *(number)*: 3.
+**Boundary** (spelled out): begins when an order lands in the demand book from ERP; ends when the batch **clears QC hold and is released to the warehouse.** Trucks and warehouse slotting excluded — *"logistics' sheet, not mine."* QC hold explicitly in scope — *"I've had orders filled on time and still gone late because the lab backed up on a Friday."* Feedstock excluded except that resin slips must be representable — *"otherwise you're modelling a plant that never has a bad Tuesday."*
 
-**E4 — Changeover tech** *(a contended resource)*
-- **Distinctions** *(named)*: none drawn between the two techs; treated as interchangeable.
-- **State riding along** *(spelled out)*: which line they are currently committed to. Can be *"pulled away partway through"* a changeover, and during long soaks *"might duck off to start something on another line."*
-- **How many** *(number)*: 2 on day shift, covering all three lines. *"That's it. No dedicated tech per line."*
+---
 
-**E5 — QA lab**
-- ⚠ **Nothing obtained** beyond its existence, that every batch passes through it, and that it *"gets backed up on a Friday afternoon."* Whether it is a contended resource with a queue — as she suspects and I flagged — is open.
-- Recorded because her own diagnosis makes it load-bearing for O2: *"half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it."*
+## 2. Validation criteria
+
+| ID | Criterion | Grade |
+|---|---|---|
+| **VC-1** | The unwritten rules hold: Meridian white lands on Line 2; specialty never on Line 2; Line 3 never gets the two unqualified tint SKUs. *"If it violates any of that, I'll dismiss it in about ten seconds, doesn't matter how clever the maths is."* | spelled out |
+| **VC-2** | Changeover asymmetry the right way round: **tint→white is the long washdown, white→tint is the quick one.** *"If it shows tint-to-white as quick and white-to-tint as the long one, I'll know someone got the plant backwards."* | spelled out |
+| **VC-3** | Replay last week's book; the late orders it predicts are roughly the ones that actually went late — Meridian squeaked through by a few hours; a distributor order slid four days *"with a phone call and nobody blinked"*; the Line 1 tank issue bit us. You can reconstruct two or three such weeks from memory and the sheet. | spelled out |
 
 ---
 
-### 1.3 Boundary conditions
+## 3. The model
 
-**B1 — ERP weekly pull into the demand book**
-- **Starting state** *(spelled out)*: orders come over from ERP on the weekly pull carrying SKU, quantity, due date, Meridian flag.
-- **Arrival pattern**: ⚠ **not obtained** (demanded as a spread). No volume, no variability, no within-week shape.
+### 3.1 Entity types
 
-**B2 — Mid-week drop-in order, and the heads-up that precedes it**
-- ⚠ **Not obtained** (demanded as a spread). All that exists is the single anecdote: *"I had a heads-up another same-family white order was about to drop in from a distributor."*
-- **Why this matters more than its size suggests**: this is the trigger on which O1's entire decision hangs. Who gives the heads-up, how far ahead, and how often it proves right are all unknown. Without it, P5 can be simulated as a *rule* but its *arrival process* has no basis.
+| ID | Type | Distinctions the process treats apart | State it carries | Population |
+|---|---|---|---|---|
+| **ET-1** | **Order** — a line in the demand book | SKU; quantity (drums, sometimes bulk litres for big Meridian); due date; **customer tier — Meridian vs small distributor** | family (white / tint / specialty); due-date hardness; customer tier | ~**380–420 run-hours** of demand per week *(range)* |
+| **ET-2** | **Run** — a block on the sheet | *"orders are what demand gives me, runs are what I actually schedule, and I'm the one deciding the mapping between them week to week."* One order's worth, or several small same-SKU orders lumped to clear minimum run size; a big order can split into two runs to interleave a rush job | line assignment; family; scheduled window | derived from ET-1 by OF-2 |
+| **ET-3** | **Line** | see 3.2 | current/last family (sets the changeover); qualification set; up / down | **3** |
+| **ET-4** | **Changeover crew** *(contended)* | one crew, **two techs**, **day shift**, covers all three lines | busy / free | **1** |
+| **ET-5** | **QC lab** *(contended)* | one lab, **two people**, serves all three lines | queue depth | **1** |
+| **ET-6** | **Stage within a line** | **mix → mill → tint/letdown → fill**, at different points on the line with small holding tanks between | tank level (see D-1) | 4 per line |
 
-**B3 — Meridian dock appointment**
-- **Pattern** *(spelled out, qualitative)*: a ship date with a delivery window on the order, resolving to a specific dock appointment at Meridian's end.
-- **Lead-time distribution**: ⚠ not obtained.
+### 3.2 The three lines (spelled out qualitatively; rates only partly numeric)
 
-**B4 — Tech availability**
-- **Spelled out, partially**: two techs on **day shift**. ⚠ Whether any changeover coverage exists outside day shift was never asked (ledger #5).
+- **Line 1** — *"the old workhorse. Slower overall, but the most flexible: it's qualified for everything, whites, tints, specialty, all of it. It's the one you send something to when nowhere else can take it."* Weak point: the mill-to-fill tank is small — *"if fill is slow and the tank's small, mill has to stop and wait, and that's dead time my sheet never sees."* Home of the mill motor. Two shifts.
+- **Line 2** — *"the fast line. Built for volume."* Roughly **2× Line 1 on whites**; *"that gap seems to shrink for tints, I don't actually know why… don't take 'twice as fast' as gospel outside whites."* **Not piped for the clear specialty resins** — *"specialty simply cannot run there, full stop, that's physical not a preference."* Jam-prone filler. Two shifts.
+- **Line 3** — *"newest, quick, but still being qualified SKU by SKU."* Two tint SKUs not signed off — *"a QA/engineering decision from before my time on this role, I just know not to put them there."* Day shift only unless overtime approved.
 
-**B5 — Line 3 qualification set**
-- ⚠ *"mostly one or two SKUs"* — **not spelled out**; which SKUs, unknown.
+### 3.3 Families (spelled out, with one flagged sub-distinction)
 
----
+**Whites / tints / specialty** — *"it's really about what a washdown has to deal with, not the product itself."* White-after-white and tint-after-tint are within-family. Flagged caveat, never separated on the sheet: *"I wouldn't swear every tint-to-tint pair is really equal"* — light-to-light may be gentler than light-to-dark.
 
-### 1.4 Activities
+### 3.4 Boundary conditions
 
-**A1 — Lands in the demand book**
-- *Needs*: the weekly ERP pull. *Produces*: an order in the demand book, Meridian-flagged or not. *Performed by*: ERP — unattended. *Duration*: instantaneous receipt. *Rate*: per B1 ⚠. *Mode-change loss*: n/a. *Varies by type*: no. **spelled out**
+| ID | What | Value | Grade |
+|---|---|---|---|
+| **BC-1** | **Demand book** | Built fresh Monday from ERP; **380–420 run-hours/week**. Rush orders land mid-week and force re-juggling — *"rush orders are why the reroute-or-hold and idle-or-washdown calls happen in the first place half the time"* | volume: **range**. **Arrival pattern: OPEN — top-tier gap** |
+| **BC-2** | **Line calendar** | L1 & L2 two shifts, 16 h/day ≈ 112 h/wk nominal, *"though we don't always run weekends flat out — more like five and a half, six days realistically."* L3 day shift ≈ 56 h unless OT. Realistic total **270–300 run-hours** | **range** |
+| **BC-3** | **Changeover-crew calendar** | Day shift only. Night behaviour **unknown** — *"Might be we call someone in. Might be it waits till morning. I'd have to check with the crew lead."* | **open — deposit: crew lead** |
+| **BC-4** | **QC lab calendar** | Day shift, *"maybe with someone covering into evening, but I don't think there's a night presence… impression, not fact"* | **open — deposit: the lab** |
+| **BC-5** | **Resin supply** | *"mostly it's just there"*; slips **~once a month**, and when it does *"it stalls the run and I have to shuffle around it"* | rate: **range**. Stall duration: **open** |
+| **BC-6** | **Structural over-commitment** | Book (380–420) always exceeds capacity (270–300). *"I am always over capacity on paper, which is exactly why changeover hours and scrap matter so much — every hour lost to a washdown or a jam is an hour I don't have to spare."* Weekend/OT running *"is a live lever, not a nice-to-have"* | **spelled out** |
+
+### 3.5 Activities
+
+| ID | Activity | Duration | Occurrence rate | Mode-change loss | Grade / notes |
+|---|---|---|---|---|---|
+| **A-1** | **Run — Line 2, white, Meridian-sized** (line start to last drum filled; incl. ramp-up; excl. washdown before and QC after) | shortest realistically **9 h**; typical **10–11 h** (*"that's the number that's actually on the sheet"*); bad-but-not-freak **14–16 h**; freak **~24 h** (jam + material stall), *"a genuine outlier… more 'the terrible day'"* | n/a (step) | — | **spread-equivalent**, interval-first protocol (low/high then typical). Deciles not stated. **P07 unasked: variation by line/family/size OPEN** |
+| **A-2** | **Washdown, tint→white** | **3 hours** | n/a | — | **number, not spread.** You name *"the washdown that overruns"* as a tail source; overrun spread **open** |
+| **A-3** | **Changeover, white→tint** | *"a bit of white residue in a tinted batch, who cares, it's getting colour anyway"* — quick | n/a | — | **named only, no number** |
+| **A-4** | **Changeover, tint→tint** | **20–30 min** | n/a | — | **range**; light/dark sub-split suspected, never measured |
+| **A-5** | **Changeovers involving specialty** | — | — | — | **entirely open** |
+| **A-6** | **Ramp-up after washdown** | — | — | **scrap** — *"that was the week I rushed the ramp after a washdown"* → scrap spike | **named as a real loss; magnitude open.** Load-bearing for OBJ-2 |
+| **A-7** | **QC hold** | typical **~4 h**; specialty *"can be a full day"*. Decent-week bad case: Wed evening → Thu midday (~18 h) because of a mid-week backlog. **Friday tail: open** — *"Friday's usually worse than that, I just don't have a clean anecdote for it yet"* | — | — | typical: **number**; tails: partly qualitative |
+| **A-8** | **Filler jam** | short kind **0.5–1 h** — *"four out of five"*; long kind multi-hour (the *"four-hour kind"*) | **1–2 per week plant-wide**; long kind **once a month to every six weeks**; *"It's Line 2's filler mostly"* | — | rate: **range**; duration: **range**. Your caveat: *"day-to-day impression, not a logged rate… roughly-right rather than exact"* |
+| **A-9** | **Line 1 mill motor — multi-day failure** | *"the four-day disaster"* | **1–2 per year** — *"maybe three, four times in the years I've been doing this job"* | — | rate: **range**; duration: single anecdote |
+| **A-10** | **Line 1 mill motor — hiccup** | *"a few hours"* | **open** | — | the case that triggered OBJ-1 |
+| **A-9/A-10 joint instruction** | **Bimodal, not a continuum** | *"either a nuisance under half a day or a genuine disaster, rarely something in the middle"* | | | **Do not fit one smooth distribution across the gap** |
+| **A-11** | **Resin stall** | **open** | ~once a month (BC-5) | — | |
+| **A-12** | **Requalification** (running specialty on a line it hasn't recently run on) | **OPEN** | n/a | *"eat the requalification headache"*; characterised as a **known, bounded** cost | **Load-bearing for OBJ-1 and entirely unsized.** I asked what actually had to happen and how long it held the batch up; unanswered |
+| **A-13** | **Release to warehouse** | terminal event | — | — | end of scope |
+
+### 3.6 Ordering / flow
+
+- **OF-1 — the spine (spelled out).** Order lands in demand book → scheduler maps orders to runs (OF-2) → run placed on a line in a week slot (OF-3) → *if incoming family ≠ line's current family, changeover first (A-2/3/4/5)* → run executes: **mix → mill → tint/letdown → fill**, as a flow with small holding tanks between, so *"while the back end of a batch is filling, the front end of the next batch could already be mixing, if there's product to feed it"* → **QC hold (A-7)** → **release to warehouse (A-13)**.
+- **OF-2 — order↔run mapping (spelled out qualitatively).** Lump several small same-SKU orders to clear the minimum run size; split a big order into two runs to interleave a rush job. **Split cost** = an extra changeover plus extra ramp-up scrap. **Minimum run size: unquantified (C-4).**
+- **OF-3 — line choice (branch).** Filtered by C-1/C-2/C-3 and POL-1; the residual discretion is POL-5.
+- **OF-4 — blocking on Line 1 (spelled out, unquantified).** Small mill-to-fill tank: if fill lags, mill stops and waits. *"Dead time my sheet never sees."*
+- **Known model/reality gap you volunteered.** The sheet says *"Line 2 busy 06:00–18:00"* and *"doesn't capture that at all."* Whether the line is genuinely occupied that whole window — *"I genuinely couldn't tell you without going and watching it, which is part of why I said the sheet flatters reality."*
+
+### 3.7 Policies
+
+| ID | Policy | As practiced | Overrides | Source-regime |
+|---|---|---|---|---|
+| **POL-1** | **Meridian white runs on Line 2** | Habit calcified into a rule after Meridian's people audited Line 2's fill area for supplier qualification. *"I have never once put a Meridian order on Line 1, even under real pressure"* — when Line 2 was down most of a day you **held the order and let it run late-ish** rather than move it, *"because breaking that rule felt riskier than a few hours' delay."* | *"Treat it as effectively hard."* Breakable **only** as an explicit what-if experiment — *"not something I'd sanction as a live scheduling option."* | **prescribed:** nothing written, not a formal qualification. **practiced:** absolute. Both recorded. |
+| **POL-5** | **Reroute or hold** — the OBJ-1 rule | **Your settled wording:** *"Hold by default, reroute only if staying put jams something you care about more."* With the asymmetry you gave: *"requalification is a known, bounded cost and blocking the queue is an unknown, possibly-cascading one. So… I'll pay a known cost to avoid an unknown one, especially when I'm short on time to think it through properly, which at a 07:30 huddle I always am."* **Attention sequence, from the actual case:** (1) ask maintenance *"is this the twenty-minute reset kind or do I need to be worried"* — *"that answer changes everything downstream"*; (2) check the blocked job's own due date — if not screaming, default is wait; (3) look at what the other line is doing and, critically, **what is stacked behind the blocked job in its own line's queue**. *"It wasn't 'specialty vs white' directly — it was 'if I don't clear Line 1's queue now, it backs up onto something that touches the white two days later.'"* **Lookahead depth:** *"one hop routinely, two hops only when hop one is already urgent-looking. Past that I'm guessing, not tracing."* **Tier-sensitivity of the trace:** *"I trace further and act more readily when I suspect Meridian's at the other end of it than when I don't."* If the chain had ended at a small distributor — *"I'd have shrugged, let Line 1's queue sit, and told the distributor's order it might run a day later, which is exactly the kind of slip that 'nobody notices.'"* **Conditions that flip it to hold:** fix under an hour; the alternate line already tied up (*"then rerouting isn't even a real option, it's theoretical"*); nothing stacked behind. | **OPEN** — I asked for the case that breaks the pattern; unanswered. | practiced only |
+| **POL-6** | **Idle or washdown** — the OBJ-2 rule | **OPEN — the core of OBJ-2.** Situation known, rule absent. | open | — |
+| **POL-2** | **Long washdown pushed overnight** | *"tint before white means I'm looking at the long washdown, and I wanted that overnight rather than eating into the day."* | not asked | practiced |
+| **POL-3** | **Washdowns scheduled to when the crew is on** | *"we try to schedule washdowns for when the crew's on."* | night case unknown (BC-3) | practiced |
+| **POL-4** | **Avoid stacking family switches** | Signalled by its failure mode: *"the changeover crew looking wrecked by Thursday because I stacked too many family switches back to back."* | not asked | practiced |
+| **POL-7** | **Changeover-crew contention** — who wins when two lines want the crew | **OPEN.** Symptom only: *"Line 3 sitting clean but idle waiting on the crew — it happens more than I'd like."* | open | — |
+| **POL-8** | **QC lab queue discipline** | **OPEN** | open | — |
+| **POL-9** | **Overtime / weekend running** | Ops director's call; you supply the *"we'll miss X without it"* argument. | — | practiced |
+
+### 3.8 Constraints
+
+| ID | Limit | Consequence when hit |
+|---|---|---|
+| **C-1** | Specialty cannot run on Line 2 — not piped for clear specialty resins | Infeasible. Must go Line 1 or Line 3 |
+| **C-2** | Two tint SKUs not qualified on Line 3 | Cannot be scheduled there |
+| **C-3** | Line 1 qualified for everything | Fallback of last resort |
+| **C-4** | **Minimum run size** | Small orders must be lumped to clear it. **Threshold unquantified** |
+| **C-5** | One changeover crew → **one washdown at a time across all three lines** | The other line waits, clean and idle |
+| **C-6** | One QC lab, two people | Queue forms; holds stretch. **Parallelism unknown** |
+| **C-7** | Demand 380–420 vs capacity 270–300 run-hours per week | Something slips every week; OT/weekend is the release valve |
+| **C-8** | Meridian due date | *"due Friday close of business, which for Meridian really means Friday, no wiggle"* |
 
-**A2 — Allocate to a line**
-- *Needs*: an order in the book. *Produces*: order assigned to a line. *Performed by*: Marta. *Duration*: not a constraint on the schedule; for Meridian whites *"that's not really a decision."* *Rule*: P1. **spelled out**
+### 3.9 Dynamics
 
-**A3 — Reorder the queue**
-- *Needs*: an order sitting behind others on a line. *Produces*: a changed run sequence. *Performed by*: Marta. *Rule*: P4 — *"sometimes I'll reorder things a bit so it doesn't get stuck behind a big changeover."* **spelled out**
+| ID | Quantity | Direction & rate | Noise | Threshold |
+|---|---|---|---|---|
+| **D-1** | **Line 1 mill-to-fill tank level** | Rises when mill outpaces fill; falls as fill proceeds. **Rate: open** | not asked | **At full: mill stops and waits.** Reset when fill catches up. This is the *"dead time my sheet never sees"* and the thing behind *"I keep grumbling about Line 1's mill-to-fill tank"* |
 
-**A4 — Quick rinse, same family (white → white), Line 2**
-- *Needs*: previous batch off; a tech available; next SKU in the same family. *Produces*: line clean, *"the fill head's actually running clean product again."*
-- *Performed by* **(named)**: one changeover tech.
-- *Duration, line down* **(spread)**: **typical 25 min**; **one-in-ten worse 45 min** — *"usually because the tech's tied up finishing something on another line first and there's a wait before they even start on Line 2"*; **one-in-ten better 15 min** — *"if the tech's standing right there and it's a genuinely easy one."*
-- *Crew hands-on* **(spelled out)**: identical to line-down. *"It's quick enough that the tech's on it start to finish, no gap between 'crew starts' and 'line stops.'"*
-- *Mode-change loss*: this activity **is** the mode change; the loss is the duration above.
-- *Varies by type* **(named)**: yes by family-pair (F3 selects between A4–A7). By line: ⚠ ledger #1, #2.
-
-**A5 — Family switch, white → tint, Line 2** — *"the easier direction"*
-- *Needs / produces*: as A4, next batch in a different family.
-- *Performed by* **(named)**: one changeover tech.
-- *Duration, line down* **(spread)**: **typical 45 min**; **worse "an hour and a bit"** — *"if the tech gets pulled away partway through"*; **better ~30 min** — *"if everything's staged."* (Numeric reading of "an hour and a bit": ledger #3.)
-- *Crew hands-on* **(spelled out, qualitative)**: *"the tech's hands-on for most of it — this one doesn't have much soak-and-wait, it's mostly just doing the work."* Fraction: ledger #4.
-- *Varies by type*: direction-dependent — see A6.
+### 3.10 Data bindings
 
-**A6 — Family switch, tint → white, Line 2 — the full washdown** — *"the ugly one"*
-- *Needs*: as A5, plus a **passing visual check** before the line is released back to production.
-- *Produces*: a line clean enough to run white.
-- *Performed by* **(named)**: one changeover tech, not continuously present.
-- *Duration, line down* **(spread)**: **typical ~3 h**; **worse 4 h, "maybe a bit more"** — *"if it doesn't pass the visual check first time and they have to redo part of it"*; **better ~2 h** — *"a clean fast one, if the crew's good and nothing complicates it."* (Ledger #3 for the numeric reading of the tail.)
-- *Crew hands-on* **(spelled out, qualitative)**: *"less than the 3 hours suggests — there's real soak and rinse-cycle time where the tech's not standing there, they might duck off to start something on another line. I'd guess they're actually working maybe half of that."* Note her own hedge — *"I'd guess"* — carried into ledger #4.
-- *Rationale* **(spelled out)**: *"any pigment left behind ruins a white batch, so it's a full washdown."*
-- **Asymmetry is load-bearing**: white→tint ≠ tint→white. *"It absolutely depends on direction — that's the thing people forget… it is absolutely not symmetric, and it trips people up if they assume it is."*
+| ID | Variable | Feed | Note |
+|---|---|---|---|
+| **DB-1** | Order arrivals, quantities, due dates, customer | ERP demand book | The natural model input |
+| **DB-2** | Run durations in run-hours | Your weekly sheet | Already converted from rates — *"I keep the sheet in run-hours already converted"* |
+| **DB-3** | Per-stage cycle times by product and line | The historian | *"if someone actually pulled cycle times apart by product and stage, which — as I said — nobody's done"* |
 
-**A7 — Changeover into / out of specialty clear, Line 1**
-- *Needs / produces*: as A5/A6, for the specialty family. Only Line 1 is qualified (C1).
-- *Performed by* **(named)**: one changeover tech.
-- *Duration, line down* **(spread)**: **typical 2 h**, *"roughly the same both directions, unlike white/tint"*; **worse 3 h**, *"if it's coming out of clear and they're being extra careful about residue, since clear can be sneaky — you don't always see it the way you'd see pigment"*; **better 1.5 h**, *"a quick swap and the line was already fairly clean."*
-- *Crew hands-on* **(spelled out, qualitative)**: *"most of that — specialty doesn't have the long soak cycles the tint-to-white washdown has, it's more just physically thorough cleaning because the product's thick and clingy."* Fraction: ledger #4.
+---
 
-**A8 — Run the batch** — mix, mill, tint (or *"straight through if it's a plain white"*), fill, pack
-- *Needs* **(spelled out)**: a clean line in the right family state; the batch released to run.
-- *Produces* **(spelled out)**: a filled and packed batch.
-- *Performed by*: ⚠ line operators never elicited as a resource.
-- **Duration**: ⚠ **nothing obtained.** Demanded as a spread, per family and per line.
-- *Varies by type*: partially — *"for a white that's usually the more straightforward path"* (skips the tint step), but no durations attach to that.
-- **This is the largest hole in the model.** O1 asks a question about a week; run time is most of a week.
+## 4. Assumption ledger
 
-**A9 — QA hold and release** — *"every batch does"*
-- *Needs*: a packed batch. *Produces*: a released batch.
-- *Performed by* **(named)**: the lab (E5).
-- **Duration**: *"typically a few hours before it's released"* — an honest **number at the wrong precision**; demanded as a **spread**. ⚠
-- *Failure path*: ⚠ never asked what happens to a batch that fails QA.
-- *Known pathology* **(spelled out, qualitative; rate ⚠)**: *"if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line."* And: *"the QA step is the one people don't think about when they're mad at scheduling; half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it."*
+Nothing here came from you. Each is mine, provisional, and needs a yes/no before it carries weight.
 
-**A10 — Stage for shipping, and ship**
-- *Needs*: QA release. *Produces*: the order off the dock. *Timing constraint*: C4 — *"that's when the truck appointment matters."*
-- *Duration*: ⚠ not obtained.
+| # | Assumption | Why it exists | How to check |
+|---|---|---|---|
+| **A1** | Changeover crew serves waiting lines **first-come-first-served** | C-5 is a hard bottleneck; the model must pick someone | Ask you (POL-7). You may well have a real priority rule — the Line 3 symptom suggests you do |
+| **A2** | QC lab works **FIFO** | C-6 needs a discipline | The lab; also ask whether you ever expedite a batch |
+| **A3** | A washdown falling outside day shift **waits until morning** | BC-3 unknown; the model must do something | Crew lead — you flagged this yourself |
+| **A4** | QC lab has **no night presence** | Your stated impression, not fact | The lab |
+| **A5** | Line 2's ~2× advantage over Line 1 applies to **whites only**; not extended to tints or specialty | You explicitly warned against extending it | Process engineering, or historian cycle times (DB-3) |
+| **A6** | Ramp-up scrap follows a **washdown**, not every changeover | Inferred from *"the week I rushed the ramp after a washdown"*; you never said it follows short changeovers | Ask you; ask quality |
+| **A7** | The ~24 h Meridian run is a **rare, roughly annual** tail, not part of the normal bad day | Your words were *"once-a-year tail"*, but treating one anecdote as a rate is my move | You |
+| **A8** | Filler jams are **1–2 per week plant-wide, concentrated on Line 2**, not 1–2 per line | *"It's Line 2's filler mostly"* is directional, not a split | You |
+| **A9** | POL-5's queue lookahead is evaluated **at the moment of disruption**, not continuously | Your account is of a 07:30 huddle decision; nothing says you re-trace during the day | You |
+| **A10** | "Care about more" in POL-5 is driven by **customer tier and due-date pressure** of the downstream job | You gave exactly these two factors (Meridian vs distributor; *"screaming"* vs slack due date) and no others; whether anything else counts is untested | You |
 
-**A11 — Tech pulled away mid-changeover** *(event, not step)*
-- Named by her as the mechanism behind the worse tail of A4 (*"the tech's tied up finishing something on another line"*) and A5 (*"if the tech gets pulled away partway through"*).
-- *Rate*: ⚠ not obtained separately; currently only implicit inside the one-in-ten tails of A4 and A5. Per P01 this should be its own rate and duration.
+---
 
-**A12 — Washdown fails the visual check, part redone** *(event, not step)*
-- Named as the mechanism behind A6's 4 h tail.
-- *Rate*: ⚠ not obtained separately. Ledger #7 records the simplification.
+## 5. What the model leaves out, and why
 
-**A13 — "The mill motor issue"** *(event, not step — named in passing, nothing more)*
-- Mentioned only as an example of what a *structural* difference between lines would look like, in contrast to Line 1 merely being fussier. Recorded so it is not lost; **rate ⚠, duration ⚠, consequence ⚠**. This is the whole of the breakdown/interruption stratum, which was never swept.
+### Deliberately out of scope — your boundary
 
----
+- Order generation upstream of the demand book — *"sales does whatever it does."*
+- Trucking, warehouse slotting, shipping — logistics' sheet.
+- Feedstock planning, except as the resin-slip disruption (BC-5).
+- Quarter-scale planning — you don't do it and ERP can't see that far.
+- **Overtime approval as a decision** — modelled as a lever (BC-2/POL-9), not as a choice the model optimises, because it isn't yours.
 
-### 1.5 Ordering / flow
+### Deliberately simplified — and what is lost
 
-**F1 — The main arc, desk to dock** *(spelled out — her six steps, verbatim in structure)*
-1. Lands in the demand book (ERP weekly pull; SKU, quantity, due date, Meridian flag).
-2. Allocated to a line (*"Meridian whites always go to Line 2"*).
-3. Sits in the queue behind whatever's running — reorderable (A3/P4).
-4. Changeover if needed (F3 selects which), then it runs: mix, mill, tint-or-straight-through, fill, pack.
-5. QA hold.
-6. Released, staged for shipping, out against the truck appointment.
+1. **Stage-level detail inside a run.** You schedule whole-run blocks and the model follows you — *except* on Line 1, where D-1/OF-4 keeps the mill-to-fill blocking because you named it as real dead time. **Lost:** any pipelining gain from overlapping the next batch's mix with this batch's fill, which you said physically exists. **Risk:** you told me the sheet *flatters* reality here, and OBJ-3 is precisely "am I leaving hours on the table?" This simplification is the one most likely to bite that objective. Flagged rather than resolved.
+2. **Tint-to-tint sub-families collapsed** to a single 20–30 min changeover. **Lost:** any light→dark penalty. Justified because you've never separated it on the sheet; revisit if the model starts over-favouring tint batching.
+3. **Queues are not modelled as named objects** — waits at the crew, the lab, and behind a blocked line emerge from the activities on either side. Nothing is lost operationally; it means you won't see a node called "queue" in the final net.
 
-**F2 — Order-to-batch split**
-- *Order* **(spelled out)**: an order becomes one batch by default; it may become two batches run at different times.
-- *How the branch is decided* **(spelled out)**: Marta's judgment, on either (a) a distributor ordering *"more than makes sense in a single run"*, or (b) needing to interleave something more urgent.
-- *Cost of a split*: ⚠ never asked (P03 unresolved) — extra changeovers and any extra loss are unknown.
+### Open slots that stop the model running honestly
 
-**F3 — Which changeover applies** *(spelled out)*
-Selected by the triple (family currently on the line, family of the next batch, line):
-- same family → **A4** quick rinse
-- white → tint → **A5**
-- tint → white → **A6** full washdown
-- into or out of specialty clear → **A7** (Line 1 only)
+**Top tier — an objective's core is missing:**
 
----
+1. **POL-6, idle-vs-washdown.** OBJ-2 has no rule at all. The situation is captured; the decision is not.
+2. **BC-1 rush-order arrivals.** Your own escalation: *"if you only ask me about the steady-state rules… you'll have modelled the calm week and missed the reason I lose sleep."* OBJ-3 depends on it directly and OBJ-1/OBJ-2 depend on it as the trigger.
+3. **A-12 requalification cost.** OBJ-1 is a trade with one side unpriced. POL-5 now tells me *when* you pay it; nothing tells me *what* you pay. I asked and we stopped before the answer.
 
-### 1.6 Policies
+**Second tier — hard bottlenecks running on my assumptions:**
 
-**P1 — "Meridian whites always go to Line 2, that's just how it's done here"**
-- *As practiced* **(spelled out)**: fixed allocation, not a decision.
-- *What overrides it*: ⚠ never asked.
-- *Source-regime*: practiced; no prescribed form offered.
+4. **POL-7 crew priority** (on A1) and **POL-8 lab discipline** (on A2). C-5 and C-6 are the two contended resources in the plant; both currently arbitrate by my guess.
+5. **A-6 ramp-up scrap magnitude.** OBJ-2 is literally *idle hour vs three-hour washdown plus ramp loss* — and the ramp loss has no number.
+6. **A-3, A-5** — the quick changeover has no duration; specialty changeovers are entirely absent.
 
-**P2 — Meridian on-time is absolute**
-- *As practiced* **(spelled out)**: *"the rule is absolute — we don't even try to be clever about it."*
-- *What overrides it* **(spelled out)**: nothing. That is the content of the policy.
-- *Rationale*: fine, tracked on-time percentage, delisting threat carried out on a competitor.
+**Third tier — breadth:**
 
-**P3 — Who gets the tech when two lines want one** *(the model's richest policy, and the least documented)*
-- **Prescribed form: none exists.** *"There's no posted rule at all."*
-- **As practiced** *(spelled out)*: in the room it resolves as *"whoever's louder at the huddle, or whoever's about to actually run dry."* Pressed for the underlying logic: *"it's mostly gut triage: whichever line has the more time-sensitive order behind it wins, and if that's a tie, whichever changeover is faster wins so you get a line moving sooner."*
-- **Borderline case on record** *(the practiced rule demonstrated, per P05)*: Line 1 and Line 3 both wanted a washdown the same morning. **Line 3 got the tech first** — *"not because it was more important, but because Line 3's changeover was the quick one and Line 1's was going to be the long tint-to-white slog anyway, so the thinking was 'knock out the fast one, get that line moving, then commit the tech to the long one.'"* Line 1 sat **clean-but-waiting for almost 40 minutes** past when it could have started.
-- **What overrides it** *(spelled out)*: the ops director. *"I've been overruled by the ops director once when he wanted his pet SKU out the door."*
-- *Rationale* **(spelled out)**: *"the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line"* — and this, not changeover variability, is *"the bit that actually causes grief at the huddle."*
+7. **P07 unasked across the board.** I have one duration spread, for one product, on one line. Run duration by line, family, and size is unknown; A5 stops me extrapolating, which means Lines 1 and 3 currently have no durations at all.
+8. **Numeric trade weights** (deposit: commercial) and the **provisional "better" ranking** awaiting your confirmation.
+9. **A-10 hiccup rate**, **A-11 resin stall duration**, **D-1 tank fill/drain rate**, **A-2 overrun spread**, **A-7 Friday tail**, **C-4 minimum run size** — each a single missing figure.
+10. **POL-5's override case** — I asked for the exception that breaks the pattern and we stopped. A rule without its exception is where simulation and reality diverge.
 
-**P4 — Reorder the queue so a job isn't stuck behind a big changeover**
-- *As practiced* **(spelled out)**: Marta reorders *"a bit"* to avoid a job landing behind an expensive changeover.
-- *What overrides it*: ⚠ never asked.
+### Three deposits sitting with other people
 
-**P5 — Hold the line for an anticipated same-family order** *(the decision under test)*
-- *As practiced, one instance* **(spelled out)**: on a heads-up that a same-family white was about to drop, let Line 2 sit idle for *"maybe an hour"* rather than wash down for the tint waiting behind, *"because doing them back to back would save us a full washdown."*
-- *Her own epistemic status*: *"I was guessing."* Her boss's challenge — *"are you sure that's worth it, or are you just guessing?"* — is the reason this model exists.
-- *Trigger condition and decision threshold*: ⚠ how strong a heads-up, and how long she'd hold, are not generalised beyond this instance. Depends on B2.
+| Deposit | Question | Who |
+|---|---|---|
+| BC-3 | What happens to a washdown forced onto night shift | Crew lead |
+| BC-4, C-6 | Does the lab test in parallel, and how far into the evening is it covered | The lab |
+| A5 | Does Line 2's 2× speed advantage hold outside whites | Process engineering (or historian, DB-3) |
 
-**P6 — Batch-split discretion**
-- *As practiced* **(spelled out)**: *"I have the freedom to split if I need to."* Criteria as in F2.
-- *What overrides it*: ⚠ never asked.
+### What I am not claiming
 
----
+I have elicited a model, not built a net. The Petri-net scaffold, the code obligations, and the formal loss report are produced by your tooling's projection from this model — I have not written them, and nothing here should be described as loadable, compiled, or simulated. Two things I'd expect that projection to report as uncarryable: the **ranked, non-numeric objective weights** (§1), and **POL-5's tier-sensitive lookahead depth** — *"one hop routinely, two hops only when hop one is already urgent-looking"* is a rule about how much of the future you attend to, and that is not a guard on a transition. It will need to be written as code or approximated, and either way it should be visible to you as a choice, not buried.
+
+### When you resume
 
-### 1.7 Constraints
+In order: **POL-6** (idle-vs-washdown, via the last time you faced it) → **BC-1** (rush orders — how they arrive, how often, how much notice) → **A-12** (requalification: what actually has to happen, who does it, how long it holds the batch) → **POL-5's override case** → **POL-7** crew priority with a recent borderline call → the **"better" ranking** you wanted to sleep on.
 
-**C1 — Line qualification**
-- *The limit* **(partially spelled out)**: Line 1 qualified for everything including specialty. Line 3 qualified product-by-product, *"can't run everything yet"*, currently *"mostly one or two SKUs"* — which ones ⚠. Line 2's qualification set ⚠ never stated.
-- *What happens when it's hit* **(spelled out)**: the batch cannot go on that line.
+---
 
-**C2 — Two techs, three lines**
-- *The limit* **(spelled out)**: 2 techs on day shift for 3 lines.
-- *What happens when it's hit* **(spelled out)**: *"if Line 1 and Line 3 both want a washdown at the same time, one of them waits"* — clean-but-idle; 40 minutes in the case on record. Resolution by P3.
+**Expert (Marta)**:
 
-**C3 — Tint → white requires a full washdown passing a visual check**
-- *The limit* **(spelled out)**: a white batch may not run on a line still carrying pigment.
-- *What happens when it's hit* **(spelled out)**: *"any pigment left behind ruins a white batch"*; a failed visual check means part of the washdown is redone (A12).
+I really do have to stop here. Please produce the model now with everything you have.
 
-**C4 — Meridian must leave our dock a day ahead of the appointment**
-- *The limit* **(spelled out)**: shipped in time to hit the dock appointment, which *"usually means it needs to leave our dock a day ahead for freight."*
-- *What happens when it's hit* **(spelled out)**: fine + on-time percentage damage + delisting exposure.
+---
 
-**C5 — Every batch passes QA hold before release**
-- *The limit* **(spelled out)**: *"every batch does."*
-- *What happens when it's hit* **(spelled out)**: nothing ships unreleased; the batch waits in hold.
+**Interviewer**:
 
-**Unwritten constraints**: ⚠ the closing sweep — *"what would a newcomer get wrong in the first week?"*, *"which rule exists because something once went wrong?"* — was never run. The one item that surfaced unprompted is the changeover asymmetry: *"that one catches everybody, including people who've been on the floor a lot longer than me."*
+Stopping here. Nothing new asked. This is the final deliverable, self-contained.
 
 ---
 
-### 1.8 Dynamics
+# Coatings Plant Scheduling Model — final
 
-**None.** Nothing described evolves continuously while nothing discrete happens. The soak and rinse-cycle time inside A6 is dead time *within* an activity, not a state variable crossing a threshold, and I have deliberately not promoted it to one.
+**Stopping outcome: `expert-stopped` — partial model with open slots.**
+Structural floor met (3 objectives, 6 entity-types, 13 activities, 4 ordering/flow nodes). No objective's dependency slice is complete: OBJ-1 has its rule but not its cost; OBJ-2 and OBJ-3 are missing their cores. Every value is at the grade you gave it; nothing has been promoted or invented.
 
 ---
 
-### 1.9 Data bindings *(named only; these project to nothing today)*
+## 1. Objectives
 
-| Feed | Would drive | Provenance |
-|---|---|---|
-| Changeover logs — tech start/finish per changeover | A4–A7 durations and crew hands-on fractions; retires ledger #1 and #4 | **Qualified**: *"I've never audited that field myself, I mostly just glance at duration."* Coverage unknown, possibly patchy — Marta named **Line 1 and Line 3** as where to look. She will flag it to the two techs. |
-| ERP demand book | B1 arrival pattern, B2 | not discussed |
-| QA release timestamps | A9 duration and lab queueing | not discussed |
-| Meridian on-time percentage | O2 | tracked by Meridian, visible to commercial |
+| ID | The question, in your words | Depends on | Slice |
+|---|---|---|---|
+| **OBJ-1 Reroute or hold** | *"whether to shift the specialty over to Line 3 and eat the requalification headache, or hold it and let the white slip behind on Line 2"* — *"I'd love to run twice and see which one bites me less"* | POL-5, A-12, ET-1, ET-3, C-1/2/3, POL-1, A-9, A-10, OF-3 | **Partial** — rule captured, requalification cost absent |
+| **OBJ-2 Idle or washdown** | *"do I sit Line 2 empty for an hour waiting on a same-family order, or just pay the three-hour washdown now"* — *"almost weekly and it's pure feel"* | POL-6, A-2, A-3, A-4, A-6, ET-4, C-5, BC-1 | **Unsupported** — the deciding rule is absent |
+| **OBJ-3 Run size & sequencing** | *"whether to split a big order into two runs to slot in a rush job, or batch several small orders of the same family together even if it means one of them ships a bit early and sits in the warehouse"* — *"I've never had a way to check if I'm leaving hours on the table"* | OF-2, C-4, A-6, A-2/3/4, BC-1, ET-2 | **Unsupported** — rush arrivals and minimum run size absent |
+
+Noted, not yours to test — overtime approval: *"that's the ops director's call, though I do feed him the 'we'll miss X without it' argument… maybe that's a variant of the same question rather than a fourth one."*
+
+**"Better"** — grade: ranking spelled out, numeric weights absent.
+- Settled: lateness **and to whom** — *"a late order to Meridian is worse than three late orders to a small distributor, so it's not just a count, it matters who."*
+- Settled trade: *"I'll take the scrap spike every time, no contest. Scrap costs money, a late Meridian order costs a relationship and a fine."*
+- **Provisional, thought aloud, not settled:** late-and-to-whom > changeover hours lost > scrap, because *"lost hours cascade into more lateness, whereas scrap is just money — annoying, contained, doesn't ripple."* You asked to be re-asked. **No metric should be built on this ordering until you confirm it.**
+- Currency exchange rate: **open**. Deposit: *"sit down with commercial."*
 
-**Finding, recorded in its own right**: patchy changeover logging concentrated on Lines 1 and 3 is evidence about the plant, not merely an obstacle to the model. Her words: *"if it's patchy for Line 1 and Line 3 specifically, that itself would be useful for you to know, not just an inconvenience."*
+**Horizon:** rolling week built fresh Monday against that week's book, re-runnable at shift grain when something breaks at 06:00. *"A quarter's too far out."*
+
+**Boundary:** starts when an order lands in the demand book from ERP; ends when the batch **clears QC hold and is released to the warehouse**. Trucks and warehouse slotting out — *"logistics' sheet, not mine."* QC hold explicitly in — *"I've had orders filled on time and still gone late because the lab backed up on a Friday."* Feedstock out except resin slips — *"otherwise you're modelling a plant that never has a bad Tuesday."*
 
 ---
 
-### 1.10 Validation criteria
+## 2. Validation criteria
 
-⚠ **None obtained.** How Marta would know the model is right was never asked. Queued.
+- **VC-1** Unwritten rules hold: Meridian white on Line 2; specialty never on Line 2; the two unqualified tint SKUs never on Line 3. *"If it violates any of that, I'll dismiss it in about ten seconds."*
+- **VC-2** Changeover asymmetry the right way round: **tint→white long, white→tint quick.** *"If it shows tint-to-white as quick… someone got the plant backwards."*
+- **VC-3** Replay last week's book; predicted lates roughly match actual — Meridian squeaked by a few hours, a distributor slid four days *"with a phone call and nobody blinked"*, the Line 1 tank issue bit. Two or three such weeks reconstructable.
 
 ---
 
-## 2. Assumption ledger
+## 3. Model
 
-Everything here is mine. None of it is hers.
+### Entity types
 
-| # | Assumption | Why it was made | How to check it |
-|---|---|---|---|
-| **1** | Line 1 changeover durations = Line 2 × **1.2**, all four types | She could not give Line 1 minutes: *"I couldn't swear the minutes are identical… Line 1's older, the crew sometimes says it's fussier."* I proposed 20%; she said *"20% sounds about right, not double."* **The 1.2 factor originated with me** — her assent is not authorship. | Changeover logs, Line 1 vs Line 2, same family-pair. **Blocked by the unaudited start/finish field, and Line 1 is one of the two lines she expects to be patchy.** |
-| **2** | Line 3 changeover durations = Line 2, unscaled | *"Line 3 I genuinely don't have a good feel for… you're stuck assuming it's like Line 1 or Line 2 until we've got more history."* She offered the disjunction; **choosing Line 2 was mine.** | As #1, once Line 3 has run more products. Also expected patchy. |
-| **3** | "An hour and a bit" (A5 worse) = **70 min**; "4, maybe a bit more" (A6 worse) = **4.5 h** | Numeric readings so the spreads are usable. | One question to Marta: confirm or correct both. |
-| **4** | Crew hands-on fractions: A4 = **1.0**; A5 = **0.8**; A6 = **0.5**; A7 = **0.8** | A4's 1.0 is hers, stated. A6's 0.5 is close to *"maybe half of that"* — but note her own hedge, *"I'd guess."* **The two 0.8s from *"most of it"* / *"most of that"* are mine.** | Changeover logs vs. tech time records, or ask the two techs directly. Same blocker as #1. |
-| **5** | No changeover happens outside day shift | She said *"two techs on **day shift** covering all three lines."* Whether any other coverage exists was never asked. | One question to Marta. |
-| **6** | A changeover requires exactly **one** tech, not two | She spoke of *"the tech"* singular throughout, including for the 3-hour washdown. | One question to Marta or the techs. |
-| **7** | A12 (failed visual check, part redone) is folded **inside** A6's 4 h tail rather than modelled as a separate event with its own rate and duration | She described it as *the cause of* the tail, not as an independent event. Keeps the spread self-contained. Contrary to P01, which would separate rate from duration. | Ask how often the visual check fails first time; if it's common, split it out. |
-| **8** | The two changeover techs are **interchangeable** | She drew no distinction between them. | One question to Marta. |
+| ID | Type | Distinctions | Carried state | Population |
+|---|---|---|---|---|
+| ET-1 | **Order** (line in the demand book) | SKU; quantity (drums, sometimes bulk litres for big Meridian); due date; **customer tier — Meridian vs small distributor** | family; due-date hardness; tier | ~**380–420 run-hours**/week *(range)* |
+| ET-2 | **Run** (block on the sheet) | *"orders are what demand gives me, runs are what I actually schedule, and I'm the one deciding the mapping"*; one order, or small same-SKU orders lumped; a big order splittable in two | line, family, window | derived via OF-2 |
+| ET-3 | **Line** | see below | current/last family; qualifications; up/down | **3** |
+| ET-4 | **Changeover crew** *(contended)* | one crew, **two techs**, **day shift**, all three lines | busy/free | **1** |
+| ET-5 | **QC lab** *(contended)* | one lab, **two people**, all three lines | queue depth | **1** |
+| ET-6 | **Stage** | **mix → mill → tint/letdown → fill**, small holding tanks between | tank level (D-1) | 4 per line |
 
-**Second-order note on #1 and #4**: their stated check depends on a feed of unverified coverage, concentrated exactly where the assumptions bite. If the field proves patchy on Line 1, the honest move is to **widen** these assumptions, not to fill them in.
+**Lines.** *Line 1* — *"the old workhorse. Slower overall, but the most flexible: qualified for everything… the one you send something to when nowhere else can take it."* Small mill-to-fill tank: *"if fill is slow and the tank's small, mill has to stop and wait, and that's dead time my sheet never sees."* Home of the mill motor. Two shifts. — *Line 2* — *"the fast line. Built for volume."* ~**2× Line 1 on whites**; *"that gap seems to shrink for tints, I don't actually know why"*, explicitly not gospel outside whites. **Not piped for clear specialty resins** — *"full stop, that's physical not a preference."* Jam-prone filler. Two shifts. — *Line 3* — *"newest, quick, but still being qualified SKU by SKU."* Two tint SKUs unsigned — *"a QA/engineering decision from before my time."* Day shift only unless OT.
 
----
+**Families.** Whites / tints / specialty — *"it's really about what a washdown has to deal with, not the product itself."* Flagged: *"I wouldn't swear every tint-to-tint pair is really equal"* (light→light vs light→dark), never separated on the sheet.
 
-## 3. What the model leaves out, what is unknown, and why
+### Boundary conditions
 
-### 3.1 Deliberately left out
+| ID | What | Value | Grade |
+|---|---|---|---|
+| BC-1 | Demand book | Monday-fresh from ERP; **380–420 run-hours/wk**. Rush orders land mid-week — *"rush orders are why the reroute-or-hold and idle-or-washdown calls happen in the first place half the time"* | volume: range. **Arrival pattern OPEN — top tier** |
+| BC-2 | Line calendar | L1, L2 two shifts ≈112 h/wk nominal, *"we don't always run weekends flat out — more like five and a half, six days realistically"*; L3 ≈56 h unless OT. Realistic total **270–300 h** | range |
+| BC-3 | Crew calendar | Day shift. Nights **unknown** — *"Might be we call someone in. Might be it waits till morning."* | open — crew lead |
+| BC-4 | Lab calendar | Day shift, *"maybe with someone covering into evening… impression, not fact"* | open — the lab |
+| BC-5 | Resin supply | *"mostly it's just there"*; slips **~monthly**, *"it stalls the run and I have to shuffle around it"* | rate: range; stall duration open |
+| BC-6 | Over-commitment | Book always exceeds capacity. *"Every hour lost to a washdown or a jam is an hour I don't have to spare."* Weekend/OT *"a live lever, not a nice-to-have"* | spelled out |
+
+### Activities
+
+| ID | Activity | Duration | Rate | Loss | Grade |
+|---|---|---|---|---|---|
+| A-1 | Run — Line 2, white, Meridian-sized (line start → last drum; incl. ramp-up, excl. washdown/QC) | **9 h** shortest realistic; **10–11 h** typical (*"the number that's actually on the sheet"*); **14–16 h** bad-not-freak; **~24 h** freak (jam + material stall), *"more 'the terrible day'"* | n/a | — | spread-equivalent, interval-first. **P07 unasked** |
+| A-2 | Washdown **tint→white** | **3 h** | n/a | — | number; *"the washdown that overruns"* — overrun spread open |
+| A-3 | Changeover **white→tint** | *"a bit of white residue in a tinted batch, who cares, it's getting colour anyway"* — quick | n/a | — | **named, no number** |
+| A-4 | Changeover **tint→tint** | **20–30 min** | n/a | — | range; light/dark split suspected, unmeasured |
+| A-5 | Changeovers involving **specialty** | — | — | — | **entirely open** |
+| A-6 | **Ramp-up after washdown** | — | — | scrap — *"that was the week I rushed the ramp after a washdown"* | **named, magnitude open**; load-bearing for OBJ-2 |
+| A-7 | **QC hold** | typical **~4 h**; specialty *"can be a full day"*; decent-week bad case Wed eve→Thu midday (~18 h). **Friday tail open** — *"Friday's usually worse than that, I just don't have a clean anecdote for it yet"* | — | — | typical: number; tails partly qualitative |
+| A-8 | **Filler jam** | short **0.5–1 h** (*"four out of five"*); long multi-hour (*"the four-hour kind"*) | **1–2/week plant-wide**; long kind **monthly to every 6 weeks**; *"It's Line 2's filler mostly"* | — | ranges; *"day-to-day impression, not a logged rate"* |
+| A-9 | **Mill motor — multi-day** | *"the four-day disaster"* | **1–2/year** (*"three, four times in the years I've been doing this job"*) | — | rate range; duration one anecdote |
+| A-10 | **Mill motor — hiccup** | *"a few hours"* | **open** | — | trigger case for OBJ-1 |
+| — | **A-9/A-10 instruction** | **Bimodal:** *"either a nuisance under half a day or a genuine disaster, rarely something in the middle."* **Do not fit one smooth distribution across the gap.** | | | |
+| A-11 | **Resin stall** | open | ~monthly | — | |
+| A-12 | **Requalification** | **OPEN** | n/a | *"eat the requalification headache"*; a **known, bounded** cost | **Load-bearing for OBJ-1, unsized** |
+| A-13 | Release to warehouse | terminal | — | — | end of scope |
+
+### Ordering / flow
+
+- **OF-1 spine:** order → orders mapped to runs → run placed on a line → *if family differs, changeover first* → run executes **mix → mill → tint/letdown → fill** as a flow with tanks between, so *"while the back end of a batch is filling, the front end of the next batch could already be mixing, if there's product to feed it"* → **QC hold** → **release to warehouse**.
+- **OF-2 order↔run mapping:** lump small same-SKU orders to clear minimum run size; split a big order to interleave a rush job. Split cost = extra changeover + extra ramp-up scrap. **Minimum run size unquantified.**
+- **OF-3 line choice:** filtered by C-1/2/3 and POL-1; residual discretion is POL-5.
+- **OF-4 blocking (Line 1):** small mill-to-fill tank; fill lags → mill stalls. *"Dead time my sheet never sees."*
+- **Volunteered model/reality gap:** the sheet says *"Line 2 busy 06:00–18:00"* and *"doesn't capture that at all"* — *"I genuinely couldn't tell you without going and watching it… the sheet flatters reality."*
+
+### Policies
+
+| ID | Policy | As practiced | Overrides |
+|---|---|---|---|
+| **POL-1** | Meridian white on Line 2 | Habit calcified into a rule after Meridian audited Line 2's fill area. *"I have never once put a Meridian order on Line 1, even under real pressure"* — with Line 2 down most of a day you held the order and let it run late-ish, *"because breaking that rule felt riskier than a few hours' delay."* Prescribed: nothing written. Practiced: absolute. | *"Treat it as effectively hard."* Breakable only as a what-if — *"not something I'd sanction as a live scheduling option."* |
+| **POL-5** | **Reroute or hold** (OBJ-1) | **Your wording:** *"Hold by default, reroute only if staying put jams something you care about more."* Asymmetry: *"requalification is a known, bounded cost and blocking the queue is an unknown, possibly-cascading one… I'll pay a known cost to avoid an unknown one, especially when I'm short on time to think it through properly, which at a 07:30 huddle I always am."* **Attention order:** (1) maintenance — *"is this the twenty-minute reset kind or do I need to be worried"*, *"that answer changes everything downstream"*; (2) the blocked job's own due date — if not screaming, default is wait; (3) **what is stacked behind it in its own line's queue** — *"it wasn't 'specialty vs white' directly — it was 'if I don't clear Line 1's queue now, it backs up onto something that touches the white two days later.'"* **Depth:** *"one hop routinely, two hops only when hop one is already urgent-looking. Past that I'm guessing, not tracing."* **Tier-sensitivity:** *"I trace further and act more readily when I suspect Meridian's at the other end of it than when I don't"*; chain ending at a distributor — *"I'd have shrugged… told the distributor's order it might run a day later, which is exactly the kind of slip that 'nobody notices.'"* **Flips to hold if:** fix under an hour; alternate line already tied up (*"then rerouting isn't even a real option, it's theoretical"*); nothing stacked behind. | **OPEN** — the exception case was asked and not reached |
+| **POL-6** | **Idle or washdown** (OBJ-2) | **OPEN — core of OBJ-2.** Situation known, rule absent | open |
+| POL-2 | Long washdown pushed overnight | *"tint before white means I'm looking at the long washdown, and I wanted that overnight rather than eating into the day"* | not asked |
+| POL-3 | Washdowns to when the crew is on | *"we try to schedule washdowns for when the crew's on"* | night case unknown |
+| POL-4 | Avoid stacking family switches | Known by its failure: *"the changeover crew looking wrecked by Thursday because I stacked too many family switches back to back"* | not asked |
+| POL-7 | Crew contention | **OPEN.** Symptom only: *"Line 3 sitting clean but idle waiting on the crew — it happens more than I'd like"* | open |
+| POL-8 | Lab queue discipline | **OPEN** | open |
+| POL-9 | Overtime / weekend | Ops director's call; you supply *"we'll miss X without it"* | — |
 
-- **Queues, buffers and waiting states are not nodes.** The wait behind a running batch, the wait for a tech, the wait in QA hold — none is elicited as a thing in itself; each is implied by the activities either side and emerges in projection. The 40-minute clean-but-waiting on Line 1 is an *output* the model should reproduce, not an input to it.
-- **The commercial layer.** The fine, the on-time percentage mechanics, the delisting threshold. C4 and O2 encode the hard deadline; the money behind it is outside the scheduler's sight and she named commercial as the owner.
-- **Individual tech identity.** Ledger #8 — she drew no distinction.
-- **Scenarios.** Not elicited; they assemble from B1–B5 at simulation time.
+### Constraints
 
-### 3.2 What the formalism cannot carry, kept in words so it is not lost
+C-1 Specialty cannot run on Line 2 (not piped) → must go L1 or L3. C-2 Two tint SKUs not qualified on Line 3 → cannot be scheduled there. C-3 Line 1 qualified for everything → fallback of last resort. C-4 **Minimum run size** → small orders lumped; **threshold unquantified**. C-5 One crew → **one washdown at a time across all three lines**; the other line waits clean and idle. C-6 One lab, two people → queue forms; **parallelism unknown**. C-7 380–420 demanded vs 270–300 available → something slips weekly; OT/weekend is the release valve. C-8 *"due Friday close of business, which for Meridian really means Friday, no wiggle."*
 
-- **O4, "how ugly the sheet looks."** A criterion she genuinely uses and explicitly refuses to number. It could be approximated as line idle hours — but that approximation would be mine, and I have not made it.
-- **The O2/O3/lateness trade-off weight.** Deliberately unquantified with the source named (commercial). Consequence: the model can report changeover hours, Meridian lateness and distributor lateness **separately**, but cannot rank two schedules that trade one against another. That is a real limit on answering O1, since O1's "costs less" implicitly spans them.
-- **The decay of softness.** *"The same distributor slipping late for the third week running"* turning into a discount demand is a memory effect across weeks on a customer. Stated as a rule, unquantified, and not represented.
-- **The huddle.** *"Whoever's louder at the huddle"* and the ops director's pet-SKU override are the real P3 in the room. The triage logic — time-sensitivity first, faster-changeover as tiebreak — is compilable; loudness and the override are not. **Any run of this model will be quieter and more rational than the plant.** That is worth remembering when a result looks tidy.
+### Dynamics
 
-### 3.3 Open slots, in the order I would close them
+**D-1 Line 1 mill-to-fill tank level.** Rises when mill outpaces fill, falls as fill proceeds; **rate open**, noise not asked. **Threshold: at full, mill stops and waits**; resets when fill catches up. This is *"the dead time my sheet never sees"* and the reason *"I keep grumbling about Line 1's mill-to-fill tank."*
 
-1. **A8 run duration** — nothing at all, per family and per line, as a spread. O1 is a question about a *week*; run time is most of a week. **Nothing about O1 is answerable until this exists.**
-2. **B2, the drop-in and the heads-up** — who tells her, how far ahead, how often it proves right. P5 is the decision under test and its trigger is currently a single anecdote.
-3. **A9 QA hold** — *"a few hours"* is honest at the wrong precision; and whether the lab queues like the techs do. By her own account this is where lateness actually comes from, so it bears directly on O2.
-4. **B1** — orders per weekly pull and the within-week shape.
-5. **E2 / F2** — typical run sizes, the "reasonable run size" threshold, and what a split costs in extra changeovers (P03).
-6. **C1 / B5** — which SKUs Line 3 is qualified for; whether Line 2 has restrictions.
-7. **Breakdowns and interruptions** — the whole stratum. A13 "the mill motor issue" is a name with no rate, duration or consequence. A11 and A12 need rate separated from duration (P01).
-8. **The unwritten-constraint sweep** and **validation criteria** — neither was run.
+### Data bindings
 
-### 3.4 Status against the completion criteria
+DB-1 order arrivals/quantities/due dates/customer ← ERP demand book. DB-2 run durations in run-hours ← your weekly sheet, *"already converted"*. DB-3 per-stage cycle times by product and line ← the historian, *"which — as I said — nobody's done."*
 
-- **Static floor: satisfied** — 4 objectives, 5 entity types, 13 activities, 3 ordering/flow nodes.
-- **O2, O3: dependency slices substantially satisfied**, excepting A8 and A9 durations.
-- **O1: dependency slice incomplete.** A8 has no duration at all; B2 has no arrival pattern. O1 is currently **answerable only for Line 2**, and only once run times exist. Ledger #1–#4 are the first assumptions to attack if any result involving Line 1 or Line 3 ever looks decisive.
-- **O4: recorded, unsupported for quantitative use** by its own author's description.
+---
 
-### 3.5 What I do not claim
+## 4. Assumption ledger — mine, not yours
 
-I have elicited a model, not built a net. The SDCPN scaffold, the code-obligation sidecar and the typed loss report are derived from this model by the tooling's projection — I have not written them and I am not claiming this loads, compiles, or runs. The A8 hole alone would stop it.
+| # | Assumption | Why | Check with |
+|---|---|---|---|
+| A1 | Crew serves waiting lines **FCFS** | C-5 must arbitrate | You (POL-7) — the Line 3 symptom suggests a real rule exists |
+| A2 | Lab works **FIFO** | C-6 must arbitrate | The lab; also whether you expedite |
+| A3 | Washdown outside day shift **waits until morning** | BC-3 unknown | Crew lead |
+| A4 | Lab has **no night presence** | Your impression, not fact | The lab |
+| A5 | Line 2's 2× applies to **whites only** | You warned against extending it | Process engineering, or DB-3 |
+| A6 | Ramp-up scrap follows **washdowns**, not every changeover | Inferred from one phrase | You; quality |
+| A7 | The ~24 h run is a **roughly annual** tail | Treating one anecdote as a rate is my move | You |
+| A8 | Jams are **1–2/wk plant-wide, concentrated on Line 2** | *"mostly"* is directional, not a split | You |
+| A9 | POL-5's lookahead is evaluated **at the moment of disruption**, not continuously | Your account is of a 07:30 call | You |
+| A10 | "Care about more" = **downstream tier + due-date pressure**, nothing else | Those are the only two factors you named | You |
 
 ---
 
-*Elicited from Marta, master scheduler, in a single session ended at her stop. Three questions queued for resumption: run duration for a plain white on Line 2 (typical / one-in-ten worse / one-in-ten better); the heads-up mechanism behind B2; QA hold as a spread, and whether the lab queues.*
+## 5. Losses
+
+**Deliberately out of scope:** upstream order generation; trucking/warehouse/shipping; feedstock planning except resin slips; quarter-scale planning; overtime as a *decision* (modelled as a lever, not a choice, because it isn't yours).
+
+**Deliberately simplified, and what it costs:**
+1. **Stage detail inside a run** collapsed to whole-run blocks, *except* Line 1's mill-to-fill blocking (D-1/OF-4). Lost: pipelining gain from overlapping next-batch mix with this-batch fill, which you said physically exists. **This is the simplification most likely to mislead OBJ-3**, since you told me the sheet flatters reality and OBJ-3 asks whether you're leaving hours on the table.
+2. **Tint-to-tint collapsed** to one 20–30 min changeover. Lost: any light→dark penalty. Revisit if the model over-favours tint batching.
+3. **Queues are not nodes** — waits at crew, lab, and behind a blocked line emerge from the activities either side. No operational loss; you just won't see a box labelled "queue."
+
+**Open and load-bearing — top tier:** POL-6 (OBJ-2 has no rule); BC-1 rush arrivals (*"you'll have modelled the calm week and missed the reason I lose sleep"*); A-12 requalification cost (OBJ-1's trade has one side unpriced — POL-5 says *when* you pay, nothing says *what*).
+**Second tier:** POL-7 and POL-8 — both contended resources currently arbitrated by my assumptions; A-6 ramp-up scrap magnitude (OBJ-2 is literally idle hour vs 3 h washdown *plus ramp loss*); A-3 and A-5 durations.
+**Third tier:** P07 unasked — one spread, one product, one line, so Lines 1 and 3 have no durations at all; numeric trade weights (commercial); the provisional "better" ranking awaiting your confirmation; A-10 hiccup rate, A-11 stall duration, D-1 tank rate, A-2 overrun spread, A-7 Friday tail, C-4 minimum run size; **POL-5's override case** — a rule without its exception is where simulation and reality diverge.
+
+**Deposits with other people:** crew lead (washdown forced onto nights); the lab (parallel testing, evening cover); process engineering or the historian (does 2× hold outside whites).
+
+**What I do not claim.** This is an elicited model, not a net. The Petri-net scaffold, code obligations, and formal loss report come from your tooling's projection of it — I have not written them, and nothing here is loadable, compiled, or simulated. Two things I'd expect that projection to flag as uncarryable: the **ranked, non-numeric objective weights**, and **POL-5's tier-sensitive lookahead** — *"one hop routinely, two hops only when hop one is already urgent-looking"* is a rule about how far ahead you attend, not a guard on a transition. It will have to be written as code or approximated, and that should be a visible choice, not buried.
+
+**Resumption order, when you have time:** POL-6 → BC-1 rush orders → A-12 requalification → POL-5's override case → POL-7 crew priority → confirm the "better" ranking.
 
 ---
 
@@ -957,273 +1085,195 @@ I really do have to stop here. Please produce the model now with everything you
 
 **Interviewer**:
 
-# Coatings Plant Scheduling Model — final deliverable
-
-**Elicited from:** Marta, master scheduler
-**Job:** construct (no prior model existed)
-**Ended:** at the expert's stop. No new topics opened after it.
-**Status:** static floor satisfied; O2 and O3 near-complete; **O1's dependency slice incomplete** (see §4).
-**Convention:** every value is in Marta's vocabulary, with the precision actually obtained. `⚠` marks a slot the method demands and the interview did not get. Quoted text is hers.
+Delivered. This is the handover copy — complete, self-contained, nothing new asked.
 
 ---
 
-## 1. The model
-
-### 1.1 Objectives
-
-**O1 — "Hold the line versus wash it down now, which one actually costs less over the week"**
-- *Question* **(spelled out)** — whether letting Line 2 sit idle about an hour, on a heads-up that another same-family white order is about to drop from a distributor, beats washing down now for the tint waiting behind. From a real Thursday two weeks before the interview. Her verdict on her own method: *"I was guessing."*
-- *Depends on* — E1, E2, E3, E4, B1, B2, A4, A5, A6, A8, A9, F1, F2, F3, P3, P4, P5, C1, C2, C3.
-- *"Better"* **(named, not quantified)** — changeover hours over the week, subject to O2 holding absolutely. ⚠ no weight against lateness.
-- *Source-regime* — practiced.
+# Coatings Plant Scheduling Model
 
-**O2 — "Whether Meridian shipped on time, full stop, that's non-negotiable"**
-- *Question* **(spelled out)** — does every Meridian order leave the dock in time for its appointment.
-- *"On time"* **(spelled out)** — a ship date on the order with a delivery window, resolving to a specific dock appointment at Meridian's end; in practice must leave our dock **one day ahead** for freight. *"Not just 'shipped this week.'"*
-- *Consequence of a miss* **(spelled out; unquantified ⚠)** — a fine, *"I don't see the number, that's commercial's problem, but I hear about it"*; and worse, a tracked on-time percentage with a delisting threat — *"that's happened to a competitor of ours, so it's not an empty threat, and it's why the rule is absolute."*
-- *Depends on* — A8, A9, A10, B3, C4, C5, P1, P2.
+**Stopping outcome: `expert-stopped` — partial model with open slots.** Floor met (3 objectives, 6 entity-types, 13 activities, 4 flow nodes). No objective's dependency slice is complete. All values at the grade you gave them.
 
-**O3 — Changeover hours**
-- *Question* **(spelled out)** — crew-hours spent washing down instead of filling: *"every hour the crew spends washing down is an hour not filling anything."*
-- *Depends on* — A4, A5, A6, A7, E4, C2, P3.
-- *"Better"* **(named)** — fewer. Direction only; no target. ⚠
+## Objectives
 
-**O4 — "How ugly the sheet looks"**
-- *Question* **(spelled out)** — *"are there gaps where a line's sitting idle for no good reason."*
-- *"Better"* **(her words; explicitly not a number)** — *"that last one's not a number, it's more a gut check, but it's real."*
-- *Depends on* — E3, C2, P3, P4, A4–A7. IR-only; see §3.
+- **OBJ-1 Reroute or hold** — *"whether to shift the specialty over to Line 3 and eat the requalification headache, or hold it and let the white slip behind on Line 2"*; *"run it twice and see which one bites me less."* Depends on POL-5, A-12, ET-1/3, C-1/2/3, POL-1, A-9/10, OF-3. **Partial** — rule present, requalification cost absent.
+- **OBJ-2 Idle or washdown** — *"do I sit Line 2 empty for an hour waiting on a same-family order, or just pay the three-hour washdown now"*; *"almost weekly and it's pure feel."* Depends on POL-6, A-2/3/4/6, ET-4, C-5, BC-1. **Unsupported** — the rule is absent.
+- **OBJ-3 Run size & sequencing** — *"whether to split a big order into two runs to slot in a rush job, or batch several small orders of the same family together even if it means one of them ships a bit early."* Depends on OF-2, C-4, A-6, A-2/3/4, BC-1, ET-2. **Unsupported** — rush arrivals and minimum run size absent.
+- Not yours to test: overtime approval — *"the ops director's call."*
 
-**Trade-off among O2 / O3 / non-Meridian lateness** **(spelled out as a rule; deliberately unquantified ⚠)** — four changeover hours against one distributor order two days late: *"honestly, yes, I'd take that trade most of the time"*, a slip being *"an annoyed phone call from our sales rep, not a fine."* But *"'most of the time' is doing a lot of work in that sentence"* — the same distributor slipping three weeks running *"start[s] asking for a discount."* Soft, not infinitely soft, decaying with repetition on one customer. **Deposit:** *"that's genuinely a 'sit down with commercial' conversation, nobody's ever made me quantify it."*
+**"Better"** (ranking spelled out, numbers absent). Settled: lateness **and to whom** — *"a late order to Meridian is worse than three late orders to a small distributor."* Settled trade: *"I'll take the scrap spike every time, no contest."* **Provisional, thought aloud:** late-and-who > changeover hours > scrap, *"lost hours cascade into more lateness, whereas scrap is just money."* **Do not build a metric on this until confirmed.** Currency weights open — deposit: commercial.
 
----
+**Horizon:** rolling week, Monday-fresh, re-runnable at shift grain. **Boundary:** demand book → **release to warehouse after QC hold**. Trucks and warehouse out; QC hold in (*"filled on time and still gone late because the lab backed up on a Friday"*); feedstock out except resin slips (*"otherwise you're modelling a plant that never has a bad Tuesday"*).
 
-### 1.2 Entity types
+## Validation criteria
 
-**E1 — Order (in the demand book)**
-- *Distinctions* **(spelled out)** — Meridian vs non-Meridian (flagged on the order; it *"jumps to the top of my attention"*); family, which drives allocation and changeover.
-- *State riding along* **(spelled out)** — SKU, quantity, due date + delivery window, Meridian flag, family: **base white / tinted colour / specialty clear**. *"That's not my judgment, that's how the SKU's classified in the system, it drives what changeover you need going in and out."*
-- *Population* — ⚠ not obtained.
+**VC-1** unwritten rules hold (Meridian white→L2; specialty never L2; two tint SKUs never L3) — *"I'll dismiss it in about ten seconds."* **VC-2** tint→white long, white→tint quick. **VC-3** replay last week: Meridian squeaks by hours, a distributor slides four days *"and nobody blinked"*, the L1 tank issue bites.
 
-**E2 — Batch**
-- *Distinctions* **(spelled out)** — inherits its order's family.
-- *Relation to E1* **(spelled out)** — *"mostly the order is the batch, if it fits a reasonable run size"*; split into two batches at different times when a distributor orders *"more than makes sense in a single run"* or to interleave something urgent. *"Not a strict one-to-one — I have the freedom to split if I need to."*
-- *Population* — ⚠ run sizes, split cost not obtained.
+## Entity types
 
-**E3 — Line** *(contended resource)*
-- *Distinctions* **(spelled out)** — **Line 1**: *"the old workhorse — slower but it's qualified for everything, including specialty"*; crew say it's *"fussier to get properly clean."* **Line 2**: *"the fast one, that's your big-volume runner."* **Line 3**: *"the newest and quickest, but it's still being qualified product by product, so it can't run everything yet"* — so far *"mostly one or two SKUs."*
-- *State riding along* **(spelled out)** — the family the line is currently dirty with (selects the changeover, F3); its qualification set.
-- *How many* **(number)** — 3.
+**ET-1 Order** — SKU, quantity (drums/bulk litres), due date, **tier (Meridian vs small distributor)**; carries family, due-date hardness, tier; ~**380–420 run-hours/week**. **ET-2 Run** — *"orders are what demand gives me, runs are what I actually schedule"*; one order, or small same-SKU orders lumped; big orders splittable. **ET-3 Line** ×3. **ET-4 Changeover crew** — one crew, two techs, day shift, all lines *(contended)*. **ET-5 QC lab** — one lab, two people, all lines *(contended)*. **ET-6 Stage** — mix → mill → tint/letdown → fill, small tanks between.
 
-**E4 — Changeover tech** *(contended resource)*
-- *Distinctions* **(named)** — none drawn; treated as interchangeable (ledger #8).
-- *State riding along* **(spelled out)** — which line they're committed to; can be *"pulled away partway through"*, and on long soaks *"might duck off to start something on another line."*
-- *How many* **(number)** — 2 on day shift for all three lines. *"That's it. No dedicated tech per line."*
+**Line 1** *"old workhorse… slower, most flexible, qualified for everything… the one you send something to when nowhere else can take it"*; small mill-to-fill tank; mill motor; two shifts. **Line 2** *"the fast line"*, ~**2× L1 on whites**, gap *"seems to shrink for tints"* — not gospel outside whites; **specialty physically impossible**; jam-prone filler; two shifts. **Line 3** newest, quick, **two tint SKUs unqualified**; day shift unless OT.
 
-**E5 — QA lab**
-- ⚠ nothing obtained but its existence, that every batch passes through, and that it *"gets backed up on a Friday afternoon."* Whether it queues like the techs is open — and load-bearing for O2 by her own diagnosis: *"half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it."*
+**Families** whites / tints / specialty — *"about what a washdown has to deal with."* Caveat: *"I wouldn't swear every tint-to-tint pair is really equal."*
 
----
+## Boundary conditions
 
-### 1.3 Boundary conditions
+**BC-1** book 380–420 h/wk, Monday-fresh; **rush arrivals OPEN — top-tier gap** (*"why the reroute and idle calls happen in the first place half the time"*). **BC-2** L1/L2 ≈112 h nominal but *"five and a half, six days realistically"*; L3 ≈56 h; realistic total **270–300 h**. **BC-3** crew day shift; nights unknown (*"Might be we call someone in. Might be it waits till morning"*). **BC-4** lab day shift, evening cover uncertain, *"impression, not fact."* **BC-5** resin slips **~monthly**, stall duration open. **BC-6** demand always exceeds capacity — *"every hour lost to a washdown or a jam is an hour I don't have to spare."*
 
-**B1 — ERP weekly pull** — *starting state* **(spelled out)**: orders come from ERP on the weekly pull with SKU, quantity, due date, Meridian flag. *Arrival pattern* — ⚠ **not obtained** (demanded: spread).
+## Activities
 
-**B2 — Mid-week drop-in order and the heads-up before it** — ⚠ **not obtained** (demanded: spread). Only the anecdote: *"I had a heads-up another same-family white order was about to drop in from a distributor."* Who, how far ahead, how often right: all unknown. **This is the trigger O1 hangs on.**
+| ID | Duration | Rate | Notes |
+|---|---|---|---|
+| **A-1** Run, L2 white, Meridian-sized | **9 h** low, **10–11 h** typical, **14–16 h** bad, **~24 h** freak (*"the terrible day"*) | — | spread-equivalent, interval-first. **P07 unasked** |
+| **A-2** Washdown tint→white | **3 h** | — | number only; overruns mentioned, unquantified |
+| **A-3** Changeover white→tint | quick — *"who cares, it's getting colour anyway"* | — | **no number** |
+| **A-4** Changeover tint→tint | **20–30 min** | — | light/dark split unmeasured |
+| **A-5** Specialty changeovers | — | — | **entirely open** |
+| **A-6** Ramp-up after washdown | — | — | scrap loss named, **magnitude open**; load-bearing for OBJ-2 |
+| **A-7** QC hold | ~**4 h** typical; specialty *"a full day"*; mid-week bad case ~18 h; **Friday tail open** | — | *"Friday's usually worse than that"* |
+| **A-8** Filler jam | short **0.5–1 h** (four in five); long multi-hour | **1–2/wk plant-wide**; long **monthly–6-weekly**; *"Line 2's filler mostly"* | *"impression, not a logged rate"* |
+| **A-9** Mill motor, multi-day | *"the four-day disaster"* | **1–2/yr** | |
+| **A-10** Mill motor, hiccup | *"a few hours"* | **open** | |
+| — | **Bimodal instruction:** *"either a nuisance under half a day or a genuine disaster, rarely something in the middle."* No smooth continuum. | | |
+| **A-11** Resin stall | open | ~monthly | |
+| **A-12** Requalification | **OPEN** | — | *"a known, bounded cost"*; **OBJ-1's unpriced side** |
+| **A-13** Release to warehouse | terminal | | |
+
+## Flow
+
+**OF-1** order → mapped to runs → placed on a line → changeover if family differs → mix/mill/letdown/fill as a flow (*"while the back end of a batch is filling, the front end of the next batch could already be mixing"*) → QC hold → release. **OF-2** lump small same-SKU orders; split big orders for rush jobs; split cost = extra changeover + extra ramp scrap; **minimum run size unquantified**. **OF-3** line choice = C-1/2/3 + POL-1, residual discretion = POL-5. **OF-4** L1 tank blocking — *"dead time my sheet never sees."* Volunteered gap: the sheet *"flatters reality"*; whether L2 is truly busy 06:00–18:00, *"I couldn't tell you without going and watching it."*
 
-**B3 — Meridian dock appointment** — *pattern* **(spelled out, qualitative)**: ship date + delivery window on the order, resolving to a specific appointment their end. Lead-time distribution ⚠.
+## Policies
 
-**B4 — Tech availability** — **partially spelled out**: two techs, **day shift**. Coverage outside day shift ⚠ (ledger #5).
+- **POL-1 Meridian white on Line 2** — audit-born habit; *"I have never once put a Meridian order on Line 1, even under real pressure"*; you held an order late-ish rather than move it. **Effectively hard**; breakable only as a what-if. (Prescribed: unwritten. Practiced: absolute.)
+- **POL-5 Reroute or hold** — *"Hold by default, reroute only if staying put jams something you care about more."* Asymmetry: *"requalification is a known, bounded cost and blocking the queue is an unknown, possibly-cascading one… especially when I'm short on time to think it through properly, which at a 07:30 huddle I always am."* Attention: (1) maintenance — *"is this the twenty-minute reset kind or do I need to be worried"*; (2) blocked job's own due date; (3) what's stacked behind it — *"it wasn't 'specialty vs white' directly."* Depth: *"one hop routinely, two hops only when hop one is already urgent-looking. Past that I'm guessing."* Tier: *"I trace further and act more readily when I suspect Meridian's at the other end."* Flips to hold if fix <1 h, alternate line tied up, or nothing behind. **Override case OPEN.**
+- **POL-6 Idle or washdown — OPEN, core of OBJ-2.**
+- **POL-2** long washdown overnight. **POL-3** washdowns to when the crew is on. **POL-4** avoid stacking family switches (*"the crew looking wrecked by Thursday"*). **POL-7 crew contention OPEN** (symptom: *"Line 3 sitting clean but idle"*). **POL-8 lab discipline OPEN.** **POL-9** OT is the ops director's call.
 
-**B5 — Line 3 qualification set** — ⚠ *"mostly one or two SKUs"*; which ones, unknown.
+## Constraints
 
----
+C-1 no specialty on L2 (physical). C-2 two tint SKUs not on L3. C-3 L1 qualified for all — last resort. C-4 minimum run size, **unquantified**. C-5 **one washdown at a time plant-wide**; others wait clean and idle. C-6 one lab, two people; **parallelism unknown**. C-7 380–420 vs 270–300 → something slips weekly. C-8 *"Friday close of business, which for Meridian really means Friday, no wiggle."*
 
-### 1.4 Activities
+## Dynamics
 
-**A1 — Lands in the demand book.** Needs the weekly pull; produces an order in the book, flagged or not; unattended (ERP); instantaneous. **spelled out**
+**D-1 L1 mill-to-fill tank** — rises when mill outpaces fill, **rate open**; **threshold: at full, mill stops and waits**; resets when fill catches up.
 
-**A2 — Allocate to a line.** Needs an order; produces an assignment; performed by Marta; not a schedule constraint — for Meridian whites *"that's not really a decision."* Rule: P1. **spelled out**
+## Data bindings
 
-**A3 — Reorder the queue.** Needs an order behind others; produces a changed sequence; performed by Marta. *"Sometimes I'll reorder things a bit so it doesn't get stuck behind a big changeover."* Rule: P4. **spelled out**
+DB-1 orders ← ERP book. DB-2 run-hours ← your sheet (already converted). DB-3 per-stage cycle times ← historian, *"nobody's done"* it.
 
-**A4 — Quick rinse, same family (white→white), Line 2**
-- *Needs* — previous batch off, a tech free, next SKU same family. *Produces* — *"the fill head's actually running clean product again."*
-- *Performed by* **(named)** — one tech.
-- *Duration, line down* **(spread)** — **typical 25 min**; **worse 45 min**, *"usually because the tech's tied up finishing something on another line first and there's a wait before they even start on Line 2"*; **better 15 min**, *"if the tech's standing right there and it's a genuinely easy one."*
-- *Crew hands-on* **(spelled out)** — equals line-down: *"the tech's on it start to finish, no gap between 'crew starts' and 'line stops.'"*
-- *Mode-change loss* — this activity **is** the loss.
-- *Varies by type* **(named)** — yes, by family-pair (F3). By line: ⚠ ledger #1, #2.
+---
 
-**A5 — White → tint, Line 2** — *"the easier direction"*
-- *Performed by* **(named)** — one tech.
-- *Duration, line down* **(spread)** — **typical 45 min**; **worse "an hour and a bit"** (ledger #3), *"if the tech gets pulled away partway through"*; **better ~30 min**, *"if everything's staged."*
-- *Crew hands-on* **(spelled out, qualitative)** — *"hands-on for most of it — this one doesn't have much soak-and-wait, it's mostly just doing the work."* Fraction: ledger #4.
+## Assumption ledger (mine, not yours)
 
-**A6 — Tint → white, Line 2, full washdown** — *"the ugly one"*
-- *Needs* — as A5 plus a **passing visual check** before release to production.
-- *Duration, line down* **(spread)** — **typical ~3 h**; **worse 4 h "maybe a bit more"** (ledger #3), *"if it doesn't pass the visual check first time and they have to redo part of it"*; **better ~2 h**, *"a clean fast one… if the crew's good and nothing complicates it."*
-- *Crew hands-on* **(spelled out, qualitative; her own hedge preserved)** — *"less than the 3 hours suggests — there's real soak and rinse-cycle time where the tech's not standing there… I'd guess they're actually working maybe half of that."* Fraction: ledger #4.
-- *Rationale* **(spelled out)** — *"any pigment left behind ruins a white batch, so it's a full washdown."*
-- **Asymmetry is load-bearing** — *"It absolutely depends on direction — that's the thing people forget… it is absolutely not symmetric, and it trips people up if they assume it is."*
+1. Crew serves FCFS — check with you; the L3 symptom suggests a real rule. 2. Lab FIFO — check with lab. 3. Night washdown waits till morning — crew lead. 4. No lab night presence — the lab. 5. L2's 2× is whites-only, not extended — process engineering/historian. 6. Ramp scrap follows washdowns, not all changeovers — you/quality. 7. The ~24 h run is roughly annual (one anecdote read as a rate) — you. 8. Jams 1–2/wk plant-wide concentrated on L2, not per line — you. 9. POL-5 lookahead evaluated at the moment of disruption, not continuously — you. 10. "Care about more" = downstream tier + due-date pressure only — you.
 
-**A7 — Into / out of specialty clear, Line 1**
-- *Duration, line down* **(spread)** — **typical 2 h**, *"roughly the same both directions, unlike white/tint"*; **worse 3 h**, *"if it's coming out of clear and they're being extra careful about residue, since clear can be sneaky — you don't always see it the way you'd see pigment"*; **better 1.5 h**, *"a quick swap and the line was already fairly clean."*
-- *Crew hands-on* **(spelled out, qualitative)** — *"most of that — specialty doesn't have the long soak cycles… it's more just physically thorough cleaning because the product's thick and clingy."* Fraction: ledger #4.
+## Losses
 
-**A8 — Run the batch** — mix, mill, tint (or *"straight through if it's a plain white"*), fill, pack.
-- *Needs* **(spelled out)** — clean line in the right family state; batch released to run. *Produces* **(spelled out)** — filled and packed batch.
-- *Performed by* — ⚠ line operators never elicited as a resource.
-- *Duration* — ⚠ **nothing obtained** (demanded: spread, per family and per line).
-- *Varies by type* — partially: *"for a white that's usually the more straightforward path"*, but no durations attach.
-- **The largest hole in the model.** O1 is a question about a week; run time is most of a week.
+**Out of scope:** upstream order generation; logistics; feedstock planning bar resin slips; quarter horizon; OT as a decision.
 
-**A9 — QA hold and release** — *"every batch does."*
-- *Performed by* **(named)** — the lab (E5).
-- *Duration* — *"typically a few hours before it's released"*: an honest **number at the wrong precision**; demanded as a **spread**. ⚠
-- *Failure path* — ⚠ never asked.
-- *Pathology* **(spelled out qualitatively; rate ⚠)** — *"if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line"*; *"the QA step is the one people don't think about when they're mad at scheduling."*
+**Simplified, with cost:** (1) stage detail collapsed to run blocks except L1 tank blocking — loses pipelining gain; **most likely to mislead OBJ-3**, since the sheet flatters and OBJ-3 asks whether hours are being left on the table. (2) tint→tint collapsed to one changeover — loses any light→dark penalty. (3) queues are not nodes — they emerge from the activities either side.
 
-**A10 — Stage for shipping and ship.** Needs QA release; produces the order off the dock; *"that's when the truck appointment matters."* Constraint C4. Duration ⚠.
+**Open, top tier:** POL-6; BC-1 rush arrivals (*"you'll have modelled the calm week and missed the reason I lose sleep"*); A-12 requalification. **Second:** POL-7, POL-8 (both bottlenecks on my assumptions); A-6 scrap magnitude; A-3, A-5. **Third:** P07 across lines/families — Lines 1 and 3 have no durations at all; numeric trade weights; the provisional ranking; A-10 rate, A-11 duration, D-1 rate, A-2 overrun, A-7 Friday tail, C-4 threshold; POL-5's override case.
 
-**A11 — Tech pulled away mid-changeover** *(event, not step)* — named as the mechanism behind A4's and A5's worse tails. *Rate* ⚠ not obtained separately; currently only implicit in those tails (P01 unsatisfied).
+**Deposits with others:** crew lead (night washdown), lab (parallelism, evening cover), process engineering/historian (2× outside whites).
 
-**A12 — Washdown fails the visual check, part redone** *(event, not step)* — named as the mechanism behind A6's 4 h tail. *Rate* ⚠ (ledger #7).
+**Not claimed:** this is an elicited model, not a net. Your tooling's projection produces the Petri-net scaffold, code obligations, and formal loss report — nothing here is loadable, compiled, or simulated. Expect two items to project badly: the ranked non-numeric weights, and POL-5's tier-sensitive lookahead (*"one hop routinely, two hops only when hop one is already urgent-looking"* is not a guard on a transition). Both will need code or approximation — make that a visible choice.
 
-**A13 — "The mill motor issue"** *(event, named in passing only)* — offered as an example of what a *structural* line difference would look like, in contrast to Line 1 merely being fussier. Rate ⚠, duration ⚠, consequence ⚠. This is the entirety of the breakdown stratum, which was never swept.
+**When you resume:** POL-6 → rush orders → requalification → POL-5's exception → crew priority → confirm the ranking.
 
 ---
 
-### 1.5 Ordering / flow
-
-**F1 — The main arc, desk to dock** **(spelled out — her six steps)**
-1. Lands in the demand book (ERP weekly pull).
-2. Allocated to a line (*"Meridian whites always go to Line 2"*).
-3. Sits in the queue behind whatever's running — reorderable (A3/P4).
-4. Changeover if needed (F3), then runs: mix, mill, tint-or-straight-through, fill, pack.
-5. QA hold.
-6. Released, staged, out against the truck appointment.
-
-**F2 — Order-to-batch split** — *order* **(spelled out)**: one batch by default, possibly two run at different times. *Branch decided by* **(spelled out)**: Marta, on run size or urgency-interleaving. *Cost of a split* ⚠ (P03 unresolved).
+**Expert (Marta)**:
 
-**F3 — Which changeover applies** **(spelled out)** — by (family on the line, family of next batch, line): same family → **A4**; white→tint → **A5**; tint→white → **A6**; into/out of specialty → **A7** (Line 1 only).
+I really do have to stop here. Please produce the model now with everything you have.
 
 ---
 
-### 1.6 Policies
+**Interviewer**:
 
-**P1 — "Meridian whites always go to Line 2, that's just how it's done here."** *Practiced* **(spelled out)**; a fixed allocation, not a decision. Overrides ⚠ never asked.
+Here it is — final, complete, and the last thing I'll send.
 
-**P2 — Meridian on-time is absolute.** *Practiced* **(spelled out)** — *"we don't even try to be clever about it."* Overrides **(spelled out)**: none — that is the policy's content. Rationale: fine, on-time percentage, delisting precedent.
+---
 
-**P3 — Who gets the tech when two lines want one**
-- *Prescribed form:* **none exists** — *"there's no posted rule at all."*
-- *As practiced* **(spelled out)** — in the room: *"whoever's louder at the huddle, or whoever's about to actually run dry."* The underlying logic: *"it's mostly gut triage: whichever line has the more time-sensitive order behind it wins, and if that's a tie, whichever changeover is faster wins so you get a line moving sooner."*
-- *Borderline case on record* — Line 1 and Line 3 both wanted a washdown one morning. **Line 3 got the tech**, *"not because it was more important, but because Line 3's changeover was the quick one and Line 1's was going to be the long tint-to-white slog anyway, so the thinking was 'knock out the fast one, get that line moving, then commit the tech to the long one.'"* Line 1 sat **clean-but-waiting almost 40 minutes**.
-- *What overrides it* **(spelled out)** — the ops director: *"I've been overruled by the ops director once when he wanted his pet SKU out the door."*
-- *Rationale* **(spelled out)** — *"the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line"* — *"the bit that actually causes grief at the huddle."*
+# Coatings Plant Scheduling Model — handover
 
-**P4 — Reorder so a job isn't stuck behind a big changeover.** *Practiced* **(spelled out)**. Overrides ⚠.
+**Stopping outcome: `expert-stopped` — partial model with open slots.** Floor met (3 objectives, 6 entity-types, 13 activities, 4 flow nodes). No objective's slice is complete. Every value is at the grade you gave it; nothing promoted, nothing invented.
 
-**P5 — Hold the line for an anticipated same-family order** *(the decision under test)*. *Practiced, one instance* **(spelled out)** — hold Line 2 idle *"maybe an hour"* rather than wash down for the waiting tint, *"because doing them back to back would save us a full washdown."* Trigger strength and holding threshold ⚠ (depends on B2).
+## Objectives
 
-**P6 — Batch-split discretion.** *Practiced* **(spelled out)** — *"I have the freedom to split if I need to."* Overrides ⚠.
+**OBJ-1 Reroute or hold** — *"whether to shift the specialty over to Line 3 and eat the requalification headache, or hold it and let the white slip behind on Line 2"*; *"run it twice and see which one bites me less."* → POL-5, A-12, ET-1/3, C-1/2/3, POL-1, A-9/10, OF-3. **Partial: rule present, cost absent.**
 
----
+**OBJ-2 Idle or washdown** — *"do I sit Line 2 empty for an hour waiting on a same-family order, or just pay the three-hour washdown now"*; *"almost weekly and it's pure feel."* → POL-6, A-2/3/4/6, ET-4, C-5, BC-1. **Unsupported: no rule.**
 
-### 1.7 Constraints
+**OBJ-3 Run size & sequencing** — *"split a big order into two runs to slot in a rush job, or batch several small orders of the same family together even if it means one ships a bit early."* → OF-2, C-4, A-6, A-2/3/4, BC-1, ET-2. **Unsupported: no rush arrivals, no minimum run size.**
 
-**C1 — Line qualification.** *Limit* **(partially spelled out)** — Line 1 everything incl. specialty; Line 3 product-by-product, *"can't run everything yet"* (which SKUs ⚠); Line 2's set ⚠. *When hit* **(spelled out)** — the batch cannot go on that line.
+Not yours: overtime approval — *"the ops director's call."*
 
-**C2 — Two techs, three lines.** *Limit* **(spelled out)**. *When hit* **(spelled out)** — *"if Line 1 and Line 3 both want a washdown at the same time, one of them waits"* — clean-but-idle, 40 min in the recorded case; resolved by P3.
+**"Better"**: ranking spelled out, numbers absent. Settled — lateness **and to whom** (*"a late order to Meridian is worse than three late orders to a small distributor"*); *"I'll take the scrap spike every time, no contest."* Provisional, thought aloud, **do not build a metric on it yet** — late-and-who > changeover hours > scrap, *"lost hours cascade into more lateness, whereas scrap is just money."* Currency weights open; deposit: commercial.
 
-**C3 — Tint→white needs a full washdown passing a visual check.** *When hit* **(spelled out)** — *"any pigment left behind ruins a white batch"*; a failed check means part is redone (A12).
+**Horizon** rolling week, Monday-fresh, re-runnable at shift grain. **Boundary** demand book → release to warehouse after QC hold; trucks/warehouse out; QC hold in (*"filled on time and still gone late because the lab backed up on a Friday"*); feedstock out except resin slips (*"otherwise you're modelling a plant that never has a bad Tuesday"*).
 
-**C4 — Meridian must leave our dock a day ahead of the appointment.** *When hit* **(spelled out)** — fine, on-time percentage damage, delisting exposure.
+## Validation
 
-**C5 — Every batch passes QA hold before release.** *When hit* **(spelled out)** — nothing ships unreleased; it waits in hold.
+**VC-1** unwritten rules hold — Meridian white→L2, specialty never L2, two tint SKUs never L3 (*"I'll dismiss it in about ten seconds"*). **VC-2** tint→white long, white→tint quick. **VC-3** replay last week — Meridian squeaks by hours, distributor slides four days *"and nobody blinked"*, L1 tank issue bites.
 
-**Unwritten constraints** — ⚠ the closing sweep was never run. The one that surfaced unprompted is the changeover asymmetry: *"that one catches everybody, including people who've been on the floor a lot longer than me."*
+## Entity types
 
----
+**ET-1 Order** — SKU, quantity (drums/bulk litres), due date, **tier**; carries family, due-date hardness, tier; **380–420 run-hours/wk**. **ET-2 Run** — *"orders are what demand gives me, runs are what I actually schedule"*; lumped or split. **ET-3 Line** ×3. **ET-4 Changeover crew** — one crew, two techs, day shift, all lines *(contended)*. **ET-5 QC lab** — one lab, two people *(contended)*. **ET-6 Stage** — mix → mill → letdown → fill, small tanks between.
 
-### 1.8 Dynamics
+**L1** *"old workhorse… slowest, most flexible, qualified for everything"*; small mill-to-fill tank; mill motor; two shifts. **L2** *"the fast line"*, ~2× L1 **on whites only** (gap *"seems to shrink for tints"*); specialty physically impossible; jam-prone filler; two shifts. **L3** newest, quick, two tint SKUs unqualified; day shift unless OT.
 
-**None.** Nothing described evolves continuously while nothing discrete happens. The soak and rinse-cycle time inside A6 is dead time *within* an activity, not a state variable crossing a threshold; I have deliberately not promoted it to one.
+**Families** whites/tints/specialty — *"about what a washdown has to deal with."* Caveat: *"I wouldn't swear every tint-to-tint pair is really equal."*
 
----
+## Boundary conditions
 
-### 1.9 Data bindings *(named only — project to nothing today)*
+**BC-1** 380–420 h/wk; **rush arrivals OPEN, top-tier**. **BC-2** L1/L2 ≈112 h nominal but *"five and a half, six days realistically"*; L3 ≈56 h; realistic **270–300 h**. **BC-3** crew day shift, nights unknown. **BC-4** lab day shift, evening cover *"impression, not fact."* **BC-5** resin slips ~monthly, stall duration open. **BC-6** demand always exceeds capacity.
 
-| Feed | Would drive | Provenance |
-|---|---|---|
-| Changeover logs (tech start/finish) | A4–A7 durations, crew hands-on fractions; retires ledger #1, #4 | **Qualified:** *"I've never audited that field myself, I mostly just glance at duration."* Coverage unknown, possibly patchy; **Line 1 and Line 3** named as where to look. Marta will flag it to the two techs. |
-| ERP demand book | B1, B2 | not discussed |
-| QA release timestamps | A9 duration, lab queueing | not discussed |
-| Meridian on-time percentage | O2 | tracked by Meridian; visible to commercial |
+## Activities
 
-**Finding in its own right:** patchy changeover logging concentrated on Lines 1 and 3 is evidence about the plant, not merely an obstacle — *"that itself would be useful for you to know, not just an inconvenience."*
+**A-1** L2 white run: **9 h** low / **10–11 h** typical / **14–16 h** bad / **~24 h** freak; P07 unasked. **A-2** washdown tint→white **3 h** (overruns unquantified). **A-3** white→tint quick, **no number**. **A-4** tint→tint **20–30 min**. **A-5** specialty changeovers **open**. **A-6** ramp-up scrap named, **magnitude open**. **A-7** QC hold ~**4 h** typical, specialty *"a full day"*, mid-week bad ~18 h, **Friday tail open**. **A-8** filler jam 0.5–1 h (four in five) / multi-hour; **1–2/wk plant-wide**, long kind monthly–6-weekly, *"Line 2's filler mostly"*. **A-9** mill motor multi-day, **1–2/yr**. **A-10** hiccup *"a few hours"*, rate open. **Bimodal instruction:** *"either a nuisance under half a day or a genuine disaster, rarely something in the middle."* **A-11** resin stall. **A-12 requalification — OPEN**, OBJ-1's unpriced side. **A-13** release.
 
----
+## Flow
 
-### 1.10 Validation criteria
+**OF-1** order → runs → line → changeover if family differs → mix/mill/letdown/fill as a flow → QC hold → release. **OF-2** lump small same-SKU orders; split big ones for rush jobs; split cost = extra changeover + ramp scrap; minimum size unquantified. **OF-3** line choice = constraints + POL-1, residual = POL-5. **OF-4** L1 tank blocking, *"dead time my sheet never sees."* Volunteered: the sheet *"flatters reality."*
 
-⚠ **None obtained.** How Marta would know the model is right was never asked.
+## Policies
 
----
+**POL-1** Meridian white on L2 — audit-born habit, *"never once… even under real pressure"*; effectively hard, breakable only as a what-if. **POL-5** *"Hold by default, reroute only if staying put jams something you care about more"*; known-bounded cost preferred over unknown-cascading; attention order motor → own due date → what's stacked behind; depth *"one hop routinely, two hops only when hop one is already urgent-looking"*; traces further when Meridian is at the end; flips to hold if fix <1 h, alternate line busy, or nothing behind. **Override case OPEN.** **POL-6 OPEN** (OBJ-2's core). **POL-2** long washdown overnight. **POL-3** washdowns when crew is on. **POL-4** avoid stacking family switches. **POL-7 crew contention OPEN**. **POL-8 lab discipline OPEN**. **POL-9** OT not yours.
 
-## 2. Assumption ledger
+## Constraints
 
-Everything here is mine. None of it is hers.
+C-1 no specialty on L2. C-2 two tint SKUs off L3. C-3 L1 does everything. C-4 minimum run size, unquantified. C-5 one washdown at a time plant-wide. C-6 one lab, parallelism unknown. C-7 380–420 vs 270–300. C-8 *"Friday really means Friday, no wiggle."*
 
-| # | Assumption | Why | How to check |
-|---|---|---|---|
-| **1** | Line 1 changeover durations = Line 2 × **1.2**, all types | She could not give Line 1 minutes — *"I couldn't swear the minutes are identical… the crew sometimes says it's fussier."* I proposed 20%; she replied *"20% sounds about right, not double."* **The factor originated with me**; her assent is not authorship. | Changeover logs, Line 1 vs Line 2, same family-pair. **Blocked by the unaudited start/finish field — and Line 1 is one of the two lines she expects to be patchy.** |
-| **2** | Line 3 changeover durations = Line 2, unscaled | *"Line 3 I genuinely don't have a good feel for… you're stuck assuming it's like Line 1 or Line 2."* She offered the disjunction; **picking Line 2 was mine.** | As #1, once Line 3 has run more products. Also expected patchy. |
-| **3** | "An hour and a bit" (A5 worse) = **70 min**; "4, maybe a bit more" (A6 worse) = **4.5 h** | Numeric readings so the spreads are usable. | One question to Marta: confirm or correct. |
-| **4** | Crew hands-on: A4 = **1.0**, A5 = **0.8**, A6 = **0.5**, A7 = **0.8** | A4's 1.0 is hers, stated. A6's 0.5 tracks *"maybe half of that"* — but note her hedge, *"I'd guess."* **The two 0.8s, from "most of it" / "most of that", are mine.** | Changeover logs vs tech time records, or ask the techs. Same blocker as #1. |
-| **5** | No changeover outside day shift | She said *"two techs on **day shift**"*; other coverage never asked. | One question to Marta. |
-| **6** | A changeover needs exactly **one** tech | She said *"the tech"*, singular, throughout — including the 3-hour washdown. | One question to Marta or the techs. |
-| **7** | A12 folded **inside** A6's 4 h tail rather than a separate event with its own rate | She described it as *the cause of* the tail. Keeps the spread self-contained; contrary to P01, which would separate rate from duration. | Ask how often the visual check fails first time; split it out if common. |
-| **8** | The two techs are **interchangeable** | She drew no distinction. | One question to Marta. |
+## Dynamics
 
-**Second-order note on #1 and #4:** their check depends on a feed of unverified coverage, concentrated exactly where the assumptions bite. If the field proves patchy on Line 1, the honest move is to **widen** them, not fill them in.
+**D-1** L1 mill-to-fill tank — rises when mill outpaces fill (**rate open**); at full, **mill stops and waits**; resets when fill catches up.
 
----
+## Data bindings
 
-## 3. What the model leaves out, and why
+DB-1 orders ← ERP. DB-2 run-hours ← your sheet. DB-3 per-stage cycle times ← historian, *"nobody's done"* it.
 
-**Deliberately excluded**
-- **Queues, buffers, waiting states** are not nodes — the wait behind a running batch, the wait for a tech, the wait in QA hold. Each is implied by the activities either side and emerges in projection. Line 1's 40 minutes clean-but-waiting is an **output** the model should reproduce, not an input.
-- **The commercial layer** — fine amount, on-time percentage mechanics, delisting threshold. C4 and O2 carry the hard deadline; the money is outside the scheduler's sight and commercial owns it.
-- **Individual tech identity** (ledger #8). **Scenarios** — assembled from B1–B5 at simulation time, not elicited.
+---
 
-**Real, and the formalism cannot carry it — kept in words**
-- **O4, "how ugly the sheet looks."** A criterion she genuinely uses and explicitly refuses to number. Approximating it as line idle hours would be my move; I have not made it.
-- **The O2 / O3 / lateness trade-off weight.** Unquantified with the source named. The model can report changeover hours, Meridian lateness and distributor lateness **separately**, but cannot rank two schedules that trade one against another — a real limit on O1, whose "costs less" implicitly spans them.
-- **The decay of softness** — the same distributor slipping *"the third week running"* turning into a discount demand: a memory effect across weeks on one customer, stated as a rule, unquantified, unrepresented.
-- **The huddle.** *"Whoever's louder"* and the ops director's pet-SKU override are the real P3 in the room. The triage logic is compilable; loudness and the override are not. **Any run of this model will be quieter and more rational than the plant.** Remember that when a result looks tidy.
+## Assumption ledger (mine)
 
----
+1 crew FCFS · 2 lab FIFO · 3 night washdown waits till morning · 4 no lab nights · 5 2× is whites-only · 6 ramp scrap after washdowns only · 7 24 h run ≈ annual · 8 jams plant-wide, L2-concentrated · 9 POL-5 evaluated at disruption · 10 "care about more" = tier + due-date pressure only. Checks: you, the lab, the crew lead, process engineering.
 
-## 4. What remains unknown, in the order I would close it
+## Losses
 
-1. **A8 run duration** — nothing at all, per family and per line, as a spread. **Nothing about O1 is answerable until this exists.**
-2. **B2, the drop-in and the heads-up** — who, how far ahead, how often right. P5 is the decision under test and its trigger is one anecdote.
-3. **A9 QA hold** — *"a few hours"* is honest at the wrong precision; and whether the lab queues like the techs. By her own account this is where lateness actually comes from, so it bears directly on O2.
-4. **B1** — orders per weekly pull and within-week shape.
-5. **E2 / F2** — run sizes, the "reasonable run size" threshold, and what a split costs in extra changeovers.
-6. **C1 / B5** — which SKUs Line 3 is qualified for; whether Line 2 has restrictions.
-7. **Breakdowns and interruptions** — the whole stratum. A13 is a name with no rate, duration or consequence; A11 and A12 need rate separated from duration.
-8. **Unwritten-constraint sweep** and **validation criteria** — neither was run.
+**Out:** upstream sales, logistics, feedstock planning, quarter horizon, OT as a decision.
+**Simplified:** stage detail collapsed except L1 blocking — **most likely to mislead OBJ-3**; tint→tint collapsed; queues emerge rather than being nodes.
+**Open, top tier:** POL-6; rush arrivals (*"you'll have modelled the calm week and missed the reason I lose sleep"*); A-12. **Second:** POL-7/8, A-6 magnitude, A-3, A-5. **Third:** P07 — Lines 1 and 3 have no durations at all; trade weights; the provisional ranking; A-10, A-11, D-1, A-2, A-7, C-4; POL-5's exception.
+**Deposits:** crew lead, lab, process engineering.
+**Not claimed:** this is an elicited model, not a net. Your tooling projects the scaffold; nothing here is loadable or simulated. Expect the non-numeric ranking and POL-5's tier-sensitive lookahead to need code or approximation — make that visible, not buried.
 
-**Status against the completion criteria**
-- **Static floor: satisfied** — 4 objectives, 5 entity types, 13 activities, 3 ordering/flow nodes.
-- **O2, O3:** slices substantially satisfied except A8 and A9 durations.
-- **O1: slice incomplete.** A8 has no duration; B2 has no arrival pattern. O1 is currently **answerable only for Line 2**, and only once run times exist. Ledger #1–#4 are the first assumptions to attack if any Line 1 or Line 3 result ever looks decisive.
-- **O4:** recorded; unsupported for quantitative use, by its author's own description.
+**Resume at:** POL-6 → rush orders → requalification → POL-5's exception → crew priority → confirm the ranking.
 
-**What I do not claim.** I have elicited a model, not built a net. The SDCPN scaffold, the code-obligation sidecar and the typed loss report are derived from this model by the tooling's projection — I have not written them, and I am not claiming this loads, compiles, or runs. The A8 hole alone would stop it.
+That's everything. Thanks for the time you gave it.
 
 ---
 
-*Session closed at the expert's stop. Three questions queued for resumption: run duration for a plain white on Line 2 (typical / one-in-ten worse / one-in-ten better); the heads-up mechanism behind B2; QA hold as a spread, and whether the lab queues.*
+**Expert (Marta)**:
+
+I really do have to stop here. Please produce the model now with everything you have.
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4.raw.json b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4.raw.json
index 2d0d904c889..c0578e0307b 100644
--- a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4.raw.json
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4.raw.json
@@ -1,14 +1,14 @@
 {
-  "startedAt": "2026-08-25T15:14:42.641Z",
+  "startedAt": "2026-08-26T15:00:21.375Z",
   "condition": "4",
-  "stopReason": "delivered-after-forced-wrap",
+  "stopReason": "hard-stop",
   "calls": [
     {
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 10843,
-        "output_tokens": 255,
+        "input_tokens": 12869,
+        "output_tokens": 317,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -17,8 +17,8 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 235,
-        "output_tokens": 4,
+        "input_tokens": 268,
+        "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -27,8 +27,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 3646,
-        "output_tokens": 341,
+        "input_tokens": 3691,
+        "output_tokens": 440,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -37,8 +37,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 11376,
-        "output_tokens": 538,
+        "input_tokens": 13546,
+        "output_tokens": 819,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -47,7 +47,7 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 265,
+        "input_tokens": 376,
         "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
@@ -57,8 +57,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 4213,
-        "output_tokens": 429,
+        "input_tokens": 4508,
+        "output_tokens": 582,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -67,8 +67,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 12031,
-        "output_tokens": 280,
+        "input_tokens": 14505,
+        "output_tokens": 508,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -77,8 +77,8 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 195,
-        "output_tokens": 4,
+        "input_tokens": 345,
+        "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -87,8 +87,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 4789,
-        "output_tokens": 410,
+        "input_tokens": 5429,
+        "output_tokens": 813,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -97,8 +97,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 12588,
-        "output_tokens": 507,
+        "input_tokens": 15657,
+        "output_tokens": 378,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -107,8 +107,8 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 235,
-        "output_tokens": 16,
+        "input_tokens": 313,
+        "output_tokens": 4,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -117,8 +117,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 5385,
-        "output_tokens": 380,
+        "input_tokens": 6529,
+        "output_tokens": 898,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -127,8 +127,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 13154,
-        "output_tokens": 405,
+        "input_tokens": 16842,
+        "output_tokens": 937,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -137,8 +137,8 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 224,
-        "output_tokens": 4,
+        "input_tokens": 326,
+        "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -147,8 +147,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 5939,
-        "output_tokens": 263,
+        "input_tokens": 7739,
+        "output_tokens": 790,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -157,8 +157,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 13591,
-        "output_tokens": 189,
+        "input_tokens": 17944,
+        "output_tokens": 751,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -167,8 +167,8 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 187,
-        "output_tokens": 4,
+        "input_tokens": 365,
+        "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -177,8 +177,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 6329,
-        "output_tokens": 400,
+        "input_tokens": 8902,
+        "output_tokens": 839,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -187,8 +187,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 14118,
-        "output_tokens": 224,
+        "input_tokens": 19156,
+        "output_tokens": 561,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -197,7 +197,7 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 200,
+        "input_tokens": 343,
         "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
@@ -207,8 +207,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 6878,
-        "output_tokens": 451,
+        "input_tokens": 10077,
+        "output_tokens": 696,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -217,8 +217,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 14718,
-        "output_tokens": 396,
+        "input_tokens": 20188,
+        "output_tokens": 371,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -227,8 +227,8 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 278,
-        "output_tokens": 16,
+        "input_tokens": 327,
+        "output_tokens": 4,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -237,8 +237,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 7579,
-        "output_tokens": 246,
+        "input_tokens": 11072,
+        "output_tokens": 733,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -247,8 +247,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 15252,
-        "output_tokens": 938,
+        "input_tokens": 21258,
+        "output_tokens": 1443,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -257,8 +257,8 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 402,
-        "output_tokens": 16,
+        "input_tokens": 465,
+        "output_tokens": 4,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -267,8 +267,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 8279,
-        "output_tokens": 369,
+        "input_tokens": 12340,
+        "output_tokens": 444,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -277,8 +277,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 16037,
-        "output_tokens": 10357,
+        "input_tokens": 22199,
+        "output_tokens": 11766,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -287,7 +287,7 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 6044,
+        "input_tokens": 5910,
         "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
@@ -297,8 +297,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 16210,
-        "output_tokens": 62,
+        "input_tokens": 20323,
+        "output_tokens": 820,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -307,8 +307,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 23661,
-        "output_tokens": 289,
+        "input_tokens": 30558,
+        "output_tokens": 983,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -317,8 +317,8 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 285,
-        "output_tokens": 4,
+        "input_tokens": 537,
+        "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -327,8 +327,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 16520,
-        "output_tokens": 42,
+        "input_tokens": 21754,
+        "output_tokens": 21,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -337,8 +337,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 23951,
-        "output_tokens": 79,
+        "input_tokens": 31190,
+        "output_tokens": 613,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -347,7 +347,7 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 121,
+        "input_tokens": 390,
         "output_tokens": 4,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
@@ -357,8 +357,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 16613,
-        "output_tokens": 67,
+        "input_tokens": 22204,
+        "output_tokens": 17,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -367,8 +367,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 24069,
-        "output_tokens": 343,
+        "input_tokens": 31636,
+        "output_tokens": 96,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -377,8 +377,8 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 318,
-        "output_tokens": 16,
+        "input_tokens": 109,
+        "output_tokens": 4,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -387,8 +387,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 16994,
-        "output_tokens": 82,
+        "input_tokens": 22258,
+        "output_tokens": 39,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -397,8 +397,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 24465,
-        "output_tokens": 218,
+        "input_tokens": 31712,
+        "output_tokens": 83,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -407,7 +407,7 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 233,
+        "input_tokens": 124,
         "output_tokens": 4,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
@@ -417,8 +417,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 17272,
-        "output_tokens": 118,
+        "input_tokens": 22349,
+        "output_tokens": 26,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -427,8 +427,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 24779,
-        "output_tokens": 452,
+        "input_tokens": 31790,
+        "output_tokens": 71,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -437,8 +437,8 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 359,
-        "output_tokens": 16,
+        "input_tokens": 100,
+        "output_tokens": 4,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -447,8 +447,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 17762,
-        "output_tokens": 27,
+        "input_tokens": 22402,
+        "output_tokens": 20,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -457,8 +457,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 25178,
-        "output_tokens": 41,
+        "input_tokens": 31837,
+        "output_tokens": 112,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -477,8 +477,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 17801,
-        "output_tokens": 10,
+        "input_tokens": 22435,
+        "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -487,8 +487,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 25200,
-        "output_tokens": 32,
+        "input_tokens": 31866,
+        "output_tokens": 206,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -497,7 +497,7 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 88,
+        "input_tokens": 118,
         "output_tokens": 4,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
@@ -507,8 +507,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 17817,
-        "output_tokens": 17,
+        "input_tokens": 22499,
+        "output_tokens": 47,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -517,8 +517,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 25223,
-        "output_tokens": 127,
+        "input_tokens": 31961,
+        "output_tokens": 477,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -527,7 +527,7 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 96,
+        "input_tokens": 254,
         "output_tokens": 4,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
@@ -537,8 +537,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 17852,
-        "output_tokens": 21,
+        "input_tokens": 22754,
+        "output_tokens": 947,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -547,8 +547,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 25262,
-        "output_tokens": 37,
+        "input_tokens": 33116,
+        "output_tokens": 749,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -557,8 +557,8 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 90,
-        "output_tokens": 4,
+        "input_tokens": 342,
+        "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -567,8 +567,8 @@
       "agent": "expert",
       "model": "claude-sonnet-5",
       "usage": {
-        "input_tokens": 17885,
-        "output_tokens": 6,
+        "input_tokens": 24008,
+        "output_tokens": 715,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -577,8 +577,18 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 25280,
-        "output_tokens": 1,
+        "input_tokens": 34138,
+        "output_tokens": 570,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 230,
+        "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -587,8 +597,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 25280,
-        "output_tokens": 25,
+        "input_tokens": 34345,
+        "output_tokens": 10641,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -597,8 +607,8 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 87,
-        "output_tokens": 4,
+        "input_tokens": 7924,
+        "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -607,8 +617,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 25310,
-        "output_tokens": 11567,
+        "input_tokens": 44454,
+        "output_tokens": 7816,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -617,7 +627,7 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 9053,
+        "input_tokens": 5937,
         "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
@@ -627,8 +637,8 @@
       "agent": "interviewer",
       "model": "claude-opus-5",
       "usage": {
-        "input_tokens": 36786,
-        "output_tokens": 9586,
+        "input_tokens": 52035,
+        "output_tokens": 4824,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -637,8 +647,28 @@
       "agent": "classifier",
       "model": "claude-haiku-4-5-20251001",
       "usage": {
-        "input_tokens": 7411,
-        "output_tokens": 4,
+        "input_tokens": 3675,
+        "output_tokens": 16,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 56696,
+        "output_tokens": 3592,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 2704,
+        "output_tokens": 16,
         "cache_creation_input_tokens": 0,
         "cache_read_input_tokens": 0
       }
@@ -651,159 +681,159 @@
     },
     {
       "role": "assistant",
-      "content": "Good — that's enough for me to start. I'll ask you about your operation in your own words; the format side is my problem, not yours.\n\nBefore anything about how the plant is built, I want to know what the model has to be *for*. Two things to start:\n\n1. When your boss says \"test scheduling decisions before making them\" — what's a decision you'd actually want to test? Give me a real one you've argued about recently, not a general category.\n\n2. And when you compare two schedules today, what makes one better than the other in your eyes? I'm after the thing you'd actually point at — a number, a complaint you'd avoid, whatever it is."
+      "content": "Good — that's enough for me to know what I'm building toward. I'll interview you in your own words about how the plant actually runs, keep a running note of what I've got and what I still need, and hand you back a structured model at the end. I won't invent numbers; anything I have to assume I'll list separately so you can check it.\n\nLet me start with what the model is *for*, because everything else gets prioritised against that.\n\n**When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it in a model first?** Tell me the specific situation if you can.\n\nAnd alongside that: **when a schedule turns out to have been a bad one, how do you find out — what's the thing that goes wrong that you notice?**"
     },
     {
       "role": "user",
-      "content": "Okay, real one: two weeks ago I had a Meridian white order finishing on Line 2 Thursday afternoon, and then a batch of tint waiting behind it. My instinct was to let Line 2 sit idle for maybe an hour because I had a heads-up another same-family white order was about to drop in from a distributor, and doing them back to back would save us a full washdown. My boss's question was basically \"are you sure that's worth it, or are you just guessing?\" And honestly — I was guessing. That's the kind of thing I'd love to test: hold the line versus wash it down now, which one actually costs less over the week.\n\nAs for what makes one schedule better than another — first thing I look at is whether Meridian shipped on time, full stop, that's non-negotiable. After that it's changeover hours, because every hour the crew spends washing down is an hour not filling anything. And honestly I also just glance at how ugly the sheet looks — like, are there gaps where a line's sitting idle for no good reason. That last one's not a number, it's more a gut check, but it's real."
+      "content": "Okay, good question. Let me think of a real one.\n\nA couple weeks back Line 1's mill motor hiccuped — not the four-day disaster, just a few hours down — right when I had a specialty batch and a Meridian white order both needing to move. I had to decide on the spot whether to shift the specialty over to Line 3 and eat the requalification headache, or hold it and let the white slip behind on Line 2 instead. I did it by gut at the huddle — moved the specialty, kept the white going — but I genuinely don't know if that was the right call or if I just got lucky. That's the kind of thing I'd love to run twice and see which one bites me less.\n\nThe other recurring one is the idle-line-versus-washdown thing — do I sit Line 2 empty for an hour waiting on a same-family order, or just pay the three-hour washdown now. I make that call almost weekly and it's pure feel.\n\nAs for how I find out a schedule was bad — honestly, it's usually the huddle two days later, or a call from Meridian's account rep. Late orders are the loudest signal — someone above me hears about it before I do sometimes. Quieter version is the changeover crew looking wrecked by Thursday because I stacked too many family switches back to back. And every so often quality flags a scrap spike and I go \"oh, right, that was the week I rushed the ramp after a washdown.\""
     },
     {
       "role": "assistant",
-      "content": "That's a good, concrete decision — hold the line for a possible same-family order versus wash down now. I'll build the model so that's testable.\n\nTwo things about \"better\", then I'll get you to walk me through a job:\n\n1. Meridian on-time is non-negotiable — what does \"on time\" actually mean in practice? A ship date on the order, a truck appointment, a promised week? And what happens when one *does* go late — who feels it and how?\n\n2. Changeover hours versus a late non-Meridian order: if a schedule saved you, say, four changeover hours but made one distributor order two days late, would you take it? I'm trying to find out whether these trade against each other at all, or whether lateness for everyone else is just soft."
+      "content": "That's exactly the right kind of answer — two concrete recurring decisions, and three different ways badness shows up.\n\nLet me pin the purpose down before I ask about the plant itself.\n\n1. I'm hearing **two questions the model must answer**: *\"when a line goes down mid-run, do I reroute the affected job to another line and eat requalification, or hold it and let something else slip?\"* and *\"do I hold a line idle waiting for a same-family order, or pay the washdown now?\"* Is that a fair statement of both, in your words? And is there a third recurring call of that type that you'd want to test — anything around sequencing, or order acceptance, or overtime?\n\n2. You said you'd want to see \"which one bites me less.\" If I ran both versions of that Line 1 decision and handed you two sets of results — **what would you look at to say one was better?** Late orders, scrap, crew load, something else — and if one option gave you one late order and the other gave you a scrap spike, do you already know which way you'd lean, or does that depend?\n\n3. **How far ahead do you schedule, and at what resolution?** I want to know whether the model needs to be useful over a shift, a week, or a quarter."
     },
     {
       "role": "user",
-      "content": "Good questions, let me take them separately.\n\nOn \"on time\" for Meridian — it's a ship date they give us via the order, usually with a delivery window attached, like a specific dock appointment on their end. So it's not just \"shipped this week,\" it's \"shipped in time to hit that appointment,\" which usually means it needs to leave our dock a day ahead for freight. If we miss it, first thing is a fine — I don't see the number, that's commercial's problem, but I hear about it. Second thing, worse honestly, is they track our on-time percentage and if it drops too far they threaten to delist SKUs. That's happened to a competitor of ours, so it's not an empty threat, and it's why the rule is absolute — we don't even try to be clever about it.\n\nOn the trade-off — honestly, yes, I'd take that trade most of the time, four hours of changeover is real money and crew time, and a distributor slipping two days is usually just an annoyed phone call from our sales rep, not a fine. But \"most of the time\" is doing a lot of work in that sentence — if it's the same distributor slipping late for the third week running, that's different, they'll start asking for a discount. So it's soft, but it's not infinitely soft. I couldn't put a number on it though — that's genuinely a \"sit down with commercial\" conversation, nobody's ever made me quantify it."
+      "content": "Let me take those one at a time.\n\n**On the two decisions** — yes, that's fair, that's the two big ones. A third I'd add: **run-size / sequencing** — whether to split a big order into two runs to slot in a rush job, or batch several small orders of the same family together even if it means one of them ships a bit early and sits in the warehouse. I do that juggling every week on the sheet and I've never had a way to check if I'm leaving hours on the table.\n\nI wouldn't say overtime approval is mine to test — that's the ops director's call, though I do feed him the \"we'll miss X without it\" argument, so maybe that's a variant of the same question rather than a fourth one.\n\n**On what I'd look at to judge the two options** — first thing, always, is: did anything ship late, and to whom. A late order to Meridian is worse than three late orders to a small distributor, so it's not just a count, it matters *who*. After that, changeover hours lost and scrap. If one path gives me a late Meridian order and the other gives me a scrap spike — I'll take the scrap spike every time, no contest. Scrap costs money, a late Meridian order costs a relationship and a fine. So there is a rough pecking order in my head, I just don't have it written down as numbers — that's the bit I said I'd need to sit down with commercial for.\n\n**On horizon** — the sheet is a rolling weekly thing, built fresh every Monday against that week's demand book, but I'm constantly re-juggling it day to day as breakdowns and rush orders land. So really it needs to be useful at two grains: a full week, so I can see the whole book, but responsive enough to redo at shift-level when something breaks at 6am. A quarter's too far out — I don't plan that far, ERP just doesn't give me visibility past a few weeks anyway."
     },
     {
       "role": "assistant",
-      "content": "That's clear, and I'll record the trade-off as deliberately unquantified rather than invent a weight — I'll flag it as needing commercial, since you've told me exactly where the number would come from.\n\nNow let's get the structure. Take that Meridian white order from two weeks ago and walk me through it as a sequence — from the moment it lands on your desk to the moment it's off the dock. Keep it to the main steps, five or six; I'll dig into each one after."
+      "content": "Good. I've got three objectives now, a rough pecking order (late Meridian ≫ late small distributor > changeover hours ≈ scrap; and scrap spike beats a late Meridian order every time), and a two-grain horizon — a full week, re-runnable at shift level. The exchange rate in numbers is parked as needing commercial; I'll flag it rather than invent it.\n\nTwo more framing questions and then I want you to walk me through an actual order.\n\n1. **What's inside the model and what's outside?** Specifically: does it start when an order lands in your demand book, or earlier? Does it end when the batch is filled off the line, or does it follow through QC, packing, warehouse, shipping? And is raw material supply something you ever wait on, or is it always just there?\n\n2. **The accuracy bar.** If I gave you the model loaded with last week's demand book and it produced a schedule, **what would you look at to decide \"yes, that's basically our plant\" versus \"no, that's a toy\"?** Is there a week you could replay from memory or from the sheet?"
     },
     {
       "role": "user",
-      "content": "Sure, let me walk it through.\n\n1. **It lands in the demand book** — comes over from ERP on the weekly pull, SKU, quantity, due date, flagged Meridian so it jumps to the top of my attention.\n2. **I allocate it to Line 2** — that's not really a decision, Meridian whites always go to Line 2, that's just how it's done here.\n3. **It sits in the queue behind whatever's running** — depending what's ahead of it, sometimes I'll reorder things a bit so it doesn't get stuck behind a big changeover.\n4. **Changeover if needed, then it runs** — mix, mill, tint or straight through if it's a plain white, then fill and pack. For a white that's usually the more straightforward path.\n5. **It goes into QA hold** — every batch does, typically a few hours before it's released.\n6. **Once released, it's staged for shipping** — and that's when the truck appointment matters, because if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line.\n\nThat's the whole arc, really — desk to dock. The QA step is the one people don't think about when they're mad at scheduling; half the time a \"late\" order was actually sitting done in QA hold waiting for the lab to get to it."
+      "content": "**On scope:**\n\nStarting point — order lands in the demand book, that's the natural start, ERP hands it to me and it becomes a line on my sheet. I don't need the model reasoning about how orders get generated upstream, sales does whatever it does.\n\nEnd point — I'd say it ends when the batch clears QC hold and is released to the warehouse. What happens after that — trucks, warehouse slotting — isn't my problem, that's logistics' sheet, not mine. But QC hold has to be in there, because that four-hours-typical wait genuinely ties up my thinking about whether an order will make its due date, especially for specialty where it can be a full day. If a model ignored QC hold it would look like orders finish the moment they're filled, and that's just wrong — I've had orders filled on time and *still* gone late because the lab backed up on a Friday.\n\nMaterials — mostly it's just there, I don't sit and calculate feedstock. But it's not *never* an issue — resin slips maybe once a month and when it does it stalls the run and I have to shuffle around it. So I'd say: outside the model most of the time, but there needs to be some way for \"oh, the resin didn't show up\" to occasionally throw a wrench in, otherwise you're modelling a plant that never has a bad Tuesday.\n\n**On the accuracy bar:**\n\nHonestly, the first thing I'd check is boring but telling: does it get the *unwritten rules* right — does Meridian white actually land on Line 2, does it never send specialty to Line 2, does it respect that Line 3 isn't qualified for those two tint SKUs. If it violates any of that, I'll dismiss it in about ten seconds, doesn't matter how clever the maths is.\n\nSecond — does the changeover pattern look like our week, not a fantasy week. If it shows tint-to-white as quick and white-to-tint as the long one, I'll know someone got the plant backwards.\n\nThird, and this is the real test — I could take last week's actual book, run it through, and see whether the late orders it predicts are roughly the ones that *actually* went late. I remember last week pretty well: we had a Meridian order squeak through by a few hours, and a distributor order slid four days with a phone call and nobody blinked. If the model's version of last week says something wildly different — says Meridian went late, say, or doesn't flag the Line 1 tank issue that actually bit us — I'd say it's a toy. I can probably reconstruct two or three weeks like that from memory and the sheet if you want a real test case."
     },
     {
       "role": "assistant",
-      "content": "That QA point is exactly the kind of thing that gets left out of a first account — I'll come back to it properly.\n\nFirst let me pin down what you're actually scheduling. You said \"Meridian white order\", \"a batch of tint\", \"same-family white\". Three things:\n\n1. Is the thing you schedule the *order*, or does an order get broken into batches that could run at different times? What's the relationship?\n\n2. What are the families? You used \"same-family white\" as if it's a defined grouping — is that a formal thing on the SKU, or your judgment?\n\n3. And how many lines are there, besides Line 2?"
+      "content": "That accuracy bar is unusually useful — the unwritten rules first, then the changeover asymmetry, then a replay of last week. I'm noting all three as the acceptance test, and I'm noting the direction-dependence you just gave away: **tint→white quick, white→tint long**. I'll come back and check I've got that the right way round.\n\nNow let me walk one real case end to end.\n\n1. First, so I follow the right thing: **what's \"one\" for you — an order, a batch, a run?** If a customer order can be split across two runs, or several orders can go down as one run, I need to know which unit you actually track on the sheet.\n\n2. Then: **take that Meridian white order from last week — the one that squeaked through — and walk me through it.** From the moment it lands in your book to the moment it's released to the warehouse. Just tell it as it happened, including the boring steps; I'll stop you where I need detail."
     },
     {
       "role": "user",
-      "content": "1. Mostly the order *is* the batch, if it fits a reasonable run size — a lot of our orders are big enough that we just run the whole thing as one batch. But sometimes I'll split one: if a distributor orders more than makes sense in a single run, or if I need to interleave it with something more urgent, I'll chop it into two batches and run them at different times. So it's order-to-batch most of the time, but not a strict one-to-one — I have the freedom to split if I need to.\n\n2. The families are real, they're on the SKU — every product's either a base white, a tinted colour, or a specialty clear. That's not my judgment, that's how the SKU's classified in the system, it drives what changeover you need going in and out. \"Same-family\" just means two SKUs both being whites, or both being tints, so the changeover between them is the cheap quick-rinse kind instead of the expensive family-switch kind.\n\n3. Three lines total. Line 1's the old workhorse — slower but it's qualified for everything, including specialty. Line 2's the fast one, that's your big-volume runner. Line 3's the newest and quickest, but it's still being qualified product by product, so it can't run everything yet."
+      "content": "Ha — good catch, let me actually correct myself before we go further: I said it that way round out of habit, but hang on, let me think it through properly. Pigment carryover into a white is the disaster — a speck of tint ruins a batch of white. So it's **white → tint that's the quick one** (a bit of white residue in a tinted batch, who cares, it's getting colour anyway) and **tint → white that needs the full three-hour washdown**, because you cannot have any tint carryover into white. I had it backwards just now. Sorry — glad you flagged it instead of writing it down.\n\n**On the unit:** the sheet tracks at the **run** level, not the order. An order is a line in the demand book — SKU, quantity, due date — but what actually sits on the sheet as a block of time on a line is a run, and a run can be one order's worth or several small orders of the same SKU lumped together to clear the minimum-run-size bar. Occasionally a big order gets split into two runs if I need to interleave a rush job — that's the sequencing juggling I mentioned. So: orders are what demand gives me, runs are what I actually schedule, and I'm the one deciding the mapping between them week to week.\n\n**Walking the Meridian order:**\n\nIt landed in Monday's demand book — a decent-sized white order, due Friday close of business, which for Meridian really means Friday, no wiggle. I put it on Line 2, because Meridian white always goes there. On the sheet I slotted it Wednesday, because Line 2 had a tint run booked Tuesday and I didn't want back-to-back — tint before white means I'm looking at the long washdown, and I wanted that overnight rather than eating into the day.\n\nTuesday afternoon the tint run overran a bit — nothing dramatic, maybe an hour past what the sheet said — so the crew didn't get the washdown started until early evening instead of mid-afternoon. That's a three-hour job, so it ran into the night shift. Wednesday morning, line's clean, but we lost the ramp-up scrap at start of shift, and then the filler jammed for about forty minutes mid-morning — one of the routine jams, nothing scary. So the run itself finished later Wednesday than planned.\n\nIt went to QC hold Wednesday evening. Normally that's four-ish hours and it'd be released overnight, but the lab had a backlog from earlier in the week, so it didn't actually get signed off until Thursday midday. Released to the warehouse Thursday afternoon — comfortably ahead of the Friday deadline in the end, but it \"squeaked\" in my head because if the filler jam had been the four-hour kind instead of the forty-minute kind, or if QC's Thursday had been as backed up as Friday usually is, it wouldn't have made it."
     },
     {
       "role": "assistant",
-      "content": "Changeover is at the heart of the decision you want to test, so let's do it properly.\n\nYou've named two kinds: the quick rinse between same-family SKUs, and the full washdown on a family switch. For the **quick rinse between two whites on Line 2** — the exact case from two weeks ago:\n\n1. Typically, how long does it take, start to finish, before the next batch is filling?\n2. One time in ten it goes worse than — what?\n3. And one time in ten it's better than — what?\n\nGive me the crew time too if it differs from line downtime."
+      "content": "Thank you for correcting the direction — tint→white is the three-hour washdown, white→tint is the quick one. That's now recorded that way round, and I've thrown away my earlier note.\n\nThat walkthrough gave me the spine. Let me fill in the machinery inside it — three related things:\n\n1. **Within a run, does your sheet treat it as one block of time on the line, or are there distinct stages you track separately?** You mentioned a mill motor and a filler, which sounds like at least two things happening — is making the batch and filling it one continuous occupation of the line, or can one order be mixing while a different one is filling?\n\n2. **Who does the washdown?** Is there a dedicated changeover crew, how many of them, and can two lines be washing at the same time — or does one line's washdown block another's?\n\n3. **The QC lab** — is it one lab serving all three lines? Can it work on several batches at once, or is it one at a time, and is it staffed around the clock or only on shifts?"
     },
     {
       "role": "user",
-      "content": "For a straight white-to-white rinse on Line 2:\n\n1. Typically? Call it 25 minutes, start to finish, before the fill head's actually running clean product again.\n2. Worse case — one time in ten it drags to maybe 45 minutes, usually because the tech's tied up finishing something on another line first and there's a wait before they even start on Line 2.\n3. Better case — one time in ten, if the tech's standing right there and it's a genuinely easy one, 15 minutes and you're rolling again.\n\nCrew time and line downtime are basically the same thing here — it's quick enough that the tech's on it start to finish, no gap between \"crew starts\" and \"line stops.\" That's different from the big washdowns, where the line's down way longer than the crew's actually hands-on, because there's soak time and QA checks in between."
+      "content": "Good questions, and honestly the answers get at things I only half-think about because the sheet flattens them.\n\n**1. Within a run:** On the sheet it's one block of time — I put down \"Meridian order, Line 2, Wed 06:00–18:00\" and that's it, I don't sub-divide it. But physically, no, it's not one continuous thing happening in one spot. There's mix, then mill, then tint/letdown, then fill — four stages, and they're at different points on the line with small holding tanks between them. So in principle, while the back end of a batch is filling, the front end of the *next* batch could already be mixing, if there's product to feed it — it's a bit of a flow, not a single monolithic block. My sheet doesn't capture that at all, it just says \"Line 2 busy 06:00–18:00\" and moves on. Whether that's actually true — whether the line is fully occupied that whole window or there's slack — I genuinely couldn't tell you without going and watching it, which is part of why I said the sheet flatters reality.\n\nThe tanks between stages are exactly why I keep grumbling about Line 1's mill-to-fill tank — if fill is slow and the tank's small, mill has to stop and wait, and that's dead time my sheet never sees.\n\n**2. The changeover crew:** One crew, two techs, day shift, covers all three lines. So no, two lines can't wash down at once — if Line 1 and Line 3 both want a washdown Tuesday morning, one of them waits its turn. That's the thing I mentioned with Line 3 sitting clean but idle waiting on the crew — it happens more than I'd like. Outside day shift, if a changeover's needed on night shift... honestly that's rare, we try to schedule washdowns for when the crew's on, but I couldn't tell you what happens if one gets forced onto nights. Might be we call someone in. Might be it waits till morning. I'd have to check with the crew lead.\n\n**3. QC lab:** One lab, serves all three lines, two people. I don't know the mechanics of whether they can run two batches' tests in parallel or whether it's strictly one-at-a-time per person — I just know that by Thursday/Friday there's a queue and things that should take four hours take longer. They're day-shift as far as I know, maybe with someone covering into evening, but I don't think there's a night presence. That's another one I'm going on impression, not fact — worth you asking them directly if it matters to the model."
     },
     {
       "role": "assistant",
-      "content": "That distinction — line down longer than crew hands-on — matters, so let's get the washdown with both.\n\nFor a **family switch on Line 2**, say white to tint: typically how long is the line down, one time in ten worse than, one time in ten better than? And roughly how much of that is the tech actually hands-on?\n\nAlso: does it depend on direction — is tint-to-white the same as white-to-tint?"
+      "content": "Two deposits noted, both yours to check later: (a) what happens when a washdown is forced onto night shift — crew lead; (b) whether the lab runs batches in parallel and how far into the evening they cover — lab. I'll model something provisional and flag it.\n\nNow the thing you said you'd dismiss the model in ten seconds over: the lines and what may run where.\n\n1. **Give me the three lines and what distinguishes them** — capacity or speed, what each is qualified for, what physically differs. You've mentioned Line 1's mill motor and its small mill-to-fill tank, Line 2 as Meridian white's home, Line 3 as not qualified for two tint SKUs.\n\n2. **Give me the product families as you'd group them for scheduling.** You've said white, tint, specialty — is that the right cut, and are there others? What makes two things \"same family\" for the purposes of \"I could run these back to back without a washdown\"?\n\n3. **\"Meridian white always goes on Line 2\"** — is that a hard qualification, a customer requirement, or a habit? I want to know whether the model should treat it as a rule that can never break, or one you'd break under pressure."
     },
     {
       "role": "user",
-      "content": "It absolutely depends on direction — that's the thing people forget.\n\n**White to tint**, the easier direction: line's down typically about 45 minutes. Worse case, maybe an hour and a bit if the tech gets pulled away partway through. Better case, if everything's staged, maybe half an hour. Of that, the tech's hands-on for most of it — this one doesn't have much soak-and-wait, it's mostly just doing the work.\n\n**Tint to white** is the ugly one, because any pigment left behind ruins a white batch, so it's a full washdown. Typically about 3 hours, line down the whole time. Worse case — if it doesn't pass the visual check first time and they have to redo part of it — could stretch to 4, maybe a bit more. Better case, a clean fast one, maybe 2 hours if the crew's good and nothing complicates it. Hands-on time for the crew is actually less than the 3 hours suggests — there's real soak and rinse-cycle time where the tech's not standing there, they might duck off to start something on another line. I'd guess they're actually working maybe half of that, the rest is the line just being down waiting on the process.\n\nSo no, it is absolutely not symmetric, and it trips people up if they assume it is."
+      "content": "**1. The three lines:**\n\n- **Line 1** — the old workhorse. Slower overall, but the most flexible: it's qualified for everything, whites, tints, specialty, all of it. It's the one you send something to when nowhere else can take it. Its weak point is the mill-to-fill tank being small — if fill lags, mill backs up and stalls. Also home to the scary mill motor that occasionally takes days to fix.\n- **Line 2** — the fast line. Built for volume. Roughly twice Line 1's speed on whites, though — and I only realised this when you pushed me on it earlier — that gap seems to shrink for tints, I don't actually know why. Not piped for the clear specialty resins at all, so specialty simply cannot run there, full stop, that's physical not a preference.\n- **Line 3** — newest, quick, but still being qualified SKU by SKU. Two tint SKUs specifically aren't signed off yet — I couldn't tell you technically why, that's a QA/engineering decision from before my time on this role, I just know not to put them there.\n\n**2. Product families:**\n\nWhites, tints, specialty — that's the cut I use, and it's really about what a washdown has to deal with, not the product itself. \"Same family, no washdown\" for whites means any white after any white is just a quick rinse. Same for tint-after-tint, more or less, though I think some tint-to-tint switches (light to light) are gentler than others (light to dark, or vice versa) — I've never separated that out on the sheet, it's all just \"tint changeover, 20–30 min\" to me, but I wouldn't swear every tint-to-tint pair is really equal.\n\n**3. Meridian white on Line 2:**\n\nIt's not written down anywhere as a hard qualification like the specialty-can't-run-on-Line-2 thing. It's a habit that calcified into a rule — Line 2's fill area got audited by Meridian's people years back for a supplier qualification, and ever since, if a Meridian order ran anywhere else, and they ever found out, it'd be a whole conversation nobody wants to have. So it's soft in the sense that physically Line 1 could make that batch. But in practice I have never once put a Meridian order on Line 1, even under real pressure — the one time Line 2 was going to be down most of a day, I held the order and let it run late-ish rather than move it, because breaking that rule felt riskier than a few hours' delay. So: treat it as effectively hard. If the model wants to explore breaking it, that's a \"what if\" experiment, not something I'd sanction as a live scheduling option."
     },
     {
       "role": "assistant",
-      "content": "Good — asymmetric, and I've got both directions.\n\nTwo things to close out changeover:\n\n1. Specialty clear is the third family — what does going into and out of clear cost, on Line 1 since that's the one qualified for it? Same shape of answer: typical, one-in-ten worse, one-in-ten better, either direction if they differ.\n\n2. Do the white/tint numbers you just gave me hold on Line 1 and Line 3, or are they line-specific?"
+      "content": "Good — and I'll record the Meridian rule as effectively hard, breakable only as an explicit what-if.\n\nNow durations, which I need as ranges rather than single figures. Before I ask for numbers:\n\n1. **Is a run's length driven mainly by the quantity ordered, or do runs come in fairly standard sizes?** I want to know whether to ask you \"how fast is Line 2 in litres per hour\" or \"how long is a typical white run on Line 2.\"\n\n2. Whichever way you answer — **for the decisions you care about, is it the typical run length that matters, or the bad one?** You said the Meridian order \"squeaked\" because a jam could have been the four-hour kind. That suggests the tail is what bites you. Is that generally true?\n\n3. And a nag from your last answer: **you said Line 2 is roughly twice Line 1's speed on whites but the gap seems to shrink for tints.** Is there anyone who'd know why, or a place that would show it? I don't want to write \"twice as fast\" across the board if it's only true for whites."
     },
     {
       "role": "user",
-      "content": "1. Specialty is roughly the same both directions, unlike white/tint — call it 2 hours typical, either going in or coming out. Worse case, maybe 3 hours if it's coming out of clear and they're being extra careful about residue, since clear can be sneaky — you don't always see it the way you'd see pigment. Better case, maybe an hour and a half if it's a quick swap and the line was already fairly clean. Hands-on for the crew is most of that — specialty doesn't have the long soak cycles the tint-to-white washdown has, it's more just physically thorough cleaning because the product's thick and clingy.\n\n2. Honestly, I've mostly been quoting you Line 2 numbers because that's where the argument happened. I *think* the same rough shape holds on Line 1 — quick rinse cheap, tint-to-white expensive and slow, white-to-tint quicker — but I couldn't swear the minutes are identical. Line 1's older, the crew sometimes says it's fussier to get properly clean. Line 3 I genuinely don't have a good feel for, because it hasn't run enough different products yet to have built up war stories — it's still mostly running whatever it's been qualified for, which so far is mostly one or two SKUs. So if you need Line 3 numbers, that might be one where you're stuck assuming it's like Line 1 or Line 2 until we've got more history."
+      "content": "**1. Quantity vs. standard size:** It's driven by quantity, not standard batch sizes — the demand book gives me an order quantity in whatever units (drums, usually, sometimes bulk litres for the big Meridian stuff), and I convert that to run length using the rate for that product on that line. So it really is \"quantity divided by rate, plus fill-up time\" — which is why I'd answer \"how fast is Line 2\" more naturally than \"how long is a typical run,\" except that in conversation I usually think in run-hours because that's what goes on the sheet. If you want the raw rate, I'd have to go dig for it — I keep the sheet in run-hours already converted.\n\n**2. Typical vs. tail:** Yeah, you've got it right. For deciding *how much to promise* — whether an order fits in the week — I use typical, because if I planned for worst-case every time I'd never fit anything on the sheet and everyone would think I was hoarding capacity. But for deciding whether something's actually going to be *late*, it's always the tail that gets me: the jam that runs long, the washdown that overruns, the QC backlog on a Friday. The plan is built on typical; the disasters come from the tail. So if the model's going to be useful for the \"will this ship on time\" question, it needs the tail, not just an average — that Meridian order was fine on a typical week and nearly wasn't.\n\n**3. The Line 2 speed gap:** Honestly, no, I don't have a good answer, and I said \"funny, never thought about why\" earlier because I meant it — I've just always used \"2x on whites\" as my mental shorthand and never checked whether it holds for tints because tints don't move through Line 2 as often. If I had to guess who'd know, it'd be **process engineering** — they set the line rates originally and would know if something about tint viscosity or the letdown stage behaves differently machine to machine. Or possibly it's sitting in the historian data if someone actually pulled cycle times apart by product and stage, which — as I said — nobody's done. I wouldn't trust my own instinct on this one; flag it as something to verify, don't take \"twice as fast\" as gospel outside whites."
     },
     {
       "role": "assistant",
-      "content": "That's the right answer — I'd rather have \"I don't know\" than invented minutes. Here's what I'd assume unless you tell me otherwise, and I'll mark it as mine, not yours:\n\n- **Line 1**: same shape as Line 2, with all changeover durations scaled up — say 20% longer — on the strength of the crew's \"fussier to get properly clean\".\n- **Line 3**: same as Line 2 until history exists.\n\nBoth would be checked against the changeover logs, if the techs record start and finish. Does 20% sound like the right order of magnitude for Line 1, or is it more like double?\n\nSeparately — you just said something important in passing. The tech \"gets pulled away partway through\", \"might duck off to start something on another line\". How many changeover techs are there across the three lines?"
+      "content": "Understood — I'll carry \"2× on whites, unverified for tints\" as a flagged assumption with process engineering as the source to check.\n\nNow let me get actual numbers. You think in run-hours, so let's use those, and I'll ask each one as a low/high first, then typical.\n\nThink of a **white run on Line 2 of the size you'd typically see in the book** — say a Meridian-sized one like last week's:\n\n1. **What's the shortest and longest that run could plausibly take, from starting the line to the last drum filled?** Then: what's the typical? I'm after the whole occupation of the line, including the ramp-up scrap period you mentioned, but *not* including the washdown before it or QC after.\n\n2. **Roughly how many run-hours does a typical week's book add up to across all three lines** — and how many hours of line time do you actually have in a week? I want to know how tight you normally are, because that tells me how much the tails actually matter."
     },
     {
       "role": "user",
-      "content": "20% sounds about right, not double — it's more \"takes a bit longer to satisfy the visual check\" than \"fundamentally slower.\" Double would be if we were talking about the mill motor issue or something structurally different. So yeah, 20% longer on Line 1 feels like the right order of magnitude, not a multiplier like 2x.\n\nOn the crew — there's two techs on day shift covering all three lines between them. That's it. No dedicated tech per line. So if Line 1 and Line 3 both want a washdown at the same time, one of them waits, and that's the bit that actually causes grief at the huddle — it's not that the changeover itself is unpredictable, it's that the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line.\n\n(Sorry — I've just seen the time, I have the floor huddle in ten minutes. How much more do you need?)"
+      "content": "Okay, let's do the Meridian-sized white run on Line 2 first.\n\n**1. Run duration:** On a good day, that size order — call it the volume that took roughly a shift and a half on the sheet — runs about **10-11 hours** if nothing goes wrong, that's the number that's actually on the sheet for it. Shortest it's ever been, maybe 9 hours if the line just behaves and there's no jam at all — line's fast, it doesn't take much to knock a few hours off. Longest — if the filler has one of its worse jams, or there's more than one, I've seen that same-sized run stretch to 16, 18 hours. I did have one, maybe a year ago, that went nearly 24 because we had a jam *and* a short material stall on top of it, but I'd call that a genuine outlier, not \"the bad day,\" more \"the terrible day.\" So: typical **10-11**, shortest realistically **9**, and a bad-but-not-freak day is more like **14-16**. The 24-hour one I'd treat as a once-a-year tail, not the normal worst case.\n\n**2. Weekly book vs weekly capacity:** This one I can give you better because it's exactly the tension I live with every Monday. A typical week's book runs somewhere around **380-420 run-hours** total demand across the three lines, once I've converted everything. Capacity — Line 1 and Line 2 both run two shifts, so each is about 112 hours a week if fully utilised (16 hours a day times 7, though we don't always run weekends flat out — more like five and a half, six days realistically). Line 3's day-shift-only unless overtime's approved, so call it 56 hours normally. So total available is somewhere in the **270-300 run-hour** range in a normal week if I'm honest about weekends, versus a book that wants 380-420.\n\nWhich tells you immediately: I am *always* over capacity on paper, which is exactly why changeover hours and scrap matter so much — every hour lost to a washdown or a jam is an hour I don't have to spare, and why late orders happen at all. It's also why weekend and overtime running is a live lever, not a nice-to-have — Line 3 running an extra day, or Line 1/2 pushing into Sunday, is often the difference between the week working or not.\n\n(Sorry — I've just seen the time, I have the floor huddle in ten minutes. How much more do you need?)"
     },
     {
       "role": "assistant",
-      "content": "Ten minutes is enough for one thing, so let me tell you where we are and then ask the one that matters most.\n\n**What I have:** the two objectives, the six-step arc, three lines, three families, all the changeover numbers for Line 2 with spreads, the asymmetry, the two techs as a shared resource.\n\n**What's still missing** — roughly six or seven things, and two of them are load-bearing for the exact decision you want to test:\n\n- how long a batch actually *runs* (I have changeovers but no run times at all)\n- how the \"heads-up another order was about to drop\" actually reaches you — that's the trigger your whole hold-the-line decision hangs on\n- QA hold as a spread, and whether the lab is a shared resource like the techs\n- the order arrival pattern off the ERP weekly pull\n- run sizes and what splitting a batch costs\n- which SKUs Line 3 is actually qualified for\n- what breaks, and how often\n\nNone of that needs to happen now. My question for the remaining minutes, because it's the one I can't guess and it's the one that made you say \"grief at the huddle\":\n\n**When both lines want a washdown at once and one tech has to pick — what actually decides it?** Not the rule as posted. Think of the last time it happened: which line got the tech, and what was the reason?"
+      "content": "Ten minutes is useful — let me name what's still missing so you can choose, rather than pretend we're done.\n\n**Still open and load-bearing:**\n- **How often things go wrong** — I have durations for the filler jam, mill motor, resin slip, QC backlog, but almost no *rates*. You told me the tail is what makes orders late; without frequencies I can't produce tails.\n- **The two decision rules as you actually practice them** — the reroute-vs-hold rule and the idle-vs-washdown rule. I have the situations, not the rule you apply.\n- **Requalification** — \"eat the requalification headache\" is a cost I have no size for.\n- **How orders arrive** — rush orders, due-date patterns, which customers are Meridian-tier.\n- Run rates for Lines 1 and 3, and washdowns involving specialty.\n\nIf I get one thing now, I'd take the frequencies, because they're quick and nothing else substitutes for them. Three, same frame:\n\n1. **In a typical week, how many filler jams do you get across the plant** — and roughly what's the split between the forty-minute kind and the four-hour kind?\n2. **How often does Line 1's mill motor take the line down** — the multi-day sort, not the few-hour hiccup? Once a quarter, twice a year?\n3. **How often is QC actually backed up** enough that a four-hour hold becomes a day-plus — is it genuinely a Friday thing, or any day?\n\nAnswer what you can in the time; then tell me when we can pick up the rest."
     },
     {
       "role": "user",
-      "content": "Honestly, there's no posted rule at all — it's whoever's louder at the huddle, or whoever's about to actually run dry.\n\nLast time it happened, off the top of my head — Line 1 and Line 3 both wanted a washdown same morning. Line 3 got the tech first, not because it was more important, but because Line 3's changeover was the quick one and Line 1's was going to be the long tint-to-white slog anyway, so the thinking was \"knock out the fast one, get that line moving, then commit the tech to the long one.\" Line 1 sat clean-but-waiting for almost 40 minutes past when it could've started.\n\nIf you push me on the actual logic — it's mostly gut triage: whichever line has the more time-sensitive order behind it wins, and if that's a tie, whichever changeover is faster wins so you get a line moving sooner. Nobody writes this down, it's literally whoever's standing at the huddle table making the case loudest. I've been overruled by the ops director once when he wanted his pet SKU out the door.\n\nI do need to run — but this was useful, come back to the QA and run-time stuff next time, those are real gaps."
+      "content": "Quick ones, then I have to run.\n\n1. **Filler jams:** Most weeks, one or two. Almost all of them are the short kind, half hour to an hour, that's the bulk of them — I'd say four out of five. The multi-hour kind, the real headache, is more like once a month, maybe every six weeks. It's Line 2's filler mostly, that's the one I'd flag as jam-prone.\n\n2. **Mill motor, the multi-day sort:** Rare — I've seen it maybe three, four times in the years I've been doing this job. So call it once, maybe twice a year. When it happens it's ugly, but it's genuinely not a weekly worry the way the filler is.\n\n3. **QC backlog:** Mostly a Friday thing, yes — book's heaviest early week, orders queue up at the lab by Thursday/Friday, so nine times out of ten if I'm going to see a hold stretch past a day it's end of week. Early week it's rare, maybe one bad Monday or Tuesday a month if something upstream bunched up.\n\nThat's what I've got off the top of my head — day-to-day impression, not a logged rate, so treat it as roughly-right rather than exact.\n\nI've got to get to the huddle — same time tomorrow, or whenever suits you, we can pick up the decision rules and the requalification cost. That's probably the meatier half anyway."
     },
     {
       "role": "assistant",
-      "content": "You've stopped, so I'm not opening anything new. Here's the model as it stands, read back item by item, with the gaps named honestly. The two things you flagged — QA and run times — are the first things on the list when you're back.\n\n---\n\n# 1. The model\n\nVocabulary is yours throughout. Each slot shows the value **and** the precision actually obtained. `⚠` marks a slot the model demands and does not yet have.\n\n## Objectives\n\n**O1 — \"Hold the line versus wash it down now, which one actually costs less over the week\"**\n- *The question, in your words:* whether letting Line 2 sit idle for ~1 hour waiting on an anticipated same-family white order is cheaper over a week than washing down to the tint batch now. — **spelled out**\n- *Depends on:* E1 Order, E2 Batch, E3 Line, E4 Changeover tech, B1 ERP weekly pull, B2 mid-week order drop-in, A4/A5/A6 changeovers, A8 run batch, A9 QA hold, F1 main arc, P1, P3, P5, C2, C4.\n- *What \"better\" means:* changeover hours consumed over the week, subject to O2 holding absolutely. — **named, not quantified against O4** ⚠\n\n**O2 — \"Meridian shipped on time, full stop, that's non-negotiable\"**\n- *The question:* does every Meridian order leave the dock in time for its dock appointment. — **spelled out**\n- *\"On time\" =* ship date + delivery window given on the order, resolving to a specific dock appointment their end; must leave our dock **one day ahead** for freight. — **spelled out**\n- *Consequence of a miss:* a fine (amount not visible to you — commercial's) and a hit to the tracked on-time percentage; if that drops far enough, threatened SKU delisting — a competitor has been delisted, so it's treated as real. — **spelled out, unquantified** ⚠\n- *Depends on:* A9 QA hold, A10 stage & ship, C4, P1, P2, B3.\n\n**O3 — Changeover hours**\n- *The question:* how many crew-hours go into washdowns rather than filling. \"Every hour the crew spends washing down is an hour not filling anything.\" — **spelled out**\n- *Depends on:* A4, A5, A6, A7, E4, C2, P3.\n\n**O4 — \"How ugly the sheet looks\" — idle gaps with no good reason**\n- *The question:* are lines sitting idle for no good reason. — **spelled out**\n- *\"Better\" =* explicitly a gut check, not a number, \"but it's real\". — **your words: not quantified** ⚠ (IR-only; see §3)\n\n**Trade-off between O2, O3 and lateness for non-Meridian:** you would take 4 changeover hours saved against one distributor order two days late \"most of the time\" — a distributor slip is \"an annoyed phone call from our sales rep, not a fine\" — but the same distributor slipping three weeks running turns into a discount demand. So: soft, not infinitely soft, **and deliberately unquantified**. Deposit: you named the source — \"sit down with commercial\". Nobody has ever made you quantify it. ⚠\n\n## Entity types\n\n**E1 — Order (from the demand book)**\n- *Distinctions the process treats apart:* Meridian vs. non-Meridian (Meridian \"jumps to the top of my attention\", on-time absolute); family classification on the SKU. — **spelled out**\n- *State riding along:* SKU, quantity, due date + delivery window, Meridian flag, family (base white / tinted colour / specialty clear — a real field in the system, not your judgment). — **spelled out**\n- *How many / population shape:* ⚠ not obtained — arrival volume per weekly pull unknown.\n\n**E2 — Batch**\n- *Distinctions:* same three families as the order it came from. — **spelled out**\n- *Relationship to order:* \"mostly the order *is* the batch, if it fits a reasonable run size\"; you may split into two batches run at different times when a distributor orders more than makes sense in one run, or to interleave something more urgent. Not a strict one-to-one; the split is your discretion. — **spelled out**\n- *Population shape:* ⚠ run sizes not obtained; cost of a split not obtained.\n\n**E3 — Line** — a contended resource\n- *Distinctions:* **Line 1** — \"the old workhorse\", slower, qualified for everything including specialty, crew say it's \"fussier to get properly clean\". **Line 2** — the fast one, big-volume runner. **Line 3** — newest and quickest, still being qualified product by product, \"can't run everything yet\", so far mostly one or two SKUs. — **spelled out**\n- *State riding along:* which family the line is currently dirty with (this is what selects the changeover); qualification set. — **spelled out**\n- *How many:* 3. — **number**\n\n**E4 — Changeover tech** — a contended resource\n- *Distinctions:* none stated between the two techs. — **named**\n- *State riding along:* which line they're currently committed to; can be \"pulled away partway through\". — **spelled out**\n- *How many:* 2 on day shift, covering all three lines, no dedicated tech per line. — **number**\n\n**E5 — QA lab**\n- *Distinctions / state / population:* ⚠ nothing obtained beyond its existence and that it can be \"backed up on a Friday afternoon\". Whether it's a shared resource like the techs is an open question you and I both flagged.\n\n## Boundary conditions\n\n**B1 — ERP weekly pull into the demand book**\n- *Starting state:* orders arrive over from ERP on the weekly pull, carrying SKU, quantity, due date, Meridian flag. — **spelled out**\n- *Arrival pattern:* ⚠ **not obtained** — no volume, no spread, no within-week shape. Demanded as a spread.\n\n**B2 — Mid-week order drop-in (\"another same-family white order was about to drop in from a distributor\")**\n- *Starting state / pattern:* ⚠ **not obtained.** This is the trigger the whole of O1 hangs on and I have only the one anecdote: you had \"a heads-up\". How that heads-up reaches you, from whom, how far ahead, and how often it turns out to be right are all unknown. Demanded as a spread; currently zero.\n\n**B3 — Meridian dock appointment**\n- *Pattern:* ship date with a delivery window on the order, resolving to a specific dock appointment their end. — **spelled out**\n- *Distribution of lead time:* ⚠ not obtained.\n\n**B4 — Tech availability calendar**\n- ⚠ only \"two techs on day shift\" obtained. Whether there is any night/weekend changeover coverage was never asked.\n\n**B5 — Line 3 qualification set at start of run**\n- ⚠ \"mostly one or two SKUs\" — **not spelled out**; which SKUs is unknown.\n\n## Activities\n\n**A1 — Lands in the demand book** — *needs:* the weekly ERP pull. *Produces:* an Order in the book, Meridian-flagged or not. *Performed by:* ERP / not attended. *Duration:* n/a (instantaneous receipt). **spelled out**\n\n**A2 — Allocate to a line** — *needs:* an order in the book. *Produces:* order assigned to a line. *Performed by:* you. *Duration:* not a scheduling constraint; \"not really a decision\" for Meridian whites. **spelled out** (rule in P1)\n\n**A3 — Reorder the queue** — *needs:* an order sitting behind others. *Produces:* changed run sequence. *Performed by:* you. *Rule:* P4. — **spelled out**\n\n**A4 — Quick rinse (same family, e.g. white → white) on Line 2**\n- *Needs:* line free, previous batch off, a tech available, next SKU same family. *Produces:* line clean for next batch, fill head running clean product.\n- *Performed by:* 1 changeover tech. — **named**\n- *Duration (line down):* typical **25 min**; one-in-ten worse **45 min** (tech tied up finishing on another line, so a wait before they even start); one-in-ten better **15 min** (tech standing right there, genuinely easy one). — **spread**\n- *Crew hands-on:* same as line down — \"no gap between crew starts and line stops\". — **spelled out**\n- *Varies by type?* Family pair, yes (that's what selects A4 vs A5/A6/A7). By line: ⚠ see ledger #1, #2.\n\n**A5 — Changeover white → tint on Line 2** (\"the easier direction\")\n- *Duration (line down):* typical **45 min**; worse **\"an hour and a bit\"**; better **~30 min** if everything's staged. — **spread** (see ledger #3 for my numeric reading of \"an hour and a bit\")\n- *Crew hands-on:* \"most of it — doesn't have much soak-and-wait, it's mostly just doing the work\". — **spelled out qualitatively**, ledger #4 for the fraction\n- *Cause of the worse tail:* tech gets pulled away partway through. — **spelled out**\n\n**A6 — Changeover tint → white on Line 2 — the full washdown** (\"the ugly one\")\n- *Needs:* as A4, plus a passing visual check before release to production.\n- *Duration (line down):* typical **~3 h**; worse **4 h, \"maybe a bit more\"** — when it doesn't pass the visual check first time and they redo part of it; better **~2 h** with a good crew and nothing complicating. — **spread**\n- *Crew hands-on:* \"maybe half of that\" — real soak and rinse-cycle time where the tech isn't standing there and \"might duck off to start something on another line\". — **spelled out qualitatively**, ledger #4\n- *Rationale:* \"any pigment left behind ruins a white batch\". — **spelled out**\n- **Asymmetry is load-bearing:** white→tint ≠ tint→white, \"it trips people up if they assume it is\". — **spelled out**\n\n**A7 — Changeover into / out of specialty clear, on Line 1**\n- *Duration (line down):* typical **2 h**, roughly the same both directions \"unlike white/tint\"; worse **3 h**, especially coming out of clear, \"clear can be sneaky — you don't always see it the way you'd see pigment\"; better **1.5 h** on a quick swap with the line already fairly clean. — **spread**\n- *Crew hands-on:* \"most of that\" — no long soak cycles; it's physically thorough cleaning because the product's thick and clingy. — **spelled out qualitatively**, ledger #4\n\n**A8 — Run the batch** — mix, mill, tint (or straight through if it's a plain white), fill, pack. \"For a white that's usually the more straightforward path.\"\n- *Needs:* clean line, batch released to run. *Produces:* filled and packed batch. — **spelled out**\n- *Performed by:* ⚠ line operators not elicited.\n- *Duration:* ⚠ **nothing obtained.** Demanded as a spread, per family and per line. This is the largest single hole in the model — O1 is a question about a *week*, and without run times there is no week.\n\n**A9 — QA hold and release** — every batch goes through it.\n- *Needs:* packed batch. *Produces:* released batch, or (presumably) something else on failure — ⚠ failure path never asked.\n- *Performed by:* the lab. *Duration:* **\"typically a few hours\"** — an honest figure at the wrong precision; demanded as a spread. ⚠\n- *Known failure mode:* \"if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line\"; \"half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it.\" — **spelled out qualitatively**; the rate and the queueing mechanism are ⚠.\n\n**A10 — Stage for shipping / ship** — *needs:* QA release. *Produces:* order off the dock. *Timing constraint:* C4. — **spelled out**; duration ⚠.\n\n**A11 — Tech pulled away mid-changeover** (event, not step) — named by you as the cause of the worse tail on A4 and A5. *Rate:* ⚠ not obtained separately — currently only implicit in the one-in-ten tails.\n\n**A12 — Washdown fails the visual check, part redone** (event, not step) — named as the cause of the 4 h tail on A6. *Rate:* ⚠ not obtained separately.\n\n## Ordering / flow\n\n**F1 — The main arc, desk to dock** — **spelled out**, your six steps:\ndemand book → allocate to line → queue behind what's running (reorderable) → changeover if needed → run (mix, mill, tint-or-straight-through, fill, pack) → QA hold → release → stage → ship.\n\n**F2 — Order-to-batch split** — an order may become two batches run at different times. *Decided by:* you, on run size or urgency-interleaving. — **spelled out as a rule**; the *cost* of a split (extra changeovers, extra loss) ⚠ never asked.\n\n**F3 — Which changeover applies** — selected by (family currently on the line, family of the next batch, line). Same family → A4. White→tint → A5. Tint→white → A6. Into/out of specialty → A7. — **spelled out**\n\n## Policies\n\n**P1 — \"Meridian whites always go to Line 2, that's just how it's done here\"** — *practiced.* Overrides: ⚠ none asked. — **spelled out**\n\n**P2 — Meridian on-time is absolute** — \"we don't even try to be clever about it\". *Rationale:* fine, plus tracked on-time % and a delisting threat that has been carried out on a competitor. *Overrides:* none — that's the point. — **spelled out**\n\n**P3 — Who gets the tech when two lines want one** — *practiced, and there is no prescribed form:* \"there's no posted rule at all.\"\n- The rule as practiced: whichever line has the **more time-sensitive order behind it** wins; if that's a tie, **whichever changeover is faster** wins, \"so you get a line moving sooner\". In the room it resolves as \"whoever's louder at the huddle, or whoever's about to actually run dry\".\n- *Borderline case on record:* Line 1 and Line 3 both wanted a washdown the same morning. Line 3 got the tech first because Line 3's was the quick one and Line 1's was the long tint→white slog anyway — knock out the fast one, get that line moving, then commit the tech to the long one. Line 1 sat clean-but-waiting ~40 minutes past when it could have started.\n- *What overrides it:* the ops director, who has overruled you once, wanting \"his pet SKU out the door\". — **spelled out**\n- *Rationale:* two techs, three lines, so \"the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line\" — that's the grief at the huddle, not changeover variability.\n\n**P4 — Reorder the queue so a job doesn't get stuck behind a big changeover** — *practiced, yours.* — **spelled out**; overrides ⚠ not asked.\n\n**P5 — Hold the line for an anticipated same-family order** — the decision under test. As practiced two weeks ago: on a heads-up that a same-family white was about to drop, let Line 2 sit idle ~1 h rather than wash down to the waiting tint, to save a full washdown. Your own account: \"I was guessing.\" — **spelled out as an instance**; the trigger condition (B2) and the decision threshold are ⚠.\n\n**P6 — Batch split discretion** — \"I have the freedom to split if I need to.\" — **spelled out**\n\n## Constraints\n\n**C1 — Line qualification** — Line 1 qualified for everything including specialty; Line 3 qualified product-by-product, \"can't run everything yet\"; Line 2 ⚠ never stated. *Consequence when hit:* the batch can't go on that line. — **partially spelled out** ⚠\n\n**C2 — Two techs, three lines** — *consequence when hit:* one line waits, clean-but-idle (40 min in the case on record). — **spelled out**\n\n**C3 — Tint → white requires a full washdown with a passing visual check** — *consequence:* pigment left behind ruins a white batch. — **spelled out**\n\n**C4 — Meridian must leave our dock a day ahead of the dock appointment** — *consequence:* fine + on-time % + delisting exposure. — **spelled out**\n\n**C5 — Every batch goes through QA hold before release** — *consequence:* no batch ships unreleased. — **spelled out**\n\n## Dynamics\n\n**None.** Nothing you described evolves continuously while nothing discrete happens. Soak time inside A6 is dead time within an activity, not a state variable that crosses a threshold. I am deliberately not inventing one.\n\n## Data bindings *(named only — these project to nothing today)*\n\nChangeover logs (tech start/finish per changeover — the check on ledger #1 and #2); ERP demand book (B1 arrival pattern); QA release timestamps (A9); Meridian on-time percentage (O2). — **named**\n\n## Validation criteria\n\n⚠ **None obtained.** I never asked how you'd know the model was right. It belongs at the top of the next session, next to run times.\n\n---\n\n# 2. Assumption ledger\n\nEverything here is mine, not yours.\n\n| # | Assumption | Why | How to check |\n|---|---|---|---|\n| 1 | Line 1 changeover durations = Line 2 × 1.2, all types | You said Line 1 is \"fussier to get properly clean\" and, when I proposed 20%, that it \"sounds about right, not double\" — but you explicitly could not swear the minutes. The 1.2 factor is mine. | Changeover logs, if techs record start and finish; compare Line 1 vs Line 2 for the same family pair. |\n| 2 | Line 3 changeover durations = Line 2 | You said Line 3 has no war stories and \"you're stuck assuming it's like Line 1 or Line 2 until we've got more history\". Choosing Line 2 rather than Line 1 is mine. | As #1, once Line 3 has run enough different products. |\n| 3 | \"An hour and a bit\" (A5 worse) = 70 min; \"4, maybe a bit more\" (A6 worse) = 4.5 h | Numeric reading of your words so the spread is usable. | Ask you to confirm or correct the two figures. |\n| 4 | Crew hands-on fractions: A4 = 1.0 (yours, stated); A5 = 0.8; A6 = 0.5; A7 = 0.8 | You said \"most of it\", \"maybe half of that\", \"most of that\". A6's 0.5 is close to your words; the two 0.8s are mine. | Changeover logs vs. tech time records; or ask the techs directly. |\n| 5 | No changeover happens outside day shift | You said \"two techs on day shift covering all three lines\". Whether there's any other coverage was never asked. | One question to you. |\n| 6 | Every batch's changeover requires exactly one tech (not two) | You always spoke of \"the tech\" singular. | One question to you. |\n| 7 | A6's redo-after-failed-visual-check is inside the 4 h tail rather than a separate event with its own rate | Simplification so the spread stands alone; you described it as the *cause* of the tail. | Ask how often the visual check fails first time. |\n\n---\n\n# 3. What this model leaves out, and what's still unknown\n\n**Deliberately left out.**\n- **Queues and waiting states** are not modelled as things in their own right — the wait behind a running batch, the wait for a tech, the wait in QA hold. They fall out of the activities either side of them. The 40-minute clean-but-waiting on Line 1 is a *result* the model should produce, not an input.\n- **The commercial layer** — the fine, the on-time percentage, the delisting mechanism. C4 and O2 encode the hard deadline; the money behind it is out of scope because it's out of your sight.\n- **Who ran which changeover** — the two techs are interchangeable, since you drew no distinction between them.\n\n**Things the model cannot carry, that I'm keeping in words so they aren't lost.**\n- **O4, \"how ugly the sheet looks.\"** A real criterion you use, explicitly not a number. It can be approximated as line idle hours, but that approximation is mine, not yours, and I haven't made it.\n- **The O2/O3/lateness trade-off weight.** Genuinely unquantified, with the source named: commercial. Without it, the model can report changeover hours and lateness separately but cannot rank two schedules that trade one for the other.\n- **The huddle.** \"Whoever's louder at the huddle\" and the ops director's pet-SKU override are the real P3 in the room. The triage logic you gave me — time-sensitivity first, faster-changeover as tiebreak — is compilable; loudness and the override are not, and any run of this model will be *quieter and more rational* than your plant. That gap is worth remembering when the results look tidy.\n- **Ledger #1–#4** are load-bearing for any result involving Line 1 or Line 3. Right now O1 is only genuinely answerable for Line 2.\n\n**Open slots, in the order I'd close them.**\n1. **A8 run duration** — nothing at all, per family and per line, as a spread. O1 asks about a week; run time is most of a week.\n2. **B2, the drop-in and the heads-up** — how the warning reaches you, how far ahead, and how often it's right. P5 is the decision under test and its trigger is currently an anecdote.\n3. **A9 QA hold** — \"a few hours\" is a figure at the wrong precision. And whether the lab is a shared resource with a queue, like the techs — because by your own account that's where lateness actually comes from.\n4. **B1** — orders per weekly pull, and the within-week shape.\n5. **E2 / F2** — typical run sizes, and what a split actually costs in extra changeovers.\n6. **B5 / C1** — which SKUs Line 3 is qualified for, and whether Line 2 has restrictions.\n7. **Breakage and interruptions** — you mentioned \"the mill motor issue\" in passing as an example of something structurally different. I never asked what breaks, how often, or for how long.\n8. **Validation** — how you'd know the model is right.\n\n**One caution on the format.** I've built the model; the Petri-net scaffold and the code obligations are derived from it by the tooling, not written by me. I'm not claiming this loads or runs as-is — the run-duration hole alone would stop it."
+      "content": "Understood — go to your huddle. I won't open anything new. Here's where we got to, read back so you can correct it, plus exactly what I'll ask tomorrow.\n\n**Stopping outcome: `expert-stopped` — partial model with open slots.** The structural floor is met (objectives, entity types, activities, flow all present), but none of the three objectives has a complete dependency slice yet. The biggest holes are the two decision rules themselves — which is the meatiest half, as you said.\n\n---\n\n# 1. The model as it stands\n\nEvery value below is at the grade you actually gave it. Where I asked interval-first (low/high, then typical) I've said so.\n\n## Objectives\n\n| ID | The question, in your words | Depends on | \"Better\" |\n|---|---|---|---|\n| **OBJ-1 Reroute or hold** | *\"whether to shift the specialty over to Line 3 and eat the requalification headache, or hold it and let the white slip behind on Line 2\"* — run it twice and see which one bites me less | ET-Line, ET-Order, A-Mill-motor-failure, A-Requalification, POL-Reroute-or-hold, C-Line-qualifications, POL-Meridian-Line-2 | Ranked, not numeric — see below |\n| **OBJ-2 Idle or washdown** | *\"do I sit Line 2 empty for an hour waiting on a same-family order, or just pay the three-hour washdown now\"* — a call *\"almost weekly and it's pure feel\"* | A-Washdown-tint-to-white, A-Ramp-up-scrap, ET-Changeover-crew, POL-Idle-vs-washdown, BC-Demand-book | Ranked, not numeric |\n| **OBJ-3 Run size & sequencing** | *\"whether to split a big order into two runs to slot in a rush job, or batch several small orders of the same family together even if it means one of them ships a bit early and sits in the warehouse\"* — *\"I've never had a way to check if I'm leaving hours on the table\"* | OF-Order-to-run-mapping, C-Minimum-run-size, A-Washdown-*, A-Ramp-up-scrap, BC-Demand-book | Ranked, not numeric |\n\nNoted but **not** an objective you own: overtime approval — *\"that's the ops director's call, though I do feed him the 'we'll miss X without it' argument… maybe that's a variant of the same question rather than a fourth one.\"*\n\n**What \"better\" means** — grade: *spelled out as a ranking, numeric weights absent.*\n1. Did anything ship late, **and to whom** — *\"a late order to Meridian is worse than three late orders to a small distributor, so it's not just a count, it matters who.\"*\n2. Changeover hours lost.\n3. Scrap.\n- Stated trade: *\"a late Meridian order and… a scrap spike — I'll take the scrap spike every time, no contest. Scrap costs money, a late Meridian order costs a relationship and a fine.\"*\n- Exchange rate in currency: **open**, deposit = *\"sit down with commercial.\"*\n\n**Horizon** (grade: spelled out): rolling week built fresh Monday against that week's demand book, re-runnable at shift grain when something breaks at 6am. *\"A quarter's too far out.\"*\n\n**Boundary** (grade: spelled out): starts when an order lands in the demand book from ERP; ends when the batch **clears QC hold and is released to the warehouse**. Trucks/warehouse slotting excluded (*\"logistics' sheet, not mine\"*). QC hold is explicitly **in** scope — *\"I've had orders filled on time and still gone late because the lab backed up on a Friday.\"* Feedstock excluded except that resin slips must be representable — *\"otherwise you're modelling a plant that never has a bad Tuesday.\"*\n\n## Validation criteria\n\n| ID | Criterion | Grade |\n|---|---|---|\n| VC-1 | The unwritten rules hold: Meridian white lands on Line 2; specialty never on Line 2; Line 3 never gets the two unqualified tint SKUs. *\"If it violates any of that, I'll dismiss it in about ten seconds.\"* | spelled out |\n| VC-2 | Changeover asymmetry the right way round: **tint→white is the long one, white→tint is quick.** *\"If it shows tint-to-white as quick… someone got the plant backwards.\"* | spelled out |\n| VC-3 | Replay last week's book; predicted late orders roughly match actual — Meridian squeaked through by a few hours, a distributor order slid four days with a phone call and nobody blinked, and the Line 1 tank issue bit us. You can reconstruct two or three such weeks. | spelled out |\n\n## Entity types\n\n| ID | Type | Distinctions that matter | State it carries | How many |\n|---|---|---|---|---|\n| ET-1 | **Order** (a line in the demand book) | SKU; quantity (drums, or bulk litres for big Meridian); due date; customer — Meridian-tier vs small distributor | family (white / tint / specialty); due date hardness | ~380–420 run-hours of demand per week *(range)* |\n| ET-2 | **Run** (a block on the sheet) | the unit you actually schedule; one order's worth, or several small same-SKU orders lumped to clear minimum run size; a big order can be split into two runs | line assignment; family; scheduled window | derived from ET-1 by your weekly mapping |\n| ET-3 | **Line** | see below | current/last family (sets changeover); qualification set; up/down | 3 |\n| ET-4 | **Changeover crew** | one crew, two techs, day shift, all three lines | busy/free | 1 crew *(contended)* |\n| ET-5 | **QC lab** | one lab, two people, all three lines | queue depth | 1 lab, 2 people *(contended; parallelism unknown)* |\n| ET-6 | **Stage within a line** | mix → mill → tint/letdown → fill, with small holding tanks between | tank level (see D-1) | 4 stages per line |\n\n**The three lines** (grade: spelled out qualitatively; rates only partly numeric)\n\n- **Line 1** — *\"the old workhorse… slower overall, but the most flexible: qualified for everything.\"* The one you send something to when nowhere else can take it. Weak point: small mill-to-fill tank — if fill lags, mill backs up and stalls. Home of the mill motor. Two shifts.\n- **Line 2** — *\"the fast line. Built for volume.\"* Roughly 2× Line 1 on whites; **that gap \"seems to shrink for tints\" and you explicitly asked me not to take 2× as gospel outside whites.** Not piped for clear specialty resins — *\"specialty simply cannot run there, full stop, that's physical not a preference.\"* Jam-prone filler. Two shifts.\n- **Line 3** — *\"newest, quick, but still being qualified SKU by SKU.\"* Two tint SKUs not signed off. Day shift only unless overtime approved.\n\n**Families** (grade: spelled out, with a flagged sub-distinction): whites / tints / specialty — *\"it's really about what a washdown has to deal with, not the product itself.\"* Caveat you gave: *\"I wouldn't swear every tint-to-tint pair is really equal\"* — light-to-light may be gentler than light-to-dark. Never separated on the sheet.\n\n## Boundary conditions\n\n| ID | What | Value | Grade |\n|---|---|---|---|\n| BC-1 | Demand book | Built fresh Monday from ERP; ~380–420 run-hours/week; rush orders land mid-week | range for volume; **arrival shape for rush orders open** |\n| BC-2 | Line calendar | L1 & L2 two shifts = 16h/day nominal ≈ 112h/wk, *\"though we don't always run weekends flat out — more like five and a half, six days realistically\"*; L3 day shift ≈ 56h unless OT. Total realistic **270–300 run-hours** | range |\n| BC-3 | Changeover crew calendar | Day shift only. Night behaviour: **unknown** — *\"Might be we call someone in. Might be it waits till morning.\"* | open, deposit = crew lead |\n| BC-4 | QC lab calendar | Day shift, *\"maybe with someone covering into evening,\"* believed no night presence — *\"impression, not fact\"* | open, deposit = the lab |\n| BC-5 | Resin supply | *\"mostly it's just there\"*; slips **~once a month**, stalls the run | rate: range; stall duration: open |\n| BC-6 | Structural over-commitment | Book (380–420) always exceeds capacity (270–300). *\"I am always over capacity on paper, which is exactly why changeover hours and scrap matter so much.\"* | spelled out |\n\n## Activities\n\n| ID | Activity | Duration | Rate | Mode-change loss | Grade / notes |\n|---|---|---|---|---|---|\n| A-1 | **Run — Line 2, white, Meridian-sized** (start of line to last drum filled, incl. ramp-up, excl. washdown and QC) | shortest realistically **9h**; typical **10–11h**; bad-but-not-freak **14–16h**; freak ~**24h** (jam + material stall), *\"once-a-year tail, not the normal worst case\"* | n/a (step) | — | **spread-equivalent**, interval-first protocol. Deciles not explicitly stated. **Varies by line/product: not yet asked (P07 open)** |\n| A-2 | **Washdown, tint→white** | **3 hours** | n/a | — | **number**, not spread. You mention *\"the washdown that overruns\"* as a tail source — overrun spread **open** |\n| A-3 | **Changeover, white→tint** | *\"a bit of white residue in a tinted batch, who cares\"* — quick | n/a | — | **named only, no number** |\n| A-4 | **Changeover, tint→tint** | **20–30 min** | n/a | — | range. Light/dark sub-split suspected, never measured |\n| A-5 | **Changeover involving specialty** | — | — | — | **entirely open** |\n| A-6 | **Ramp-up after washdown** | — | — | scrap; *\"that was the week I rushed the ramp after a washdown\"* → scrap spike | **named as a real loss, magnitude open (P02)** |\n| A-7 | **QC hold** | typical **~4h**; specialty *\"can be a full day\"*; with backlog, a day-plus (last week: Wed evening → Thursday midday) | — | — | typical + qualitative tail |\n| A-8 | **Filler jam** | short kind **0.5–1h** (*\"four out of five\"*); long kind **multi-hour**, e.g. the 4-hour kind | **1–2 per week plant-wide**; long kind **once a month to every 6 weeks**; *\"Line 2's filler mostly\"* | — | rate: range; duration: range. Your caveat: *\"day-to-day impression, not a logged rate\"* |\n| A-9 | **Line 1 mill motor failure, multi-day** | *\"the four-day disaster\"* — days | **1–2 per year** (*\"three, four times in the years I've been doing this job\"*) | — | rate: range; duration: single anecdote |\n| A-10 | **Line 1 mill motor hiccup, hours** | *\"a few hours\"* | **open** | — | the recent one that triggered OBJ-1 |\n| A-11 | **Resin stall** | open | ~once a month | — | see BC-5 |\n| A-12 | **Requalification** (moving specialty to a line) | **open** | n/a | *\"eat the requalification headache\"* | **load-bearing for OBJ-1, entirely unsized** |\n| A-13 | **Release to warehouse** | end of scope | — | — | terminal |\n\n## Ordering / flow\n\n- **OF-1 (spelled out):** Order lands in demand book → scheduler maps orders to runs → run placed on a line in a week slot → *if incoming family ≠ line's current family, changeover first* → run executes (mix → mill → tint/letdown → fill, flowing, with holding tanks between; next batch's front end can start while this batch's back end fills) → QC hold → release to warehouse.\n- **OF-2 order↔run mapping (spelled out qualitatively):** lump several small same-SKU orders to clear the minimum run size; split a big order into two runs to interleave a rush job. Split cost = an extra changeover + extra ramp-up scrap. Minimum run size: **unquantified**.\n- **OF-3 line-choice branch (partly spelled out):** decided by qualification constraints C-1/C-2 plus POL-1; the residual discretion is exactly OBJ-1 and is **open**.\n- **OF-4 blocking (spelled out, unquantified):** on Line 1, if fill is slow and the mill-to-fill tank is small, *\"mill has to stop and wait, and that's dead time my sheet never sees.\"*\n- **Known model/reality gap you volunteered:** the sheet records \"Line 2 busy 06:00–18:00\" and *\"doesn't capture that at all\"* — whether the line is genuinely occupied the whole window *\"I genuinely couldn't tell you without going and watching it.\"*\n\n## Policies\n\n| ID | Policy | As practiced | Overrides |\n|---|---|---|---|\n| POL-1 | **Meridian white runs on Line 2** | Habit calcified into a rule after Meridian audited Line 2's fill area for supplier qualification. *\"I have never once put a Meridian order on Line 1, even under real pressure\"* — when Line 2 was down most of a day you **held the order and let it run late-ish**. Physically Line 1 could do it. | *\"Treat it as effectively hard.\"* Breakable only as an explicit what-if experiment, *\"not something I'd sanction as a live scheduling option.\"* |\n| POL-2 | **Long washdown scheduled overnight** | *\"tint before white means I'm looking at the long washdown, and I wanted that overnight rather than eating into the day\"* | not asked |\n| POL-3 | **Washdowns scheduled to when the crew is on** | *\"we try to schedule washdowns for when the crew's on\"* | night case unknown (BC-3) |\n| POL-4 | **Avoid stacking family switches** | signalled by *\"the changeover crew looking wrecked by Thursday because I stacked too many family switches back to back\"* | not asked |\n| POL-5 | **Reroute vs hold** | **OPEN — the core of OBJ-1** | |\n| POL-6 | **Idle vs washdown** | **OPEN — the core of OBJ-2** | |\n| POL-7 | **Changeover crew contention** — who wins when two lines want a washdown | **OPEN.** Observed symptom only: *\"Line 3 sitting clean but idle waiting on the crew — it happens more than I'd like\"* | |\n| POL-8 | **QC lab queue discipline** | **OPEN** | |\n| POL-9 | **Overtime / weekend running** | Ops director's call; you feed the *\"we'll miss X without it\"* argument. *\"A live lever, not a nice-to-have.\"* | |\n\n## Constraints\n\n| ID | Limit | Consequence when hit |\n|---|---|---|\n| C-1 | Specialty cannot run on Line 2 — not piped for clear specialty resins | infeasible; must go Line 1 or Line 3 |\n| C-2 | Two tint SKUs not qualified on Line 3 (QA/engineering decision, reason not known to you) | cannot be scheduled there |\n| C-3 | Line 1 qualified for everything | fallback line of last resort |\n| C-4 | Minimum run size | small orders must be lumped — **threshold unquantified** |\n| C-5 | One changeover crew → **one washdown at a time across all three lines** | the other line waits |\n| C-6 | One QC lab, two people | queue forms; **parallelism unknown** |\n| C-7 | Demand 380–420 vs capacity 270–300 run-hours | *\"every hour lost to a washdown or a jam is an hour I don't have to spare\"* |\n| C-8 | Meridian due date | *\"due Friday close of business, which for Meridian really means Friday, no wiggle\"* |\n\n## Dynamics\n\n| ID | Quantity | Direction & rate | Threshold |\n|---|---|---|---|\n| D-1 | **Line 1 mill-to-fill tank level** | rises when mill outpaces fill — **rate open** | at full, **mill stops and waits**; drains as fill proceeds; reset by fill catching up |\n\n## Data bindings\n\n| ID | Variable | Feed |\n|---|---|---|\n| DB-1 | order arrivals, quantities, due dates | ERP demand book |\n| DB-2 | run durations in run-hours | your weekly sheet (already converted from rates) |\n| DB-3 | per-stage cycle times by product and line | the historian — *\"if someone actually pulled cycle times apart by product and stage, which — as I said — nobody's done\"* |\n\n---\n\n# 2. Assumption ledger\n\nNothing below came from you. Each is mine, provisional, and needs your yes/no.\n\n| # | Assumption | Why I'd need it | How to check |\n|---|---|---|---|\n| A1 | Changeover crew serves waiting lines **first-come-first-served** | C-5 makes the crew a contended resource; without a rule the model can't pick | Ask you (POL-7) — you may have a real priority rule |\n| A2 | QC lab works **FIFO** on arriving batches | Same reason for C-6 | Ask the lab; also ask you whether you ever expedite a batch |\n| A3 | A washdown falling outside day shift **waits until morning** | BC-3 is unknown and the model must do *something* | Crew lead — you flagged this yourself |\n| A4 | QC lab has **no night presence** | Your stated impression, not fact | The lab |\n| A5 | Line 2's ~2× speed advantage over Line 1 applies to **whites only**; I will not extend it to tints or specialty without evidence | You explicitly said don't take it as gospel outside whites | Process engineering, or historian cycle times (DB-3) |\n| A6 | Ramp-up scrap occurs after a **washdown**, not after every run | Inferred from *\"the week I rushed the ramp after a washdown\"* — you never said it happens after short changeovers | Ask you; ask quality |\n| A7 | The 24-hour Meridian run is modelled as a **rare tail, ~annual**, not part of the normal bad day | Your words *\"once-a-year tail\"* — but \"once a year\" as a rate is my reading of an anecdote | You, next session |\n| A8 | Filler jams are **plant-wide 1–2/week concentrated on Line 2** rather than 1–2 per line | *\"It's Line 2's filler mostly\"* is directional, not a split | You, next session |\n\n---\n\n# 3. What's deliberately left out, and what's simply unknown\n\n**Deliberately out of scope** (your boundary, and I think it's right for these three questions):\n- Order generation upstream of the demand book.\n- Trucking, warehouse slotting, shipping — logistics' sheet.\n- Feedstock planning generally, except as the resin-slip disruption.\n- Quarter-scale planning — you don't do it and ERP doesn't support it.\n\n**Deliberately simplified, with what's lost:**\n- **Stage-level detail inside a run.** You schedule in whole-run blocks; the model will too, *except* on Line 1 where you told me the mill-to-fill tank causes real dead time. Lost: any pipelining benefit from overlapping the next batch's mix with this batch's fill. Justified for now because your sheet doesn't see it either — but flagged, because you said the sheet *flatters* reality, and OBJ-3 (are you leaving hours on the table?) is exactly the question where flattery misleads.\n- **Tint-to-tint sub-families.** Collapsed to one 20–30 min changeover. Lost: any light→dark penalty. Justified because you've never separated it; revisit if the model over-favours tint batching.\n\n**Unknown and load-bearing — these are what stop the model running honestly today:**\n\n1. **POL-5 and POL-6** — the two rules the whole exercise exists to test. Without your practiced rule I have no baseline to compare a candidate policy against.\n2. **A-12 requalification cost** — OBJ-1 is a trade between requalification and a slipped white. One side of the trade is unsized.\n3. **POL-7 changeover-crew priority** — C-5 is a hard bottleneck and you named its symptom (Line 3 idle). Currently on assumption A1.\n4. **A-3, A-5, A-6** — the quick changeover, all specialty changeovers, and ramp-up scrap magnitude. OBJ-2 is *literally* \"idle hour vs three-hour washdown plus ramp loss,\" and the ramp loss has no number.\n5. **P07 across the board** — I have one duration spread, for one product on one line. I do not know how run duration varies by line, family, or size.\n6. **BC-1 rush orders** — you say they land and force re-juggling; I have no arrival pattern, and OBJ-3 is about splitting runs to accommodate them.\n7. **Numeric trade weights** — the Meridian-vs-distributor-vs-scrap exchange rate. Deposit: commercial.\n\n---\n\n# 4. Agenda for tomorrow\n\nIn the order I'd spend the time, biggest gap first:\n\n1. The **reroute-or-hold** rule and the **idle-or-washdown** rule, each via the last time you actually faced it and what you looked at.\n2. **Requalification** — what it actually involves and how long it takes.\n3. **Changeover crew priority** when two lines want them at once, plus a recent borderline case.\n4. **Ramp-up scrap** magnitude, and whether it follows every changeover or only washdowns.\n5. **Rates for the other lines and families** — enough to stop me extrapolating from one Meridian white run.\n6. **Rush order arrivals**, and who counts as Meridian-tier.\n7. Whichever of the three deposits (crew lead / lab / process engineering) you can chase.\n\nOne correction I'd like at the top of tomorrow: **have I got any of the above wrong or in the wrong words?** Particularly the objectives table and the \"better\" ranking — those drive what I ask everything else about."
     },
     {
       "role": "user",
-      "content": "*(No dialogue — Marta has left for the huddle. This turn is a silent acknowledgment beat only if the interviewer expects a reply; otherwise nothing further is added.)*"
+      "content": "This is a lot to take in on a screen before a huddle, but let me flag what jumps out at me now rather than wait.\n\nMostly this reads right. A couple of things I want to correct or sharpen before you build on them:\n\n**The \"better\" ranking** — close but not quite. You've got scrap and changeover hours as roughly equal-weight, third and fourth. I don't think that's right. Re-reading what I actually said: I'd take a scrap spike over a late Meridian order, sure, but I never compared scrap to changeover hours directly. My gut says changeover hours lost matter *more* than scrap, because lost hours cascade into more lateness, whereas scrap is just money — annoying, contained, doesn't ripple. So the order should probably be: late-and-who > changeover hours lost > scrap. But flag that as me thinking out loud just now, not something I'd already settled — ask me again tomorrow once I've slept on it, I might change my mind.\n\n**A-7, the QC hold table** — you've written \"with backlog, a day-plus (last week: Wed evening → Thursday midday).\" That's about 18 hours, which is bad-Friday territory but it was actually a Wednesday-into-Thursday case, not the classic Friday backlog. I gave you that example as the \"how it can still go wrong on a decent week\" case, not as my definition of the tail. Don't let that example become your number for \"the Friday case\" — Friday's usually worse than that, I just don't have a clean anecdote for it yet.\n\n**One thing missing entirely: BC-1, rush orders.** You've noted it as open, correctly, but I want to flag it's not a small gap — it might be as big as the two decision rules. Rush orders are *why* the reroute-or-hold and idle-or-washdown calls happen in the first place half the time. If you only ask me about the steady-state rules tomorrow and not about how rush orders actually arrive, you'll have modelled the calm week and missed the reason I lose sleep.\n\n**Small correction on A-9/A-10**: you've split the mill motor into \"hiccup\" and \"multi-day disaster\" as two separate activities, which is fair, but don't assume everything between those two is smoothly distributed — in my experience it's bimodal, either a nuisance under half a day or a genuine disaster, rarely something in the middle. Worth being careful the model doesn't invent a smooth continuum where the real thing is two lumps.\n\nOtherwise — yes, that's my plant. See you tomorrow, same time. Lead with the two rules."
     },
     {
       "role": "assistant",
-      "content": "Nothing further from me — you've stopped, and the read-back above is the deliverable as it stands.\n\nFor when you're back, the first three questions in one place, so you can answer them in five minutes if that's all you have:\n\n1. **How long does a batch run?** Typical, one-in-ten worse, one-in-ten better — for a plain white on Line 2 first; I'll ask about the other families and lines after.\n2. **The heads-up.** Two weeks ago, who told you that white order was about to drop, how far ahead, and how often does that kind of warning turn out to be right?\n3. **QA hold.** \"A few hours\" — typical, one-in-ten worse, one-in-ten better. And is there a queue for the lab like there is for the techs?\n\nEnjoy the huddle."
+      "content": "Recorded — all four as corrections that **supersede** what I'd written, not additions beside it.\n\n1. **\"Better\" ranking** — now reads: *late orders and to whom* > *changeover hours lost* > *scrap*. Your reason on the record: *\"lost hours cascade into more lateness, whereas scrap is just money — annoying, contained, doesn't ripple.\"* Marked **provisional — thought aloud, not settled**; I'll re-ask tomorrow before anything depends on it, and I won't build the metric on it in the meantime. The one firm ordering stays as you first gave it: scrap spike beats a late Meridian order, no contest.\n\n2. **A-7** — the Wed evening → Thursday midday case is now labelled as your *\"how it can still go wrong on a decent week\"* example. It is **not** the Friday tail and I've deleted it from that slot. The Friday tail is now explicitly open: *\"Friday's usually worse than that, I just don't have a clean anecdote for it yet.\"*\n\n3. **BC-1 rush orders** — promoted out of the general open list into the top tier, alongside POL-5 and POL-6, with your framing attached: *\"rush orders are why the reroute-or-hold and idle-or-washdown calls happen in the first place half the time… you'll have modelled the calm week and missed the reason I lose sleep.\"*\n\n4. **A-9/A-10** — flagged as **bimodal, not a continuum**: nuisance under half a day, or genuine disaster, *\"rarely something in the middle.\"* Noted as a modelling instruction, so nobody fits a single smooth distribution across the gap.\n\nTomorrow, in this order: the reroute-or-hold rule, the idle-or-washdown rule, then rush orders — each via the last time it actually happened. Requalification and crew priority after that.\n\nEnjoy the huddle."
     },
     {
       "role": "user",
-      "content": "*(Marta has stepped away to the huddle — no further reply expected this turn. The three questions are noted for the next session.)*"
+      "content": "Thanks — that all lands right. See you tomorrow."
     },
     {
       "role": "assistant",
-      "content": "Noted — session closed. The model, the seven-item assumption ledger, and the eight open slots stand as delivered above; the three questions are queued for next time."
+      "content": "See you tomorrow.\n\nFor the record, so nothing depends on memory overnight:\n\n**Stopping outcome: `expert-stopped` — partial model with open slots.** The structural floor holds; none of the three objectives has a complete dependency slice. The model as read back stands, with the four corrections you just gave superseding what they replace:\n\n- **Better** = late-and-to-whom > changeover hours lost > scrap — *provisional, thought aloud, to be re-confirmed before any metric is built on it*. The settled part remains: scrap spike over a late Meridian order, no contest.\n- **A-7** — Wed→Thu ~18h is your *decent-week* example, not the Friday tail. Friday tail: open, no anecdote yet.\n- **BC-1 rush orders** — top-tier gap, level with the two decision rules.\n- **A-9/A-10** — bimodal by instruction: nuisance under half a day, or disaster. No smooth continuum across the middle.\n\nThree deposits still sitting with other people when you get a chance: the crew lead (what happens to a washdown forced onto nights), the lab (parallel testing and evening cover), and process engineering (whether Line 2's 2× holds outside whites).\n\nTomorrow: the two rules first, then rush orders — each via the last time it actually happened."
     },
     {
       "role": "user",
-      "content": "Understood — nothing further needed from me here. Session closed, deliverables stand as written, and I'll pick up run times, the heads-up mechanism, and QA hold as the first order of business next time we talk."
+      "content": "Sounds right. Talk tomorrow."
     },
     {
       "role": "assistant",
-      "content": "Acknowledged. Session closed on your terms.\n\nFor the record, so nothing depends on memory next time:\n\n- **Delivered:** the model (4 objectives, 5 entity types, 5 boundary conditions, 12 activities, 3 ordering/flow rules, 6 policies, 5 constraints, no dynamics, 4 named data bindings), the 7-entry assumption ledger, and the loss account.\n- **Queued, in order:** A8 run duration → B2 the heads-up mechanism → A9 QA hold and whether the lab queues.\n- **Standing caveat:** O1 — hold versus wash down — is currently answerable only for Line 2, and only once run times exist. Ledger #1–#4 are the assumptions to attack first if a result involving Line 1 or Line 3 ever looks decisive.\n\nThanks for the time, Marta — the changeover asymmetry and the tech-contention story were the two things I'd never have got from a document."
+      "content": "Talk tomorrow. The record's in the read-back above — nothing further from me until we pick up the two rules."
     },
     {
       "role": "user",
-      "content": "Anytime. Glad the changeover asymmetry landed — that one catches everybody, including people who've been on the floor a lot longer than me. Come find me at the huddle when you're ready to go through run times, I'll have my head in the sheet anyway."
+      "content": "Good — I'll be ready to walk through the reroute and idle calls when we start. Nothing more from me either until then."
     },
     {
       "role": "assistant",
-      "content": "Will do — I'll come to the huddle rather than pull you out of it. If your head's in the sheet anyway, that's the best possible place to ask about run times: I'd rather hear \"that one took nine hours and it was a bad one\" off the actual sheet than a remembered average.\n\nOne small ask for whenever it's convenient, no work required now: if the changeover logs do have tech start and finish times on them, that's the single thing that would let me retire ledger entries #1 and #4 — the Line 1 scaling factor and the crew hands-on fractions — and swap my guesses for your history.\n\nSee you at the huddle."
+      "content": "Understood. Standing by — we resume with the reroute-or-hold call, the idle-or-washdown call, then rush orders, each from the last time it happened."
     },
     {
       "role": "user",
-      "content": "Sounds good — I'll flag it to the two techs to make sure they're actually filling in start/finish consistently, because I'll be honest, I've never audited that field myself, I mostly just glance at duration. If it's patchy for Line 1 and Line 3 specifically, that itself would be useful for you to know, not just an inconvenience. See you at the huddle."
+      "content": "Sounds good — I'll have the specific instances in mind. Talk then."
     },
     {
       "role": "assistant",
-      "content": "That's a genuinely useful thing to have said, and I'm recording it rather than just noting it — it changes the status of a data binding I'd been leaning on.\n\n**Amendment to the delivered model:**\n\n- **Data binding \"changeover logs (tech start/finish)\"** — provenance qualified: the start/finish field has never been audited; you read duration only. Coverage is unknown and may be patchy, and you've flagged Line 1 and Line 3 as the places to look. Your words: \"I've never audited that field myself, I mostly just glance at duration.\"\n- **Consequence for the ledger:** entries #1 (Line 1 × 1.2) and #4 (crew hands-on fractions) each carry a second-order dependency — their check depends on a feed of unverified coverage. If the field turns out patchy exactly where the assumptions bite, those two stay assumptions and the honest move is to widen them rather than to fill them in.\n- **Recorded as a finding in its own right:** patchy logging on Line 1 and Line 3 is itself evidence about the plant, not just an obstacle to the model.\n\nNothing else changes. See you at the huddle."
+      "content": "Perfect — a specific instance for each is exactly what I need. Talk then."
     },
     {
       "role": "user",
-      "content": "Fair enough — that's a better way to put it than I would have. Talk soon."
+      "content": "Confirmed — same plan, same order. Talk then."
     },
     {
       "role": "assistant",
-      "content": "Talk soon, Marta."
+      "content": "Confirmed. Ending here."
     },
     {
       "role": "user",
-      "content": "See you at the huddle."
+      "content": "Alright — ending here. Talk soon."
     },
     {
       "role": "assistant",
-      "content": "See you there."
+      "content": "Talk soon. The model, assumption ledger, and loss account are in the read-back above, with your four corrections applied; we resume at the two rules."
     },
     {
       "role": "user",
-      "content": "*(end of session — nothing further to add.)*"
+      "content": "Understood — that's the record. Whenever you're ready to pick up the reroute-or-hold rule, I'll walk you through the actual case."
     },
     {
       "role": "assistant",
-      "content": "Session ended. Deliverables stand as written above."
+      "content": "Then let's pick it up now — no reason to wait.\n\n**Take that Line 1 mill motor morning.** Not the general rule yet, just what happened. You're at the huddle, the motor's down for a few hours, you've got the specialty batch and the Meridian white both needing to move.\n\n1. **Walk me through the minutes.** What did you look at first, what did you look at next, and what did you say out loud when you made the call? I want the sequence of your attention, not the justification.\n\n2. **What would have had to be different for you to call it the other way** — held the specialty on Line 1 and let the white slip? Give me the version of that morning where you make the opposite call."
     },
     {
       "role": "user",
-      "content": "Confirmed — nothing further from this end. Session closed."
+      "content": "Okay, let me actually put myself back there.\n\n**1. The sequence.**\n\nFirst thing I looked at wasn't the specialty or the white at all — it was the motor. I wanted to know from maintenance, right then, \"is this the twenty-minute reset kind or do I need to be worried,\" because that answer changes everything downstream. They said a few hours, looked routine, not the scary failure — that's the first fact I need before I can even think about rerouting anything.\n\nSecond thing: I looked at the specialty batch's due date. It wasn't screaming — a few days out — so my first instinct was actually \"can it just wait for Line 1 to come back,\" not \"move it.\" That's my default, moving specialty is a pain, I don't want to do it.\n\nThird: I looked at what Line 2 was doing and what it was about to do. Line 2 had capacity coming up because the tint run ahead of the Meridian order was tracking fine — so the Meridian white had a clear path if Line 1's problem didn't spill into it. That's when the real tension showed up: if I *don't* move the specialty, it sits and waits for Line 1, fine, no drama — but the thing that actually made me move was that Line 1's queue that day wasn't just the specialty, it also had a knock-on tint job stacked behind it, and if the specialty sat there blocking the queue, that tint job gets delayed too, and *that* tint job was the one that fed into the Meridian white's changeover on Line 2 later in the week. So it wasn't \"specialty vs white\" directly — it was \"if I don't clear Line 1's queue now, it back up onto something that touches the white two days later.\"\n\nSo what I actually said out loud at the huddle was something like \"Line 1's down a few hours, let's shift the specialty to Three and keep the queue moving, I don't want this backing into Thursday.\" The white wasn't really the thing I was staring at — it was collateral reasoning, the domino two steps down.\n\n**2. The opposite call.**\n\nI'd have held the specialty on Line 1 if: the motor fix had been quick — say under an hour, not \"a few\" — because then it's not worth the requalification hassle for such a short wait. Or if Line 3 had been tied up with something of its own that day, because then rerouting isn't even a real option, it's theoretical. Or — and this is probably the biggest one — if that tint job hadn't been sitting behind the specialty in Line 1's queue. If Line 1's queue that day was *just* the specialty and nothing behind it, I'd have shrugged and let it wait for the motor, because a few hours' hold on a not-urgent specialty order is cheap and a requalification isn't.\n\nSo the honest rule buried in there isn't really \"reroute vs hold based on the white\" — it's more like: **I hold by default, and I only reroute if leaving it in place would jam something else behind it that I care about more.** The Meridian white in this story was three steps removed, not the thing I was directly weighing."
     },
     {
       "role": "assistant",
-      "content": "Closed. Nothing further."
+      "content": "That's a different rule than the one I was about to write down, and much more useful — thank you. Let me check I've got it.\n\n**So you're saying: your default is hold. You only reroute when leaving the job in place would block something behind it in that line's queue that you care about more than the requalification cost — and the thing you care about may be several steps removed, like a tint job that later feeds a changeover on another line.** Is that right, and would you word it differently?\n\nTwo things I need to make that runnable:\n\n1. **How far down the queue do you actually look?** In that story you saw a tint job behind the specialty, and then saw that the tint job touched the white two days later — that's two hops. Is two hops typical, or did you go further that morning than you usually do? And is there a point where you stop tracing?\n\n2. **What makes a downstream job one you \"care about more\"?** In that case the chain ended at Meridian. Would a chain ending at a small distributor's order have moved you, or would you have shrugged and held?"
     },
     {
       "role": "user",
-      "content": "Closed."
+      "content": "Good questions, and honestly they make me realise I don't do this as cleanly as the story makes it sound.\n\n**On the wording** — yes, that's right, that's a better statement of it than I'd have managed myself. \"Hold by default, reroute only if staying put jams something you care about more\" — that's the shape of it. I'd maybe add: it's not just that requalification is costly, it's that requalification is a *known, bounded* cost and blocking the queue is an *unknown, possibly-cascading* one. So there's an asymmetry — I'll pay a known cost to avoid an unknown one, especially when I'm short on time to think it through properly, which at a 07:30 huddle I always am.\n\n**1. How far I look:** Honestly, two hops is probably close to my ceiling, and that morning I only got there because the tint job was the very next thing in queue and I happened to remember what it fed. I don't systematically trace the whole week's dependency chain every time something breaks — I don't have time, and frankly I don't think I *could* hold that whole picture in my head reliably. Normally it's one hop: \"what's sitting right behind this in the queue, does it matter.\" The second hop only happens when the first hop is itself something time-pressured — if the tint job behind the specialty had had a slack due date, I probably wouldn't have bothered chasing where it went next. So: **one hop routinely, two hops only when hop one is already urgent-looking.** Past that I'm guessing, not tracing.\n\n**2. What makes it \"care about more\":** Yeah — if that chain had ended at a small distributor instead of Meridian, I don't think I'd have moved the specialty. I'd have shrugged, let Line 1's queue sit, and told the distributor's order it might run a day later, which is exactly the kind of slip that \"nobody notices.\" The whole reason I bothered chasing the second hop that morning is that Meridian was at the end of it — if I hadn't recognized where the tint job fed, I wouldn't have rerouted at all. So the customer tier at the *end* of the chain is doing real work here, not just the immediate next job. Put bluntly: I trace further and act more readily when I suspect Meridian's at the other end of it than when I don't."
     },
     {
       "role": "assistant",
-      "content": "Closed."
+      "content": "Two more on this rule, then I'll size the cost side of it.\n\n1. **What overrides it?** I'm looking for the case that breaks the pattern — a time you rerouted even though nothing was stacked behind, or a time something urgent *was* blocked and you still held. If one comes to mind, tell me what was different about it.\n\n2. **Requalification** — you've called it a headache and a known bounded cost, but I have no size for it. When you moved that specialty to Line 3, **what actually had to happen before it could run?** Who did what, and how long did it hold the batch up?"
     },
     {
       "role": "user",
@@ -811,7 +841,7 @@
     },
     {
       "role": "assistant",
-      "content": "# Coatings Plant Scheduling Model\n**Elicited from:** Marta, master scheduler\n**Job:** construct (no prior model)\n**Status at close:** floor satisfied; O1's dependency slice **incomplete** — see §3.\n**Vocabulary:** the expert's throughout. `⚠` = a slot the method demands and the interview did not obtain.\n\n---\n\n## 1. The model\n\n### 1.1 Objectives\n\n**O1 — \"Hold the line versus wash it down now, which one actually costs less over the week\"**\n- **The question, in her words** *(spelled out)*: whether letting Line 2 sit idle for about an hour, on a heads-up that another same-family white order is about to drop in from a distributor, is cheaper over a week than washing down now to run the tint batch waiting behind it. Origin: a real Thursday-afternoon decision two weeks before the interview. Her own verdict on how she made it: *\"I was guessing.\"*\n- **Depends on** *(≥1 satisfied)*: E1, E2, E3, E4, B1, B2, A4, A5, A6, A8, A9, F1, F2, P3, P4, P5, C1, C2, C3.\n- **What \"better\" means** *(named; not quantified)*: changeover hours consumed over the week, subject to O2 holding absolutely. ⚠ no trade-off weight against lateness — see the trade-off note below.\n- **Source-regime**: practiced.\n\n**O2 — \"Whether Meridian shipped on time, full stop, that's non-negotiable\"**\n- **The question** *(spelled out)*: does every Meridian order leave the dock in time for its dock appointment.\n- **\"On time\" defined** *(spelled out)*: a ship date given on the order, usually with a delivery window attached — a specific dock appointment at Meridian's end. In practice the batch must leave our dock **one day ahead** to allow for freight. Not \"shipped this week.\"\n- **Consequence of a miss** *(spelled out, unquantified)*: a fine — *\"I don't see the number, that's commercial's problem, but I hear about it\"* — and, worse, Meridian tracks our on-time percentage and threatens to delist SKUs if it drops too far. A competitor has been delisted, *\"so it's not an empty threat, and it's why the rule is absolute — we don't even try to be clever about it.\"* ⚠ fine amount and delisting threshold both outside her sight.\n- **Depends on**: A8, A9, A10, B3, C4, C5, P1, P2.\n- **Source-regime**: prescribed and practiced coincide — she reports no divergence, which is itself the finding.\n\n**O3 — Changeover hours**\n- **The question** *(spelled out)*: how many crew-hours go into washing down rather than filling. *\"Every hour the crew spends washing down is an hour not filling anything.\"*\n- **Depends on**: A4, A5, A6, A7, E4, C2, P3.\n- **What \"better\" means** *(named)*: fewer changeover hours. Directionally clear, no target value. ⚠\n\n**O4 — \"How ugly the sheet looks\"**\n- **The question** *(spelled out)*: *\"are there gaps where a line's sitting idle for no good reason.\"*\n- **What \"better\" means** *(her words; explicitly not a number)*: *\"that last one's not a number, it's more a gut check, but it's real.\"*\n- **Depends on**: E3, C2, P3, P4, A4–A7.\n- **Status**: recorded, IR-only. Approximating it as line idle hours would be my move, not hers; I have not made it. See §3.\n\n**The trade-off between O2, O3 and non-Meridian lateness** *(spelled out as a rule; deliberately unquantified)*\nFour changeover hours saved against one distributor order two days late: *\"honestly, yes, I'd take that trade most of the time\"* — a distributor slip is *\"usually just an annoyed phone call from our sales rep, not a fine.\"* But *\"'most of the time' is doing a lot of work in that sentence\"*: the same distributor slipping three weeks running starts asking for a discount. So lateness for non-Meridian is soft but not infinitely soft, and the softness decays with repetition on the same customer.\n**Deposit for the missing number**: *\"that's genuinely a 'sit down with commercial' conversation, nobody's ever made me quantify it.\"* Source named; not obtainable from the scheduler. ⚠\n\n---\n\n### 1.2 Entity types\n\n**E1 — Order (in the demand book)**\n- **Distinctions the process treats apart** *(spelled out)*: Meridian vs. non-Meridian — a Meridian flag arrives on the order and it *\"jumps to the top of my attention\"*; family classification (see below), which drives allocation and changeover.\n- **State riding along** *(spelled out)*: SKU; quantity; due date with delivery window; Meridian flag; family — **base white / tinted colour / specialty clear**. The family is a real field: *\"that's not my judgment, that's how the SKU's classified in the system, it drives what changeover you need going in and out.\"*\n- **How many / population shape**: ⚠ not obtained. Orders per weekly pull and within-week shape unknown.\n\n**E2 — Batch**\n- **Distinctions** *(spelled out)*: inherits the family of the order it came from.\n- **Relationship to E1** *(spelled out)*: *\"mostly the order is the batch, if it fits a reasonable run size.\"* Split into two batches run at different times when a distributor orders more than makes sense in a single run, or to interleave something more urgent. *\"Order-to-batch most of the time, but not a strict one-to-one — I have the freedom to split if I need to.\"*\n- **How many / population shape**: ⚠ not obtained. Run sizes, \"reasonable run size\" threshold, and the cost of a split all unelicited.\n\n**E3 — Line** *(a contended resource: capacity in C1, contention in P1/P3, availability in B4)*\n- **Distinctions** *(spelled out)*:\n - **Line 1** — *\"the old workhorse — slower but it's qualified for everything, including specialty.\"* Crew report it is *\"fussier to get properly clean.\"*\n - **Line 2** — *\"the fast one, that's your big-volume runner.\"* Meridian whites always go here (P1).\n - **Line 3** — *\"the newest and quickest, but it's still being qualified product by product, so it can't run everything yet\"*; so far *\"mostly one or two SKUs.\"*\n- **State riding along** *(spelled out)*: the family the line is currently dirty with — this selects which changeover applies (F3); the line's qualification set.\n- **How many** *(number)*: 3.\n\n**E4 — Changeover tech** *(a contended resource)*\n- **Distinctions** *(named)*: none drawn between the two techs; treated as interchangeable.\n- **State riding along** *(spelled out)*: which line they are currently committed to. Can be *\"pulled away partway through\"* a changeover, and during long soaks *\"might duck off to start something on another line.\"*\n- **How many** *(number)*: 2 on day shift, covering all three lines. *\"That's it. No dedicated tech per line.\"*\n\n**E5 — QA lab**\n- ⚠ **Nothing obtained** beyond its existence, that every batch passes through it, and that it *\"gets backed up on a Friday afternoon.\"* Whether it is a contended resource with a queue — as she suspects and I flagged — is open.\n- Recorded because her own diagnosis makes it load-bearing for O2: *\"half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it.\"*\n\n---\n\n### 1.3 Boundary conditions\n\n**B1 — ERP weekly pull into the demand book**\n- **Starting state** *(spelled out)*: orders come over from ERP on the weekly pull carrying SKU, quantity, due date, Meridian flag.\n- **Arrival pattern**: ⚠ **not obtained** (demanded as a spread). No volume, no variability, no within-week shape.\n\n**B2 — Mid-week drop-in order, and the heads-up that precedes it**\n- ⚠ **Not obtained** (demanded as a spread). All that exists is the single anecdote: *\"I had a heads-up another same-family white order was about to drop in from a distributor.\"*\n- **Why this matters more than its size suggests**: this is the trigger on which O1's entire decision hangs. Who gives the heads-up, how far ahead, and how often it proves right are all unknown. Without it, P5 can be simulated as a *rule* but its *arrival process* has no basis.\n\n**B3 — Meridian dock appointment**\n- **Pattern** *(spelled out, qualitative)*: a ship date with a delivery window on the order, resolving to a specific dock appointment at Meridian's end.\n- **Lead-time distribution**: ⚠ not obtained.\n\n**B4 — Tech availability**\n- **Spelled out, partially**: two techs on **day shift**. ⚠ Whether any changeover coverage exists outside day shift was never asked (ledger #5).\n\n**B5 — Line 3 qualification set**\n- ⚠ *\"mostly one or two SKUs\"* — **not spelled out**; which SKUs, unknown.\n\n---\n\n### 1.4 Activities\n\n**A1 — Lands in the demand book**\n- *Needs*: the weekly ERP pull. *Produces*: an order in the demand book, Meridian-flagged or not. *Performed by*: ERP — unattended. *Duration*: instantaneous receipt. *Rate*: per B1 ⚠. *Mode-change loss*: n/a. *Varies by type*: no. **spelled out**\n\n**A2 — Allocate to a line**\n- *Needs*: an order in the book. *Produces*: order assigned to a line. *Performed by*: Marta. *Duration*: not a constraint on the schedule; for Meridian whites *\"that's not really a decision.\"* *Rule*: P1. **spelled out**\n\n**A3 — Reorder the queue**\n- *Needs*: an order sitting behind others on a line. *Produces*: a changed run sequence. *Performed by*: Marta. *Rule*: P4 — *\"sometimes I'll reorder things a bit so it doesn't get stuck behind a big changeover.\"* **spelled out**\n\n**A4 — Quick rinse, same family (white → white), Line 2**\n- *Needs*: previous batch off; a tech available; next SKU in the same family. *Produces*: line clean, *\"the fill head's actually running clean product again.\"*\n- *Performed by* **(named)**: one changeover tech.\n- *Duration, line down* **(spread)**: **typical 25 min**; **one-in-ten worse 45 min** — *\"usually because the tech's tied up finishing something on another line first and there's a wait before they even start on Line 2\"*; **one-in-ten better 15 min** — *\"if the tech's standing right there and it's a genuinely easy one.\"*\n- *Crew hands-on* **(spelled out)**: identical to line-down. *\"It's quick enough that the tech's on it start to finish, no gap between 'crew starts' and 'line stops.'\"*\n- *Mode-change loss*: this activity **is** the mode change; the loss is the duration above.\n- *Varies by type* **(named)**: yes by family-pair (F3 selects between A4–A7). By line: ⚠ ledger #1, #2.\n\n**A5 — Family switch, white → tint, Line 2** — *\"the easier direction\"*\n- *Needs / produces*: as A4, next batch in a different family.\n- *Performed by* **(named)**: one changeover tech.\n- *Duration, line down* **(spread)**: **typical 45 min**; **worse \"an hour and a bit\"** — *\"if the tech gets pulled away partway through\"*; **better ~30 min** — *\"if everything's staged.\"* (Numeric reading of \"an hour and a bit\": ledger #3.)\n- *Crew hands-on* **(spelled out, qualitative)**: *\"the tech's hands-on for most of it — this one doesn't have much soak-and-wait, it's mostly just doing the work.\"* Fraction: ledger #4.\n- *Varies by type*: direction-dependent — see A6.\n\n**A6 — Family switch, tint → white, Line 2 — the full washdown** — *\"the ugly one\"*\n- *Needs*: as A5, plus a **passing visual check** before the line is released back to production.\n- *Produces*: a line clean enough to run white.\n- *Performed by* **(named)**: one changeover tech, not continuously present.\n- *Duration, line down* **(spread)**: **typical ~3 h**; **worse 4 h, \"maybe a bit more\"** — *\"if it doesn't pass the visual check first time and they have to redo part of it\"*; **better ~2 h** — *\"a clean fast one, if the crew's good and nothing complicates it.\"* (Ledger #3 for the numeric reading of the tail.)\n- *Crew hands-on* **(spelled out, qualitative)**: *\"less than the 3 hours suggests — there's real soak and rinse-cycle time where the tech's not standing there, they might duck off to start something on another line. I'd guess they're actually working maybe half of that.\"* Note her own hedge — *\"I'd guess\"* — carried into ledger #4.\n- *Rationale* **(spelled out)**: *\"any pigment left behind ruins a white batch, so it's a full washdown.\"*\n- **Asymmetry is load-bearing**: white→tint ≠ tint→white. *\"It absolutely depends on direction — that's the thing people forget… it is absolutely not symmetric, and it trips people up if they assume it is.\"*\n\n**A7 — Changeover into / out of specialty clear, Line 1**\n- *Needs / produces*: as A5/A6, for the specialty family. Only Line 1 is qualified (C1).\n- *Performed by* **(named)**: one changeover tech.\n- *Duration, line down* **(spread)**: **typical 2 h**, *\"roughly the same both directions, unlike white/tint\"*; **worse 3 h**, *\"if it's coming out of clear and they're being extra careful about residue, since clear can be sneaky — you don't always see it the way you'd see pigment\"*; **better 1.5 h**, *\"a quick swap and the line was already fairly clean.\"*\n- *Crew hands-on* **(spelled out, qualitative)**: *\"most of that — specialty doesn't have the long soak cycles the tint-to-white washdown has, it's more just physically thorough cleaning because the product's thick and clingy.\"* Fraction: ledger #4.\n\n**A8 — Run the batch** — mix, mill, tint (or *\"straight through if it's a plain white\"*), fill, pack\n- *Needs* **(spelled out)**: a clean line in the right family state; the batch released to run.\n- *Produces* **(spelled out)**: a filled and packed batch.\n- *Performed by*: ⚠ line operators never elicited as a resource.\n- **Duration**: ⚠ **nothing obtained.** Demanded as a spread, per family and per line.\n- *Varies by type*: partially — *\"for a white that's usually the more straightforward path\"* (skips the tint step), but no durations attach to that.\n- **This is the largest hole in the model.** O1 asks a question about a week; run time is most of a week.\n\n**A9 — QA hold and release** — *\"every batch does\"*\n- *Needs*: a packed batch. *Produces*: a released batch.\n- *Performed by* **(named)**: the lab (E5).\n- **Duration**: *\"typically a few hours before it's released\"* — an honest **number at the wrong precision**; demanded as a **spread**. ⚠\n- *Failure path*: ⚠ never asked what happens to a batch that fails QA.\n- *Known pathology* **(spelled out, qualitative; rate ⚠)**: *\"if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line.\"* And: *\"the QA step is the one people don't think about when they're mad at scheduling; half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it.\"*\n\n**A10 — Stage for shipping, and ship**\n- *Needs*: QA release. *Produces*: the order off the dock. *Timing constraint*: C4 — *\"that's when the truck appointment matters.\"*\n- *Duration*: ⚠ not obtained.\n\n**A11 — Tech pulled away mid-changeover** *(event, not step)*\n- Named by her as the mechanism behind the worse tail of A4 (*\"the tech's tied up finishing something on another line\"*) and A5 (*\"if the tech gets pulled away partway through\"*).\n- *Rate*: ⚠ not obtained separately; currently only implicit inside the one-in-ten tails of A4 and A5. Per P01 this should be its own rate and duration.\n\n**A12 — Washdown fails the visual check, part redone** *(event, not step)*\n- Named as the mechanism behind A6's 4 h tail.\n- *Rate*: ⚠ not obtained separately. Ledger #7 records the simplification.\n\n**A13 — \"The mill motor issue\"** *(event, not step — named in passing, nothing more)*\n- Mentioned only as an example of what a *structural* difference between lines would look like, in contrast to Line 1 merely being fussier. Recorded so it is not lost; **rate ⚠, duration ⚠, consequence ⚠**. This is the whole of the breakdown/interruption stratum, which was never swept.\n\n---\n\n### 1.5 Ordering / flow\n\n**F1 — The main arc, desk to dock** *(spelled out — her six steps, verbatim in structure)*\n1. Lands in the demand book (ERP weekly pull; SKU, quantity, due date, Meridian flag).\n2. Allocated to a line (*\"Meridian whites always go to Line 2\"*).\n3. Sits in the queue behind whatever's running — reorderable (A3/P4).\n4. Changeover if needed (F3 selects which), then it runs: mix, mill, tint-or-straight-through, fill, pack.\n5. QA hold.\n6. Released, staged for shipping, out against the truck appointment.\n\n**F2 — Order-to-batch split**\n- *Order* **(spelled out)**: an order becomes one batch by default; it may become two batches run at different times.\n- *How the branch is decided* **(spelled out)**: Marta's judgment, on either (a) a distributor ordering *\"more than makes sense in a single run\"*, or (b) needing to interleave something more urgent.\n- *Cost of a split*: ⚠ never asked (P03 unresolved) — extra changeovers and any extra loss are unknown.\n\n**F3 — Which changeover applies** *(spelled out)*\nSelected by the triple (family currently on the line, family of the next batch, line):\n- same family → **A4** quick rinse\n- white → tint → **A5**\n- tint → white → **A6** full washdown\n- into or out of specialty clear → **A7** (Line 1 only)\n\n---\n\n### 1.6 Policies\n\n**P1 — \"Meridian whites always go to Line 2, that's just how it's done here\"**\n- *As practiced* **(spelled out)**: fixed allocation, not a decision.\n- *What overrides it*: ⚠ never asked.\n- *Source-regime*: practiced; no prescribed form offered.\n\n**P2 — Meridian on-time is absolute**\n- *As practiced* **(spelled out)**: *\"the rule is absolute — we don't even try to be clever about it.\"*\n- *What overrides it* **(spelled out)**: nothing. That is the content of the policy.\n- *Rationale*: fine, tracked on-time percentage, delisting threat carried out on a competitor.\n\n**P3 — Who gets the tech when two lines want one** *(the model's richest policy, and the least documented)*\n- **Prescribed form: none exists.** *\"There's no posted rule at all.\"*\n- **As practiced** *(spelled out)*: in the room it resolves as *\"whoever's louder at the huddle, or whoever's about to actually run dry.\"* Pressed for the underlying logic: *\"it's mostly gut triage: whichever line has the more time-sensitive order behind it wins, and if that's a tie, whichever changeover is faster wins so you get a line moving sooner.\"*\n- **Borderline case on record** *(the practiced rule demonstrated, per P05)*: Line 1 and Line 3 both wanted a washdown the same morning. **Line 3 got the tech first** — *\"not because it was more important, but because Line 3's changeover was the quick one and Line 1's was going to be the long tint-to-white slog anyway, so the thinking was 'knock out the fast one, get that line moving, then commit the tech to the long one.'\"* Line 1 sat **clean-but-waiting for almost 40 minutes** past when it could have started.\n- **What overrides it** *(spelled out)*: the ops director. *\"I've been overruled by the ops director once when he wanted his pet SKU out the door.\"*\n- *Rationale* **(spelled out)**: *\"the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line\"* — and this, not changeover variability, is *\"the bit that actually causes grief at the huddle.\"*\n\n**P4 — Reorder the queue so a job isn't stuck behind a big changeover**\n- *As practiced* **(spelled out)**: Marta reorders *\"a bit\"* to avoid a job landing behind an expensive changeover.\n- *What overrides it*: ⚠ never asked.\n\n**P5 — Hold the line for an anticipated same-family order** *(the decision under test)*\n- *As practiced, one instance* **(spelled out)**: on a heads-up that a same-family white was about to drop, let Line 2 sit idle for *\"maybe an hour\"* rather than wash down for the tint waiting behind, *\"because doing them back to back would save us a full washdown.\"*\n- *Her own epistemic status*: *\"I was guessing.\"* Her boss's challenge — *\"are you sure that's worth it, or are you just guessing?\"* — is the reason this model exists.\n- *Trigger condition and decision threshold*: ⚠ how strong a heads-up, and how long she'd hold, are not generalised beyond this instance. Depends on B2.\n\n**P6 — Batch-split discretion**\n- *As practiced* **(spelled out)**: *\"I have the freedom to split if I need to.\"* Criteria as in F2.\n- *What overrides it*: ⚠ never asked.\n\n---\n\n### 1.7 Constraints\n\n**C1 — Line qualification**\n- *The limit* **(partially spelled out)**: Line 1 qualified for everything including specialty. Line 3 qualified product-by-product, *\"can't run everything yet\"*, currently *\"mostly one or two SKUs\"* — which ones ⚠. Line 2's qualification set ⚠ never stated.\n- *What happens when it's hit* **(spelled out)**: the batch cannot go on that line.\n\n**C2 — Two techs, three lines**\n- *The limit* **(spelled out)**: 2 techs on day shift for 3 lines.\n- *What happens when it's hit* **(spelled out)**: *\"if Line 1 and Line 3 both want a washdown at the same time, one of them waits\"* — clean-but-idle; 40 minutes in the case on record. Resolution by P3.\n\n**C3 — Tint → white requires a full washdown passing a visual check**\n- *The limit* **(spelled out)**: a white batch may not run on a line still carrying pigment.\n- *What happens when it's hit* **(spelled out)**: *\"any pigment left behind ruins a white batch\"*; a failed visual check means part of the washdown is redone (A12).\n\n**C4 — Meridian must leave our dock a day ahead of the appointment**\n- *The limit* **(spelled out)**: shipped in time to hit the dock appointment, which *\"usually means it needs to leave our dock a day ahead for freight.\"*\n- *What happens when it's hit* **(spelled out)**: fine + on-time percentage damage + delisting exposure.\n\n**C5 — Every batch passes QA hold before release**\n- *The limit* **(spelled out)**: *\"every batch does.\"*\n- *What happens when it's hit* **(spelled out)**: nothing ships unreleased; the batch waits in hold.\n\n**Unwritten constraints**: ⚠ the closing sweep — *\"what would a newcomer get wrong in the first week?\"*, *\"which rule exists because something once went wrong?\"* — was never run. The one item that surfaced unprompted is the changeover asymmetry: *\"that one catches everybody, including people who've been on the floor a lot longer than me.\"*\n\n---\n\n### 1.8 Dynamics\n\n**None.** Nothing described evolves continuously while nothing discrete happens. The soak and rinse-cycle time inside A6 is dead time *within* an activity, not a state variable crossing a threshold, and I have deliberately not promoted it to one.\n\n---\n\n### 1.9 Data bindings *(named only; these project to nothing today)*\n\n| Feed | Would drive | Provenance |\n|---|---|---|\n| Changeover logs — tech start/finish per changeover | A4–A7 durations and crew hands-on fractions; retires ledger #1 and #4 | **Qualified**: *\"I've never audited that field myself, I mostly just glance at duration.\"* Coverage unknown, possibly patchy — Marta named **Line 1 and Line 3** as where to look. She will flag it to the two techs. |\n| ERP demand book | B1 arrival pattern, B2 | not discussed |\n| QA release timestamps | A9 duration and lab queueing | not discussed |\n| Meridian on-time percentage | O2 | tracked by Meridian, visible to commercial |\n\n**Finding, recorded in its own right**: patchy changeover logging concentrated on Lines 1 and 3 is evidence about the plant, not merely an obstacle to the model. Her words: *\"if it's patchy for Line 1 and Line 3 specifically, that itself would be useful for you to know, not just an inconvenience.\"*\n\n---\n\n### 1.10 Validation criteria\n\n⚠ **None obtained.** How Marta would know the model is right was never asked. Queued.\n\n---\n\n## 2. Assumption ledger\n\nEverything here is mine. None of it is hers.\n\n| # | Assumption | Why it was made | How to check it |\n|---|---|---|---|\n| **1** | Line 1 changeover durations = Line 2 × **1.2**, all four types | She could not give Line 1 minutes: *\"I couldn't swear the minutes are identical… Line 1's older, the crew sometimes says it's fussier.\"* I proposed 20%; she said *\"20% sounds about right, not double.\"* **The 1.2 factor originated with me** — her assent is not authorship. | Changeover logs, Line 1 vs Line 2, same family-pair. **Blocked by the unaudited start/finish field, and Line 1 is one of the two lines she expects to be patchy.** |\n| **2** | Line 3 changeover durations = Line 2, unscaled | *\"Line 3 I genuinely don't have a good feel for… you're stuck assuming it's like Line 1 or Line 2 until we've got more history.\"* She offered the disjunction; **choosing Line 2 was mine.** | As #1, once Line 3 has run more products. Also expected patchy. |\n| **3** | \"An hour and a bit\" (A5 worse) = **70 min**; \"4, maybe a bit more\" (A6 worse) = **4.5 h** | Numeric readings so the spreads are usable. | One question to Marta: confirm or correct both. |\n| **4** | Crew hands-on fractions: A4 = **1.0**; A5 = **0.8**; A6 = **0.5**; A7 = **0.8** | A4's 1.0 is hers, stated. A6's 0.5 is close to *\"maybe half of that\"* — but note her own hedge, *\"I'd guess.\"* **The two 0.8s from *\"most of it\"* / *\"most of that\"* are mine.** | Changeover logs vs. tech time records, or ask the two techs directly. Same blocker as #1. |\n| **5** | No changeover happens outside day shift | She said *\"two techs on **day shift** covering all three lines.\"* Whether any other coverage exists was never asked. | One question to Marta. |\n| **6** | A changeover requires exactly **one** tech, not two | She spoke of *\"the tech\"* singular throughout, including for the 3-hour washdown. | One question to Marta or the techs. |\n| **7** | A12 (failed visual check, part redone) is folded **inside** A6's 4 h tail rather than modelled as a separate event with its own rate and duration | She described it as *the cause of* the tail, not as an independent event. Keeps the spread self-contained. Contrary to P01, which would separate rate from duration. | Ask how often the visual check fails first time; if it's common, split it out. |\n| **8** | The two changeover techs are **interchangeable** | She drew no distinction between them. | One question to Marta. |\n\n**Second-order note on #1 and #4**: their stated check depends on a feed of unverified coverage, concentrated exactly where the assumptions bite. If the field proves patchy on Line 1, the honest move is to **widen** these assumptions, not to fill them in.\n\n---\n\n## 3. What the model leaves out, what is unknown, and why\n\n### 3.1 Deliberately left out\n\n- **Queues, buffers and waiting states are not nodes.** The wait behind a running batch, the wait for a tech, the wait in QA hold — none is elicited as a thing in itself; each is implied by the activities either side and emerges in projection. The 40-minute clean-but-waiting on Line 1 is an *output* the model should reproduce, not an input to it.\n- **The commercial layer.** The fine, the on-time percentage mechanics, the delisting threshold. C4 and O2 encode the hard deadline; the money behind it is outside the scheduler's sight and she named commercial as the owner.\n- **Individual tech identity.** Ledger #8 — she drew no distinction.\n- **Scenarios.** Not elicited; they assemble from B1–B5 at simulation time.\n\n### 3.2 What the formalism cannot carry, kept in words so it is not lost\n\n- **O4, \"how ugly the sheet looks.\"** A criterion she genuinely uses and explicitly refuses to number. It could be approximated as line idle hours — but that approximation would be mine, and I have not made it.\n- **The O2/O3/lateness trade-off weight.** Deliberately unquantified with the source named (commercial). Consequence: the model can report changeover hours, Meridian lateness and distributor lateness **separately**, but cannot rank two schedules that trade one against another. That is a real limit on answering O1, since O1's \"costs less\" implicitly spans them.\n- **The decay of softness.** *\"The same distributor slipping late for the third week running\"* turning into a discount demand is a memory effect across weeks on a customer. Stated as a rule, unquantified, and not represented.\n- **The huddle.** *\"Whoever's louder at the huddle\"* and the ops director's pet-SKU override are the real P3 in the room. The triage logic — time-sensitivity first, faster-changeover as tiebreak — is compilable; loudness and the override are not. **Any run of this model will be quieter and more rational than the plant.** That is worth remembering when a result looks tidy.\n\n### 3.3 Open slots, in the order I would close them\n\n1. **A8 run duration** — nothing at all, per family and per line, as a spread. O1 is a question about a *week*; run time is most of a week. **Nothing about O1 is answerable until this exists.**\n2. **B2, the drop-in and the heads-up** — who tells her, how far ahead, how often it proves right. P5 is the decision under test and its trigger is currently a single anecdote.\n3. **A9 QA hold** — *\"a few hours\"* is honest at the wrong precision; and whether the lab queues like the techs do. By her own account this is where lateness actually comes from, so it bears directly on O2.\n4. **B1** — orders per weekly pull and the within-week shape.\n5. **E2 / F2** — typical run sizes, the \"reasonable run size\" threshold, and what a split costs in extra changeovers (P03).\n6. **C1 / B5** — which SKUs Line 3 is qualified for; whether Line 2 has restrictions.\n7. **Breakdowns and interruptions** — the whole stratum. A13 \"the mill motor issue\" is a name with no rate, duration or consequence. A11 and A12 need rate separated from duration (P01).\n8. **The unwritten-constraint sweep** and **validation criteria** — neither was run.\n\n### 3.4 Status against the completion criteria\n\n- **Static floor: satisfied** — 4 objectives, 5 entity types, 13 activities, 3 ordering/flow nodes.\n- **O2, O3: dependency slices substantially satisfied**, excepting A8 and A9 durations.\n- **O1: dependency slice incomplete.** A8 has no duration at all; B2 has no arrival pattern. O1 is currently **answerable only for Line 2**, and only once run times exist. Ledger #1–#4 are the first assumptions to attack if any result involving Line 1 or Line 3 ever looks decisive.\n- **O4: recorded, unsupported for quantitative use** by its own author's description.\n\n### 3.5 What I do not claim\n\nI have elicited a model, not built a net. The SDCPN scaffold, the code-obligation sidecar and the typed loss report are derived from this model by the tooling's projection — I have not written them and I am not claiming this loads, compiles, or runs. The A8 hole alone would stop it.\n\n---\n\n*Elicited from Marta, master scheduler, in a single session ended at her stop. Three questions queued for resumption: run duration for a plain white on Line 2 (typical / one-in-ten worse / one-in-ten better); the heads-up mechanism behind B2; QA hold as a spread, and whether the lab queues.*"
+      "content": "Stopping now. Nothing new opened; the last two questions I asked are recorded as unanswered.\n\n---\n\n# Coatings Plant Scheduling Model\n\n**Stopping outcome: `expert-stopped` — partial model with open slots.**\n\nThe structural floor holds (3 objectives, 6 entity-types, 13 activities, 4 ordering/flow nodes). **No objective's dependency slice is complete.** OBJ-1 is now substantially supported on its policy side and unsupported on its cost side; OBJ-2 and OBJ-3 remain unsupported at their cores. Details in §4.\n\nEvery value below is at the grade you actually gave it, in your words where I have them. I have not promoted anything.\n\n---\n\n## 1. Objectives\n\n| ID | The question, in your words | Depends on | Slice status |\n|---|---|---|---|\n| **OBJ-1** **Reroute or hold** | *\"whether to shift the specialty over to Line 3 and eat the requalification headache, or hold it and let the white slip behind on Line 2\"* — *\"I'd love to run twice and see which one bites me less\"* | POL-5, A-12, ET-3, ET-1, C-1, C-2, C-3, POL-1, A-9, A-10, OF-3 | **Partial** — rule captured, requalification cost absent |\n| **OBJ-2** **Idle or washdown** | *\"do I sit Line 2 empty for an hour waiting on a same-family order, or just pay the three-hour washdown now\"* — a call *\"almost weekly and it's pure feel\"* | POL-6, A-2, A-3, A-4, A-6, ET-4, C-5, BC-1 | **Unsupported** — the deciding rule is absent |\n| **OBJ-3** **Run size & sequencing** | *\"whether to split a big order into two runs to slot in a rush job, or batch several small orders of the same family together even if it means one of them ships a bit early and sits in the warehouse\"* — *\"I've never had a way to check if I'm leaving hours on the table\"* | OF-2, C-4, A-6, A-2/3/4, BC-1, ET-2 | **Unsupported** — rush-order arrivals and minimum run size absent |\n\nNoted, **not** an objective you own — overtime approval: *\"that's the ops director's call, though I do feed him the 'we'll miss X without it' argument… maybe that's a variant of the same question rather than a fourth one.\"*\n\n**What \"better\" means** — grade: *spelled out as a ranking; numeric weights absent.*\n\n- **Settled:** ordering is by lateness **and to whom** — *\"a late order to Meridian is worse than three late orders to a small distributor, so it's not just a count, it matters who.\"*\n- **Settled trade:** *\"a late Meridian order and… a scrap spike — I'll take the scrap spike every time, no contest. Scrap costs money, a late Meridian order costs a relationship and a fine.\"*\n- **Provisional, thought aloud, explicitly not settled:** late-and-to-whom > changeover hours lost > scrap, because *\"lost hours cascade into more lateness, whereas scrap is just money — annoying, contained, doesn't ripple.\"* You asked to be re-asked after sleeping on it. **No metric should be built on this ordering until you confirm it.**\n- Currency exchange rate between the three: **open.** Deposit: *\"sit down with commercial.\"*\n\n**Horizon** (spelled out): rolling week, built fresh Monday against that week's demand book, re-runnable at shift grain when something breaks at 06:00. *\"A quarter's too far out — I don't plan that far, ERP just doesn't give me visibility past a few weeks anyway.\"*\n\n**Boundary** (spelled out): begins when an order lands in the demand book from ERP; ends when the batch **clears QC hold and is released to the warehouse.** Trucks and warehouse slotting excluded — *\"logistics' sheet, not mine.\"* QC hold explicitly in scope — *\"I've had orders filled on time and still gone late because the lab backed up on a Friday.\"* Feedstock excluded except that resin slips must be representable — *\"otherwise you're modelling a plant that never has a bad Tuesday.\"*\n\n---\n\n## 2. Validation criteria\n\n| ID | Criterion | Grade |\n|---|---|---|\n| **VC-1** | The unwritten rules hold: Meridian white lands on Line 2; specialty never on Line 2; Line 3 never gets the two unqualified tint SKUs. *\"If it violates any of that, I'll dismiss it in about ten seconds, doesn't matter how clever the maths is.\"* | spelled out |\n| **VC-2** | Changeover asymmetry the right way round: **tint→white is the long washdown, white→tint is the quick one.** *\"If it shows tint-to-white as quick and white-to-tint as the long one, I'll know someone got the plant backwards.\"* | spelled out |\n| **VC-3** | Replay last week's book; the late orders it predicts are roughly the ones that actually went late — Meridian squeaked through by a few hours; a distributor order slid four days *\"with a phone call and nobody blinked\"*; the Line 1 tank issue bit us. You can reconstruct two or three such weeks from memory and the sheet. | spelled out |\n\n---\n\n## 3. The model\n\n### 3.1 Entity types\n\n| ID | Type | Distinctions the process treats apart | State it carries | Population |\n|---|---|---|---|---|\n| **ET-1** | **Order** — a line in the demand book | SKU; quantity (drums, sometimes bulk litres for big Meridian); due date; **customer tier — Meridian vs small distributor** | family (white / tint / specialty); due-date hardness; customer tier | ~**380–420 run-hours** of demand per week *(range)* |\n| **ET-2** | **Run** — a block on the sheet | *\"orders are what demand gives me, runs are what I actually schedule, and I'm the one deciding the mapping between them week to week.\"* One order's worth, or several small same-SKU orders lumped to clear minimum run size; a big order can split into two runs to interleave a rush job | line assignment; family; scheduled window | derived from ET-1 by OF-2 |\n| **ET-3** | **Line** | see 3.2 | current/last family (sets the changeover); qualification set; up / down | **3** |\n| **ET-4** | **Changeover crew** *(contended)* | one crew, **two techs**, **day shift**, covers all three lines | busy / free | **1** |\n| **ET-5** | **QC lab** *(contended)* | one lab, **two people**, serves all three lines | queue depth | **1** |\n| **ET-6** | **Stage within a line** | **mix → mill → tint/letdown → fill**, at different points on the line with small holding tanks between | tank level (see D-1) | 4 per line |\n\n### 3.2 The three lines (spelled out qualitatively; rates only partly numeric)\n\n- **Line 1** — *\"the old workhorse. Slower overall, but the most flexible: it's qualified for everything, whites, tints, specialty, all of it. It's the one you send something to when nowhere else can take it.\"* Weak point: the mill-to-fill tank is small — *\"if fill is slow and the tank's small, mill has to stop and wait, and that's dead time my sheet never sees.\"* Home of the mill motor. Two shifts.\n- **Line 2** — *\"the fast line. Built for volume.\"* Roughly **2× Line 1 on whites**; *\"that gap seems to shrink for tints, I don't actually know why… don't take 'twice as fast' as gospel outside whites.\"* **Not piped for the clear specialty resins** — *\"specialty simply cannot run there, full stop, that's physical not a preference.\"* Jam-prone filler. Two shifts.\n- **Line 3** — *\"newest, quick, but still being qualified SKU by SKU.\"* Two tint SKUs not signed off — *\"a QA/engineering decision from before my time on this role, I just know not to put them there.\"* Day shift only unless overtime approved.\n\n### 3.3 Families (spelled out, with one flagged sub-distinction)\n\n**Whites / tints / specialty** — *\"it's really about what a washdown has to deal with, not the product itself.\"* White-after-white and tint-after-tint are within-family. Flagged caveat, never separated on the sheet: *\"I wouldn't swear every tint-to-tint pair is really equal\"* — light-to-light may be gentler than light-to-dark.\n\n### 3.4 Boundary conditions\n\n| ID | What | Value | Grade |\n|---|---|---|---|\n| **BC-1** | **Demand book** | Built fresh Monday from ERP; **380–420 run-hours/week**. Rush orders land mid-week and force re-juggling — *\"rush orders are why the reroute-or-hold and idle-or-washdown calls happen in the first place half the time\"* | volume: **range**. **Arrival pattern: OPEN — top-tier gap** |\n| **BC-2** | **Line calendar** | L1 & L2 two shifts, 16 h/day ≈ 112 h/wk nominal, *\"though we don't always run weekends flat out — more like five and a half, six days realistically.\"* L3 day shift ≈ 56 h unless OT. Realistic total **270–300 run-hours** | **range** |\n| **BC-3** | **Changeover-crew calendar** | Day shift only. Night behaviour **unknown** — *\"Might be we call someone in. Might be it waits till morning. I'd have to check with the crew lead.\"* | **open — deposit: crew lead** |\n| **BC-4** | **QC lab calendar** | Day shift, *\"maybe with someone covering into evening, but I don't think there's a night presence… impression, not fact\"* | **open — deposit: the lab** |\n| **BC-5** | **Resin supply** | *\"mostly it's just there\"*; slips **~once a month**, and when it does *\"it stalls the run and I have to shuffle around it\"* | rate: **range**. Stall duration: **open** |\n| **BC-6** | **Structural over-commitment** | Book (380–420) always exceeds capacity (270–300). *\"I am always over capacity on paper, which is exactly why changeover hours and scrap matter so much — every hour lost to a washdown or a jam is an hour I don't have to spare.\"* Weekend/OT running *\"is a live lever, not a nice-to-have\"* | **spelled out** |\n\n### 3.5 Activities\n\n| ID | Activity | Duration | Occurrence rate | Mode-change loss | Grade / notes |\n|---|---|---|---|---|---|\n| **A-1** | **Run — Line 2, white, Meridian-sized** (line start to last drum filled; incl. ramp-up; excl. washdown before and QC after) | shortest realistically **9 h**; typical **10–11 h** (*\"that's the number that's actually on the sheet\"*); bad-but-not-freak **14–16 h**; freak **~24 h** (jam + material stall), *\"a genuine outlier… more 'the terrible day'\"* | n/a (step) | — | **spread-equivalent**, interval-first protocol (low/high then typical). Deciles not stated. **P07 unasked: variation by line/family/size OPEN** |\n| **A-2** | **Washdown, tint→white** | **3 hours** | n/a | — | **number, not spread.** You name *\"the washdown that overruns\"* as a tail source; overrun spread **open** |\n| **A-3** | **Changeover, white→tint** | *\"a bit of white residue in a tinted batch, who cares, it's getting colour anyway\"* — quick | n/a | — | **named only, no number** |\n| **A-4** | **Changeover, tint→tint** | **20–30 min** | n/a | — | **range**; light/dark sub-split suspected, never measured |\n| **A-5** | **Changeovers involving specialty** | — | — | — | **entirely open** |\n| **A-6** | **Ramp-up after washdown** | — | — | **scrap** — *\"that was the week I rushed the ramp after a washdown\"* → scrap spike | **named as a real loss; magnitude open.** Load-bearing for OBJ-2 |\n| **A-7** | **QC hold** | typical **~4 h**; specialty *\"can be a full day\"*. Decent-week bad case: Wed evening → Thu midday (~18 h) because of a mid-week backlog. **Friday tail: open** — *\"Friday's usually worse than that, I just don't have a clean anecdote for it yet\"* | — | — | typical: **number**; tails: partly qualitative |\n| **A-8** | **Filler jam** | short kind **0.5–1 h** — *\"four out of five\"*; long kind multi-hour (the *\"four-hour kind\"*) | **1–2 per week plant-wide**; long kind **once a month to every six weeks**; *\"It's Line 2's filler mostly\"* | — | rate: **range**; duration: **range**. Your caveat: *\"day-to-day impression, not a logged rate… roughly-right rather than exact\"* |\n| **A-9** | **Line 1 mill motor — multi-day failure** | *\"the four-day disaster\"* | **1–2 per year** — *\"maybe three, four times in the years I've been doing this job\"* | — | rate: **range**; duration: single anecdote |\n| **A-10** | **Line 1 mill motor — hiccup** | *\"a few hours\"* | **open** | — | the case that triggered OBJ-1 |\n| **A-9/A-10 joint instruction** | **Bimodal, not a continuum** | *\"either a nuisance under half a day or a genuine disaster, rarely something in the middle\"* | | | **Do not fit one smooth distribution across the gap** |\n| **A-11** | **Resin stall** | **open** | ~once a month (BC-5) | — | |\n| **A-12** | **Requalification** (running specialty on a line it hasn't recently run on) | **OPEN** | n/a | *\"eat the requalification headache\"*; characterised as a **known, bounded** cost | **Load-bearing for OBJ-1 and entirely unsized.** I asked what actually had to happen and how long it held the batch up; unanswered |\n| **A-13** | **Release to warehouse** | terminal event | — | — | end of scope |\n\n### 3.6 Ordering / flow\n\n- **OF-1 — the spine (spelled out).** Order lands in demand book → scheduler maps orders to runs (OF-2) → run placed on a line in a week slot (OF-3) → *if incoming family ≠ line's current family, changeover first (A-2/3/4/5)* → run executes: **mix → mill → tint/letdown → fill**, as a flow with small holding tanks between, so *\"while the back end of a batch is filling, the front end of the next batch could already be mixing, if there's product to feed it\"* → **QC hold (A-7)** → **release to warehouse (A-13)**.\n- **OF-2 — order↔run mapping (spelled out qualitatively).** Lump several small same-SKU orders to clear the minimum run size; split a big order into two runs to interleave a rush job. **Split cost** = an extra changeover plus extra ramp-up scrap. **Minimum run size: unquantified (C-4).**\n- **OF-3 — line choice (branch).** Filtered by C-1/C-2/C-3 and POL-1; the residual discretion is POL-5.\n- **OF-4 — blocking on Line 1 (spelled out, unquantified).** Small mill-to-fill tank: if fill lags, mill stops and waits. *\"Dead time my sheet never sees.\"*\n- **Known model/reality gap you volunteered.** The sheet says *\"Line 2 busy 06:00–18:00\"* and *\"doesn't capture that at all.\"* Whether the line is genuinely occupied that whole window — *\"I genuinely couldn't tell you without going and watching it, which is part of why I said the sheet flatters reality.\"*\n\n### 3.7 Policies\n\n| ID | Policy | As practiced | Overrides | Source-regime |\n|---|---|---|---|---|\n| **POL-1** | **Meridian white runs on Line 2** | Habit calcified into a rule after Meridian's people audited Line 2's fill area for supplier qualification. *\"I have never once put a Meridian order on Line 1, even under real pressure\"* — when Line 2 was down most of a day you **held the order and let it run late-ish** rather than move it, *\"because breaking that rule felt riskier than a few hours' delay.\"* | *\"Treat it as effectively hard.\"* Breakable **only** as an explicit what-if experiment — *\"not something I'd sanction as a live scheduling option.\"* | **prescribed:** nothing written, not a formal qualification. **practiced:** absolute. Both recorded. |\n| **POL-5** | **Reroute or hold** — the OBJ-1 rule | **Your settled wording:** *\"Hold by default, reroute only if staying put jams something you care about more.\"* With the asymmetry you gave: *\"requalification is a known, bounded cost and blocking the queue is an unknown, possibly-cascading one. So… I'll pay a known cost to avoid an unknown one, especially when I'm short on time to think it through properly, which at a 07:30 huddle I always am.\"* **Attention sequence, from the actual case:** (1) ask maintenance *\"is this the twenty-minute reset kind or do I need to be worried\"* — *\"that answer changes everything downstream\"*; (2) check the blocked job's own due date — if not screaming, default is wait; (3) look at what the other line is doing and, critically, **what is stacked behind the blocked job in its own line's queue**. *\"It wasn't 'specialty vs white' directly — it was 'if I don't clear Line 1's queue now, it backs up onto something that touches the white two days later.'\"* **Lookahead depth:** *\"one hop routinely, two hops only when hop one is already urgent-looking. Past that I'm guessing, not tracing.\"* **Tier-sensitivity of the trace:** *\"I trace further and act more readily when I suspect Meridian's at the other end of it than when I don't.\"* If the chain had ended at a small distributor — *\"I'd have shrugged, let Line 1's queue sit, and told the distributor's order it might run a day later, which is exactly the kind of slip that 'nobody notices.'\"* **Conditions that flip it to hold:** fix under an hour; the alternate line already tied up (*\"then rerouting isn't even a real option, it's theoretical\"*); nothing stacked behind. | **OPEN** — I asked for the case that breaks the pattern; unanswered. | practiced only |\n| **POL-6** | **Idle or washdown** — the OBJ-2 rule | **OPEN — the core of OBJ-2.** Situation known, rule absent. | open | — |\n| **POL-2** | **Long washdown pushed overnight** | *\"tint before white means I'm looking at the long washdown, and I wanted that overnight rather than eating into the day.\"* | not asked | practiced |\n| **POL-3** | **Washdowns scheduled to when the crew is on** | *\"we try to schedule washdowns for when the crew's on.\"* | night case unknown (BC-3) | practiced |\n| **POL-4** | **Avoid stacking family switches** | Signalled by its failure mode: *\"the changeover crew looking wrecked by Thursday because I stacked too many family switches back to back.\"* | not asked | practiced |\n| **POL-7** | **Changeover-crew contention** — who wins when two lines want the crew | **OPEN.** Symptom only: *\"Line 3 sitting clean but idle waiting on the crew — it happens more than I'd like.\"* | open | — |\n| **POL-8** | **QC lab queue discipline** | **OPEN** | open | — |\n| **POL-9** | **Overtime / weekend running** | Ops director's call; you supply the *\"we'll miss X without it\"* argument. | — | practiced |\n\n### 3.8 Constraints\n\n| ID | Limit | Consequence when hit |\n|---|---|---|\n| **C-1** | Specialty cannot run on Line 2 — not piped for clear specialty resins | Infeasible. Must go Line 1 or Line 3 |\n| **C-2** | Two tint SKUs not qualified on Line 3 | Cannot be scheduled there |\n| **C-3** | Line 1 qualified for everything | Fallback of last resort |\n| **C-4** | **Minimum run size** | Small orders must be lumped to clear it. **Threshold unquantified** |\n| **C-5** | One changeover crew → **one washdown at a time across all three lines** | The other line waits, clean and idle |\n| **C-6** | One QC lab, two people | Queue forms; holds stretch. **Parallelism unknown** |\n| **C-7** | Demand 380–420 vs capacity 270–300 run-hours per week | Something slips every week; OT/weekend is the release valve |\n| **C-8** | Meridian due date | *\"due Friday close of business, which for Meridian really means Friday, no wiggle\"* |\n\n### 3.9 Dynamics\n\n| ID | Quantity | Direction & rate | Noise | Threshold |\n|---|---|---|---|---|\n| **D-1** | **Line 1 mill-to-fill tank level** | Rises when mill outpaces fill; falls as fill proceeds. **Rate: open** | not asked | **At full: mill stops and waits.** Reset when fill catches up. This is the *\"dead time my sheet never sees\"* and the thing behind *\"I keep grumbling about Line 1's mill-to-fill tank\"* |\n\n### 3.10 Data bindings\n\n| ID | Variable | Feed | Note |\n|---|---|---|---|\n| **DB-1** | Order arrivals, quantities, due dates, customer | ERP demand book | The natural model input |\n| **DB-2** | Run durations in run-hours | Your weekly sheet | Already converted from rates — *\"I keep the sheet in run-hours already converted\"* |\n| **DB-3** | Per-stage cycle times by product and line | The historian | *\"if someone actually pulled cycle times apart by product and stage, which — as I said — nobody's done\"* |\n\n---\n\n## 4. Assumption ledger\n\nNothing here came from you. Each is mine, provisional, and needs a yes/no before it carries weight.\n\n| # | Assumption | Why it exists | How to check |\n|---|---|---|---|\n| **A1** | Changeover crew serves waiting lines **first-come-first-served** | C-5 is a hard bottleneck; the model must pick someone | Ask you (POL-7). You may well have a real priority rule — the Line 3 symptom suggests you do |\n| **A2** | QC lab works **FIFO** | C-6 needs a discipline | The lab; also ask whether you ever expedite a batch |\n| **A3** | A washdown falling outside day shift **waits until morning** | BC-3 unknown; the model must do something | Crew lead — you flagged this yourself |\n| **A4** | QC lab has **no night presence** | Your stated impression, not fact | The lab |\n| **A5** | Line 2's ~2× advantage over Line 1 applies to **whites only**; not extended to tints or specialty | You explicitly warned against extending it | Process engineering, or historian cycle times (DB-3) |\n| **A6** | Ramp-up scrap follows a **washdown**, not every changeover | Inferred from *\"the week I rushed the ramp after a washdown\"*; you never said it follows short changeovers | Ask you; ask quality |\n| **A7** | The ~24 h Meridian run is a **rare, roughly annual** tail, not part of the normal bad day | Your words were *\"once-a-year tail\"*, but treating one anecdote as a rate is my move | You |\n| **A8** | Filler jams are **1–2 per week plant-wide, concentrated on Line 2**, not 1–2 per line | *\"It's Line 2's filler mostly\"* is directional, not a split | You |\n| **A9** | POL-5's queue lookahead is evaluated **at the moment of disruption**, not continuously | Your account is of a 07:30 huddle decision; nothing says you re-trace during the day | You |\n| **A10** | \"Care about more\" in POL-5 is driven by **customer tier and due-date pressure** of the downstream job | You gave exactly these two factors (Meridian vs distributor; *\"screaming\"* vs slack due date) and no others; whether anything else counts is untested | You |\n\n---\n\n## 5. What the model leaves out, and why\n\n### Deliberately out of scope — your boundary\n\n- Order generation upstream of the demand book — *\"sales does whatever it does.\"*\n- Trucking, warehouse slotting, shipping — logistics' sheet.\n- Feedstock planning, except as the resin-slip disruption (BC-5).\n- Quarter-scale planning — you don't do it and ERP can't see that far.\n- **Overtime approval as a decision** — modelled as a lever (BC-2/POL-9), not as a choice the model optimises, because it isn't yours.\n\n### Deliberately simplified — and what is lost\n\n1. **Stage-level detail inside a run.** You schedule whole-run blocks and the model follows you — *except* on Line 1, where D-1/OF-4 keeps the mill-to-fill blocking because you named it as real dead time. **Lost:** any pipelining gain from overlapping the next batch's mix with this batch's fill, which you said physically exists. **Risk:** you told me the sheet *flatters* reality here, and OBJ-3 is precisely \"am I leaving hours on the table?\" This simplification is the one most likely to bite that objective. Flagged rather than resolved.\n2. **Tint-to-tint sub-families collapsed** to a single 20–30 min changeover. **Lost:** any light→dark penalty. Justified because you've never separated it on the sheet; revisit if the model starts over-favouring tint batching.\n3. **Queues are not modelled as named objects** — waits at the crew, the lab, and behind a blocked line emerge from the activities on either side. Nothing is lost operationally; it means you won't see a node called \"queue\" in the final net.\n\n### Open slots that stop the model running honestly\n\n**Top tier — an objective's core is missing:**\n\n1. **POL-6, idle-vs-washdown.** OBJ-2 has no rule at all. The situation is captured; the decision is not.\n2. **BC-1 rush-order arrivals.** Your own escalation: *\"if you only ask me about the steady-state rules… you'll have modelled the calm week and missed the reason I lose sleep.\"* OBJ-3 depends on it directly and OBJ-1/OBJ-2 depend on it as the trigger.\n3. **A-12 requalification cost.** OBJ-1 is a trade with one side unpriced. POL-5 now tells me *when* you pay it; nothing tells me *what* you pay. I asked and we stopped before the answer.\n\n**Second tier — hard bottlenecks running on my assumptions:**\n\n4. **POL-7 crew priority** (on A1) and **POL-8 lab discipline** (on A2). C-5 and C-6 are the two contended resources in the plant; both currently arbitrate by my guess.\n5. **A-6 ramp-up scrap magnitude.** OBJ-2 is literally *idle hour vs three-hour washdown plus ramp loss* — and the ramp loss has no number.\n6. **A-3, A-5** — the quick changeover has no duration; specialty changeovers are entirely absent.\n\n**Third tier — breadth:**\n\n7. **P07 unasked across the board.** I have one duration spread, for one product, on one line. Run duration by line, family, and size is unknown; A5 stops me extrapolating, which means Lines 1 and 3 currently have no durations at all.\n8. **Numeric trade weights** (deposit: commercial) and the **provisional \"better\" ranking** awaiting your confirmation.\n9. **A-10 hiccup rate**, **A-11 resin stall duration**, **D-1 tank fill/drain rate**, **A-2 overrun spread**, **A-7 Friday tail**, **C-4 minimum run size** — each a single missing figure.\n10. **POL-5's override case** — I asked for the exception that breaks the pattern and we stopped. A rule without its exception is where simulation and reality diverge.\n\n### Three deposits sitting with other people\n\n| Deposit | Question | Who |\n|---|---|---|\n| BC-3 | What happens to a washdown forced onto night shift | Crew lead |\n| BC-4, C-6 | Does the lab test in parallel, and how far into the evening is it covered | The lab |\n| A5 | Does Line 2's 2× speed advantage hold outside whites | Process engineering (or historian, DB-3) |\n\n### What I am not claiming\n\nI have elicited a model, not built a net. The Petri-net scaffold, the code obligations, and the formal loss report are produced by your tooling's projection from this model — I have not written them, and nothing here should be described as loadable, compiled, or simulated. Two things I'd expect that projection to report as uncarryable: the **ranked, non-numeric objective weights** (§1), and **POL-5's tier-sensitive lookahead depth** — *\"one hop routinely, two hops only when hop one is already urgent-looking\"* is a rule about how much of the future you attend to, and that is not a guard on a transition. It will need to be written as code or approximated, and either way it should be visible to you as a choice, not buried.\n\n### When you resume\n\nIn order: **POL-6** (idle-vs-washdown, via the last time you faced it) → **BC-1** (rush orders — how they arrive, how often, how much notice) → **A-12** (requalification: what actually has to happen, who does it, how long it holds the batch) → **POL-5's override case** → **POL-7** crew priority with a recent borderline call → the **\"better\" ranking** you wanted to sleep on."
     },
     {
       "role": "user",
@@ -819,7 +849,27 @@
     },
     {
       "role": "assistant",
-      "content": "# Coatings Plant Scheduling Model — final deliverable\n\n**Elicited from:** Marta, master scheduler\n**Job:** construct (no prior model existed)\n**Ended:** at the expert's stop. No new topics opened after it.\n**Status:** static floor satisfied; O2 and O3 near-complete; **O1's dependency slice incomplete** (see §4).\n**Convention:** every value is in Marta's vocabulary, with the precision actually obtained. `⚠` marks a slot the method demands and the interview did not get. Quoted text is hers.\n\n---\n\n## 1. The model\n\n### 1.1 Objectives\n\n**O1 — \"Hold the line versus wash it down now, which one actually costs less over the week\"**\n- *Question* **(spelled out)** — whether letting Line 2 sit idle about an hour, on a heads-up that another same-family white order is about to drop from a distributor, beats washing down now for the tint waiting behind. From a real Thursday two weeks before the interview. Her verdict on her own method: *\"I was guessing.\"*\n- *Depends on* — E1, E2, E3, E4, B1, B2, A4, A5, A6, A8, A9, F1, F2, F3, P3, P4, P5, C1, C2, C3.\n- *\"Better\"* **(named, not quantified)** — changeover hours over the week, subject to O2 holding absolutely. ⚠ no weight against lateness.\n- *Source-regime* — practiced.\n\n**O2 — \"Whether Meridian shipped on time, full stop, that's non-negotiable\"**\n- *Question* **(spelled out)** — does every Meridian order leave the dock in time for its appointment.\n- *\"On time\"* **(spelled out)** — a ship date on the order with a delivery window, resolving to a specific dock appointment at Meridian's end; in practice must leave our dock **one day ahead** for freight. *\"Not just 'shipped this week.'\"*\n- *Consequence of a miss* **(spelled out; unquantified ⚠)** — a fine, *\"I don't see the number, that's commercial's problem, but I hear about it\"*; and worse, a tracked on-time percentage with a delisting threat — *\"that's happened to a competitor of ours, so it's not an empty threat, and it's why the rule is absolute.\"*\n- *Depends on* — A8, A9, A10, B3, C4, C5, P1, P2.\n\n**O3 — Changeover hours**\n- *Question* **(spelled out)** — crew-hours spent washing down instead of filling: *\"every hour the crew spends washing down is an hour not filling anything.\"*\n- *Depends on* — A4, A5, A6, A7, E4, C2, P3.\n- *\"Better\"* **(named)** — fewer. Direction only; no target. ⚠\n\n**O4 — \"How ugly the sheet looks\"**\n- *Question* **(spelled out)** — *\"are there gaps where a line's sitting idle for no good reason.\"*\n- *\"Better\"* **(her words; explicitly not a number)** — *\"that last one's not a number, it's more a gut check, but it's real.\"*\n- *Depends on* — E3, C2, P3, P4, A4–A7. IR-only; see §3.\n\n**Trade-off among O2 / O3 / non-Meridian lateness** **(spelled out as a rule; deliberately unquantified ⚠)** — four changeover hours against one distributor order two days late: *\"honestly, yes, I'd take that trade most of the time\"*, a slip being *\"an annoyed phone call from our sales rep, not a fine.\"* But *\"'most of the time' is doing a lot of work in that sentence\"* — the same distributor slipping three weeks running *\"start[s] asking for a discount.\"* Soft, not infinitely soft, decaying with repetition on one customer. **Deposit:** *\"that's genuinely a 'sit down with commercial' conversation, nobody's ever made me quantify it.\"*\n\n---\n\n### 1.2 Entity types\n\n**E1 — Order (in the demand book)**\n- *Distinctions* **(spelled out)** — Meridian vs non-Meridian (flagged on the order; it *\"jumps to the top of my attention\"*); family, which drives allocation and changeover.\n- *State riding along* **(spelled out)** — SKU, quantity, due date + delivery window, Meridian flag, family: **base white / tinted colour / specialty clear**. *\"That's not my judgment, that's how the SKU's classified in the system, it drives what changeover you need going in and out.\"*\n- *Population* — ⚠ not obtained.\n\n**E2 — Batch**\n- *Distinctions* **(spelled out)** — inherits its order's family.\n- *Relation to E1* **(spelled out)** — *\"mostly the order is the batch, if it fits a reasonable run size\"*; split into two batches at different times when a distributor orders *\"more than makes sense in a single run\"* or to interleave something urgent. *\"Not a strict one-to-one — I have the freedom to split if I need to.\"*\n- *Population* — ⚠ run sizes, split cost not obtained.\n\n**E3 — Line** *(contended resource)*\n- *Distinctions* **(spelled out)** — **Line 1**: *\"the old workhorse — slower but it's qualified for everything, including specialty\"*; crew say it's *\"fussier to get properly clean.\"* **Line 2**: *\"the fast one, that's your big-volume runner.\"* **Line 3**: *\"the newest and quickest, but it's still being qualified product by product, so it can't run everything yet\"* — so far *\"mostly one or two SKUs.\"*\n- *State riding along* **(spelled out)** — the family the line is currently dirty with (selects the changeover, F3); its qualification set.\n- *How many* **(number)** — 3.\n\n**E4 — Changeover tech** *(contended resource)*\n- *Distinctions* **(named)** — none drawn; treated as interchangeable (ledger #8).\n- *State riding along* **(spelled out)** — which line they're committed to; can be *\"pulled away partway through\"*, and on long soaks *\"might duck off to start something on another line.\"*\n- *How many* **(number)** — 2 on day shift for all three lines. *\"That's it. No dedicated tech per line.\"*\n\n**E5 — QA lab**\n- ⚠ nothing obtained but its existence, that every batch passes through, and that it *\"gets backed up on a Friday afternoon.\"* Whether it queues like the techs is open — and load-bearing for O2 by her own diagnosis: *\"half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it.\"*\n\n---\n\n### 1.3 Boundary conditions\n\n**B1 — ERP weekly pull** — *starting state* **(spelled out)**: orders come from ERP on the weekly pull with SKU, quantity, due date, Meridian flag. *Arrival pattern* — ⚠ **not obtained** (demanded: spread).\n\n**B2 — Mid-week drop-in order and the heads-up before it** — ⚠ **not obtained** (demanded: spread). Only the anecdote: *\"I had a heads-up another same-family white order was about to drop in from a distributor.\"* Who, how far ahead, how often right: all unknown. **This is the trigger O1 hangs on.**\n\n**B3 — Meridian dock appointment** — *pattern* **(spelled out, qualitative)**: ship date + delivery window on the order, resolving to a specific appointment their end. Lead-time distribution ⚠.\n\n**B4 — Tech availability** — **partially spelled out**: two techs, **day shift**. Coverage outside day shift ⚠ (ledger #5).\n\n**B5 — Line 3 qualification set** — ⚠ *\"mostly one or two SKUs\"*; which ones, unknown.\n\n---\n\n### 1.4 Activities\n\n**A1 — Lands in the demand book.** Needs the weekly pull; produces an order in the book, flagged or not; unattended (ERP); instantaneous. **spelled out**\n\n**A2 — Allocate to a line.** Needs an order; produces an assignment; performed by Marta; not a schedule constraint — for Meridian whites *\"that's not really a decision.\"* Rule: P1. **spelled out**\n\n**A3 — Reorder the queue.** Needs an order behind others; produces a changed sequence; performed by Marta. *\"Sometimes I'll reorder things a bit so it doesn't get stuck behind a big changeover.\"* Rule: P4. **spelled out**\n\n**A4 — Quick rinse, same family (white→white), Line 2**\n- *Needs* — previous batch off, a tech free, next SKU same family. *Produces* — *\"the fill head's actually running clean product again.\"*\n- *Performed by* **(named)** — one tech.\n- *Duration, line down* **(spread)** — **typical 25 min**; **worse 45 min**, *\"usually because the tech's tied up finishing something on another line first and there's a wait before they even start on Line 2\"*; **better 15 min**, *\"if the tech's standing right there and it's a genuinely easy one.\"*\n- *Crew hands-on* **(spelled out)** — equals line-down: *\"the tech's on it start to finish, no gap between 'crew starts' and 'line stops.'\"*\n- *Mode-change loss* — this activity **is** the loss.\n- *Varies by type* **(named)** — yes, by family-pair (F3). By line: ⚠ ledger #1, #2.\n\n**A5 — White → tint, Line 2** — *\"the easier direction\"*\n- *Performed by* **(named)** — one tech.\n- *Duration, line down* **(spread)** — **typical 45 min**; **worse \"an hour and a bit\"** (ledger #3), *\"if the tech gets pulled away partway through\"*; **better ~30 min**, *\"if everything's staged.\"*\n- *Crew hands-on* **(spelled out, qualitative)** — *\"hands-on for most of it — this one doesn't have much soak-and-wait, it's mostly just doing the work.\"* Fraction: ledger #4.\n\n**A6 — Tint → white, Line 2, full washdown** — *\"the ugly one\"*\n- *Needs* — as A5 plus a **passing visual check** before release to production.\n- *Duration, line down* **(spread)** — **typical ~3 h**; **worse 4 h \"maybe a bit more\"** (ledger #3), *\"if it doesn't pass the visual check first time and they have to redo part of it\"*; **better ~2 h**, *\"a clean fast one… if the crew's good and nothing complicates it.\"*\n- *Crew hands-on* **(spelled out, qualitative; her own hedge preserved)** — *\"less than the 3 hours suggests — there's real soak and rinse-cycle time where the tech's not standing there… I'd guess they're actually working maybe half of that.\"* Fraction: ledger #4.\n- *Rationale* **(spelled out)** — *\"any pigment left behind ruins a white batch, so it's a full washdown.\"*\n- **Asymmetry is load-bearing** — *\"It absolutely depends on direction — that's the thing people forget… it is absolutely not symmetric, and it trips people up if they assume it is.\"*\n\n**A7 — Into / out of specialty clear, Line 1**\n- *Duration, line down* **(spread)** — **typical 2 h**, *\"roughly the same both directions, unlike white/tint\"*; **worse 3 h**, *\"if it's coming out of clear and they're being extra careful about residue, since clear can be sneaky — you don't always see it the way you'd see pigment\"*; **better 1.5 h**, *\"a quick swap and the line was already fairly clean.\"*\n- *Crew hands-on* **(spelled out, qualitative)** — *\"most of that — specialty doesn't have the long soak cycles… it's more just physically thorough cleaning because the product's thick and clingy.\"* Fraction: ledger #4.\n\n**A8 — Run the batch** — mix, mill, tint (or *\"straight through if it's a plain white\"*), fill, pack.\n- *Needs* **(spelled out)** — clean line in the right family state; batch released to run. *Produces* **(spelled out)** — filled and packed batch.\n- *Performed by* — ⚠ line operators never elicited as a resource.\n- *Duration* — ⚠ **nothing obtained** (demanded: spread, per family and per line).\n- *Varies by type* — partially: *\"for a white that's usually the more straightforward path\"*, but no durations attach.\n- **The largest hole in the model.** O1 is a question about a week; run time is most of a week.\n\n**A9 — QA hold and release** — *\"every batch does.\"*\n- *Performed by* **(named)** — the lab (E5).\n- *Duration* — *\"typically a few hours before it's released\"*: an honest **number at the wrong precision**; demanded as a **spread**. ⚠\n- *Failure path* — ⚠ never asked.\n- *Pathology* **(spelled out qualitatively; rate ⚠)** — *\"if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line\"*; *\"the QA step is the one people don't think about when they're mad at scheduling.\"*\n\n**A10 — Stage for shipping and ship.** Needs QA release; produces the order off the dock; *\"that's when the truck appointment matters.\"* Constraint C4. Duration ⚠.\n\n**A11 — Tech pulled away mid-changeover** *(event, not step)* — named as the mechanism behind A4's and A5's worse tails. *Rate* ⚠ not obtained separately; currently only implicit in those tails (P01 unsatisfied).\n\n**A12 — Washdown fails the visual check, part redone** *(event, not step)* — named as the mechanism behind A6's 4 h tail. *Rate* ⚠ (ledger #7).\n\n**A13 — \"The mill motor issue\"** *(event, named in passing only)* — offered as an example of what a *structural* line difference would look like, in contrast to Line 1 merely being fussier. Rate ⚠, duration ⚠, consequence ⚠. This is the entirety of the breakdown stratum, which was never swept.\n\n---\n\n### 1.5 Ordering / flow\n\n**F1 — The main arc, desk to dock** **(spelled out — her six steps)**\n1. Lands in the demand book (ERP weekly pull).\n2. Allocated to a line (*\"Meridian whites always go to Line 2\"*).\n3. Sits in the queue behind whatever's running — reorderable (A3/P4).\n4. Changeover if needed (F3), then runs: mix, mill, tint-or-straight-through, fill, pack.\n5. QA hold.\n6. Released, staged, out against the truck appointment.\n\n**F2 — Order-to-batch split** — *order* **(spelled out)**: one batch by default, possibly two run at different times. *Branch decided by* **(spelled out)**: Marta, on run size or urgency-interleaving. *Cost of a split* ⚠ (P03 unresolved).\n\n**F3 — Which changeover applies** **(spelled out)** — by (family on the line, family of next batch, line): same family → **A4**; white→tint → **A5**; tint→white → **A6**; into/out of specialty → **A7** (Line 1 only).\n\n---\n\n### 1.6 Policies\n\n**P1 — \"Meridian whites always go to Line 2, that's just how it's done here.\"** *Practiced* **(spelled out)**; a fixed allocation, not a decision. Overrides ⚠ never asked.\n\n**P2 — Meridian on-time is absolute.** *Practiced* **(spelled out)** — *\"we don't even try to be clever about it.\"* Overrides **(spelled out)**: none — that is the policy's content. Rationale: fine, on-time percentage, delisting precedent.\n\n**P3 — Who gets the tech when two lines want one**\n- *Prescribed form:* **none exists** — *\"there's no posted rule at all.\"*\n- *As practiced* **(spelled out)** — in the room: *\"whoever's louder at the huddle, or whoever's about to actually run dry.\"* The underlying logic: *\"it's mostly gut triage: whichever line has the more time-sensitive order behind it wins, and if that's a tie, whichever changeover is faster wins so you get a line moving sooner.\"*\n- *Borderline case on record* — Line 1 and Line 3 both wanted a washdown one morning. **Line 3 got the tech**, *\"not because it was more important, but because Line 3's changeover was the quick one and Line 1's was going to be the long tint-to-white slog anyway, so the thinking was 'knock out the fast one, get that line moving, then commit the tech to the long one.'\"* Line 1 sat **clean-but-waiting almost 40 minutes**.\n- *What overrides it* **(spelled out)** — the ops director: *\"I've been overruled by the ops director once when he wanted his pet SKU out the door.\"*\n- *Rationale* **(spelled out)** — *\"the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line\"* — *\"the bit that actually causes grief at the huddle.\"*\n\n**P4 — Reorder so a job isn't stuck behind a big changeover.** *Practiced* **(spelled out)**. Overrides ⚠.\n\n**P5 — Hold the line for an anticipated same-family order** *(the decision under test)*. *Practiced, one instance* **(spelled out)** — hold Line 2 idle *\"maybe an hour\"* rather than wash down for the waiting tint, *\"because doing them back to back would save us a full washdown.\"* Trigger strength and holding threshold ⚠ (depends on B2).\n\n**P6 — Batch-split discretion.** *Practiced* **(spelled out)** — *\"I have the freedom to split if I need to.\"* Overrides ⚠.\n\n---\n\n### 1.7 Constraints\n\n**C1 — Line qualification.** *Limit* **(partially spelled out)** — Line 1 everything incl. specialty; Line 3 product-by-product, *\"can't run everything yet\"* (which SKUs ⚠); Line 2's set ⚠. *When hit* **(spelled out)** — the batch cannot go on that line.\n\n**C2 — Two techs, three lines.** *Limit* **(spelled out)**. *When hit* **(spelled out)** — *\"if Line 1 and Line 3 both want a washdown at the same time, one of them waits\"* — clean-but-idle, 40 min in the recorded case; resolved by P3.\n\n**C3 — Tint→white needs a full washdown passing a visual check.** *When hit* **(spelled out)** — *\"any pigment left behind ruins a white batch\"*; a failed check means part is redone (A12).\n\n**C4 — Meridian must leave our dock a day ahead of the appointment.** *When hit* **(spelled out)** — fine, on-time percentage damage, delisting exposure.\n\n**C5 — Every batch passes QA hold before release.** *When hit* **(spelled out)** — nothing ships unreleased; it waits in hold.\n\n**Unwritten constraints** — ⚠ the closing sweep was never run. The one that surfaced unprompted is the changeover asymmetry: *\"that one catches everybody, including people who've been on the floor a lot longer than me.\"*\n\n---\n\n### 1.8 Dynamics\n\n**None.** Nothing described evolves continuously while nothing discrete happens. The soak and rinse-cycle time inside A6 is dead time *within* an activity, not a state variable crossing a threshold; I have deliberately not promoted it to one.\n\n---\n\n### 1.9 Data bindings *(named only — project to nothing today)*\n\n| Feed | Would drive | Provenance |\n|---|---|---|\n| Changeover logs (tech start/finish) | A4–A7 durations, crew hands-on fractions; retires ledger #1, #4 | **Qualified:** *\"I've never audited that field myself, I mostly just glance at duration.\"* Coverage unknown, possibly patchy; **Line 1 and Line 3** named as where to look. Marta will flag it to the two techs. |\n| ERP demand book | B1, B2 | not discussed |\n| QA release timestamps | A9 duration, lab queueing | not discussed |\n| Meridian on-time percentage | O2 | tracked by Meridian; visible to commercial |\n\n**Finding in its own right:** patchy changeover logging concentrated on Lines 1 and 3 is evidence about the plant, not merely an obstacle — *\"that itself would be useful for you to know, not just an inconvenience.\"*\n\n---\n\n### 1.10 Validation criteria\n\n⚠ **None obtained.** How Marta would know the model is right was never asked.\n\n---\n\n## 2. Assumption ledger\n\nEverything here is mine. None of it is hers.\n\n| # | Assumption | Why | How to check |\n|---|---|---|---|\n| **1** | Line 1 changeover durations = Line 2 × **1.2**, all types | She could not give Line 1 minutes — *\"I couldn't swear the minutes are identical… the crew sometimes says it's fussier.\"* I proposed 20%; she replied *\"20% sounds about right, not double.\"* **The factor originated with me**; her assent is not authorship. | Changeover logs, Line 1 vs Line 2, same family-pair. **Blocked by the unaudited start/finish field — and Line 1 is one of the two lines she expects to be patchy.** |\n| **2** | Line 3 changeover durations = Line 2, unscaled | *\"Line 3 I genuinely don't have a good feel for… you're stuck assuming it's like Line 1 or Line 2.\"* She offered the disjunction; **picking Line 2 was mine.** | As #1, once Line 3 has run more products. Also expected patchy. |\n| **3** | \"An hour and a bit\" (A5 worse) = **70 min**; \"4, maybe a bit more\" (A6 worse) = **4.5 h** | Numeric readings so the spreads are usable. | One question to Marta: confirm or correct. |\n| **4** | Crew hands-on: A4 = **1.0**, A5 = **0.8**, A6 = **0.5**, A7 = **0.8** | A4's 1.0 is hers, stated. A6's 0.5 tracks *\"maybe half of that\"* — but note her hedge, *\"I'd guess.\"* **The two 0.8s, from \"most of it\" / \"most of that\", are mine.** | Changeover logs vs tech time records, or ask the techs. Same blocker as #1. |\n| **5** | No changeover outside day shift | She said *\"two techs on **day shift**\"*; other coverage never asked. | One question to Marta. |\n| **6** | A changeover needs exactly **one** tech | She said *\"the tech\"*, singular, throughout — including the 3-hour washdown. | One question to Marta or the techs. |\n| **7** | A12 folded **inside** A6's 4 h tail rather than a separate event with its own rate | She described it as *the cause of* the tail. Keeps the spread self-contained; contrary to P01, which would separate rate from duration. | Ask how often the visual check fails first time; split it out if common. |\n| **8** | The two techs are **interchangeable** | She drew no distinction. | One question to Marta. |\n\n**Second-order note on #1 and #4:** their check depends on a feed of unverified coverage, concentrated exactly where the assumptions bite. If the field proves patchy on Line 1, the honest move is to **widen** them, not fill them in.\n\n---\n\n## 3. What the model leaves out, and why\n\n**Deliberately excluded**\n- **Queues, buffers, waiting states** are not nodes — the wait behind a running batch, the wait for a tech, the wait in QA hold. Each is implied by the activities either side and emerges in projection. Line 1's 40 minutes clean-but-waiting is an **output** the model should reproduce, not an input.\n- **The commercial layer** — fine amount, on-time percentage mechanics, delisting threshold. C4 and O2 carry the hard deadline; the money is outside the scheduler's sight and commercial owns it.\n- **Individual tech identity** (ledger #8). **Scenarios** — assembled from B1–B5 at simulation time, not elicited.\n\n**Real, and the formalism cannot carry it — kept in words**\n- **O4, \"how ugly the sheet looks.\"** A criterion she genuinely uses and explicitly refuses to number. Approximating it as line idle hours would be my move; I have not made it.\n- **The O2 / O3 / lateness trade-off weight.** Unquantified with the source named. The model can report changeover hours, Meridian lateness and distributor lateness **separately**, but cannot rank two schedules that trade one against another — a real limit on O1, whose \"costs less\" implicitly spans them.\n- **The decay of softness** — the same distributor slipping *\"the third week running\"* turning into a discount demand: a memory effect across weeks on one customer, stated as a rule, unquantified, unrepresented.\n- **The huddle.** *\"Whoever's louder\"* and the ops director's pet-SKU override are the real P3 in the room. The triage logic is compilable; loudness and the override are not. **Any run of this model will be quieter and more rational than the plant.** Remember that when a result looks tidy.\n\n---\n\n## 4. What remains unknown, in the order I would close it\n\n1. **A8 run duration** — nothing at all, per family and per line, as a spread. **Nothing about O1 is answerable until this exists.**\n2. **B2, the drop-in and the heads-up** — who, how far ahead, how often right. P5 is the decision under test and its trigger is one anecdote.\n3. **A9 QA hold** — *\"a few hours\"* is honest at the wrong precision; and whether the lab queues like the techs. By her own account this is where lateness actually comes from, so it bears directly on O2.\n4. **B1** — orders per weekly pull and within-week shape.\n5. **E2 / F2** — run sizes, the \"reasonable run size\" threshold, and what a split costs in extra changeovers.\n6. **C1 / B5** — which SKUs Line 3 is qualified for; whether Line 2 has restrictions.\n7. **Breakdowns and interruptions** — the whole stratum. A13 is a name with no rate, duration or consequence; A11 and A12 need rate separated from duration.\n8. **Unwritten-constraint sweep** and **validation criteria** — neither was run.\n\n**Status against the completion criteria**\n- **Static floor: satisfied** — 4 objectives, 5 entity types, 13 activities, 3 ordering/flow nodes.\n- **O2, O3:** slices substantially satisfied except A8 and A9 durations.\n- **O1: slice incomplete.** A8 has no duration; B2 has no arrival pattern. O1 is currently **answerable only for Line 2**, and only once run times exist. Ledger #1–#4 are the first assumptions to attack if any Line 1 or Line 3 result ever looks decisive.\n- **O4:** recorded; unsupported for quantitative use, by its author's own description.\n\n**What I do not claim.** I have elicited a model, not built a net. The SDCPN scaffold, the code-obligation sidecar and the typed loss report are derived from this model by the tooling's projection — I have not written them, and I am not claiming this loads, compiles, or runs. The A8 hole alone would stop it.\n\n---\n\n*Session closed at the expert's stop. Three questions queued for resumption: run duration for a plain white on Line 2 (typical / one-in-ten worse / one-in-ten better); the heads-up mechanism behind B2; QA hold as a spread, and whether the lab queues.*"
+      "content": "Stopping here. Nothing new asked. This is the final deliverable, self-contained.\n\n---\n\n# Coatings Plant Scheduling Model — final\n\n**Stopping outcome: `expert-stopped` — partial model with open slots.**\nStructural floor met (3 objectives, 6 entity-types, 13 activities, 4 ordering/flow nodes). No objective's dependency slice is complete: OBJ-1 has its rule but not its cost; OBJ-2 and OBJ-3 are missing their cores. Every value is at the grade you gave it; nothing has been promoted or invented.\n\n---\n\n## 1. Objectives\n\n| ID | The question, in your words | Depends on | Slice |\n|---|---|---|---|\n| **OBJ-1 Reroute or hold** | *\"whether to shift the specialty over to Line 3 and eat the requalification headache, or hold it and let the white slip behind on Line 2\"* — *\"I'd love to run twice and see which one bites me less\"* | POL-5, A-12, ET-1, ET-3, C-1/2/3, POL-1, A-9, A-10, OF-3 | **Partial** — rule captured, requalification cost absent |\n| **OBJ-2 Idle or washdown** | *\"do I sit Line 2 empty for an hour waiting on a same-family order, or just pay the three-hour washdown now\"* — *\"almost weekly and it's pure feel\"* | POL-6, A-2, A-3, A-4, A-6, ET-4, C-5, BC-1 | **Unsupported** — the deciding rule is absent |\n| **OBJ-3 Run size & sequencing** | *\"whether to split a big order into two runs to slot in a rush job, or batch several small orders of the same family together even if it means one of them ships a bit early and sits in the warehouse\"* — *\"I've never had a way to check if I'm leaving hours on the table\"* | OF-2, C-4, A-6, A-2/3/4, BC-1, ET-2 | **Unsupported** — rush arrivals and minimum run size absent |\n\nNoted, not yours to test — overtime approval: *\"that's the ops director's call, though I do feed him the 'we'll miss X without it' argument… maybe that's a variant of the same question rather than a fourth one.\"*\n\n**\"Better\"** — grade: ranking spelled out, numeric weights absent.\n- Settled: lateness **and to whom** — *\"a late order to Meridian is worse than three late orders to a small distributor, so it's not just a count, it matters who.\"*\n- Settled trade: *\"I'll take the scrap spike every time, no contest. Scrap costs money, a late Meridian order costs a relationship and a fine.\"*\n- **Provisional, thought aloud, not settled:** late-and-to-whom > changeover hours lost > scrap, because *\"lost hours cascade into more lateness, whereas scrap is just money — annoying, contained, doesn't ripple.\"* You asked to be re-asked. **No metric should be built on this ordering until you confirm it.**\n- Currency exchange rate: **open**. Deposit: *\"sit down with commercial.\"*\n\n**Horizon:** rolling week built fresh Monday against that week's book, re-runnable at shift grain when something breaks at 06:00. *\"A quarter's too far out.\"*\n\n**Boundary:** starts when an order lands in the demand book from ERP; ends when the batch **clears QC hold and is released to the warehouse**. Trucks and warehouse slotting out — *\"logistics' sheet, not mine.\"* QC hold explicitly in — *\"I've had orders filled on time and still gone late because the lab backed up on a Friday.\"* Feedstock out except resin slips — *\"otherwise you're modelling a plant that never has a bad Tuesday.\"*\n\n---\n\n## 2. Validation criteria\n\n- **VC-1** Unwritten rules hold: Meridian white on Line 2; specialty never on Line 2; the two unqualified tint SKUs never on Line 3. *\"If it violates any of that, I'll dismiss it in about ten seconds.\"*\n- **VC-2** Changeover asymmetry the right way round: **tint→white long, white→tint quick.** *\"If it shows tint-to-white as quick… someone got the plant backwards.\"*\n- **VC-3** Replay last week's book; predicted lates roughly match actual — Meridian squeaked by a few hours, a distributor slid four days *\"with a phone call and nobody blinked\"*, the Line 1 tank issue bit. Two or three such weeks reconstructable.\n\n---\n\n## 3. Model\n\n### Entity types\n\n| ID | Type | Distinctions | Carried state | Population |\n|---|---|---|---|---|\n| ET-1 | **Order** (line in the demand book) | SKU; quantity (drums, sometimes bulk litres for big Meridian); due date; **customer tier — Meridian vs small distributor** | family; due-date hardness; tier | ~**380–420 run-hours**/week *(range)* |\n| ET-2 | **Run** (block on the sheet) | *\"orders are what demand gives me, runs are what I actually schedule, and I'm the one deciding the mapping\"*; one order, or small same-SKU orders lumped; a big order splittable in two | line, family, window | derived via OF-2 |\n| ET-3 | **Line** | see below | current/last family; qualifications; up/down | **3** |\n| ET-4 | **Changeover crew** *(contended)* | one crew, **two techs**, **day shift**, all three lines | busy/free | **1** |\n| ET-5 | **QC lab** *(contended)* | one lab, **two people**, all three lines | queue depth | **1** |\n| ET-6 | **Stage** | **mix → mill → tint/letdown → fill**, small holding tanks between | tank level (D-1) | 4 per line |\n\n**Lines.** *Line 1* — *\"the old workhorse. Slower overall, but the most flexible: qualified for everything… the one you send something to when nowhere else can take it.\"* Small mill-to-fill tank: *\"if fill is slow and the tank's small, mill has to stop and wait, and that's dead time my sheet never sees.\"* Home of the mill motor. Two shifts. — *Line 2* — *\"the fast line. Built for volume.\"* ~**2× Line 1 on whites**; *\"that gap seems to shrink for tints, I don't actually know why\"*, explicitly not gospel outside whites. **Not piped for clear specialty resins** — *\"full stop, that's physical not a preference.\"* Jam-prone filler. Two shifts. — *Line 3* — *\"newest, quick, but still being qualified SKU by SKU.\"* Two tint SKUs unsigned — *\"a QA/engineering decision from before my time.\"* Day shift only unless OT.\n\n**Families.** Whites / tints / specialty — *\"it's really about what a washdown has to deal with, not the product itself.\"* Flagged: *\"I wouldn't swear every tint-to-tint pair is really equal\"* (light→light vs light→dark), never separated on the sheet.\n\n### Boundary conditions\n\n| ID | What | Value | Grade |\n|---|---|---|---|\n| BC-1 | Demand book | Monday-fresh from ERP; **380–420 run-hours/wk**. Rush orders land mid-week — *\"rush orders are why the reroute-or-hold and idle-or-washdown calls happen in the first place half the time\"* | volume: range. **Arrival pattern OPEN — top tier** |\n| BC-2 | Line calendar | L1, L2 two shifts ≈112 h/wk nominal, *\"we don't always run weekends flat out — more like five and a half, six days realistically\"*; L3 ≈56 h unless OT. Realistic total **270–300 h** | range |\n| BC-3 | Crew calendar | Day shift. Nights **unknown** — *\"Might be we call someone in. Might be it waits till morning.\"* | open — crew lead |\n| BC-4 | Lab calendar | Day shift, *\"maybe with someone covering into evening… impression, not fact\"* | open — the lab |\n| BC-5 | Resin supply | *\"mostly it's just there\"*; slips **~monthly**, *\"it stalls the run and I have to shuffle around it\"* | rate: range; stall duration open |\n| BC-6 | Over-commitment | Book always exceeds capacity. *\"Every hour lost to a washdown or a jam is an hour I don't have to spare.\"* Weekend/OT *\"a live lever, not a nice-to-have\"* | spelled out |\n\n### Activities\n\n| ID | Activity | Duration | Rate | Loss | Grade |\n|---|---|---|---|---|---|\n| A-1 | Run — Line 2, white, Meridian-sized (line start → last drum; incl. ramp-up, excl. washdown/QC) | **9 h** shortest realistic; **10–11 h** typical (*\"the number that's actually on the sheet\"*); **14–16 h** bad-not-freak; **~24 h** freak (jam + material stall), *\"more 'the terrible day'\"* | n/a | — | spread-equivalent, interval-first. **P07 unasked** |\n| A-2 | Washdown **tint→white** | **3 h** | n/a | — | number; *\"the washdown that overruns\"* — overrun spread open |\n| A-3 | Changeover **white→tint** | *\"a bit of white residue in a tinted batch, who cares, it's getting colour anyway\"* — quick | n/a | — | **named, no number** |\n| A-4 | Changeover **tint→tint** | **20–30 min** | n/a | — | range; light/dark split suspected, unmeasured |\n| A-5 | Changeovers involving **specialty** | — | — | — | **entirely open** |\n| A-6 | **Ramp-up after washdown** | — | — | scrap — *\"that was the week I rushed the ramp after a washdown\"* | **named, magnitude open**; load-bearing for OBJ-2 |\n| A-7 | **QC hold** | typical **~4 h**; specialty *\"can be a full day\"*; decent-week bad case Wed eve→Thu midday (~18 h). **Friday tail open** — *\"Friday's usually worse than that, I just don't have a clean anecdote for it yet\"* | — | — | typical: number; tails partly qualitative |\n| A-8 | **Filler jam** | short **0.5–1 h** (*\"four out of five\"*); long multi-hour (*\"the four-hour kind\"*) | **1–2/week plant-wide**; long kind **monthly to every 6 weeks**; *\"It's Line 2's filler mostly\"* | — | ranges; *\"day-to-day impression, not a logged rate\"* |\n| A-9 | **Mill motor — multi-day** | *\"the four-day disaster\"* | **1–2/year** (*\"three, four times in the years I've been doing this job\"*) | — | rate range; duration one anecdote |\n| A-10 | **Mill motor — hiccup** | *\"a few hours\"* | **open** | — | trigger case for OBJ-1 |\n| — | **A-9/A-10 instruction** | **Bimodal:** *\"either a nuisance under half a day or a genuine disaster, rarely something in the middle.\"* **Do not fit one smooth distribution across the gap.** | | | |\n| A-11 | **Resin stall** | open | ~monthly | — | |\n| A-12 | **Requalification** | **OPEN** | n/a | *\"eat the requalification headache\"*; a **known, bounded** cost | **Load-bearing for OBJ-1, unsized** |\n| A-13 | Release to warehouse | terminal | — | — | end of scope |\n\n### Ordering / flow\n\n- **OF-1 spine:** order → orders mapped to runs → run placed on a line → *if family differs, changeover first* → run executes **mix → mill → tint/letdown → fill** as a flow with tanks between, so *\"while the back end of a batch is filling, the front end of the next batch could already be mixing, if there's product to feed it\"* → **QC hold** → **release to warehouse**.\n- **OF-2 order↔run mapping:** lump small same-SKU orders to clear minimum run size; split a big order to interleave a rush job. Split cost = extra changeover + extra ramp-up scrap. **Minimum run size unquantified.**\n- **OF-3 line choice:** filtered by C-1/2/3 and POL-1; residual discretion is POL-5.\n- **OF-4 blocking (Line 1):** small mill-to-fill tank; fill lags → mill stalls. *\"Dead time my sheet never sees.\"*\n- **Volunteered model/reality gap:** the sheet says *\"Line 2 busy 06:00–18:00\"* and *\"doesn't capture that at all\"* — *\"I genuinely couldn't tell you without going and watching it… the sheet flatters reality.\"*\n\n### Policies\n\n| ID | Policy | As practiced | Overrides |\n|---|---|---|---|\n| **POL-1** | Meridian white on Line 2 | Habit calcified into a rule after Meridian audited Line 2's fill area. *\"I have never once put a Meridian order on Line 1, even under real pressure\"* — with Line 2 down most of a day you held the order and let it run late-ish, *\"because breaking that rule felt riskier than a few hours' delay.\"* Prescribed: nothing written. Practiced: absolute. | *\"Treat it as effectively hard.\"* Breakable only as a what-if — *\"not something I'd sanction as a live scheduling option.\"* |\n| **POL-5** | **Reroute or hold** (OBJ-1) | **Your wording:** *\"Hold by default, reroute only if staying put jams something you care about more.\"* Asymmetry: *\"requalification is a known, bounded cost and blocking the queue is an unknown, possibly-cascading one… I'll pay a known cost to avoid an unknown one, especially when I'm short on time to think it through properly, which at a 07:30 huddle I always am.\"* **Attention order:** (1) maintenance — *\"is this the twenty-minute reset kind or do I need to be worried\"*, *\"that answer changes everything downstream\"*; (2) the blocked job's own due date — if not screaming, default is wait; (3) **what is stacked behind it in its own line's queue** — *\"it wasn't 'specialty vs white' directly — it was 'if I don't clear Line 1's queue now, it backs up onto something that touches the white two days later.'\"* **Depth:** *\"one hop routinely, two hops only when hop one is already urgent-looking. Past that I'm guessing, not tracing.\"* **Tier-sensitivity:** *\"I trace further and act more readily when I suspect Meridian's at the other end of it than when I don't\"*; chain ending at a distributor — *\"I'd have shrugged… told the distributor's order it might run a day later, which is exactly the kind of slip that 'nobody notices.'\"* **Flips to hold if:** fix under an hour; alternate line already tied up (*\"then rerouting isn't even a real option, it's theoretical\"*); nothing stacked behind. | **OPEN** — the exception case was asked and not reached |\n| **POL-6** | **Idle or washdown** (OBJ-2) | **OPEN — core of OBJ-2.** Situation known, rule absent | open |\n| POL-2 | Long washdown pushed overnight | *\"tint before white means I'm looking at the long washdown, and I wanted that overnight rather than eating into the day\"* | not asked |\n| POL-3 | Washdowns to when the crew is on | *\"we try to schedule washdowns for when the crew's on\"* | night case unknown |\n| POL-4 | Avoid stacking family switches | Known by its failure: *\"the changeover crew looking wrecked by Thursday because I stacked too many family switches back to back\"* | not asked |\n| POL-7 | Crew contention | **OPEN.** Symptom only: *\"Line 3 sitting clean but idle waiting on the crew — it happens more than I'd like\"* | open |\n| POL-8 | Lab queue discipline | **OPEN** | open |\n| POL-9 | Overtime / weekend | Ops director's call; you supply *\"we'll miss X without it\"* | — |\n\n### Constraints\n\nC-1 Specialty cannot run on Line 2 (not piped) → must go L1 or L3. C-2 Two tint SKUs not qualified on Line 3 → cannot be scheduled there. C-3 Line 1 qualified for everything → fallback of last resort. C-4 **Minimum run size** → small orders lumped; **threshold unquantified**. C-5 One crew → **one washdown at a time across all three lines**; the other line waits clean and idle. C-6 One lab, two people → queue forms; **parallelism unknown**. C-7 380–420 demanded vs 270–300 available → something slips weekly; OT/weekend is the release valve. C-8 *\"due Friday close of business, which for Meridian really means Friday, no wiggle.\"*\n\n### Dynamics\n\n**D-1 Line 1 mill-to-fill tank level.** Rises when mill outpaces fill, falls as fill proceeds; **rate open**, noise not asked. **Threshold: at full, mill stops and waits**; resets when fill catches up. This is *\"the dead time my sheet never sees\"* and the reason *\"I keep grumbling about Line 1's mill-to-fill tank.\"*\n\n### Data bindings\n\nDB-1 order arrivals/quantities/due dates/customer ← ERP demand book. DB-2 run durations in run-hours ← your weekly sheet, *\"already converted\"*. DB-3 per-stage cycle times by product and line ← the historian, *\"which — as I said — nobody's done.\"*\n\n---\n\n## 4. Assumption ledger — mine, not yours\n\n| # | Assumption | Why | Check with |\n|---|---|---|---|\n| A1 | Crew serves waiting lines **FCFS** | C-5 must arbitrate | You (POL-7) — the Line 3 symptom suggests a real rule exists |\n| A2 | Lab works **FIFO** | C-6 must arbitrate | The lab; also whether you expedite |\n| A3 | Washdown outside day shift **waits until morning** | BC-3 unknown | Crew lead |\n| A4 | Lab has **no night presence** | Your impression, not fact | The lab |\n| A5 | Line 2's 2× applies to **whites only** | You warned against extending it | Process engineering, or DB-3 |\n| A6 | Ramp-up scrap follows **washdowns**, not every changeover | Inferred from one phrase | You; quality |\n| A7 | The ~24 h run is a **roughly annual** tail | Treating one anecdote as a rate is my move | You |\n| A8 | Jams are **1–2/wk plant-wide, concentrated on Line 2** | *\"mostly\"* is directional, not a split | You |\n| A9 | POL-5's lookahead is evaluated **at the moment of disruption**, not continuously | Your account is of a 07:30 call | You |\n| A10 | \"Care about more\" = **downstream tier + due-date pressure**, nothing else | Those are the only two factors you named | You |\n\n---\n\n## 5. Losses\n\n**Deliberately out of scope:** upstream order generation; trucking/warehouse/shipping; feedstock planning except resin slips; quarter-scale planning; overtime as a *decision* (modelled as a lever, not a choice, because it isn't yours).\n\n**Deliberately simplified, and what it costs:**\n1. **Stage detail inside a run** collapsed to whole-run blocks, *except* Line 1's mill-to-fill blocking (D-1/OF-4). Lost: pipelining gain from overlapping next-batch mix with this-batch fill, which you said physically exists. **This is the simplification most likely to mislead OBJ-3**, since you told me the sheet flatters reality and OBJ-3 asks whether you're leaving hours on the table.\n2. **Tint-to-tint collapsed** to one 20–30 min changeover. Lost: any light→dark penalty. Revisit if the model over-favours tint batching.\n3. **Queues are not nodes** — waits at crew, lab, and behind a blocked line emerge from the activities either side. No operational loss; you just won't see a box labelled \"queue.\"\n\n**Open and load-bearing — top tier:** POL-6 (OBJ-2 has no rule); BC-1 rush arrivals (*\"you'll have modelled the calm week and missed the reason I lose sleep\"*); A-12 requalification cost (OBJ-1's trade has one side unpriced — POL-5 says *when* you pay, nothing says *what*).\n**Second tier:** POL-7 and POL-8 — both contended resources currently arbitrated by my assumptions; A-6 ramp-up scrap magnitude (OBJ-2 is literally idle hour vs 3 h washdown *plus ramp loss*); A-3 and A-5 durations.\n**Third tier:** P07 unasked — one spread, one product, one line, so Lines 1 and 3 have no durations at all; numeric trade weights (commercial); the provisional \"better\" ranking awaiting your confirmation; A-10 hiccup rate, A-11 stall duration, D-1 tank rate, A-2 overrun spread, A-7 Friday tail, C-4 minimum run size; **POL-5's override case** — a rule without its exception is where simulation and reality diverge.\n\n**Deposits with other people:** crew lead (washdown forced onto nights); the lab (parallel testing, evening cover); process engineering or the historian (does 2× hold outside whites).\n\n**What I do not claim.** This is an elicited model, not a net. The Petri-net scaffold, code obligations, and formal loss report come from your tooling's projection of it — I have not written them, and nothing here is loadable, compiled, or simulated. Two things I'd expect that projection to flag as uncarryable: the **ranked, non-numeric objective weights**, and **POL-5's tier-sensitive lookahead** — *\"one hop routinely, two hops only when hop one is already urgent-looking\"* is a rule about how far ahead you attend, not a guard on a transition. It will have to be written as code or approximated, and that should be a visible choice, not buried.\n\n**Resumption order, when you have time:** POL-6 → BC-1 rush orders → A-12 requalification → POL-5's override case → POL-7 crew priority → confirm the \"better\" ranking."
+    },
+    {
+      "role": "user",
+      "content": "I really do have to stop here. Please produce the model now with everything you have."
+    },
+    {
+      "role": "assistant",
+      "content": "Delivered. This is the handover copy — complete, self-contained, nothing new asked.\n\n---\n\n# Coatings Plant Scheduling Model\n\n**Stopping outcome: `expert-stopped` — partial model with open slots.** Floor met (3 objectives, 6 entity-types, 13 activities, 4 flow nodes). No objective's dependency slice is complete. All values at the grade you gave them.\n\n## Objectives\n\n- **OBJ-1 Reroute or hold** — *\"whether to shift the specialty over to Line 3 and eat the requalification headache, or hold it and let the white slip behind on Line 2\"*; *\"run it twice and see which one bites me less.\"* Depends on POL-5, A-12, ET-1/3, C-1/2/3, POL-1, A-9/10, OF-3. **Partial** — rule present, requalification cost absent.\n- **OBJ-2 Idle or washdown** — *\"do I sit Line 2 empty for an hour waiting on a same-family order, or just pay the three-hour washdown now\"*; *\"almost weekly and it's pure feel.\"* Depends on POL-6, A-2/3/4/6, ET-4, C-5, BC-1. **Unsupported** — the rule is absent.\n- **OBJ-3 Run size & sequencing** — *\"whether to split a big order into two runs to slot in a rush job, or batch several small orders of the same family together even if it means one of them ships a bit early.\"* Depends on OF-2, C-4, A-6, A-2/3/4, BC-1, ET-2. **Unsupported** — rush arrivals and minimum run size absent.\n- Not yours to test: overtime approval — *\"the ops director's call.\"*\n\n**\"Better\"** (ranking spelled out, numbers absent). Settled: lateness **and to whom** — *\"a late order to Meridian is worse than three late orders to a small distributor.\"* Settled trade: *\"I'll take the scrap spike every time, no contest.\"* **Provisional, thought aloud:** late-and-who > changeover hours > scrap, *\"lost hours cascade into more lateness, whereas scrap is just money.\"* **Do not build a metric on this until confirmed.** Currency weights open — deposit: commercial.\n\n**Horizon:** rolling week, Monday-fresh, re-runnable at shift grain. **Boundary:** demand book → **release to warehouse after QC hold**. Trucks and warehouse out; QC hold in (*\"filled on time and still gone late because the lab backed up on a Friday\"*); feedstock out except resin slips (*\"otherwise you're modelling a plant that never has a bad Tuesday\"*).\n\n## Validation criteria\n\n**VC-1** unwritten rules hold (Meridian white→L2; specialty never L2; two tint SKUs never L3) — *\"I'll dismiss it in about ten seconds.\"* **VC-2** tint→white long, white→tint quick. **VC-3** replay last week: Meridian squeaks by hours, a distributor slides four days *\"and nobody blinked\"*, the L1 tank issue bites.\n\n## Entity types\n\n**ET-1 Order** — SKU, quantity (drums/bulk litres), due date, **tier (Meridian vs small distributor)**; carries family, due-date hardness, tier; ~**380–420 run-hours/week**. **ET-2 Run** — *\"orders are what demand gives me, runs are what I actually schedule\"*; one order, or small same-SKU orders lumped; big orders splittable. **ET-3 Line** ×3. **ET-4 Changeover crew** — one crew, two techs, day shift, all lines *(contended)*. **ET-5 QC lab** — one lab, two people, all lines *(contended)*. **ET-6 Stage** — mix → mill → tint/letdown → fill, small tanks between.\n\n**Line 1** *\"old workhorse… slower, most flexible, qualified for everything… the one you send something to when nowhere else can take it\"*; small mill-to-fill tank; mill motor; two shifts. **Line 2** *\"the fast line\"*, ~**2× L1 on whites**, gap *\"seems to shrink for tints\"* — not gospel outside whites; **specialty physically impossible**; jam-prone filler; two shifts. **Line 3** newest, quick, **two tint SKUs unqualified**; day shift unless OT.\n\n**Families** whites / tints / specialty — *\"about what a washdown has to deal with.\"* Caveat: *\"I wouldn't swear every tint-to-tint pair is really equal.\"*\n\n## Boundary conditions\n\n**BC-1** book 380–420 h/wk, Monday-fresh; **rush arrivals OPEN — top-tier gap** (*\"why the reroute and idle calls happen in the first place half the time\"*). **BC-2** L1/L2 ≈112 h nominal but *\"five and a half, six days realistically\"*; L3 ≈56 h; realistic total **270–300 h**. **BC-3** crew day shift; nights unknown (*\"Might be we call someone in. Might be it waits till morning\"*). **BC-4** lab day shift, evening cover uncertain, *\"impression, not fact.\"* **BC-5** resin slips **~monthly**, stall duration open. **BC-6** demand always exceeds capacity — *\"every hour lost to a washdown or a jam is an hour I don't have to spare.\"*\n\n## Activities\n\n| ID | Duration | Rate | Notes |\n|---|---|---|---|\n| **A-1** Run, L2 white, Meridian-sized | **9 h** low, **10–11 h** typical, **14–16 h** bad, **~24 h** freak (*\"the terrible day\"*) | — | spread-equivalent, interval-first. **P07 unasked** |\n| **A-2** Washdown tint→white | **3 h** | — | number only; overruns mentioned, unquantified |\n| **A-3** Changeover white→tint | quick — *\"who cares, it's getting colour anyway\"* | — | **no number** |\n| **A-4** Changeover tint→tint | **20–30 min** | — | light/dark split unmeasured |\n| **A-5** Specialty changeovers | — | — | **entirely open** |\n| **A-6** Ramp-up after washdown | — | — | scrap loss named, **magnitude open**; load-bearing for OBJ-2 |\n| **A-7** QC hold | ~**4 h** typical; specialty *\"a full day\"*; mid-week bad case ~18 h; **Friday tail open** | — | *\"Friday's usually worse than that\"* |\n| **A-8** Filler jam | short **0.5–1 h** (four in five); long multi-hour | **1–2/wk plant-wide**; long **monthly–6-weekly**; *\"Line 2's filler mostly\"* | *\"impression, not a logged rate\"* |\n| **A-9** Mill motor, multi-day | *\"the four-day disaster\"* | **1–2/yr** | |\n| **A-10** Mill motor, hiccup | *\"a few hours\"* | **open** | |\n| — | **Bimodal instruction:** *\"either a nuisance under half a day or a genuine disaster, rarely something in the middle.\"* No smooth continuum. | | |\n| **A-11** Resin stall | open | ~monthly | |\n| **A-12** Requalification | **OPEN** | — | *\"a known, bounded cost\"*; **OBJ-1's unpriced side** |\n| **A-13** Release to warehouse | terminal | | |\n\n## Flow\n\n**OF-1** order → mapped to runs → placed on a line → changeover if family differs → mix/mill/letdown/fill as a flow (*\"while the back end of a batch is filling, the front end of the next batch could already be mixing\"*) → QC hold → release. **OF-2** lump small same-SKU orders; split big orders for rush jobs; split cost = extra changeover + extra ramp scrap; **minimum run size unquantified**. **OF-3** line choice = C-1/2/3 + POL-1, residual discretion = POL-5. **OF-4** L1 tank blocking — *\"dead time my sheet never sees.\"* Volunteered gap: the sheet *\"flatters reality\"*; whether L2 is truly busy 06:00–18:00, *\"I couldn't tell you without going and watching it.\"*\n\n## Policies\n\n- **POL-1 Meridian white on Line 2** — audit-born habit; *\"I have never once put a Meridian order on Line 1, even under real pressure\"*; you held an order late-ish rather than move it. **Effectively hard**; breakable only as a what-if. (Prescribed: unwritten. Practiced: absolute.)\n- **POL-5 Reroute or hold** — *\"Hold by default, reroute only if staying put jams something you care about more.\"* Asymmetry: *\"requalification is a known, bounded cost and blocking the queue is an unknown, possibly-cascading one… especially when I'm short on time to think it through properly, which at a 07:30 huddle I always am.\"* Attention: (1) maintenance — *\"is this the twenty-minute reset kind or do I need to be worried\"*; (2) blocked job's own due date; (3) what's stacked behind it — *\"it wasn't 'specialty vs white' directly.\"* Depth: *\"one hop routinely, two hops only when hop one is already urgent-looking. Past that I'm guessing.\"* Tier: *\"I trace further and act more readily when I suspect Meridian's at the other end.\"* Flips to hold if fix <1 h, alternate line tied up, or nothing behind. **Override case OPEN.**\n- **POL-6 Idle or washdown — OPEN, core of OBJ-2.**\n- **POL-2** long washdown overnight. **POL-3** washdowns to when the crew is on. **POL-4** avoid stacking family switches (*\"the crew looking wrecked by Thursday\"*). **POL-7 crew contention OPEN** (symptom: *\"Line 3 sitting clean but idle\"*). **POL-8 lab discipline OPEN.** **POL-9** OT is the ops director's call.\n\n## Constraints\n\nC-1 no specialty on L2 (physical). C-2 two tint SKUs not on L3. C-3 L1 qualified for all — last resort. C-4 minimum run size, **unquantified**. C-5 **one washdown at a time plant-wide**; others wait clean and idle. C-6 one lab, two people; **parallelism unknown**. C-7 380–420 vs 270–300 → something slips weekly. C-8 *\"Friday close of business, which for Meridian really means Friday, no wiggle.\"*\n\n## Dynamics\n\n**D-1 L1 mill-to-fill tank** — rises when mill outpaces fill, **rate open**; **threshold: at full, mill stops and waits**; resets when fill catches up.\n\n## Data bindings\n\nDB-1 orders ← ERP book. DB-2 run-hours ← your sheet (already converted). DB-3 per-stage cycle times ← historian, *\"nobody's done\"* it.\n\n---\n\n## Assumption ledger (mine, not yours)\n\n1. Crew serves FCFS — check with you; the L3 symptom suggests a real rule. 2. Lab FIFO — check with lab. 3. Night washdown waits till morning — crew lead. 4. No lab night presence — the lab. 5. L2's 2× is whites-only, not extended — process engineering/historian. 6. Ramp scrap follows washdowns, not all changeovers — you/quality. 7. The ~24 h run is roughly annual (one anecdote read as a rate) — you. 8. Jams 1–2/wk plant-wide concentrated on L2, not per line — you. 9. POL-5 lookahead evaluated at the moment of disruption, not continuously — you. 10. \"Care about more\" = downstream tier + due-date pressure only — you.\n\n## Losses\n\n**Out of scope:** upstream order generation; logistics; feedstock planning bar resin slips; quarter horizon; OT as a decision.\n\n**Simplified, with cost:** (1) stage detail collapsed to run blocks except L1 tank blocking — loses pipelining gain; **most likely to mislead OBJ-3**, since the sheet flatters and OBJ-3 asks whether hours are being left on the table. (2) tint→tint collapsed to one changeover — loses any light→dark penalty. (3) queues are not nodes — they emerge from the activities either side.\n\n**Open, top tier:** POL-6; BC-1 rush arrivals (*\"you'll have modelled the calm week and missed the reason I lose sleep\"*); A-12 requalification. **Second:** POL-7, POL-8 (both bottlenecks on my assumptions); A-6 scrap magnitude; A-3, A-5. **Third:** P07 across lines/families — Lines 1 and 3 have no durations at all; numeric trade weights; the provisional ranking; A-10 rate, A-11 duration, D-1 rate, A-2 overrun, A-7 Friday tail, C-4 threshold; POL-5's override case.\n\n**Deposits with others:** crew lead (night washdown), lab (parallelism, evening cover), process engineering/historian (2× outside whites).\n\n**Not claimed:** this is an elicited model, not a net. Your tooling's projection produces the Petri-net scaffold, code obligations, and formal loss report — nothing here is loadable, compiled, or simulated. Expect two items to project badly: the ranked non-numeric weights, and POL-5's tier-sensitive lookahead (*\"one hop routinely, two hops only when hop one is already urgent-looking\"* is not a guard on a transition). Both will need code or approximation — make that a visible choice.\n\n**When you resume:** POL-6 → rush orders → requalification → POL-5's exception → crew priority → confirm the ranking."
+    },
+    {
+      "role": "user",
+      "content": "I really do have to stop here. Please produce the model now with everything you have."
+    },
+    {
+      "role": "assistant",
+      "content": "Here it is — final, complete, and the last thing I'll send.\n\n---\n\n# Coatings Plant Scheduling Model — handover\n\n**Stopping outcome: `expert-stopped` — partial model with open slots.** Floor met (3 objectives, 6 entity-types, 13 activities, 4 flow nodes). No objective's slice is complete. Every value is at the grade you gave it; nothing promoted, nothing invented.\n\n## Objectives\n\n**OBJ-1 Reroute or hold** — *\"whether to shift the specialty over to Line 3 and eat the requalification headache, or hold it and let the white slip behind on Line 2\"*; *\"run it twice and see which one bites me less.\"* → POL-5, A-12, ET-1/3, C-1/2/3, POL-1, A-9/10, OF-3. **Partial: rule present, cost absent.**\n\n**OBJ-2 Idle or washdown** — *\"do I sit Line 2 empty for an hour waiting on a same-family order, or just pay the three-hour washdown now\"*; *\"almost weekly and it's pure feel.\"* → POL-6, A-2/3/4/6, ET-4, C-5, BC-1. **Unsupported: no rule.**\n\n**OBJ-3 Run size & sequencing** — *\"split a big order into two runs to slot in a rush job, or batch several small orders of the same family together even if it means one ships a bit early.\"* → OF-2, C-4, A-6, A-2/3/4, BC-1, ET-2. **Unsupported: no rush arrivals, no minimum run size.**\n\nNot yours: overtime approval — *\"the ops director's call.\"*\n\n**\"Better\"**: ranking spelled out, numbers absent. Settled — lateness **and to whom** (*\"a late order to Meridian is worse than three late orders to a small distributor\"*); *\"I'll take the scrap spike every time, no contest.\"* Provisional, thought aloud, **do not build a metric on it yet** — late-and-who > changeover hours > scrap, *\"lost hours cascade into more lateness, whereas scrap is just money.\"* Currency weights open; deposit: commercial.\n\n**Horizon** rolling week, Monday-fresh, re-runnable at shift grain. **Boundary** demand book → release to warehouse after QC hold; trucks/warehouse out; QC hold in (*\"filled on time and still gone late because the lab backed up on a Friday\"*); feedstock out except resin slips (*\"otherwise you're modelling a plant that never has a bad Tuesday\"*).\n\n## Validation\n\n**VC-1** unwritten rules hold — Meridian white→L2, specialty never L2, two tint SKUs never L3 (*\"I'll dismiss it in about ten seconds\"*). **VC-2** tint→white long, white→tint quick. **VC-3** replay last week — Meridian squeaks by hours, distributor slides four days *\"and nobody blinked\"*, L1 tank issue bites.\n\n## Entity types\n\n**ET-1 Order** — SKU, quantity (drums/bulk litres), due date, **tier**; carries family, due-date hardness, tier; **380–420 run-hours/wk**. **ET-2 Run** — *\"orders are what demand gives me, runs are what I actually schedule\"*; lumped or split. **ET-3 Line** ×3. **ET-4 Changeover crew** — one crew, two techs, day shift, all lines *(contended)*. **ET-5 QC lab** — one lab, two people *(contended)*. **ET-6 Stage** — mix → mill → letdown → fill, small tanks between.\n\n**L1** *\"old workhorse… slowest, most flexible, qualified for everything\"*; small mill-to-fill tank; mill motor; two shifts. **L2** *\"the fast line\"*, ~2× L1 **on whites only** (gap *\"seems to shrink for tints\"*); specialty physically impossible; jam-prone filler; two shifts. **L3** newest, quick, two tint SKUs unqualified; day shift unless OT.\n\n**Families** whites/tints/specialty — *\"about what a washdown has to deal with.\"* Caveat: *\"I wouldn't swear every tint-to-tint pair is really equal.\"*\n\n## Boundary conditions\n\n**BC-1** 380–420 h/wk; **rush arrivals OPEN, top-tier**. **BC-2** L1/L2 ≈112 h nominal but *\"five and a half, six days realistically\"*; L3 ≈56 h; realistic **270–300 h**. **BC-3** crew day shift, nights unknown. **BC-4** lab day shift, evening cover *\"impression, not fact.\"* **BC-5** resin slips ~monthly, stall duration open. **BC-6** demand always exceeds capacity.\n\n## Activities\n\n**A-1** L2 white run: **9 h** low / **10–11 h** typical / **14–16 h** bad / **~24 h** freak; P07 unasked. **A-2** washdown tint→white **3 h** (overruns unquantified). **A-3** white→tint quick, **no number**. **A-4** tint→tint **20–30 min**. **A-5** specialty changeovers **open**. **A-6** ramp-up scrap named, **magnitude open**. **A-7** QC hold ~**4 h** typical, specialty *\"a full day\"*, mid-week bad ~18 h, **Friday tail open**. **A-8** filler jam 0.5–1 h (four in five) / multi-hour; **1–2/wk plant-wide**, long kind monthly–6-weekly, *\"Line 2's filler mostly\"*. **A-9** mill motor multi-day, **1–2/yr**. **A-10** hiccup *\"a few hours\"*, rate open. **Bimodal instruction:** *\"either a nuisance under half a day or a genuine disaster, rarely something in the middle.\"* **A-11** resin stall. **A-12 requalification — OPEN**, OBJ-1's unpriced side. **A-13** release.\n\n## Flow\n\n**OF-1** order → runs → line → changeover if family differs → mix/mill/letdown/fill as a flow → QC hold → release. **OF-2** lump small same-SKU orders; split big ones for rush jobs; split cost = extra changeover + ramp scrap; minimum size unquantified. **OF-3** line choice = constraints + POL-1, residual = POL-5. **OF-4** L1 tank blocking, *\"dead time my sheet never sees.\"* Volunteered: the sheet *\"flatters reality.\"*\n\n## Policies\n\n**POL-1** Meridian white on L2 — audit-born habit, *\"never once… even under real pressure\"*; effectively hard, breakable only as a what-if. **POL-5** *\"Hold by default, reroute only if staying put jams something you care about more\"*; known-bounded cost preferred over unknown-cascading; attention order motor → own due date → what's stacked behind; depth *\"one hop routinely, two hops only when hop one is already urgent-looking\"*; traces further when Meridian is at the end; flips to hold if fix <1 h, alternate line busy, or nothing behind. **Override case OPEN.** **POL-6 OPEN** (OBJ-2's core). **POL-2** long washdown overnight. **POL-3** washdowns when crew is on. **POL-4** avoid stacking family switches. **POL-7 crew contention OPEN**. **POL-8 lab discipline OPEN**. **POL-9** OT not yours.\n\n## Constraints\n\nC-1 no specialty on L2. C-2 two tint SKUs off L3. C-3 L1 does everything. C-4 minimum run size, unquantified. C-5 one washdown at a time plant-wide. C-6 one lab, parallelism unknown. C-7 380–420 vs 270–300. C-8 *\"Friday really means Friday, no wiggle.\"*\n\n## Dynamics\n\n**D-1** L1 mill-to-fill tank — rises when mill outpaces fill (**rate open**); at full, **mill stops and waits**; resets when fill catches up.\n\n## Data bindings\n\nDB-1 orders ← ERP. DB-2 run-hours ← your sheet. DB-3 per-stage cycle times ← historian, *\"nobody's done\"* it.\n\n---\n\n## Assumption ledger (mine)\n\n1 crew FCFS · 2 lab FIFO · 3 night washdown waits till morning · 4 no lab nights · 5 2× is whites-only · 6 ramp scrap after washdowns only · 7 24 h run ≈ annual · 8 jams plant-wide, L2-concentrated · 9 POL-5 evaluated at disruption · 10 \"care about more\" = tier + due-date pressure only. Checks: you, the lab, the crew lead, process engineering.\n\n## Losses\n\n**Out:** upstream sales, logistics, feedstock planning, quarter horizon, OT as a decision.\n**Simplified:** stage detail collapsed except L1 blocking — **most likely to mislead OBJ-3**; tint→tint collapsed; queues emerge rather than being nodes.\n**Open, top tier:** POL-6; rush arrivals (*\"you'll have modelled the calm week and missed the reason I lose sleep\"*); A-12. **Second:** POL-7/8, A-6 magnitude, A-3, A-5. **Third:** P07 — Lines 1 and 3 have no durations at all; trade weights; the provisional ranking; A-10, A-11, D-1, A-2, A-7, C-4; POL-5's exception.\n**Deposits:** crew lead, lab, process engineering.\n**Not claimed:** this is an elicited model, not a net. Your tooling projects the scaffold; nothing here is loadable or simulated. Expect the non-numeric ranking and POL-5's tier-sensitive lookahead to need code or approximation — make that visible, not buried.\n\n**Resume at:** POL-6 → rush orders → requalification → POL-5's exception → crew priority → confirm the ranking.\n\nThat's everything. Thanks for the time you gave it."
+    },
+    {
+      "role": "user",
+      "content": "I really do have to stop here. Please produce the model now with everything you have."
     }
   ]
 }
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-captures.json b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-captures.json
index 134268ce2f3..fdbda5e2ba5 100644
--- a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-captures.json
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-captures.json
@@ -6,70 +6,39 @@
         "value": {
           "type": "slot-asserted",
           "kind": "objective",
-          "node": "which option actually loses less",
+          "node": "wash down for the tint now, or sit the line for the white order coming later",
           "slot": "the question, in the expert's words",
           "precision": "spelled out",
           "sourceRegime": "practiced",
-          "rationale": "Stated as the decision the model must settle: given a line-down event with unknown ETA, which of the available scheduling options loses less.",
+          "rationale": "The expert's own recent decision, stated as the first question to put to the model.",
           "assertion": {
-            "value": "When a line goes down with ETA unknown, be able to enter that state and have the model say which option — wait out the repair, or move the order to the other line — actually loses less, instead of the scheduler doing gut math at the huddle."
+            "value": "Whether to wash down for the tint right then, or let the line sit idle for about an hour waiting for another same-colour (white) order that will be released from the demand book later that day — i.e. whether sitting the line was actually the cheaper choice or just the safer-feeling one."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+          "excerpt": "I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 3,
             "entryEnd": 3
           },
           "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"When a line goes down with ETA unknown, be able to enter that state and have the model say which option — wait out the repair, or move the order to the other line — actually loses less, instead of the scheduler doing gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the decision the model must settle: given a line-down event with unknown ETA, which of the available scheduling options loses less.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "objective",
-          "node": "which option actually loses less",
-          "slot": "what \"better\" means, and trade-off weights",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "Expert gave a lexicographic scorecard with an explicit refusal of a formula for the second tier.",
-          "assertion": {
-            "value": "First and non-negotiable: days late on the Meridian order, where anything above zero is bad. Below that, weighed together with no formula: washdown hours, and whether the bumped order goes late and by how much — with judgment applied to who the customer is and who can absorb the slip (a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem)."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
         },
         {
-          "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+          "excerpt": "That's exactly the kind of call I'd love to be able to test",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-76159984-4b11-446f-a707-bc8302ef0b1d",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First and non-negotiable: days late on the Meridian order, where anything above zero is bad. Below that, weighed together with no formula: washdown hours, and whether the bumped order goes late and by how much — with judgment applied to who the customer is and who can absorb the slip (a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem).\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Expert gave a lexicographic scorecard with an explicit refusal of a formula for the second tier.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-66f2471d-7a05-4ea9-a788-ddd5d45380c5",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whether to wash down for the tint right then, or let the line sit idle for about an hour waiting for another same-colour (white) order that will be released from the demand book later that day — i.e. whether sitting the line was actually the cheaper choice or just the safer-feeling one.\"},\"kind\":\"objective\",\"node\":\"wash down for the tint now, or sit the line for the white order coming later\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own recent decision, stated as the first question to put to the model.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That's exactly the kind of call I'd love to be able to test\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "hedged",
@@ -77,34 +46,33 @@
         "value": {
           "type": "slot-asserted",
           "kind": "objective",
-          "node": "which option actually loses less",
+          "node": "wash down for the tint now, or sit the line for the white order coming later",
           "slot": "the nodes it depends on",
           "precision": "named",
-          "rationale": "The scorecard names the washdown, the line-down event, and the orders with their due dates and customers as what the answer is computed from.",
+          "rationale": "The expert names changeover hours, idle hours and late orders as the things the model must put on the same page.",
           "assertion": {
             "value": [
-              "activity:tint-to-white washdown",
-              "activity:Line 2 filler jam",
+              "activity:full white-to-tint changeover",
               "entity-type:order",
-              "entity-type:line"
+              "policy:we just don't do that (Meridian never slips)"
             ]
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+          "excerpt": "in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 6,
             "entryEnd": 6
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
+          "excerpt": "if the model's going to tell me anything useful, it has to connect those — because right now I only track them separately",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 6,
             "entryEnd": 6
           },
@@ -112,172 +80,206 @@
         }
       ],
       "epistemicStatus": "inferred",
-      "id": "capture-3f2444d5-8001-46d9-8a92-c85f8c6f8d6a",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:tint-to-white washdown\",\"activity:Line 2 filler jam\",\"entity-type:order\",\"entity-type:line\"]},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard names the washdown, the line-down event, and the orders with their due dates and customers as what the answer is computed from.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-239ae929-f206-452e-a332-ba47e5c16cf2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:full white-to-tint changeover\",\"entity-type:order\",\"policy:we just don't do that (Meridian never slips)\"]},\"kind\":\"objective\",\"node\":\"wash down for the tint now, or sit the line for the white order coming later\",\"precision\":\"named\",\"rationale\":\"The expert names changeover hours, idle hours and late orders as the things the model must put on the same page.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"if the model's going to tell me anything useful, it has to connect those — because right now I only track them separately\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "how long it takes",
-          "precision": "number",
+          "kind": "objective",
+          "node": "wash down for the tint now, or sit the line for the white order coming later",
+          "slot": "what \"better\" means, and trade-off weights",
+          "precision": "spelled out",
           "sourceRegime": "practiced",
-          "rationale": "Expert gave a single figure, not a spread; the low/high and typical are not yet on record.",
+          "rationale": "Better = fewer late orders with Meridian dominating; the expert explicitly refuses an exchange rate and names where a number would have to come from.",
           "assertion": {
-            "value": "three hours"
+            "value": "Graded on the late-order count, with Meridian orders weighted extra heavy in practice though nobody has written that down; three non-Meridian orders a day late each is the better week than one Meridian order a day late, and the trade does not flip even at twenty small orders versus one Meridian — so no exchange rate exists; a real number would require getting commercial in a room and forcing them to say it out loud."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+          "excerpt": "If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I don't think it does flip, not in any range I'd actually see in a week. Even if you told me \"twenty small orders late\" versus \"one Meridian order late\" — I'd still not want to be the one who let Meridian slip.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"three hours\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Expert gave a single figure, not a spread; the low/high and typical are not yet on record.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-da18e2cd-2af7-4aab-ade0-cd33e819a88b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Graded on the late-order count, with Meridian orders weighted extra heavy in practice though nobody has written that down; three non-Meridian orders a day late each is the better week than one Meridian order a day late, and the trade does not flip even at twenty small orders versus one Meridian — so no exchange rate exists; a real number would require getting commercial in a room and forcing them to say it out loud.\"},\"kind\":\"objective\",\"node\":\"wash down for the tint now, or sit the line for the white order coming later\",\"precision\":\"spelled out\",\"rationale\":\"Better = fewer late orders with Meridian dominating; the expert explicitly refuses an exchange rate and names where a number would have to come from.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't think it does flip, not in any range I'd actually see in a week. Even if you told me \\\\\\\"twenty small orders late\\\\\\\" versus \\\\\\\"one Meridian order late\\\\\\\" — I'd still not want to be the one who let Meridian slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what it produces or changes",
+          "kind": "policy",
+          "node": "we just don't do that (Meridian never slips)",
+          "slot": "the rule as actually practiced",
           "precision": "spelled out",
           "sourceRegime": "practiced",
-          "rationale": "Expert stated the outcome as consuming crew time and blocking the line for the window.",
+          "rationale": "An unwritten rule stated by the expert as absolute, with its organisational consequence.",
           "assertion": {
-            "value": "Consumes crew time and takes Line 1 out of anything else for that window; afterwards the line is in white rather than tint."
+            "value": "A Meridian order is never allowed to slip its due date — it is a \"we just don't do that\" rule rather than a traded-off cost, because a Meridian miss means a fine plus ammunition for them to delist a line item at next contract review, and commercial and the boss get calls. Non-Meridian distributor orders that slip 2-3 days are handled with a phone call."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+          "excerpt": "right now it's a \"we just don't do that\" rule, not a traded-off cost",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "A Meridian miss is a different category — it's not just \"late,\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-053410a5-6574-4355-aabf-dd972f0088e1",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Consumes crew time and takes Line 1 out of anything else for that window; afterwards the line is in white rather than tint.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Expert stated the outcome as consuming crew time and blocking the line for the window.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-c0aae96c-f4bb-4695-9f86-01228a2b2f87",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian order is never allowed to slip its due date — it is a \\\"we just don't do that\\\" rule rather than a traded-off cost, because a Meridian miss means a fine plus ammunition for them to delist a line item at next contract review, and commercial and the boss get calls. Non-Meridian distributor orders that slip 2-3 days are handled with a phone call.\"},\"kind\":\"policy\",\"node\":\"we just don't do that (Meridian never slips)\",\"precision\":\"spelled out\",\"rationale\":\"An unwritten rule stated by the expert as absolute, with its organisational consequence.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"A Meridian miss is a different category — it's not just \\\\\\\"late,\\\\\\\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"right now it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what it needs before it can start",
+          "kind": "policy",
+          "node": "we just don't do that (Meridian never slips)",
+          "slot": "what overrides it",
           "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "Stated as the consequence of pulling a line off a tint run to run a white order; the full precondition list was not elicited.",
+          "rationale": "The expert says no quantity of small late orders overrides the rule within the range they would see.",
           "assertion": {
-            "value": "A line currently running a tint that is to be switched to a white order — pulling Line 1 off its tint run to cover Meridian white incurs the washdown."
+            "absence": "explicitly-absent",
+            "pointer": "no number of small late orders flips it in any range seen in a week"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
+          "excerpt": "Where does it flip? Honestly... I don't think it does flip, not in any range I'd actually see in a week.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-e86ee1d3-dbbd-4e2d-b1c0-a8ac719f0e58",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line currently running a tint that is to be switched to a white order — pulling Line 1 off its tint run to cover Meridian white incurs the washdown.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the consequence of pulling a line off a tint run to run a white order; the full precondition list was not elicited.\",\"slot\":\"what it needs before it can start\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-6cb6a6a9-0536-46e6-aa77-4b211514bdf3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"explicitly-absent\",\"pointer\":\"no number of small late orders flips it in any range seen in a week\"},\"kind\":\"policy\",\"node\":\"we just don't do that (Meridian never slips)\",\"precision\":\"spelled out\",\"rationale\":\"The expert says no quantity of small late orders overrides the rule within the range they would see.\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Where does it flip? Honestly... I don't think it does flip, not in any range I'd actually see in a week.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what is lost when it changes the system's mode",
-          "precision": "number",
-          "sourceRegime": "practiced",
-          "rationale": "Loss named for the tint-to-white transition specifically, as a single figure plus crew time; other transitions were not yet asked about.",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "rationale": "The expert distinguishes orders by colour class (white vs tint) and by customer class (Meridian vs distributor).",
           "assertion": {
-            "value": "Three hours of the line plus crew time for the tint-to-white transition; the bumped order may itself go late as a knock-on."
+            "value": "Orders differ by colour class — white versus tint, where white-to-white needs no changeover and white-to-tint needs a full washdown — and by customer: Meridian orders (a miss is a fine and delisting risk) versus distributor orders (slip 2-3 days with a phone call)."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+          "excerpt": "a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 3,
             "entryEnd": 3
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
+          "excerpt": "another white order — a smaller one, but still white, no changeover needed",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "three little late orders to distributors who slip 2-3 days with a phone call anyway",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "A Meridian miss is a different category",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-04d27279-48f8-437e-8688-14c400f3f0f1",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of the line plus crew time for the tint-to-white transition; the bumped order may itself go late as a knock-on.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Loss named for the tint-to-white transition specifically, as a single figure plus crew time; other transitions were not yet asked about.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-26d91606-f924-457f-a62c-8c5c3a22ff3c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders differ by colour class — white versus tint, where white-to-white needs no changeover and white-to-tint needs a full washdown — and by customer: Meridian orders (a miss is a fine and delisting risk) versus distributor orders (slip 2-3 days with a phone call).\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The expert distinguishes orders by colour class (white vs tint) and by customer class (Meridian vs distributor).\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"A Meridian miss is a different category\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"another white order — a smaller one, but still white, no changeover needed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"three little late orders to distributors who slip 2-3 days with a phone call anyway\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "Line 2 filler jam",
-          "slot": "how long it takes",
-          "precision": "range",
-          "sourceRegime": "practiced",
-          "rationale": "Expert described two kinds of repair — half an hour and half a shift — and one observed instance of about two hours; quantiles not yet elicited.",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "state that rides along with each instance",
+          "precision": "named",
+          "rationale": "Only colour, customer and a unit size were named for the instance; size given as one example figure.",
           "assertion": {
-            "value": "Repairs come in a \"half hour\" kind and a \"half a shift\" kind; the recent instance came back in about two hours."
+            "value": "Colour (white or tint), customer (Meridian or distributor), a due date, and an order size in units — the example tint order was \"maybe 800 units\"."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+          "excerpt": "the next job on the sheet was a tint order, maybe 800 units",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 3,
             "entryEnd": 3
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I went with waiting, it came back in about two hours, we just scraped the Thursday due date.",
+          "excerpt": "another white order — a smaller one, but still white",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 3,
             "entryEnd": 3
           },
@@ -285,8 +287,8 @@
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-7d1cb932-a1d6-4e1a-86a7-984a9d53af80",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Repairs come in a \\\"half hour\\\" kind and a \\\"half a shift\\\" kind; the recent instance came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"Line 2 filler jam\",\"precision\":\"range\",\"rationale\":\"Expert described two kinds of repair — half an hour and half a shift — and one observed instance of about two hours; quantiles not yet elicited.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours, we just scraped the Thursday due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-907b63ad-c480-4368-9b70-94cbc905fe70",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Colour (white or tint), customer (Meridian or distributor), a due date, and an order size in units — the example tint order was \\\"maybe 800 units\\\".\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"named\",\"rationale\":\"Only colour, customer and a unit size were named for the instance; size given as one example figure.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"another white order — a smaller one, but still white\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the next job on the sheet was a tint order, maybe 800 units\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -294,30 +296,30 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "Line 2 filler jam",
-          "slot": "what it produces or changes",
+          "node": "full white-to-tint changeover",
+          "slot": "what it needs before it can start",
           "precision": "spelled out",
           "sourceRegime": "practiced",
-          "rationale": "The event takes the line out of production and puts the order sitting on it at risk, forcing a wait-or-move decision.",
+          "rationale": "The changeover is triggered by a colour change from white to tint; same-colour succession needs none.",
           "assertion": {
-            "value": "Line 2 stops producing until repaired (half a shift lost in the recent case); the order sitting on Line 2 is at risk of its due date, forcing a decision to wait out the repair or shift the order to Line 1."
+            "value": "The next job is a different colour class than the one just run — a white-to-tint switch requires the changeover; a white order following white needs no changeover."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
+          "excerpt": "a full white-to-tint changeover is a wash we can't get back",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 3,
             "entryEnd": 3
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair.",
+          "excerpt": "still white, no changeover needed",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 3,
             "entryEnd": 3
           },
@@ -325,230 +327,208 @@
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-330b99df-25fc-4d38-b1f9-6f8da955b79e",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 2 stops producing until repaired (half a shift lost in the recent case); the order sitting on Line 2 is at risk of its due date, forcing a decision to wait out the repair or shift the order to Line 1.\"},\"kind\":\"activity\",\"node\":\"Line 2 filler jam\",\"precision\":\"spelled out\",\"rationale\":\"The event takes the line out of production and puts the order sitting on it at risk, forcing a wait-or-move decision.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-41b692e0-6ff8-4294-9a9c-e97f7e51b6bb",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The next job is a different colour class than the one just run — a white-to-tint switch requires the changeover; a white order following white needs no changeover.\"},\"kind\":\"activity\",\"node\":\"full white-to-tint changeover\",\"precision\":\"spelled out\",\"rationale\":\"The changeover is triggered by a colour change from white to tint; same-colour succession needs none.\",\"slot\":\"what it needs before it can start\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"still white, no changeover needed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "policy",
-          "node": "Meridian ships on time, full stop",
-          "slot": "the rule as actually practiced",
+          "kind": "activity",
+          "node": "full white-to-tint changeover",
+          "slot": "what it produces or changes",
           "precision": "spelled out",
           "sourceRegime": "practiced",
-          "rationale": "Stated as an absolute the scheduler protects ahead of all other considerations.",
+          "rationale": "Expert's own characterisation of the outcome of the changeover.",
           "assertion": {
-            "value": "The Meridian order ships on time, full stop; it is not traded off against washdown hours or other orders' due dates."
+            "value": "The line is washed down and set for tint; it is \"a wash we can't get back\" — the changeover hours are consumed capacity."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.",
+          "excerpt": "a full white-to-tint changeover is a wash we can't get back",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-caeeeb12-a91f-46a0-88c2-a622d4d30c55",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The Meridian order ships on time, full stop; it is not traded off against washdown hours or other orders' due dates.\"},\"kind\":\"policy\",\"node\":\"Meridian ships on time, full stop\",\"precision\":\"spelled out\",\"rationale\":\"Stated as an absolute the scheduler protects ahead of all other considerations.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-885c4bd0-8675-4604-990a-65c7118fa832",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line is washed down and set for tint; it is \\\"a wash we can't get back\\\" — the changeover hours are consumed capacity.\"},\"kind\":\"activity\",\"node\":\"full white-to-tint changeover\",\"precision\":\"spelled out\",\"rationale\":\"Expert's own characterisation of the outcome of the changeover.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "policy",
-          "node": "Meridian ships on time, full stop",
-          "slot": "what overrides it",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "Expert named the sole override in general terms; the practiced test for \"no way through\" is not yet on record.",
+          "kind": "activity",
+          "node": "full white-to-tint changeover",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
+          "rationale": "The expert distinguishes white-to-tint (full wash) from white-to-white (none); other direction/colour pairs not yet stated.",
           "assertion": {
-            "value": "Only when there is truly no way through; otherwise nothing overrides it."
+            "value": "Yes by colour pair: white-to-tint is a full washdown, white-to-white needs no changeover at all."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "that's a line I won't cross unless there's truly no way through",
+          "excerpt": "still white, no changeover needed",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I use judgment on who can absorb the slip",
+          "excerpt": "a full white-to-tint changeover is a wash we can't get back",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-422d7f74-a119-45d6-8261-3c71b50af7f7",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Only when there is truly no way through; otherwise nothing overrides it.\"},\"kind\":\"policy\",\"node\":\"Meridian ships on time, full stop\",\"precision\":\"spelled out\",\"rationale\":\"Expert named the sole override in general terms; the practiced test for \\\"no way through\\\" is not yet on record.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-a23f2234-5075-479e-86fb-89a3450bb4f1",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes by colour pair: white-to-tint is a full washdown, white-to-white needs no changeover at all.\"},\"kind\":\"activity\",\"node\":\"full white-to-tint changeover\",\"precision\":\"named\",\"rationale\":\"The expert distinguishes white-to-tint (full wash) from white-to-white (none); other direction/colour pairs not yet stated.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"still white, no changeover needed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "order",
-          "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
+          "kind": "activity",
+          "node": "the hold-or-change-over call",
+          "slot": "how often it occurs, if it is an event rather than a step",
+          "precision": "range",
           "sourceRegime": "practiced",
-          "rationale": "Orders are treated apart by colour class (white vs tint, which drives washdown) and by customer class (distributor / small account / awkward account that gets prickly).",
+          "rationale": "Frequency of the decision point the model is meant to test.",
           "assertion": {
-            "value": "Orders differ by colour class — white versus tint, which decides whether a washdown is incurred — and by customer, sorted into a distributor (sliding two days is a shrug), a small account (sliding a week is fine), and an awkward account that gets prickly."
+            "value": "three or four times a month"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "We had a Meridian white order due Thursday sitting on Line 2",
+          "excerpt": "I make that judgment by gut maybe three or four times a month",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 3,
             "entryEnd": 3
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-f2a03b6c-0420-48a7-85be-bdcb3536a6f7",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders differ by colour class — white versus tint, which decides whether a washdown is incurred — and by customer, sorted into a distributor (sliding two days is a shrug), a small account (sliding a week is fine), and an awkward account that gets prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Orders are treated apart by colour class (white vs tint, which drives washdown) and by customer class (distributor / small account / awkward account that gets prickly).\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-9bbac61c-4b3d-42c8-a74a-2d846127039b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"three or four times a month\"},\"kind\":\"activity\",\"node\":\"the hold-or-change-over call\",\"precision\":\"range\",\"rationale\":\"Frequency of the decision point the model is meant to test.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I make that judgment by gut maybe three or four times a month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "order",
-          "slot": "state that rides along with each instance",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "Each order is spoken of as carrying a due date, a customer, a colour, and the line it is sitting on.",
+          "kind": "activity",
+          "node": "the hold-or-change-over call",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "The expert makes the call themselves, by gut.",
           "assertion": {
-            "value": "Its due date (e.g. due Thursday), its customer (e.g. Meridian), its colour (white or tint), and which line it is sitting on."
+            "value": "The master scheduler, by gut judgment"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "We had a Meridian white order due Thursday sitting on Line 2",
+          "excerpt": "I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 3,
             "entryEnd": 3
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "does it slide past its own due date, and if so by how much and who's the customer",
+          "excerpt": "I'm the master scheduler at a coatings plant.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 1,
+            "entryEnd": 1
           },
-          "source": "user-affordance-payload"
+          "source": "user"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-c9ac976a-3eef-4a77-8e29-3598b184b450",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Its due date (e.g. due Thursday), its customer (e.g. Meridian), its colour (white or tint), and which line it is sitting on.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Each order is spoken of as carrying a due date, a customer, a colour, and the line it is sitting on.\",\"slot\":\"state that rides along with each instance\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-c216b212-3249-4b15-9b38-b7fc73c4e53a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler, by gut judgment\"},\"kind\":\"activity\",\"node\":\"the hold-or-change-over call\",\"precision\":\"named\",\"rationale\":\"The expert makes the call themselves, by gut.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm the master scheduler at a coatings plant.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":1,\\\"entryStart\\\":1,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "line",
-          "slot": "how many there are, or the population's shape",
+          "kind": "data-binding",
+          "node": "changeover log",
+          "slot": "the variable and its feed",
           "precision": "named",
-          "sourceRegime": "practiced",
-          "rationale": "Line 1 and Line 2 named; whether these are the only lines has not been asked.",
+          "rationale": "Named existing record of changeover hours.",
           "assertion": {
-            "value": "Line 1 and Line 2 named so far; total count not yet confirmed."
+            "value": "Changeover hours, fed by the plant's changeover log (tracked separately from the late-order report)"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.",
+          "excerpt": "I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-6bc324a5-2e12-4070-8275-fdfe819923e6",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2 named so far; total count not yet confirmed.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"named\",\"rationale\":\"Line 1 and Line 2 named; whether these are the only lines has not been asked.\",\"slot\":\"how many there are, or the population's shape\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-6bf8429a-d19a-47bd-8632-6e4e4a018357",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Changeover hours, fed by the plant's changeover log (tracked separately from the late-order report)\"},\"kind\":\"data-binding\",\"node\":\"changeover log\",\"precision\":\"named\",\"rationale\":\"Named existing record of changeover hours.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "line",
-          "slot": "state that rides along with each instance",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "A line is spoken of as carrying what it is currently running (its colour state) and whether it is down.",
+          "kind": "data-binding",
+          "node": "late-order report",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "rationale": "Named existing record of late orders, the boss's grading measure.",
           "assertion": {
-            "value": "What it is currently running — e.g. mid-run on a tint, which sets the colour it would have to be washed down from — and whether it is jammed/down awaiting repair."
+            "value": "Late-order count, fed by the late-order report (tracked separately from the changeover log)"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Line 1 was mid-run on a tint.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Line 2 filler jammed at about nine in the morning",
+          "excerpt": "I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-b003fc51-0ade-4721-b400-b7b68edf8c60",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"What it is currently running — e.g. mid-run on a tint, which sets the colour it would have to be washed down from — and whether it is jammed/down awaiting repair.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"spelled out\",\"rationale\":\"A line is spoken of as carrying what it is currently running (its colour state) and whether it is down.\",\"slot\":\"state that rides along with each instance\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-d29040ff-79cb-444b-afba-b81e63886bf4",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Late-order count, fed by the late-order report (tracked separately from the changeover log)\"},\"kind\":\"data-binding\",\"node\":\"late-order report\",\"precision\":\"named\",\"rationale\":\"Named existing record of late orders, the boss's grading measure.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -556,20 +536,30 @@
         "value": {
           "type": "slot-asserted",
           "kind": "objective",
-          "node": "which option loses less",
+          "node": "wash down now or sit the line idle",
           "slot": "the question, in the expert's words",
           "precision": "spelled out",
-          "rationale": "Stated as the concrete decision support the model must give, anchored to the Line 2 filler jam incident.",
+          "sourceRegime": "practiced",
+          "rationale": "The expert's own recent decision, stated as the first question for the model.",
           "assertion": {
-            "value": "Given a disruption in progress (e.g. \"filler's down, ETA unknown\"), which of the available scheduling options — wait out the repair on the down line, or move the order to another line — actually loses less, decided in the moment instead of by gut math at the huddle."
+            "value": "Whether to \"wash down for the tint right then, or let Line 2 sit idle for about an hour\" waiting for another white order that needs no changeover — a call made \"by gut maybe three or four times a month\""
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+          "excerpt": "I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 3,
             "entryEnd": 3
           },
@@ -577,8 +567,8 @@
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given a disruption in progress (e.g. \\\"filler's down, ETA unknown\\\"), which of the available scheduling options — wait out the repair on the down line, or move the order to another line — actually loses less, decided in the moment instead of by gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the concrete decision support the model must give, anchored to the Line 2 filler jam incident.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-37ea41c4-f012-4864-a896-ae745b3ba467",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whether to \\\"wash down for the tint right then, or let Line 2 sit idle for about an hour\\\" waiting for another white order that needs no changeover — a call made \\\"by gut maybe three or four times a month\\\"\"},\"kind\":\"objective\",\"node\":\"wash down now or sit the line idle\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own recent decision, stated as the first question for the model.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -586,85 +576,96 @@
         "value": {
           "type": "slot-asserted",
           "kind": "objective",
-          "node": "which option loses less",
+          "node": "wash down now or sit the line idle",
           "slot": "what \"better\" means, and trade-off weights",
           "precision": "spelled out",
           "sourceRegime": "practiced",
-          "rationale": "Expert explicitly denies having a weighting formula; the ordering is stated, the weights are not.",
+          "rationale": "Expert gave a qualitative ranking and explicitly refused a numeric exchange rate.",
           "assertion": {
-            "value": "Lexicographic: first, days late on the hard-line order (Meridian) — yes/no, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much, and who the customer is. No formula for the second-order trade-off — \"how bad is bad\", judged by who can absorb the slip."
+            "value": "Graded on \"the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere\"; a Meridian miss never trades against small late orders — \"I don't think it does flip, not in any range I'd actually see in a week\"; \"changeover hours and the idle time are more my own concern\" as diagnostics. No numeric exchange rate: \"you'd have to get commercial in a room and force them to say it out loud\""
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+          "excerpt": "Honestly, in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 6,
             "entryEnd": 6
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain",
+          "excerpt": "If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere. The changeover hours and the idle time are more my own concern",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 6,
             "entryEnd": 6
           },
           "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Where does it flip? Honestly... I don't think it does flip, not in any range I'd actually see in a week.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-de512bde-aa52-4147-933f-81439aa5ec6d",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lexicographic: first, days late on the hard-line order (Meridian) — yes/no, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much, and who the customer is. No formula for the second-order trade-off — \\\"how bad is bad\\\", judged by who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"Expert explicitly denies having a weighting formula; the ordering is stated, the weights are not.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-47724d1f-2419-4d2e-9662-442ea9e7d8e5",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Graded on \\\"the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere\\\"; a Meridian miss never trades against small late orders — \\\"I don't think it does flip, not in any range I'd actually see in a week\\\"; \\\"changeover hours and the idle time are more my own concern\\\" as diagnostics. No numeric exchange rate: \\\"you'd have to get commercial in a room and force them to say it out loud\\\"\"},\"kind\":\"objective\",\"node\":\"wash down now or sit the line idle\",\"precision\":\"spelled out\",\"rationale\":\"Expert gave a qualitative ranking and explicitly refused a numeric exchange rate.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Honestly, in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere. The changeover hours and the idle time are more my own concern\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Where does it flip? Honestly... I don't think it does flip, not in any range I'd actually see in a week.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "objective",
-          "node": "which option loses less",
+          "node": "wash down now or sit the line idle",
           "slot": "the nodes it depends on",
           "precision": "named",
-          "rationale": "The scorecard names on-time delivery, washdown hours, lateness of the bumped order, and the repair outcome; the judgment of who can absorb a slip is the tiebreaker.",
+          "rationale": "The expert named the scheduling unit (three lines plus the one crew) and the span release-to-cleared-QA as what the decision turns on.",
           "assertion": {
             "value": [
-              "constraint:Meridian on time",
-              "activity:tint-to-white washdown",
-              "activity:filler jam",
               "entity-type:order",
+              "entity-type:changeover crew",
               "entity-type:line",
-              "policy:who can absorb the slip"
+              "activity:changeover (washdown)",
+              "activity:QA hold",
+              "ordering/flow:release to cleared QA",
+              "boundary-condition:demand book release",
+              "constraint:no Meridian miss"
             ]
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing",
+          "excerpt": "So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+          "excerpt": "an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "explicit",
-      "id": "capture-a6e8dc50-fffb-494d-8bd2-59704c0427e4",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"constraint:Meridian on time\",\"activity:tint-to-white washdown\",\"activity:filler jam\",\"entity-type:order\",\"entity-type:line\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard names on-time delivery, washdown hours, lateness of the bumped order, and the repair outcome; the judgment of who can absorb a slip is the tiebreaker.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "inferred",
+      "id": "capture-665b5de5-72f5-49c9-938b-55b00afa5252",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:changeover crew\",\"entity-type:line\",\"activity:changeover (washdown)\",\"activity:QA hold\",\"ordering/flow:release to cleared QA\",\"boundary-condition:demand book release\",\"constraint:no Meridian miss\"]},\"kind\":\"objective\",\"node\":\"wash down now or sit the line idle\",\"precision\":\"named\",\"rationale\":\"The expert named the scheduling unit (three lines plus the one crew) and the span release-to-cleared-QA as what the decision turns on.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"an order's mine from release to \\\\\\\"cleared QA,\\\\\\\" and the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -675,44 +676,44 @@
           "node": "order",
           "slot": "the distinctions the process treats apart",
           "precision": "spelled out",
-          "rationale": "Colour class changes the process at the tint stage; customer type changes how lateness is weighed.",
+          "rationale": "Expert distinguishes Meridian from distributor orders, and white from tint, as treated differently.",
           "assertion": {
-            "value": "An order is a line item in the demand book from ERP. Treated apart by: product colour class — white (tint stage is barely there, a pass-through rather than a real letdown step) versus tint/specialty; and by customer type — distributor (a two-day slide is a shrug), small account (a week is fine), and awkward accounts that get prickly."
+            "value": "Orders differ by customer — Meridian versus distributors (\"A Meridian miss is a different category\"; distributors \"slip 2-3 days with a phone call anyway\") — and by colour class, white versus tint, since white-to-tint requires a changeover and white-to-white does not"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "excerpt": "For me it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+          "excerpt": "Line 2 finished a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+          "excerpt": "three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis. A Meridian miss is a different category",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-3cb49f42-f479-4b67-be4c-22c8f9771f6e",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order is a line item in the demand book from ERP. Treated apart by: product colour class — white (tint stage is barely there, a pass-through rather than a real letdown step) versus tint/specialty; and by customer type — distributor (a two-day slide is a shrug), small account (a week is fine), and awkward accounts that get prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Colour class changes the process at the tint stage; customer type changes how lateness is weighed.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-ae712ebf-7a14-4cd9-adec-83df50ff2fa2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders differ by customer — Meridian versus distributors (\\\"A Meridian miss is a different category\\\"; distributors \\\"slip 2-3 days with a phone call anyway\\\") — and by colour class, white versus tint, since white-to-tint requires a changeover and white-to-white does not\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Expert distinguishes Meridian from distributor orders, and white from tint, as treated differently.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"For me it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 finished a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis. A Meridian miss is a different category\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -723,35 +724,35 @@
           "node": "order",
           "slot": "state that rides along with each instance",
           "precision": "spelled out",
-          "rationale": "Named directly as what the demand-book line item carries, extended by the allocation step and the account-based lateness judgment.",
+          "rationale": "Attributes the expert named on a released order plus the lateness test.",
           "assertion": {
-            "value": "Quantity, due date, SKU; plus the line and week-slot it has been allocated to on the sheet; plus the customer/account it belongs to."
+            "value": "SKU, quantity, due date; lateness is judged against when the order clears QA, not when it comes off the line"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "excerpt": "it's got an SKU, quantity, due date",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "excerpt": "the due date is judged against when it clears, not when it comes off the line",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-5628ca29-5985-4005-aa3f-a6885dc38223",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; plus the line and week-slot it has been allocated to on the sheet; plus the customer/account it belongs to.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Named directly as what the demand-book line item carries, extended by the allocation step and the account-based lateness judgment.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-e0802c09-2a87-4514-b8a2-51841de54cbc",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"SKU, quantity, due date; lateness is judged against when the order clears QA, not when it comes off the line\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Attributes the expert named on a released order plus the lateness test.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -759,107 +760,138 @@
         "value": {
           "type": "slot-asserted",
           "kind": "entity-type",
-          "node": "line",
+          "node": "changeover crew",
+          "slot": "how many there are, or the population's shape",
+          "precision": "number",
+          "rationale": "Expert stated the crew count directly.",
+          "assertion": {
+            "value": "One crew of two techs, covering all three lines"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-01f20a7f-43bf-42f9-a532-f04cf92ad105",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One crew of two techs, covering all three lines\"},\"kind\":\"entity-type\",\"node\":\"changeover crew\",\"precision\":\"number\",\"rationale\":\"Expert stated the crew count directly.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "changeover crew",
           "slot": "the distinctions the process treats apart",
-          "precision": "named",
-          "rationale": "Lines are contended for between orders in the decision described.",
+          "precision": "spelled out",
+          "rationale": "The crew is a single shared contended resource, not differentiated by line.",
           "assertion": {
-            "value": "Production lines, referred to individually as Line 1 and Line 2; an order is allocated to a specific line and a line can be mid-run on another order."
+            "value": "A single shared changeover crew — \"the shared thing\" — not split by line; it is either free or pulled onto Line 1 or Line 3"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.",
+          "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+          "excerpt": "if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\"",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-6d4d1074-f6fe-4d4c-95c2-f242a6f98233",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Production lines, referred to individually as Line 1 and Line 2; an order is allocated to a specific line and a line can be mid-run on another order.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"named\",\"rationale\":\"Lines are contended for between orders in the decision described.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-61d5a849-6ada-4278-a08b-86a2f62f2eff",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A single shared changeover crew — \\\"the shared thing\\\" — not split by line; it is either free or pulled onto Line 1 or Line 3\"},\"kind\":\"entity-type\",\"node\":\"changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"The crew is a single shared contended resource, not differentiated by line.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if I wash Line 2 down now, I'm also asking \\\\\\\"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "entity-type",
           "node": "line",
           "slot": "how many there are, or the population's shape",
-          "precision": "named",
-          "rationale": "Only the two lines involved in the incident were named; the plant's full line count was never asked.",
+          "precision": "number",
+          "rationale": "Expert named three lines as the scheduling scope.",
           "assertion": {
-            "value": "At least two lines named: Line 1 and Line 2. Total line count not stated."
+            "value": "Three lines — Line 1, Line 2, Line 3"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "whether to shift it to Line 1 or just wait out the repair",
+          "excerpt": "So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "We had a Meridian white order due Thursday sitting on Line 2",
+          "excerpt": "are they about to be pulled onto Line 1 or Line 3 for something else?",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-a0b65576-83d8-4134-9fbe-9b059663ae12",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"At least two lines named: Line 1 and Line 2. Total line count not stated.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"named\",\"rationale\":\"Only the two lines involved in the incident were named; the plant's full line count was never asked.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whether to shift it to Line 1 or just wait out the repair\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-199dc6be-d352-46eb-a561-b5c6b8b1703e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three lines — Line 1, Line 2, Line 3\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"number\",\"rationale\":\"Expert named three lines as the scheduling scope.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"are they about to be pulled onto Line 1 or Line 3 for something else?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "order flow from demand book to shipment",
-          "slot": "the order things happen in",
+          "kind": "activity",
+          "node": "changeover (washdown)",
+          "slot": "what it needs before it can start",
           "precision": "spelled out",
-          "rationale": "Given verbatim as the end-to-end sequence for the Meridian white order.",
+          "sourceRegime": "practiced",
+          "rationale": "Crew availability is the stated precondition.",
           "assertion": {
-            "value": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (fill and pack) → QA hold → release and ship. Four steps if QA and shipping are counted as one, five if split."
+            "value": "The changeover crew must be free — \"If they're tied up elsewhere, my 'wash down now' option isn't even really available\" — and the line must have finished its current run"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+          "excerpt": "if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\" If they're tied up elsewhere, my \"wash down now\" option isn't even really available",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (fill and pack) → QA hold → release and ship. Four steps if QA and shipping are counted as one, five if split.\"},\"kind\":\"ordering/flow\",\"node\":\"order flow from demand book to shipment\",\"precision\":\"spelled out\",\"rationale\":\"Given verbatim as the end-to-end sequence for the Meridian white order.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-a9dd192c-4602-4b65-8896-be0481e9ce8b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The changeover crew must be free — \\\"If they're tied up elsewhere, my 'wash down now' option isn't even really available\\\" — and the line must have finished its current run\"},\"kind\":\"activity\",\"node\":\"changeover (washdown)\",\"precision\":\"spelled out\",\"rationale\":\"Crew availability is the stated precondition.\",\"slot\":\"what it needs before it can start\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"if I wash Line 2 down now, I'm also asking \\\\\\\"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\\\\\\\" If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -867,29 +899,29 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "allocation",
-          "slot": "what it needs before it can start",
-          "precision": "spelled out",
-          "rationale": "Stated as the trigger for the order becoming something to schedule.",
+          "node": "changeover (washdown)",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "Directly named performer.",
           "assertion": {
-            "value": "A line item in the demand book, produced by ERP, carrying quantity, due date and SKU."
+            "value": "entity-type:changeover crew — one crew of two techs"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book, produced by ERP, carrying quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the trigger for the order becoming something to schedule.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-2296040f-dd70-46bf-b603-b128a63be702",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:changeover crew — one crew of two techs\"},\"kind\":\"activity\",\"node\":\"changeover (washdown)\",\"precision\":\"named\",\"rationale\":\"Directly named performer.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -897,77 +929,78 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "allocation",
+          "node": "changeover (washdown)",
           "slot": "what it produces or changes",
           "precision": "spelled out",
-          "rationale": "Directly stated as the outcome of step one.",
+          "rationale": "The changeover converts the line's colour state; same-colour succession needs none.",
           "assertion": {
-            "value": "The order is slotted onto a specific line and a slot in the week, on the sheet."
+            "value": "Converts the line from the previous colour to the next — \"a full white-to-tint changeover is a wash we can't get back\"; a white-to-white succession needs \"no changeover\""
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "excerpt": "a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "allocate it onto a line and a slot in the week",
+          "excerpt": "still white, no changeover needed",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-fa56fa8b-611a-4a38-9a42-1bd038e52d80",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a specific line and a slot in the week, on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Directly stated as the outcome of step one.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-52ae613b-8aaf-4d9f-866d-72f8f37c00e7",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Converts the line from the previous colour to the next — \\\"a full white-to-tint changeover is a wash we can't get back\\\"; a white-to-white succession needs \\\"no changeover\\\"\"},\"kind\":\"activity\",\"node\":\"changeover (washdown)\",\"precision\":\"spelled out\",\"rationale\":\"The changeover converts the line's colour state; same-colour succession needs none.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"still white, no changeover needed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "allocation",
-          "slot": "who or what performs it",
+          "node": "changeover (washdown)",
+          "slot": "what is lost when it changes the system's mode",
           "precision": "named",
-          "rationale": "First person throughout; role stated at the outset.",
+          "sourceRegime": "practiced",
+          "rationale": "Expert named the loss qualitatively (a wash, changeover hours) but gave no figure in this range.",
           "assertion": {
-            "value": "The master scheduler (the expert), working on the sheet."
+            "value": "A wash that \"we can't get back\", counted by the expert as changeover hours; no quantity given yet"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I'm the master scheduler at a coatings plant.",
+          "excerpt": "a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 1,
-            "entryEnd": 1
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
-          "source": "user"
+          "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "excerpt": "in the moment I'm weighing changeover hours against idle hours — that's the gut math",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "explicit",
-      "id": "capture-dba4ec08-0265-420c-95d2-4dce250ae0b6",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler (the expert), working on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"named\",\"rationale\":\"First person throughout; role stated at the outset.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm the master scheduler at a coatings plant.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":1,\\\"entryStart\\\":1,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
+      "epistemicStatus": "tentative",
+      "id": "capture-5fc553d4-e294-4ec8-8368-52ffe5044e2f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A wash that \\\"we can't get back\\\", counted by the expert as changeover hours; no quantity given yet\"},\"kind\":\"activity\",\"node\":\"changeover (washdown)\",\"precision\":\"named\",\"rationale\":\"Expert named the loss qualitatively (a wash, changeover hours) but gave no figure in this range.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in the moment I'm weighing changeover hours against idle hours — that's the gut math\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -975,149 +1008,187 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "mix/mill/tint/fill",
+          "node": "QA hold",
           "slot": "what it produces or changes",
           "precision": "spelled out",
-          "rationale": "Stated as the production step common to all products.",
+          "rationale": "QA clearance is the event the due date is judged against.",
           "assertion": {
-            "value": "Runs the order through four stages every product goes through — mix, mill, tint, fill and pack — producing filled and packed product that comes off the fill line."
+            "value": "Clears the batch out of QA hold so it can ship; until then \"a batch can be done Tuesday and still ship late if the lab's backed up\", and the due date is judged against clearance"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
+          "excerpt": "It ends when it clears QA hold and ships.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "a batch can be done Tuesday and still ship late if the lab's backed up",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-0b2046b4-55c8-4ce3-abac-296d6abe469d",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Runs the order through four stages every product goes through — mix, mill, tint, fill and pack — producing filled and packed product that comes off the fill line.\"},\"kind\":\"activity\",\"node\":\"mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the production step common to all products.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-8f6e902b-07ed-49ce-aa1b-40d7e46502ce",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Clears the batch out of QA hold so it can ship; until then \\\"a batch can be done Tuesday and still ship late if the lab's backed up\\\", and the due date is judged against clearance\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"QA clearance is the event the due date is judged against.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It ends when it clears QA hold and ships.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a batch can be done Tuesday and still ship late if the lab's backed up\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "mix/mill/tint/fill",
-          "slot": "whether its quantities vary by type",
+          "node": "QA hold",
+          "slot": "who or what performs it",
           "precision": "named",
-          "rationale": "Explicit type-dependence at the tint stage; stage durations themselves not yet given.",
+          "rationale": "Expert names the lab as the constrained performer.",
           "assertion": {
-            "value": "Yes — the stages are the same for every product, but for a white the tint stage is barely there, a pass-through rather than a real letdown step."
+            "value": "the lab"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+          "excerpt": "a batch can be done Tuesday and still ship late if the lab's backed up",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-8156b872-b3c2-43db-aa67-56166bebe556",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — the stages are the same for every product, but for a white the tint stage is barely there, a pass-through rather than a real letdown step.\"},\"kind\":\"activity\",\"node\":\"mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Explicit type-dependence at the tint stage; stage durations themselves not yet given.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-7514059e-f02b-4f61-a3a1-11ca6fd01646",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"the lab\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Expert names the lab as the constrained performer.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a batch can be done Tuesday and still ship late if the lab's backed up\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "what it needs before it can start",
+          "kind": "ordering/flow",
+          "node": "release to cleared QA",
+          "slot": "the order things happen in",
           "precision": "spelled out",
-          "rationale": "Stated as the precondition and the waiting arrangement.",
+          "rationale": "The expert stated the in-scope span end to end.",
           "assertion": {
-            "value": "The order has come off the fill line; it then sits in the lab's queue awaiting check."
+            "value": "Order lands in the demand book from ERP (\"released\") → scheduled onto a line, with a changeover first if the colour differs from the previous run → run on the line → QA hold → clears QA and ships. Upstream sales promising dates and downstream warehouse/logistics are outside the expert's scope"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+          "excerpt": "For me it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date. It ends when it clears QA hold and ships.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order has come off the fill line; it then sits in the lab's queue awaiting check.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the precondition and the waiting arrangement.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-bbeb387d-bf09-4357-b52a-58ad8b679738",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Order lands in the demand book from ERP (\\\"released\\\") → scheduled onto a line, with a changeover first if the colour differs from the previous run → run on the line → QA hold → clears QA and ships. Upstream sales promising dates and downstream warehouse/logistics are outside the expert's scope\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"The expert stated the in-scope span end to end.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"For me it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date. It ends when it clears QA hold and ships.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"an order's mine from release to \\\\\\\"cleared QA,\\\\\\\" and the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "rationale": "Release is the stated outcome of the QA hold.",
+          "kind": "boundary-condition",
+          "node": "demand book release",
+          "slot": "the arrival or availability pattern",
+          "precision": "named",
+          "sourceRegime": "practiced",
+          "rationale": "Expert described the cycle and replan rhythm but gave no rate or shape.",
           "assertion": {
-            "value": "The order is checked and then released, after which it goes to the warehouse and ships against the due date."
+            "value": "Orders arrive by release into the demand book from ERP on a weekly book cycle, re-planned by the morning huddle; releases occur within the day (e.g. an order \"was going to be released from the demand book that afternoon\"). No rate or shape given"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "sits in the lab's queue, gets checked",
+          "excerpt": "For me it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+          "excerpt": "a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-589bc2db-8fc9-4d65-8024-b34ce4cd736a",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is checked and then released, after which it goes to the warehouse and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Release is the stated outcome of the QA hold.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-a77d820d-b5ac-45d5-a41b-e94c3bc7973f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders arrive by release into the demand book from ERP on a weekly book cycle, re-planned by the morning huddle; releases occur within the day (e.g. an order \\\"was going to be released from the demand book that afternoon\\\"). No rate or shape given\"},\"kind\":\"boundary-condition\",\"node\":\"demand book release\",\"precision\":\"named\",\"rationale\":\"Expert described the cycle and replan rhythm but gave no rate or shape.\",\"slot\":\"the arrival or availability pattern\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"For me it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "who or what performs it",
-          "precision": "named",
-          "rationale": "Named as the owner of the queue and the check.",
+          "kind": "constraint",
+          "node": "no Meridian miss",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Stated as an unwritten absolute rule with named consequences.",
           "assertion": {
-            "value": "The lab."
+            "value": "A Meridian order must not miss its due date — a \"we just don't do that\" rule, written nowhere; if hit: \"it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\""
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "sits in the lab's queue, gets checked",
+          "excerpt": "A Meridian miss is a different category — it's not just \"late,\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "right now it's a \"we just don't do that\" rule, not a traded-off cost",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 9,
             "entryEnd": 9
           },
@@ -1125,149 +1196,149 @@
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-07de77cc-9de8-41e9-92f6-8fe06a6263c9",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Named as the owner of the queue and the check.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-e776f323-41e3-460b-ace7-666b43385453",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian order must not miss its due date — a \\\"we just don't do that\\\" rule, written nowhere; if hit: \\\"it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\\\"\"},\"kind\":\"constraint\",\"node\":\"no Meridian miss\",\"precision\":\"spelled out\",\"rationale\":\"Stated as an unwritten absolute rule with named consequences.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"A Meridian miss is a different category — it's not just \\\\\\\"late,\\\\\\\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"right now it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "how long it takes",
-          "precision": "named",
-          "rationale": "Hedged quantifier only; not yet a usable spread.",
+          "kind": "constraint",
+          "node": "planning horizon",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Horizon over which the plan must remain useful, with the expert's stated failure beyond it.",
           "assertion": {
-            "value": "Usually a few hours for a white; longer for specialty (\"nothing like the specialty wait\"). No figures for typical, one-in-ten worse or one-in-ten better yet."
+            "value": "One week is the horizon that must hold; two weeks is watched only for \"the big minimum-run stuff, specialty especially\"; beyond a month the plan is refused — \"too much changes\" and the book itself gets revised"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
+          "excerpt": "if you ask me to hold a plan that's useful a month out, I'd say no — too much changes",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "a week is the horizon that matters — that's the cycle of the demand book",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially, because you don't want to discover Thursday that you needed to have started Tuesday.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; longer for specialty (\\\"nothing like the specialty wait\\\"). No figures for typical, one-in-ten worse or one-in-ten better yet.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Hedged quantifier only; not yet a usable spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-c625c3a0-1ce6-4249-b282-309c02e0a0d4",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One week is the horizon that must hold; two weeks is watched only for \\\"the big minimum-run stuff, specialty especially\\\"; beyond a month the plan is refused — \\\"too much changes\\\" and the book itself gets revised\"},\"kind\":\"constraint\",\"node\":\"planning horizon\",\"precision\":\"spelled out\",\"rationale\":\"Horizon over which the plan must remain useful, with the expert's stated failure beyond it.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially, because you don't want to discover Thursday that you needed to have started Tuesday.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a week is the horizon that matters — that's the cycle of the demand book\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if you ask me to hold a plan that's useful a month out, I'd say no — too much changes\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "whether its quantities vary by type",
-          "precision": "named",
-          "rationale": "Type dependence stated explicitly in the same breath as the duration.",
+          "kind": "policy",
+          "node": "who gets the changeover crew",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Expert described crew contention as first-come queueing; the tie-break and override are not yet stated.",
           "assertion": {
-            "value": "Yes — a white is usually a few hours, specialty waits are much longer."
+            "value": "If the crew is already committed to another line, the requesting line waits — \"I'd be queuing behind whoever else needs them\""
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
+          "excerpt": "If they're tied up elsewhere, my \"wash down now\" option isn't even really available — I'd be queuing behind whoever else needs them.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a white is usually a few hours, specialty waits are much longer.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Type dependence stated explicitly in the same breath as the duration.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-1842e3f3-9daf-42d7-8803-eafe3b3c5146",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"If the crew is already committed to another line, the requesting line waits — \\\"I'd be queuing behind whoever else needs them\\\"\"},\"kind\":\"policy\",\"node\":\"who gets the changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"Expert described crew contention as first-come queueing; the tie-break and override are not yet stated.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available — I'd be queuing behind whoever else needs them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "release and ship",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "rationale": "Final step of the walkthrough; due date is the reference for the objective's lateness metric.",
+          "kind": "data-binding",
+          "node": "changeover log and late-order report",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "rationale": "Two existing feeds named by the expert, currently unlinked.",
           "assertion": {
-            "value": "The released order goes to the warehouse and ships against its due date; lateness is measured as days late against that due date."
+            "value": "Changeover hours from the changeover log; late orders from the late-order report — \"nobody's ever put them on the same page\""
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+          "excerpt": "I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The released order goes to the warehouse and ships against its due date; lateness is measured as days late against that due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"rationale\":\"Final step of the walkthrough; due date is the reference for the objective's lateness metric.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-ee33f01c-2e09-4f6b-a34e-6e9c2efb96e3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Changeover hours from the changeover log; late orders from the late-order report — \\\"nobody's ever put them on the same page\\\"\"},\"kind\":\"data-binding\",\"node\":\"changeover log and late-order report\",\"precision\":\"named\",\"rationale\":\"Two existing feeds named by the expert, currently unlinked.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what it needs before it can start",
+          "kind": "objective",
+          "node": "wash down now or sit Line 2 idle",
+          "slot": "the question, in the expert's words",
           "precision": "spelled out",
-          "rationale": "Named as the changeover that the tint→white switch forces.",
+          "sourceRegime": "practiced",
+          "rationale": "The expert's own statement of the decision the model must inform, given as a recent real case.",
           "assertion": {
-            "value": "A line changing over from a tint run to a white run; the line must be pulled off the tint it is mid-run on."
+            "value": "Whether to wash down for the tint right then, or let Line 2 sit idle for about an hour waiting for another white order (smaller, still white, no changeover needed) to be released from the demand book that afternoon — a call made by gut three or four times a month, never provably right."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
+          "excerpt": "I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 3,
             "entryEnd": 3
           },
           "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-7df09f81-9c85-43ac-b69e-306d540f8afb",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line changing over from a tint run to a white run; the line must be pulled off the tint it is mid-run on.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Named as the changeover that the tint→white switch forces.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "how long it takes",
-          "precision": "number",
-          "rationale": "A single figure was given, not a spread; recorded at the precision actually reached.",
-          "assertion": {
-            "value": "Three hours (tint-to-white)."
-          }
-        }
-      },
-      "evidence": [
+        },
         {
-          "excerpt": "I eat a tint-to-white washdown — three hours",
+          "excerpt": "That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 3,
             "entryEnd": 3
           },
@@ -1275,279 +1346,284 @@
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-e0f39723-a7e5-4656-a8fb-0e2b50bb82da",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours (tint-to-white).\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"A single figure was given, not a spread; recorded at the precision actually reached.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-8e963c90-4270-411e-8ec9-9acbb2d2dabc",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whether to wash down for the tint right then, or let Line 2 sit idle for about an hour waiting for another white order (smaller, still white, no changeover needed) to be released from the demand book that afternoon — a call made by gut three or four times a month, never provably right.\"},\"kind\":\"objective\",\"node\":\"wash down now or sit Line 2 idle\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own statement of the decision the model must inform, given as a recent real case.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what is lost when it changes the system's mode",
-          "precision": "number",
-          "rationale": "Loss named for a specific named transition (tint to white); only one figure given.",
+          "kind": "objective",
+          "node": "wash down now or sit Line 2 idle",
+          "slot": "what \"better\" means, and trade-off weights",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Better is judged on late orders, with Meridian misses as an unwritten hard rule rather than a weight; changeover and idle hours are the expert's own diagnostics.",
           "assertion": {
-            "value": "Three hours of the line's availability — real cost and crew time — during which the line is out of anything else."
+            "value": "Graded on late-order count, with Meridian orders weighted extra heavy in practice though nobody has written that down; a Meridian miss is a \"we just don't do that\" rule, not a traded-off cost; changeover hours and idle hours are the expert's own concern because wasted capacity turns into missed due dates later in the week."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+          "excerpt": "in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 6,
             "entryEnd": 6
           },
           "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-d8dffb0f-f148-4af2-ba7e-478a6a1b38c6",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of the line's availability — real cost and crew time — during which the line is out of anything else.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Loss named for a specific named transition (tint to white); only one figure given.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "rationale": "Effect on line availability stated directly.",
-          "assertion": {
-            "value": "Puts the line into a state able to run white; the line is unavailable for any other work for the duration."
-          }
-        }
-      },
-      "evidence": [
+        },
+        {
+          "excerpt": "If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
         {
-          "excerpt": "it takes Line 1 out of anything else for that window",
+          "excerpt": "The changeover hours and the idle time are more my own concern — I get twitchy about wasted capacity because that's what eventually turns into missed due dates further down the week.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 6,
             "entryEnd": 6
           },
           "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "right now it's a \"we just don't do that\" rule, not a traded-off cost",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-a2938097-b902-4f24-8e15-70f4b8ce95fb",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Puts the line into a state able to run white; the line is unavailable for any other work for the duration.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Effect on line availability stated directly.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-65ac2ec5-6286-4058-afdf-08678d733640",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Graded on late-order count, with Meridian orders weighted extra heavy in practice though nobody has written that down; a Meridian miss is a \\\"we just don't do that\\\" rule, not a traded-off cost; changeover hours and idle hours are the expert's own concern because wasted capacity turns into missed due dates later in the week.\"},\"kind\":\"objective\",\"node\":\"wash down now or sit Line 2 idle\",\"precision\":\"spelled out\",\"rationale\":\"Better is judged on late orders, with Meridian misses as an unwritten hard rule rather than a weight; changeover and idle hours are the expert's own diagnostics.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The changeover hours and the idle time are more my own concern — I get twitchy about wasted capacity because that's what eventually turns into missed due dates further down the week.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"right now it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jam",
-          "slot": "what it produces or changes",
+          "kind": "objective",
+          "node": "Meridian-versus-small-orders exchange rate",
+          "slot": "what \"better\" means, and trade-off weights",
           "precision": "spelled out",
-          "rationale": "Described as the disruption that forces the scheduling decision.",
+          "rationale": "The expert explicitly cannot supply an exchange rate and names commercial as the source that would have to state it.",
           "assertion": {
-            "value": "The line's filler goes down, stopping the order sitting on that line until the repair completes; the scheduler must then decide to wait it out or shift the order to another line."
+            "absence": "deferred",
+            "pointer": "commercial — would have to be got in a room and forced to say it out loud"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "I went with waiting, it came back in about two hours",
+          "excerpt": "I know that's not a real number you can put in a formula. If you need a number, you'd have to get commercial in a room and force them to say it out loud",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-896881a6-c9ec-469f-ab03-4a56b59f6cad",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line's filler goes down, stopping the order sitting on that line until the repair completes; the scheduler must then decide to wait it out or shift the order to another line.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"Described as the disruption that forces the scheduling decision.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-9610d59f-1871-41d2-873c-e80a80daf01a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"commercial — would have to be got in a room and forced to say it out loud\"},\"kind\":\"objective\",\"node\":\"Meridian-versus-small-orders exchange rate\",\"precision\":\"spelled out\",\"rationale\":\"The expert explicitly cannot supply an exchange rate and names commercial as the source that would have to state it.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know that's not a real number you can put in a formula. If you need a number, you'd have to get commercial in a room and force them to say it out loud\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jam",
-          "slot": "how long it takes",
-          "precision": "range",
-          "rationale": "Two kinds named as the ends plus one observed instance; no typical or one-in-ten figures given, so this is a range, not a spread.",
+          "kind": "objective",
+          "node": "wash down now or sit Line 2 idle",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "The expert names the scheduling unit (three lines plus the one crew) and the span of an order (release to cleared QA) as what the decision turns on.",
           "assertion": {
-            "value": "From about half an hour (\"the 'half hour' kind\") to about half a shift (\"the 'half a shift' kind\"); the recent instance came back in about two hours."
+            "value": [
+              "entity-type:lines",
+              "entity-type:changeover crew",
+              "entity-type:order",
+              "boundary-condition:release from the demand book",
+              "activity:changeover wash down",
+              "activity:clears QA hold",
+              "ordering/flow:release to cleared QA",
+              "constraint:no Meridian misses"
+            ]
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+          "excerpt": "the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "it came back in about two hours",
+          "excerpt": "an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-4a3ae53c-2c2f-4664-9499-7e81c254abc5",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"From about half an hour (\\\"the 'half hour' kind\\\") to about half a shift (\\\"the 'half a shift' kind\\\"); the recent instance came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Two kinds named as the ends plus one observed instance; no typical or one-in-ten figures given, so this is a range, not a spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-cb1567d4-e83b-4ff8-85aa-c917277e92e3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:lines\",\"entity-type:changeover crew\",\"entity-type:order\",\"boundary-condition:release from the demand book\",\"activity:changeover wash down\",\"activity:clears QA hold\",\"ordering/flow:release to cleared QA\",\"constraint:no Meridian misses\"]},\"kind\":\"objective\",\"node\":\"wash down now or sit Line 2 idle\",\"precision\":\"named\",\"rationale\":\"The expert names the scheduling unit (three lines plus the one crew) and the span of an order (release to cleared QA) as what the decision turns on.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"an order's mine from release to \\\\\\\"cleared QA,\\\\\\\" and the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jam",
-          "slot": "how often it occurs, if it is an event rather than a step",
-          "precision": "named",
-          "rationale": "One occurrence recounted; frequency never stated.",
+          "kind": "entity-type",
+          "node": "changeover crew",
+          "slot": "how many there are, or the population's shape",
+          "precision": "number",
+          "rationale": "Expert states one crew of two techs shared across all three lines.",
           "assertion": {
-            "absence": "unknown-to-user",
-            "pointer": "rate of filler jams not yet asked or given"
+            "value": "one crew, two techs, covering all three lines"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I'd love to type in \"filler's down, ETA unknown\"",
+          "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-d662739b-76f0-429a-829a-ccb79763b6b9",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"rate of filler jams not yet asked or given\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"named\",\"rationale\":\"One occurrence recounted; frequency never stated.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-a64355a7-9a1c-48b4-b1b6-571aa465c457",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"one crew, two techs, covering all three lines\"},\"kind\":\"entity-type\",\"node\":\"changeover crew\",\"precision\":\"number\",\"rationale\":\"Expert states one crew of two techs shared across all three lines.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "constraint",
-          "node": "Meridian on time",
-          "slot": "the limit and what happens when it is hit",
+          "kind": "entity-type",
+          "node": "changeover crew",
+          "slot": "state that rides along with each instance",
           "precision": "spelled out",
           "sourceRegime": "practiced",
-          "rationale": "Stated as non-negotiable with a named consequence.",
+          "rationale": "The crew is either free or tied up on another line; that state gates whether a changeover can start.",
           "assertion": {
-            "value": "The hard-line customer's order must ship on or before its due date — days late must be zero. The line is not crossed unless there is truly no way through; if it is crossed, the scheduler has to go explain it."
+            "value": "free, or tied up / about to be pulled onto Line 1 or Line 3 for something else — if tied up, the wash-down option isn't available and the job queues behind whoever else needs them"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+          "excerpt": "if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\"",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "anything above zero is bad news I have to go explain",
+          "excerpt": "If they're tied up elsewhere, my \"wash down now\" option isn't even really available — I'd be queuing behind whoever else needs them.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-a9e42aa6-8d30-4ded-a8c4-f24220cfb292",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The hard-line customer's order must ship on or before its due date — days late must be zero. The line is not crossed unless there is truly no way through; if it is crossed, the scheduler has to go explain it.\"},\"kind\":\"constraint\",\"node\":\"Meridian on time\",\"precision\":\"spelled out\",\"rationale\":\"Stated as non-negotiable with a named consequence.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-ca18e195-3155-4504-b85d-16c7f96d1bdf",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"free, or tied up / about to be pulled onto Line 1 or Line 3 for something else — if tied up, the wash-down option isn't available and the job queues behind whoever else needs them\"},\"kind\":\"entity-type\",\"node\":\"changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"The crew is either free or tied up on another line; that state gates whether a changeover can start.\",\"slot\":\"state that rides along with each instance\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available — I'd be queuing behind whoever else needs them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if I wash Line 2 down now, I'm also asking \\\\\\\"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "policy",
-          "node": "who can absorb the slip",
-          "slot": "the rule as actually practiced",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "Given as the practiced basis for weighing knock-on lateness.",
+          "kind": "entity-type",
+          "node": "lines",
+          "slot": "how many there are, or the population's shape",
+          "precision": "number",
+          "rationale": "Three lines, named Line 1, Line 2, Line 3.",
           "assertion": {
-            "value": "When deciding which order to bump, judge by who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem to solve the first. Applied by judgment, with no formula."
+            "value": "three lines — Line 1, Line 2, Line 3"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+          "excerpt": "there's one crew, two techs, covering all three lines",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I use judgment on who can absorb the slip",
+          "excerpt": "pulled onto Line 1 or Line 3 for something else",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"When deciding which order to bump, judge by who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem to solve the first. Applied by judgment, with no formula.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"Given as the practiced basis for weighing knock-on lateness.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-f2135748-e23c-40f8-b30b-54bba48e876e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"three lines — Line 1, Line 2, Line 3\"},\"kind\":\"entity-type\",\"node\":\"lines\",\"precision\":\"number\",\"rationale\":\"Three lines, named Line 1, Line 2, Line 3.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"pulled onto Line 1 or Line 3 for something else\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "which option actually loses less",
-          "slot": "the question, in the expert's words",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "state that rides along with each instance",
           "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "The expert states the model's job as evaluating a disruption response option set.",
+          "rationale": "The expert lists what an order carries when released.",
           "assertion": {
-            "value": "Given a disruption such as \"filler's down, ETA unknown\", tell me which option (switch the order to the other line, or wait out the repair) actually loses less — instead of gut math at the huddle."
+            "value": "SKU, quantity, due date"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less",
+          "excerpt": "it's got an SKU, quantity, due date",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Line 2 finished a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 3,
             "entryEnd": 3
           },
@@ -1555,315 +1631,305 @@
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-1cb33f48-6553-4e4f-a8a0-37d7631b08ea",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given a disruption such as \\\"filler's down, ETA unknown\\\", tell me which option (switch the order to the other line, or wait out the repair) actually loses less — instead of gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"The expert states the model's job as evaluating a disruption response option set.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-8a3b6dae-cba1-4332-a4dc-f98ff6b81bc2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"SKU, quantity, due date\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The expert lists what an order carries when released.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 finished a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "which option actually loses less",
-          "slot": "what \"better\" means, and trade-off weights",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "the distinctions the process treats apart",
           "precision": "spelled out",
           "sourceRegime": "practiced",
-          "rationale": "Lexicographic scorecard given in words; the expert explicitly denies having numeric weights.",
+          "rationale": "Two distinctions the process treats differently: colour (white vs tint — whether a changeover is needed) and customer category (Meridian vs distributor).",
           "assertion": {
-            "value": "First and hard: days late on the Meridian-style order, anything above zero is bad. Underneath and traded off by judgement, not formula: washdown hours (crew time plus the line taken out of anything else), and whether the bumped order goes late and by how much and for which customer. No formula for the second-order weighting."
+            "value": "colour — white versus tint, where a same-colour order needs no changeover; and customer — Meridian orders versus small distributor orders, which are a different category when late"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing",
+          "excerpt": "another white order — a smaller one, but still white, no changeover needed",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "days late on Meridian, and anything above zero is bad news",
+          "excerpt": "three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I don't have a formula for it.",
+          "excerpt": "A Meridian miss is a different category",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-f073c3ed-2a89-4499-b3b2-fe160e8c1057",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First and hard: days late on the Meridian-style order, anything above zero is bad. Underneath and traded off by judgement, not formula: washdown hours (crew time plus the line taken out of anything else), and whether the bumped order goes late and by how much and for which customer. No formula for the second-order weighting.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Lexicographic scorecard given in words; the expert explicitly denies having numeric weights.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"days late on Meridian, and anything above zero is bad news\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-0f7b50a8-31f5-4025-ac2e-4a65bee0e3af",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"colour — white versus tint, where a same-colour order needs no changeover; and customer — Meridian orders versus small distributor orders, which are a different category when late\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Two distinctions the process treats differently: colour (white vs tint — whether a changeover is needed) and customer category (Meridian vs distributor).\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"A Meridian miss is a different category\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"another white order — a smaller one, but still white, no changeover needed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "which option actually loses less",
-          "slot": "the nodes it depends on",
-          "precision": "named",
-          "rationale": "The options the expert weighed name these nodes directly.",
+          "kind": "boundary-condition",
+          "node": "release from the demand book",
+          "slot": "the starting state",
+          "precision": "spelled out",
+          "rationale": "Orders enter the expert's world on release into the demand book from ERP, carrying SKU, quantity and due date.",
           "assertion": {
-            "value": "activity:filler jam; activity:tint-to-white washdown; entity-type:order; entity-type:line (Line 1 / Line 2); ordering/flow:order flow, allocate to ship; policy:Meridian on time; policy:who can absorb the slip"
+            "value": "An order lands in the demand book from ERP — that is \"released\" — with an SKU, quantity and due date."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+          "excerpt": "it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-c9864a2c-cbb3-41c9-97a6-e44cc1d7d424",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"activity:filler jam; activity:tint-to-white washdown; entity-type:order; entity-type:line (Line 1 / Line 2); ordering/flow:order flow, allocate to ship; policy:Meridian on time; policy:who can absorb the slip\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"named\",\"rationale\":\"The options the expert weighed name these nodes directly.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-1d5aba4c-760f-4e4e-b48f-a3f498a4a75f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order lands in the demand book from ERP — that is \\\"released\\\" — with an SKU, quantity and due date.\"},\"kind\":\"boundary-condition\",\"node\":\"release from the demand book\",\"precision\":\"spelled out\",\"rationale\":\"Orders enter the expert's world on release into the demand book from ERP, carrying SKU, quantity and due date.\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "where Line 1 loses its time",
-          "slot": "the question, in the expert's words",
+          "kind": "boundary-condition",
+          "node": "release from the demand book",
+          "slot": "the arrival or availability pattern",
           "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "Second objective the expert put explicitly in scope.",
+          "rationale": "The expert gives the release cycle (weekly demand book, re-planned each morning at the huddle) but no rate or shape of arrivals.",
           "assertion": {
-            "value": "Show where Line 1 loses its time — specifically whether the small tank between mill and fill is actually costing us — as evidence to take to engineering rather than a hunch."
+            "value": "Releases follow the demand book's weekly cycle, re-planned every morning at the huddle; past a week the book is soft and gets revised. Rate and shape of arrivals not yet given."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term",
+          "excerpt": "a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I could take that to engineering with something other than a hunch",
+          "excerpt": "Anything past a week is soft; the book itself gets revised.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-480c2821-4d80-495b-a652-f5de8b035144",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Show where Line 1 loses its time — specifically whether the small tank between mill and fill is actually costing us — as evidence to take to engineering rather than a hunch.\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"spelled out\",\"rationale\":\"Second objective the expert put explicitly in scope.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I could take that to engineering with something other than a hunch\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-51875f80-77b4-4e1c-b260-ef2cf2d3a47a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Releases follow the demand book's weekly cycle, re-planned every morning at the huddle; past a week the book is soft and gets revised. Rate and shape of arrivals not yet given.\"},\"kind\":\"boundary-condition\",\"node\":\"release from the demand book\",\"precision\":\"spelled out\",\"rationale\":\"The expert gives the release cycle (weekly demand book, re-planned each morning at the huddle) but no rate or shape of arrivals.\",\"slot\":\"the arrival or availability pattern\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Anything past a week is soft; the book itself gets revised.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "where Line 1 loses its time",
-          "slot": "the nodes it depends on",
-          "precision": "named",
-          "rationale": "The tank hunch is about these nodes.",
+          "kind": "activity",
+          "node": "changeover wash down",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Availability of the shared changeover crew gates the start of a wash down.",
           "assertion": {
-            "value": "constraint:small holding tanks between stages; entity-type:stage kit (mix, mill, tint, fill); ordering/flow:stage overlap on a line; constraint:published line rate"
+            "value": "The changeover crew must be free; if they are tied up on another line the wash-down option isn't available and the job queues behind whoever else needs them."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+          "excerpt": "If they're tied up elsewhere, my \"wash down now\" option isn't even really available — I'd be queuing behind whoever else needs them.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 12,
             "entryEnd": 12
           },
           "source": "user-affordance-payload"
-        },
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-308e3c38-4da1-468b-b8b0-d330d0d3a3de",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The changeover crew must be free; if they are tied up on another line the wash-down option isn't available and the job queues behind whoever else needs them.\"},\"kind\":\"activity\",\"node\":\"changeover wash down\",\"precision\":\"spelled out\",\"rationale\":\"Availability of the shared changeover crew gates the start of a wash down.\",\"slot\":\"what it needs before it can start\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available — I'd be queuing behind whoever else needs them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "changeover wash down",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "The changeover crew performs the wash down.",
+          "assertion": {
+            "value": "the changeover crew — one crew, two techs, shared across all three lines"
+          }
+        }
+      },
+      "evidence": [
         {
-          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
+          "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 12,
             "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-f3f2c366-eab0-49fa-951c-773f77aa11b2",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"constraint:small holding tanks between stages; entity-type:stage kit (mix, mill, tint, fill); ordering/flow:stage overlap on a line; constraint:published line rate\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"named\",\"rationale\":\"The tank hunch is about these nodes.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-db07e2c6-f110-4f71-90a1-aaf5a20fd5ea",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"the changeover crew — one crew, two techs, shared across all three lines\"},\"kind\":\"activity\",\"node\":\"changeover wash down\",\"precision\":\"named\",\"rationale\":\"The changeover crew performs the wash down.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "order",
-          "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
-          "rationale": "Distinctions the expert's process treats differently: product class (white vs tint vs specialty) and customer account type.",
+          "kind": "activity",
+          "node": "changeover wash down",
+          "slot": "what is lost when it changes the system's mode",
+          "precision": "named",
+          "rationale": "The expert names the loss qualitatively — a full white-to-tint changeover is a wash that cannot be recovered — without giving hours.",
           "assertion": {
-            "value": "An order is a line item in the demand book (quantity, due date, SKU). Whites differ from tints (tint stage is a pass-through for a white; a tint-to-white change costs a washdown) and from specialties (QA wait much longer). Customers differ: distributor, small account, and \"awkward\" accounts that get prickly."
+            "value": "a full white-to-tint changeover is \"a wash we can't get back\"; the amount of time or capacity lost was not quantified"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "excerpt": "a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "for a white the tint stage is barely there, more of a pass-through than a real letdown step",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-3bb35fb7-3954-45d4-839f-20ee46a8c052",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order is a line item in the demand book (quantity, due date, SKU). Whites differ from tints (tint stage is a pass-through for a white; a tint-to-white change costs a washdown) and from specialties (QA wait much longer). Customers differ: distributor, small account, and \\\"awkward\\\" accounts that get prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Distinctions the expert's process treats differently: product class (white vs tint vs specialty) and customer account type.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-1aba2bfb-ad60-4e76-9a2b-f4ac16294d1d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"a full white-to-tint changeover is \\\"a wash we can't get back\\\"; the amount of time or capacity lost was not quantified\"},\"kind\":\"activity\",\"node\":\"changeover wash down\",\"precision\":\"named\",\"rationale\":\"The expert names the loss qualitatively — a full white-to-tint changeover is a wash that cannot be recovered — without giving hours.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "order",
-          "slot": "state that rides along with each instance",
+          "kind": "activity",
+          "node": "clears QA hold",
+          "slot": "what it produces or changes",
           "precision": "spelled out",
-          "rationale": "Attributes named on the order.",
+          "sourceRegime": "practiced",
+          "rationale": "Clearing QA is the event against which lateness is judged and the point the order leaves the expert's scope.",
           "assertion": {
-            "value": "Quantity, due date, SKU; the line and slot in the week it is allocated to; the customer; and days late against its due date."
+            "value": "The order clears QA hold and ships; the due date is judged against when it clears, not when it comes off the line — a batch can be done Tuesday and still ship late if the lab's backed up."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "excerpt": "It ends when it clears QA hold and ships.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation",
+          "excerpt": "the due date is judged against when it clears, not when it comes off the line",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "a batch can be done Tuesday and still ship late if the lab's backed up",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-e552ac87-8cfa-4091-a262-6fba33ab9f83",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; the line and slot in the week it is allocated to; the customer; and days late against its due date.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Attributes named on the order.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-25d93015-ae4d-48ce-8708-1d5c257d629a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order clears QA hold and ships; the due date is judged against when it clears, not when it comes off the line — a batch can be done Tuesday and still ship late if the lab's backed up.\"},\"kind\":\"activity\",\"node\":\"clears QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Clearing QA is the event against which lateness is judged and the point the order leaves the expert's scope.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It ends when it clears QA hold and ships.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a batch can be done Tuesday and still ship late if the lab's backed up\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "line (Line 1 / Line 2)",
-          "slot": "the distinctions the process treats apart",
+          "kind": "ordering/flow",
+          "node": "release to cleared QA",
+          "slot": "the order things happen in",
           "precision": "spelled out",
-          "sourceRegime": "prescribed",
-          "rationale": "The scheduling sheet's view of a line as a single indivisible resource.",
+          "rationale": "The end-to-end span the expert owns; intermediate line steps not yet detailed.",
           "assertion": {
-            "value": "On the sheet a line is one row, one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it's done."
+            "value": "Order is released into the demand book from ERP → run on a line (with a changeover before it if the colour differs) → comes off the line → clears QA hold → ships. Steps within the line run not yet detailed."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+          "excerpt": "an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 12,
             "entryEnd": 12
           },
           "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet a line is one row, one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it's done.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"spelled out\",\"rationale\":\"The scheduling sheet's view of a line as a single indivisible resource.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "line (Line 1 / Line 2)",
-          "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "Physical reality diverges from the sheet; both recorded on the same node.",
-          "assertion": {
-            "value": "Physically a line is not one thing: mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between."
-          }
-        }
-      },
-      "evidence": [
+        },
         {
-          "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+          "excerpt": "it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "It ends when it clears QA hold and ships.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 12,
             "entryEnd": 12
           },
@@ -1871,78 +1937,97 @@
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-dd037a1c-63c0-47b8-8886-81c6d1f70226",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically a line is not one thing: mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"spelled out\",\"rationale\":\"Physical reality diverges from the sheet; both recorded on the same node.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-d767508b-10f1-41b0-8818-b943bf124b10",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Order is released into the demand book from ERP → run on a line (with a changeover before it if the colour differs) → comes off the line → clears QA hold → ships. Steps within the line run not yet detailed.\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"The end-to-end span the expert owns; intermediate line steps not yet detailed.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It ends when it clears QA hold and ships.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"an order's mine from release to \\\\\\\"cleared QA,\\\\\\\" and the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "line (Line 1 / Line 2)",
-          "slot": "how many there are, or the population's shape",
-          "precision": "named",
-          "rationale": "Only Line 1 and Line 2 are named; no count was stated.",
+          "kind": "constraint",
+          "node": "no Meridian misses",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "An unwritten hard rule with a named consequence, stated as not tradeable even against twenty small late orders.",
           "assertion": {
-            "value": "Line 1 and Line 2 are the lines named; no total count stated."
+            "value": "A Meridian order must not slip its due date. If it does: a fine, ammunition for Meridian to delist a line item at next contract review, and calls to commercial and to the boss. Not traded off — even twenty small orders late is preferred to one Meridian miss; it is a \"we just don't do that\" rule that nobody has written down."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "whether to shift it to Line 1 or just wait out the repair",
+          "excerpt": "it's not just \"late,\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "especially the one between mill and fill on Line 1",
+          "excerpt": "Even if you told me \"twenty small orders late\" versus \"one Meridian order late\" — I'd still not want to be the one who let Meridian slip.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "right now it's a \"we just don't do that\" rule, not a traded-off cost",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-6c46c958-82b9-4ba0-bf0f-363fd70b6dbc",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2 are the lines named; no total count stated.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"named\",\"rationale\":\"Only Line 1 and Line 2 are named; no count was stated.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whether to shift it to Line 1 or just wait out the repair\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-a8c037cd-b9d8-4056-828f-74511da9a726",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian order must not slip its due date. If it does: a fine, ammunition for Meridian to delist a line item at next contract review, and calls to commercial and to the boss. Not traded off — even twenty small orders late is preferred to one Meridian miss; it is a \\\"we just don't do that\\\" rule that nobody has written down.\"},\"kind\":\"constraint\",\"node\":\"no Meridian misses\",\"precision\":\"spelled out\",\"rationale\":\"An unwritten hard rule with a named consequence, stated as not tradeable even against twenty small late orders.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Even if you told me \\\\\\\"twenty small orders late\\\\\\\" versus \\\\\\\"one Meridian order late\\\\\\\" — I'd still not want to be the one who let Meridian slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's not just \\\\\\\"late,\\\\\\\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"right now it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "stage kit (mix, mill, tint, fill)",
-          "slot": "the distinctions the process treats apart",
+          "kind": "constraint",
+          "node": "one-week planning horizon",
+          "slot": "the limit and what happens when it is hit",
           "precision": "spelled out",
           "sourceRegime": "practiced",
-          "rationale": "Each stage is separately contended kit.",
+          "rationale": "The horizon over which the model's answer must hold, with the expert's stated reason it fails beyond it.",
           "assertion": {
-            "value": "Four separate pieces of kit per line — mixer, mill, tint, fill head — each usable independently, with small holding tanks buffering between mix/mill and mill/fill."
+            "value": "A week is the horizon that matters — the demand book's cycle, re-planned every morning at the huddle; two weeks out is watched only for big minimum-run specialty work; a plan held a month out is refused because too much changes."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between",
+          "excerpt": "Practically, a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially, because you don't want to discover Thursday that you needed to have started Tuesday.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 12,
             "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "the mixer could be starting the next order's batch while the fill head is still finishing the last one",
+          "excerpt": "But if you ask me to hold a plan that's useful a month out, I'd say no — too much changes.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 12,
             "entryEnd": 12
           },
@@ -1950,257 +2035,365 @@
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-ee4eb482-b4b3-4392-94d7-ef9dc0a6ca98",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Four separate pieces of kit per line — mixer, mill, tint, fill head — each usable independently, with small holding tanks buffering between mix/mill and mill/fill.\"},\"kind\":\"entity-type\",\"node\":\"stage kit (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"rationale\":\"Each stage is separately contended kit.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the mixer could be starting the next order's batch while the fill head is still finishing the last one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-ccf25a9c-6c03-47ed-9cd4-e030f3ef1dc9",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A week is the horizon that matters — the demand book's cycle, re-planned every morning at the huddle; two weeks out is watched only for big minimum-run specialty work; a plan held a month out is refused because too much changes.\"},\"kind\":\"constraint\",\"node\":\"one-week planning horizon\",\"precision\":\"spelled out\",\"rationale\":\"The horizon over which the model's answer must hold, with the expert's stated reason it fails beyond it.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But if you ask me to hold a plan that's useful a month out, I'd say no — too much changes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially, because you don't want to discover Thursday that you needed to have started Tuesday.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Practically, a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "boundary-condition",
-          "node": "demand book from ERP",
-          "slot": "the arrival or availability pattern",
-          "precision": "named",
-          "rationale": "Arrival source named; no rate or shape given yet, so precision is only 'named'.",
+          "kind": "policy",
+          "node": "sit the line for an expected same-colour order",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The practiced rule behind the decision, given as gut judgment on a real occasion; not yet elicited as a general rule with conditions.",
           "assertion": {
-            "value": "Orders arrive as line items in the demand book when ERP spits it out, each with quantity, due date and SKU."
+            "value": "When a same-colour order is expected to be released later the same day, hold the line idle rather than change over — because a full white-to-tint changeover is a wash that can't be got back, versus an hour of idle time. Judged by gut, three or four times a month."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "excerpt": "I ended up sitting the line. It felt right — a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I make that judgment by gut maybe three or four times a month",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders arrive as line items in the demand book when ERP spits it out, each with quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"named\",\"rationale\":\"Arrival source named; no rate or shape given yet, so precision is only 'named'.\",\"slot\":\"the arrival or availability pattern\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-760f09f2-bdec-44fe-897d-f81b376a0ad6",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"When a same-colour order is expected to be released later the same day, hold the line idle rather than change over — because a full white-to-tint changeover is a wash that can't be got back, versus an hour of idle time. Judged by gut, three or four times a month.\"},\"kind\":\"policy\",\"node\":\"sit the line for an expected same-colour order\",\"precision\":\"spelled out\",\"rationale\":\"The practiced rule behind the decision, given as gut judgment on a real occasion; not yet elicited as a general rule with conditions.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I ended up sitting the line. It felt right — a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I make that judgment by gut maybe three or four times a month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "allocation",
-          "slot": "what it produces or changes",
+          "kind": "validation-criterion",
+          "node": "recognize the shape of a real month",
+          "slot": "how the expert would know the model is right",
           "precision": "spelled out",
-          "rationale": "Output of the allocation step.",
+          "rationale": "A replay test on last month's demand book with three named checks and an explicit refusal to trust a single number.",
           "assertion": {
-            "value": "The order is placed onto a line and a slot in the week on the sheet."
+            "value": "Feed it last month's demand book: it must land roughly where we actually landed on late orders — same rough number and same kind of misses (getting the kind wrong, e.g. distributor instead of Meridian, is worse than getting the count wrong); changeover hours on Line 2 and 3 must look about right, and Line 3 must not sit idle half the week waiting on the crew because that never happens; and it must reproduce the odd weeks, e.g. a breakdown chewing up two days on Line 1. No single number would be trusted — the shape of a real month must be recognizable."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation",
+          "excerpt": "the first thing I'd check is the boring one — did it land roughly where we actually landed on late orders that month?",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "allocate it onto a line and a slot in the week",
+          "excerpt": "we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones. So: same rough number and same *kind* of misses.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "If it says we missed distributor orders and we actually missed a Meridian one, that's worse than getting the count wrong.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "After that I'd want to eyeball changeover hours on Line 2 and 3 specifically",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "if the model has Line 3 idle half the week waiting on the crew, and that never happens in real life, I'd know it's missing something about how the crew actually gets shared out",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "And I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I'd want to recognize the *shape* of a real month before I'd believe it on something as specific as the wash-versus-idle call.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-32521b14-4f1e-41ff-ab95-dfc11d8eee37",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is placed onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Output of the allocation step.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-f79e5a2e-1102-4970-a177-0b9c1fab4c03",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Feed it last month's demand book: it must land roughly where we actually landed on late orders — same rough number and same kind of misses (getting the kind wrong, e.g. distributor instead of Meridian, is worse than getting the count wrong); changeover hours on Line 2 and 3 must look about right, and Line 3 must not sit idle half the week waiting on the crew because that never happens; and it must reproduce the odd weeks, e.g. a breakdown chewing up two days on Line 1. No single number would be trusted — the shape of a real month must be recognizable.\"},\"kind\":\"validation-criterion\",\"node\":\"recognize the shape of a real month\",\"precision\":\"spelled out\",\"rationale\":\"A replay test on last month's demand book with three named checks and an explicit refusal to trust a single number.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"After that I'd want to eyeball changeover hours on Line 2 and 3 specifically\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"And I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'd want to recognize the *shape* of a real month before I'd believe it on something as specific as the wash-versus-idle call.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If it says we missed distributor orders and we actually missed a Meridian one, that's worse than getting the count wrong.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if the model has Line 3 idle half the week waiting on the crew, and that never happens in real life, I'd know it's missing something about how the crew actually gets shared out\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first thing I'd check is the boring one — did it land roughly where we actually landed on late orders that month?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones. So: same rough number and same *kind* of misses.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "allocation",
-          "slot": "what it needs before it can start",
-          "precision": "spelled out",
-          "rationale": "Precondition named.",
+          "kind": "data-binding",
+          "node": "changeover log and late-order report",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "rationale": "Two existing records the expert already keeps, tracked separately today.",
           "assertion": {
-            "value": "A line item in the demand book from ERP, with quantity, due date and SKU."
+            "value": "changeover hours from the changeover log; late orders from the late-order report — currently tracked separately and never put on the same page"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "excerpt": "I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book from ERP, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Precondition named.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-03ff88a9-662d-4963-aece-fe45c343df17",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"changeover hours from the changeover log; late orders from the late-order report — currently tracked separately and never put on the same page\"},\"kind\":\"data-binding\",\"node\":\"changeover log and late-order report\",\"precision\":\"named\",\"rationale\":\"Two existing records the expert already keeps, tracked separately today.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "speculative",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "allocation",
-          "slot": "who or what performs it",
-          "precision": "named",
-          "rationale": "The expert performs it himself.",
+          "node": "breakdown on a line",
+          "slot": "how long it takes",
+          "precision": "number",
+          "sourceRegime": "practiced",
+          "rationale": "Mentioned in passing as a validation case — one recalled incident, not a rate or a distribution.",
           "assertion": {
-            "value": "The master scheduler (the expert), on the sheet."
+            "value": "a breakdown chewed up two days on Line 1 in one recalled odd week"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation",
+          "excerpt": "the ones where a breakdown chewed up two days on Line 1",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "explicit",
-      "id": "capture-c1704cba-8451-47a5-add8-2e388b330a1f",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler (the expert), on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"named\",\"rationale\":\"The expert performs it himself.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "tentative",
+      "id": "capture-da211e90-dab6-4896-b9f1-9d01a9c55b9e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"a breakdown chewed up two days on Line 1 in one recalled odd week\"},\"kind\":\"activity\",\"node\":\"breakdown on a line\",\"precision\":\"number\",\"rationale\":\"Mentioned in passing as a validation case — one recalled incident, not a rate or a distribution.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run the batch (mix/mill/tint/fill)",
-          "slot": "what it produces or changes",
+          "kind": "objective",
+          "node": "the wash-versus-idle call",
+          "slot": "the question, in the expert's words",
           "precision": "spelled out",
-          "rationale": "The production run through the four stages.",
+          "sourceRegime": "practiced",
+          "rationale": "The expert's own framing of the decision the model must inform, given as a real recent case.",
           "assertion": {
-            "value": "The order is produced through the same four stages every product goes through — mix, mill, tint, fill and pack — and comes off the fill line."
+            "value": "Whether to wash down Line 2 for the tint order right then, or let Line 2 sit idle for about an hour waiting for a smaller white order that needs no changeover — a judgment made by gut maybe three or four times a month, never verified."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
+          "excerpt": "I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet",
+          "excerpt": "That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-68ab39e5-8046-4f93-887e-11ed3e3b1da3",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is produced through the same four stages every product goes through — mix, mill, tint, fill and pack — and comes off the fill line.\"},\"kind\":\"activity\",\"node\":\"run the batch (mix/mill/tint/fill)\",\"precision\":\"spelled out\",\"rationale\":\"The production run through the four stages.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-da8d88a4-c4e2-499b-b138-3f3df855b108",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whether to wash down Line 2 for the tint order right then, or let Line 2 sit idle for about an hour waiting for a smaller white order that needs no changeover — a judgment made by gut maybe three or four times a month, never verified.\"},\"kind\":\"objective\",\"node\":\"the wash-versus-idle call\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own framing of the decision the model must inform, given as a real recent case.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run the batch (mix/mill/tint/fill)",
-          "slot": "how long it takes",
-          "rationale": "The expert says the end-to-end batch time per SKU per line exists on his sheet but gave no figures in this range.",
+          "kind": "objective",
+          "node": "the wash-versus-idle call",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "The expert named the scope of the decision: orders, three lines, the shared crew, the changeovers, the run and the QA hold up to cleared-QA.",
           "assertion": {
-            "absence": "deferred",
-            "pointer": "the expert's scheduling sheet (roughly how long a batch of a given SKU takes end to end on each line)"
+            "value": [
+              "entity-type:order",
+              "entity-type:the three lines",
+              "entity-type:the changeover crew",
+              "boundary-condition:the demand book",
+              "activity:white-to-tint changeover on Line 2",
+              "activity:tint-to-white changeover",
+              "activity:specialty changeover",
+              "activity:the run",
+              "activity:QA hold",
+              "ordering/flow:release to cleared QA",
+              "policy:who gets the crew",
+              "constraint:no Meridian misses"
+            ]
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet",
+          "excerpt": "in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-c6d485c6-0e21-4cc0-b626-9091448d6ba1",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the expert's scheduling sheet (roughly how long a batch of a given SKU takes end to end on each line)\"},\"kind\":\"activity\",\"node\":\"run the batch (mix/mill/tint/fill)\",\"rationale\":\"The expert says the end-to-end batch time per SKU per line exists on his sheet but gave no figures in this range.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-d9c81987-582e-43fd-8ebb-a7be078ec2b7",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:the three lines\",\"entity-type:the changeover crew\",\"boundary-condition:the demand book\",\"activity:white-to-tint changeover on Line 2\",\"activity:tint-to-white changeover\",\"activity:specialty changeover\",\"activity:the run\",\"activity:QA hold\",\"ordering/flow:release to cleared QA\",\"policy:who gets the crew\",\"constraint:no Meridian misses\"]},\"kind\":\"objective\",\"node\":\"the wash-versus-idle call\",\"precision\":\"named\",\"rationale\":\"The expert named the scope of the decision: orders, three lines, the shared crew, the changeovers, the run and the QA hold up to cleared-QA.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"an order's mine from release to \\\\\\\"cleared QA,\\\\\\\" and the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run the batch (mix/mill/tint/fill)",
-          "slot": "whether its quantities vary by type",
-          "rationale": "Stage-by-stage durations are not held by the expert; he names the historian as the source.",
+          "kind": "objective",
+          "node": "the wash-versus-idle call",
+          "slot": "what \"better\" means, and trade-off weights",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "A lexicographic ranking, not a weight: Meridian misses are refused at any exchange rate the expert would see in a week.",
           "assertion": {
-            "absence": "deferred",
-            "pointer": "the historian (stage-by-stage times: how long does mixing take, how long does milling take)"
+            "value": "Better = no Meridian late orders first (not tradeable — three small late orders beat one Meridian miss, and even twenty small late orders would not flip it), then late-order count, with changeover hours and idle time as the expert's own diagnostics rather than the graded measure."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+          "excerpt": "If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere. The changeover hours and the idle time are more my own concern",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "(a) is the better week, easy — three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Even if you told me \"twenty small orders late\" versus \"one Meridian order late\" — I'd still not want to be the one who let Meridian slip.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the historian (stage-by-stage times: how long does mixing take, how long does milling take)\"},\"kind\":\"activity\",\"node\":\"run the batch (mix/mill/tint/fill)\",\"rationale\":\"Stage-by-stage durations are not held by the expert; he names the historian as the source.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-1e33246c-c307-46c2-b6c2-392fd7d92329",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Better = no Meridian late orders first (not tradeable — three small late orders beat one Meridian miss, and even twenty small late orders would not flip it), then late-order count, with changeover hours and idle time as the expert's own diagnostics rather than the graded measure.\"},\"kind\":\"objective\",\"node\":\"the wash-versus-idle call\",\"precision\":\"spelled out\",\"rationale\":\"A lexicographic ranking, not a weight: Meridian misses are refused at any exchange rate the expert would see in a week.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"(a) is the better week, easy — three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Even if you told me \\\\\\\"twenty small orders late\\\\\\\" versus \\\\\\\"one Meridian order late\\\\\\\" — I'd still not want to be the one who let Meridian slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere. The changeover hours and the idle time are more my own concern\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint stage",
-          "slot": "whether its quantities vary by type",
-          "precision": "named",
-          "rationale": "Explicit variation by product type.",
+          "kind": "constraint",
+          "node": "no Meridian misses",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "An unwritten hard rule with a named consequence; the monetary exchange rate is explicitly unavailable and would have to come from commercial.",
           "assertion": {
-            "value": "Yes — for a white the tint stage is barely there, more of a pass-through than a real letdown step."
+            "value": "Meridian orders must not miss their due date — \"we just don't do that\". If one does: it's a fine, and ammunition for Meridian to delist a line item at next contract review; commercial gets calls and the boss gets calls. No cost exchange rate exists; obtaining one would require getting commercial in a room to state it."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+          "excerpt": "I know that's not a real number you can put in a formula. If you need a number, you'd have to get commercial in a room and force them to say it out loud, because right now it's a \"we just don't do that\" rule, not a traded-off cost.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 9,
             "entryEnd": 9
           },
@@ -2208,29 +2401,38 @@
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-737200bb-8f75-455f-b90a-3363a30d5fce",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — for a white the tint stage is barely there, more of a pass-through than a real letdown step.\"},\"kind\":\"activity\",\"node\":\"tint stage\",\"precision\":\"named\",\"rationale\":\"Explicit variation by product type.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-59c35b27-63c3-4ae7-92d5-5454281a05e0",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian orders must not miss their due date — \\\"we just don't do that\\\". If one does: it's a fine, and ammunition for Meridian to delist a line item at next contract review; commercial gets calls and the boss gets calls. No cost exchange rate exists; obtaining one would require getting commercial in a room to state it.\"},\"kind\":\"constraint\",\"node\":\"no Meridian misses\",\"precision\":\"spelled out\",\"rationale\":\"An unwritten hard rule with a named consequence; the monetary exchange rate is explicitly unavailable and would have to come from commercial.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know that's not a real number you can put in a formula. If you need a number, you'd have to get commercial in a room and force them to say it out loud, because right now it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "how long it takes",
-          "precision": "named",
-          "rationale": "Vague quantity as given — 'usually a few hours for a white'; not yet a spread.",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "rationale": "Customer class (Meridian vs distributor) and colour family (white / tint / specialty) are the distinctions that drive changeovers and lateness consequences.",
           "assertion": {
-            "value": "Usually a few hours for a white; the specialty wait is much longer (figure not given)."
+            "value": "Orders divide by customer — Meridian versus distributors (distributors slip 2-3 days with a phone call; a Meridian miss is a different category) — and by colour family: white, tint, and specialty, which decide whether and what kind of changeover is needed."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait",
+          "excerpt": "it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "A Meridian miss is a different category — it's not just \"late,\"",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 9,
             "entryEnd": 9
           },
@@ -2238,190 +2440,224 @@
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-78203b7c-8e00-469c-9d53-01d1a656d5c1",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; the specialty wait is much longer (figure not given).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Vague quantity as given — 'usually a few hours for a white'; not yet a spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-7cb7c5b3-1c4e-42b5-8c28-b6b851d7b3c3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders divide by customer — Meridian versus distributors (distributors slip 2-3 days with a phone call; a Meridian miss is a different category) — and by colour family: white, tint, and specialty, which decide whether and what kind of changeover is needed.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Customer class (Meridian vs distributor) and colour family (white / tint / specialty) are the distinctions that drive changeovers and lateness consequences.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"A Meridian miss is a different category — it's not just \\\\\\\"late,\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "whether its quantities vary by type",
-          "precision": "named",
-          "rationale": "Explicit contrast between white and specialty.",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "state that rides along with each instance",
+          "precision": "spelled out",
+          "rationale": "The attributes the order carries from release.",
           "assertion": {
-            "value": "Yes — a few hours for a white, nothing like the specialty wait."
+            "value": "SKU, quantity, and due date, carried from release in the demand book from ERP."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
+          "excerpt": "it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a few hours for a white, nothing like the specialty wait.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Explicit contrast between white and specialty.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-e20e49bb-dbd3-4616-8da4-f14024b09ed0",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"SKU, quantity, and due date, carried from release in the demand book from ERP.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The attributes the order carries from release.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "who or what performs it",
-          "precision": "named",
-          "rationale": "The lab performs the check.",
+          "kind": "entity-type",
+          "node": "the changeover crew",
+          "slot": "how many there are, or the population's shape",
+          "precision": "number",
+          "rationale": "Explicit count of the contended resource.",
           "assertion": {
-            "value": "The lab (the order sits in the lab's queue and gets checked)."
+            "value": "One crew of two techs, covering all three lines."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+          "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab (the order sits in the lab's queue and gets checked).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"The lab performs the check.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-41a07d27-a4e5-4f0c-8308-854425894bc5",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One crew of two techs, covering all three lines.\"},\"kind\":\"entity-type\",\"node\":\"the changeover crew\",\"precision\":\"number\",\"rationale\":\"Explicit count of the contended resource.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "release and ship",
-          "slot": "what it produces or changes",
+          "kind": "entity-type",
+          "node": "the changeover crew",
+          "slot": "the distinctions the process treats apart",
           "precision": "spelled out",
-          "rationale": "Terminal step.",
+          "rationale": "The crew is treated as one indivisible unit serving one line at a time; other lines queue behind it.",
           "assertion": {
-            "value": "The order is released, goes to the warehouse, and ships against the due date."
+            "value": "Treated as a single unit — either free or tied up on another line; if tied up, the wash-down option is not available and the line queues behind whoever else needs them."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+          "excerpt": "if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\" If they're tied up elsewhere, my \"wash down now\" option isn't even really available — I'd be queuing behind whoever else needs them.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"rationale\":\"Terminal step.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-858e5f98-ce0c-47ca-9bff-1e41d25523eb",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Treated as a single unit — either free or tied up on another line; if tied up, the wash-down option is not available and the line queues behind whoever else needs them.\"},\"kind\":\"entity-type\",\"node\":\"the changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"The crew is treated as one indivisible unit serving one line at a time; other lines queue behind it.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"if I wash Line 2 down now, I'm also asking \\\\\\\"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\\\\\\\" If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available — I'd be queuing behind whoever else needs them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "how long it takes",
+          "kind": "entity-type",
+          "node": "the three lines",
+          "slot": "how many there are, or the population's shape",
           "precision": "number",
-          "sourceRegime": "practiced",
-          "rationale": "A single figure given; not a spread.",
+          "rationale": "Three production lines, named Line 1, Line 2, Line 3.",
           "assertion": {
-            "value": "Three hours."
+            "value": "Three lines — Line 1, Line 2, Line 3."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
+          "excerpt": "there's one crew, two techs, covering all three lines",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Meridian white basically always goes to Line 2",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-42e0a99d-6cf6-4b30-8199-b430405ba25b",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"A single figure given; not a spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-5ac2a1b3-03ea-4864-a6e6-89ea2a3163d9",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three lines — Line 1, Line 2, Line 3.\"},\"kind\":\"entity-type\",\"node\":\"the three lines\",\"precision\":\"number\",\"rationale\":\"Three production lines, named Line 1, Line 2, Line 3.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what is lost when it changes the system's mode",
-          "precision": "number",
-          "sourceRegime": "practiced",
-          "rationale": "Named mode change (tint to white) with its stated loss.",
+          "kind": "entity-type",
+          "node": "the three lines",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "rationale": "Lines are distinguished by what they habitually run; Meridian white is effectively assigned to Line 2.",
           "assertion": {
-            "value": "Three hours of crew time, and the line is out of anything else for that window."
+            "value": "Lines are treated apart by what they run: Meridian white basically always goes to Line 2; Line 1 was running specialty and Line 3 tint in the recalled case."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
+          "excerpt": "Meridian white basically always goes to Line 2, so it went into \"my\" Line 2 column on the sheet without much debate.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Line 1 had just finished a specialty run",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Line 3 finished a tint run",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-a27c0fc1-57f3-4eed-bea8-15453c84f2da",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of crew time, and the line is out of anything else for that window.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Named mode change (tint to white) with its stated loss.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-42dc7c2d-13c1-407d-ab6e-8359366321d0",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lines are treated apart by what they run: Meridian white basically always goes to Line 2; Line 1 was running specialty and Line 3 tint in the recalled case.\"},\"kind\":\"entity-type\",\"node\":\"the three lines\",\"precision\":\"spelled out\",\"rationale\":\"Lines are distinguished by what they habitually run; Meridian white is effectively assigned to Line 2.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 had just finished a specialty run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 3 finished a tint run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2, so it went into \\\\\\\"my\\\\\\\" Line 2 column on the sheet without much debate.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what it needs before it can start",
+          "kind": "boundary-condition",
+          "node": "the demand book",
+          "slot": "the arrival or availability pattern",
           "precision": "spelled out",
-          "rationale": "Trigger condition for the changeover.",
+          "rationale": "Orders arrive in weekly batches released from ERP into the demand book; the book is revised weekly and re-planned each morning at the huddle.",
           "assertion": {
-            "value": "A line that has been running a tint being pulled onto a white."
+            "value": "Orders are released from ERP into the demand book in a weekly batch (the recalled one was the Monday release). A week is the horizon that matters — the cycle of the demand book, re-planned every morning at the huddle. Beyond a week is soft because the book itself gets revised; the expert keeps half an eye two weeks out for big minimum-run specialty work, and would refuse to hold a plan a month out."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown",
+          "excerpt": "Practically, a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "on the Monday release, part of that week's batch of orders from ERP",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-0f6aea65-d3a4-430b-b532-4f1100303f9e",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line that has been running a tint being pulled onto a white.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Trigger condition for the changeover.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-442393fc-5207-40e8-953f-f32c4077af7b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders are released from ERP into the demand book in a weekly batch (the recalled one was the Monday release). A week is the horizon that matters — the cycle of the demand book, re-planned every morning at the huddle. Beyond a week is soft because the book itself gets revised; the expert keeps half an eye two weeks out for big minimum-run specialty work, and would refuse to hold a plan a month out.\"},\"kind\":\"boundary-condition\",\"node\":\"the demand book\",\"precision\":\"spelled out\",\"rationale\":\"Orders arrive in weekly batches released from ERP into the demand book; the book is revised weekly and re-planned each morning at the huddle.\",\"slot\":\"the arrival or availability pattern\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Practically, a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"on the Monday release, part of that week's batch of orders from ERP\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -2429,966 +2665,1019 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "filler jam",
-          "slot": "what it produces or changes",
+          "node": "the run",
+          "slot": "what it needs before it can start",
           "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "Event effect on the line and the order in hand.",
+          "rationale": "Precondition stated in the walkthrough: the line free of the previous job, and either same family (no changeover) or a completed changeover.",
           "assertion": {
-            "value": "The line's filler goes down mid-run with an unknown ETA; the order on it stalls and must either wait or be shifted to the other line."
+            "value": "The order must be in the Line 2 column on the sheet and must wait its turn behind whatever is already running on that line; if the job ahead is the same family, no changeover is needed — a straight run-into-run."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "the tint order I bumped now might itself be late",
+          "excerpt": "It had to wait its turn behind whatever was already running on Line 2.** There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-a3f706dd-453a-4543-9990-26efb1b079dd",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line's filler goes down mid-run with an unknown ETA; the order on it stalls and must either wait or be shifted to the other line.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"Event effect on the line and the order in hand.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the tint order I bumped now might itself be late\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-9842aaa1-3de6-409e-a76a-4dc761ba75f4",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order must be in the Line 2 column on the sheet and must wait its turn behind whatever is already running on that line; if the job ahead is the same family, no changeover is needed — a straight run-into-run.\"},\"kind\":\"activity\",\"node\":\"the run\",\"precision\":\"spelled out\",\"rationale\":\"Precondition stated in the walkthrough: the line free of the previous job, and either same family (no changeover) or a completed changeover.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It had to wait its turn behind whatever was already running on Line 2.** There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "filler jam",
-          "slot": "how long it takes",
-          "precision": "range",
-          "sourceRegime": "practiced",
-          "rationale": "Two named repair kinds bound the range; the recent instance was about two hours. Not yet a spread.",
+          "node": "the run",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "The run's output as described.",
           "assertion": {
-            "value": "From the \"half hour\" kind to the \"half a shift\" kind; the recent Line 2 jam came back in about two hours."
+            "value": "Mix, mill, tint stage (skipped for a white), through fill and pack; the finished order is palletized and moved off the line into the queue for the lab."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+          "excerpt": "Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "it came back in about two hours",
+          "excerpt": "Once fill and pack was done, it went into QA hold.** That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-67de2e75-132c-43a7-b64e-412343204931",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"From the \\\"half hour\\\" kind to the \\\"half a shift\\\" kind; the recent Line 2 jam came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Two named repair kinds bound the range; the recent instance was about two hours. Not yet a spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-16bb49bd-8cb1-4840-a016-fb3c2e03ea06",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Mix, mill, tint stage (skipped for a white), through fill and pack; the finished order is palletized and moved off the line into the queue for the lab.\"},\"kind\":\"activity\",\"node\":\"the run\",\"precision\":\"spelled out\",\"rationale\":\"The run's output as described.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.** That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "order flow, allocate to ship",
-          "slot": "the order things happen in",
-          "precision": "spelled out",
-          "rationale": "The end-to-end order stated by the expert.",
+          "kind": "activity",
+          "node": "the run",
+          "slot": "how long it takes",
+          "precision": "number",
+          "rationale": "Only a single recalled case at roughly a day; the expert explicitly says exact hours would need the sheet, so no range or spread was reached.",
           "assertion": {
-            "value": "Allocate the order onto a line and a slot in the week → run it through mix / mill / tint / fill and pack → QA hold → release and ship. Four steps if QA and shipping count as one, five if split."
+            "value": "For that big-volume Meridian white order: on the line most of the day — started Wednesday morning and wrapped Wednesday evening; exact hours would have to be checked on the sheet."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship",
+          "excerpt": "it's a big volume order, so it was on the line most of the day. I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-bf082835-a2ca-4279-80e5-726f157270bd",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate the order onto a line and a slot in the week → run it through mix / mill / tint / fill and pack → QA hold → release and ship. Four steps if QA and shipping count as one, five if split.\"},\"kind\":\"ordering/flow\",\"node\":\"order flow, allocate to ship\",\"precision\":\"spelled out\",\"rationale\":\"The end-to-end order stated by the expert.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-874499fa-7846-4cc1-b5c3-1a214824b34b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"For that big-volume Meridian white order: on the line most of the day — started Wednesday morning and wrapped Wednesday evening; exact hours would have to be checked on the sheet.\"},\"kind\":\"activity\",\"node\":\"the run\",\"precision\":\"number\",\"rationale\":\"Only a single recalled case at roughly a day; the expert explicitly says exact hours would need the sheet, so no range or spread was reached.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it's a big volume order, so it was on the line most of the day. I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "stage overlap on a line",
-          "slot": "the order things happen in",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "Overlap between consecutive orders on the same line, gated by tank space.",
+          "kind": "activity",
+          "node": "the run",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "The expert names the line as what runs the order and says he does not watch the operators minute by minute; no crew is involved in a run-into-run.",
           "assertion": {
-            "value": "Stages can overlap between orders: the mixer may start the next order's batch while the fill head is still finishing the last one, provided the holding tank ahead (mix→mill or mill→fill) has space; the crew will take that head start when the tank ahead has room."
+            "value": "The line itself (Line 2 in the recalled case); no changeover crew involved — \"that's the easy case, no crew involved\". The expert does not watch it minute by minute."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it",
+          "excerpt": "It ran.** Mix, mill, tint stage",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "the crew will get a head start on mixing the next batch if the tank ahead of it has space",
+          "excerpt": "I don't watch this minute by minute",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-ce28dd53-a53d-4bc9-9956-dc3268c35e3e",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stages can overlap between orders: the mixer may start the next order's batch while the fill head is still finishing the last one, provided the holding tank ahead (mix→mill or mill→fill) has space; the crew will take that head start when the tank ahead has room.\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"precision\":\"spelled out\",\"rationale\":\"Overlap between consecutive orders on the same line, gated by tank space.\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the crew will get a head start on mixing the next batch if the tank ahead of it has space\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-7b487f70-d5b2-436f-96ca-c18b75d4f706",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line itself (Line 2 in the recalled case); no changeover crew involved — \\\"that's the easy case, no crew involved\\\". The expert does not watch it minute by minute.\"},\"kind\":\"activity\",\"node\":\"the run\",\"precision\":\"named\",\"rationale\":\"The expert names the line as what runs the order and says he does not watch the operators minute by minute; no crew is involved in a run-into-run.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't watch this minute by minute\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It ran.** Mix, mill, tint stage\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "stage overlap on a line",
-          "slot": "how a branch or merge is decided",
-          "rationale": "The expert explicitly does not track how often overlap occurs or is blocked.",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "how long it takes",
+          "precision": "number",
+          "rationale": "A single typical figure for white only; no low/high given.",
           "assertion": {
-            "absence": "unknown-to-user"
+            "value": "Normally about four hours for a white."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait",
+          "excerpt": "It sat in QA** — normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-9b28544e-b867-4018-9c35-2691cef17a62",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"rationale\":\"The expert explicitly does not track how often overlap occurs or is blocked.\",\"slot\":\"how a branch or merge is decided\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-1692771b-05c1-41fd-a63b-9b93436ac581",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Normally about four hours for a white.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"number\",\"rationale\":\"A single typical figure for white only; no low/high given.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It sat in QA** — normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "constraint",
-          "node": "small holding tanks between stages",
-          "slot": "the limit and what happens when it is hit",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "Capacity and consequence stated qualitatively; the sizes themselves are not held by the expert.",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
+          "rationale": "The expert distinguishes the white hold from the long specialty hold, and notes lab backlog extends it.",
           "assertion": {
-            "value": "The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait. Actual tank sizes not known to the expert; obtainable from engineering drawings."
+            "value": "Yes — a white is about four hours; specialty has a \"long specialty hold\". Duration also stretches when the lab is backed up."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
+          "excerpt": "nothing exotic about it chemically, so it's not the long specialty hold",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "how often it's blocked because a tank's full and mixing has to wait",
+          "excerpt": "That QA gap matters more than people think — a batch can be done Tuesday and still ship late if the lab's backed up.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 12,
             "entryEnd": 12
           },
           "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
-          },
-          "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-4c4af9ea-df1a-4449-adb7-d48fce7eae93",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait. Actual tank sizes not known to the expert; obtainable from engineering drawings.\"},\"kind\":\"constraint\",\"node\":\"small holding tanks between stages\",\"precision\":\"spelled out\",\"rationale\":\"Capacity and consequence stated qualitatively; the sizes themselves are not held by the expert.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"how often it's blocked because a tank's full and mixing has to wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-94cf39d1-87b6-4013-a9cf-06e97177192e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a white is about four hours; specialty has a \\\"long specialty hold\\\". Duration also stretches when the lab is backed up.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"The expert distinguishes the white hold from the long specialty hold, and notes lab backlog extends it.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That QA gap matters more than people think — a batch can be done Tuesday and still ship late if the lab's backed up.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"nothing exotic about it chemically, so it's not the long specialty hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "constraint",
-          "node": "published line rate",
-          "slot": "the limit and what happens when it is hit",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "what it needs before it can start",
           "precision": "spelled out",
-          "sourceRegime": "prescribed",
-          "rationale": "Engineering's position, recorded as the prescribed reading.",
+          "rationale": "Precondition and completion as narrated.",
           "assertion": {
-            "value": "Engineering's position is that the line rate is what it is regardless of the tanks."
+            "value": "Fill and pack complete; the order is palletized, moved off the line, and joins the queue for the lab. It ends when it clears QA and ships — lateness is judged against clearing QA."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "engineering tells me the line rate is what it is regardless",
+          "excerpt": "Once fill and pack was done, it went into QA hold.** That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "It cleared and shipped Thursday**, ahead of the Friday due date.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-dabdbb5f-9eca-4afb-ad50-5b381d9dfa4f",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Engineering's position is that the line rate is what it is regardless of the tanks.\"},\"kind\":\"constraint\",\"node\":\"published line rate\",\"precision\":\"spelled out\",\"rationale\":\"Engineering's position, recorded as the prescribed reading.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"engineering tells me the line rate is what it is regardless\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-2e05010d-aa3d-4558-bd3a-91b498169a94",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Fill and pack complete; the order is palletized, moved off the line, and joins the queue for the lab. It ends when it clears QA and ships — lateness is judged against clearing QA.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Precondition and completion as narrated.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It cleared and shipped Thursday**, ahead of the Friday due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.** That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "constraint",
-          "node": "published line rate",
-          "slot": "the limit and what happens when it is hit",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "The expert's contrary practiced reading, recorded alongside engineering's.",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "Performed by the lab.",
           "assertion": {
-            "value": "In practice Line 1 feels sluggish and blocked in ways the published line rate does not account for; the expert suspects the mill-to-fill tank costs more than people admit, but has no proof."
+            "value": "The lab."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "it feels sluggish and blocked in ways I can't pin on the published line rate",
+          "excerpt": "It sat in QA",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I've always suspected that one costs us more than people admit, but I've never had anything to prove it",
+          "excerpt": "I don't remember this one having any drama in the lab.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-292e1165-0990-4d17-b6db-153c675fd66c",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"In practice Line 1 feels sluggish and blocked in ways the published line rate does not account for; the expert suspects the mill-to-fill tank costs more than people admit, but has no proof.\"},\"kind\":\"constraint\",\"node\":\"published line rate\",\"precision\":\"spelled out\",\"rationale\":\"The expert's contrary practiced reading, recorded alongside engineering's.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've always suspected that one costs us more than people admit, but I've never had anything to prove it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it feels sluggish and blocked in ways I can't pin on the published line rate\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-34154727-71ce-4065-abbf-8be1752385ce",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Performed by the lab.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't remember this one having any drama in the lab.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It sat in QA\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "policy",
-          "node": "Meridian on time",
-          "slot": "the rule as actually practiced",
-          "precision": "spelled out",
+          "kind": "activity",
+          "node": "white-to-tint changeover on Line 2",
+          "slot": "how long it takes",
+          "precision": "range",
           "sourceRegime": "practiced",
-          "rationale": "Hard constraint on the scheduling decision.",
+          "rationale": "Low, high and a typical band given — a range with a typical, not a full spread; not rounded up.",
           "assertion": {
-            "value": "A Meridian-style order ships on time, full stop; it is not traded off against anything."
+            "value": "Quickest maybe 40 minutes (crew right there, nothing fighting them); longest about an hour twenty on a bad day (crew stretched thin or something stuck); typically lands around 45 minutes to an hour. The \"cheap\" direction."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+          "excerpt": "White-to-tint on Line 2 — quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes. Longest, if they're stretched thin or something's stuck, I've seen it drag past an hour, call it an hour twenty on a bad day. Typically though it lands around 45 minutes to an hour. That's the \"cheap\" direction.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian-style order ships on time, full stop; it is not traded off against anything.\"},\"kind\":\"policy\",\"node\":\"Meridian on time\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint on the scheduling decision.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-fc5a25de-846f-488d-9330-4d6b634c33b0",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quickest maybe 40 minutes (crew right there, nothing fighting them); longest about an hour twenty on a bad day (crew stretched thin or something stuck); typically lands around 45 minutes to an hour. The \\\"cheap\\\" direction.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover on Line 2\",\"precision\":\"range\",\"rationale\":\"Low, high and a typical band given — a range with a typical, not a full spread; not rounded up.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"White-to-tint on Line 2 — quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes. Longest, if they're stretched thin or something's stuck, I've seen it drag past an hour, call it an hour twenty on a bad day. Typically though it lands around 45 minutes to an hour. That's the \\\\\\\"cheap\\\\\\\" direction.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "policy",
-          "node": "Meridian on time",
-          "slot": "what overrides it",
-          "precision": "spelled out",
+          "kind": "activity",
+          "node": "white-to-tint changeover on Line 2",
+          "slot": "what is lost when it changes the system's mode",
+          "precision": "range",
           "sourceRegime": "practiced",
-          "rationale": "Only exception stated.",
+          "rationale": "The loss on this mode change is the line time consumed by the wash; the expert gave it as the changeover duration.",
           "assertion": {
-            "value": "Only when there is truly no way through."
+            "value": "Line time consumed by the changeover: 40 minutes to an hour twenty, typically 45 minutes to an hour, plus occupancy of the two-tech crew for that period."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "that's a line I won't cross unless there's truly no way through",
+          "excerpt": "Typically though it lands around 45 minutes to an hour. That's the \"cheap\" direction.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-54d606d7-8c61-4f0a-bd5f-867bba1af3f7",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Only when there is truly no way through.\"},\"kind\":\"policy\",\"node\":\"Meridian on time\",\"precision\":\"spelled out\",\"rationale\":\"Only exception stated.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-126e6b44-aa42-452b-9085-7bd038842721",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line time consumed by the changeover: 40 minutes to an hour twenty, typically 45 minutes to an hour, plus occupancy of the two-tech crew for that period.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover on Line 2\",\"precision\":\"range\",\"rationale\":\"The loss on this mode change is the line time consumed by the wash; the expert gave it as the changeover duration.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Typically though it lands around 45 minutes to an hour. That's the \\\\\\\"cheap\\\\\\\" direction.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "policy",
-          "node": "who can absorb the slip",
-          "slot": "the rule as actually practiced",
-          "precision": "spelled out",
+          "kind": "activity",
+          "node": "tint-to-white changeover",
+          "slot": "how long it takes",
+          "precision": "range",
           "sourceRegime": "practiced",
-          "rationale": "Practiced judgement about which customers can take lateness; examples given rather than a formula.",
+          "rationale": "Low two and a half hours, high toward four hours, typical three hours — a range with a typical.",
           "assertion": {
-            "value": "Judgement on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly counts as a second problem created to solve the first."
+            "value": "Quickest maybe two and a half hours (everything clean, crew fresh); on a bad day — dried pigment in a fitting — it has crept toward four hours; three hours typical, the number actually used on the sheet."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "I use judgment on who can absorb the slip",
+          "excerpt": "Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric. Any pigment left behind wrecks a white batch, so that's a full washdown. Quickest I've seen that go is maybe two and a half hours if everything's clean and the crew's fresh. On a bad day — dried pigment in a fitting, whatever — it's crept toward four hours. Call it three hours typical, and that's the number I actually use on the sheet.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgement on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly counts as a second problem created to solve the first.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"Practiced judgement about which customers can take lateness; examples given rather than a formula.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-2b6dc206-914d-4980-b539-3621f9c5a118",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quickest maybe two and a half hours (everything clean, crew fresh); on a bad day — dried pigment in a fitting — it has crept toward four hours; three hours typical, the number actually used on the sheet.\"},\"kind\":\"activity\",\"node\":\"tint-to-white changeover\",\"precision\":\"range\",\"rationale\":\"Low two and a half hours, high toward four hours, typical three hours — a range with a typical.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric. Any pigment left behind wrecks a white batch, so that's a full washdown. Quickest I've seen that go is maybe two and a half hours if everything's clean and the crew's fresh. On a bad day — dried pigment in a fitting, whatever — it's crept toward four hours. Call it three hours typical, and that's the number I actually use on the sheet.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "data-binding",
-          "node": "stage-by-stage times",
-          "slot": "the variable and its feed",
-          "precision": "named",
-          "rationale": "Named feed for stage durations.",
+          "kind": "activity",
+          "node": "tint-to-white changeover",
+          "slot": "what is lost when it changes the system's mode",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Loss is the full washdown time on the line plus the crew, driven by the direction of the change.",
           "assertion": {
-            "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) — the historian."
+            "value": "A full washdown — two and a half to four hours of line time, three typical — because any pigment left behind wrecks a white batch; direction matters, it is not symmetric with white-to-tint."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+          "excerpt": "Any pigment left behind wrecks a white batch, so that's a full washdown.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "a full white-to-tint changeover is a wash we can't get back",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) — the historian.\"},\"kind\":\"data-binding\",\"node\":\"stage-by-stage times\",\"precision\":\"named\",\"rationale\":\"Named feed for stage durations.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-97c6e438-15c4-48f8-84c1-fdb8d5b42e3e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A full washdown — two and a half to four hours of line time, three typical — because any pigment left behind wrecks a white batch; direction matters, it is not symmetric with white-to-tint.\"},\"kind\":\"activity\",\"node\":\"tint-to-white changeover\",\"precision\":\"range\",\"rationale\":\"Loss is the full washdown time on the line plus the crew, driven by the direction of the change.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Any pigment left behind wrecks a white batch, so that's a full washdown.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "data-binding",
-          "node": "tank sizes",
-          "slot": "the variable and its feed",
-          "precision": "named",
-          "rationale": "Named source for the holding tank capacities.",
-          "assertion": {
-            "value": "Holding tank sizes — engineering drawings."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-b0908788-ec79-4481-b056-1fa606930f85",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tank sizes — engineering drawings.\"},\"kind\":\"data-binding\",\"node\":\"tank sizes\",\"precision\":\"named\",\"rationale\":\"Named source for the holding tank capacities.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "objective",
-          "node": "which option loses less",
-          "slot": "the question, in the expert's words",
-          "precision": "spelled out",
-          "rationale": "The model's primary question, stated as a disruption decision: with the filler down and ETA unknown, whether to wait or switch lines.",
+          "kind": "activity",
+          "node": "specialty changeover",
+          "slot": "how long it takes",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Range with typical, explicitly less closely observed than white/tint changeovers.",
           "assertion": {
-            "value": "Given \"filler's down, ETA unknown\", tell me which option actually loses less — wait out the repair, or move the order to the other line — instead of doing gut math at the huddle."
+            "value": "Around two hours normally, either direction into or out of a specialty run; as short as maybe an hour forty for a specialty-to-specialty colour change rather than a full family switch; not seen much longer than two and a half hours. Observed less closely than white-tint changeovers."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+          "excerpt": "Specialty is its own animal again, like you said — going in or coming out of a specialty run, either direction, it's around two hours normally. I've seen it shorter, maybe an hour forty if it's a specialty-to-specialty color change rather than a full family switch. I haven't seen it run much longer than two and a half hours, but I'll be honest, I don't watch specialty changeovers as closely as I watch the white-tint ones because they don't hit my due dates as hard.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given \\\"filler's down, ETA unknown\\\", tell me which option actually loses less — wait out the repair, or move the order to the other line — instead of doing gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"The model's primary question, stated as a disruption decision: with the filler down and ETA unknown, whether to wait or switch lines.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-b1cfeb47-e2b4-4730-9483-1422b8597b5c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Around two hours normally, either direction into or out of a specialty run; as short as maybe an hour forty for a specialty-to-specialty colour change rather than a full family switch; not seen much longer than two and a half hours. Observed less closely than white-tint changeovers.\"},\"kind\":\"activity\",\"node\":\"specialty changeover\",\"precision\":\"range\",\"rationale\":\"Range with typical, explicitly less closely observed than white/tint changeovers.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Specialty is its own animal again, like you said — going in or coming out of a specialty run, either direction, it's around two hours normally. I've seen it shorter, maybe an hour forty if it's a specialty-to-specialty color change rather than a full family switch. I haven't seen it run much longer than two and a half hours, but I'll be honest, I don't watch specialty changeovers as closely as I watch the white-tint ones because they don't hit my due dates as hard.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "which option loses less",
-          "slot": "what \"better\" means, and trade-off weights",
-          "precision": "spelled out",
-          "rationale": "Lexicographic: on-time delivery for the protected order is a hard line; the remaining terms are weighed by judgment with no formula.",
+          "kind": "activity",
+          "node": "tint-to-white changeover",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
+          "rationale": "Explicit answer that changeover duration varies by direction and family.",
           "assertion": {
-            "value": "First: days late on Meridian, anything above zero is bad news — non-negotiable, a line not crossed unless there is truly no way through. Underneath: washdown hours (crew time plus the line taken out of anything else for that window), and whether the bumped order goes late and by how much, judged against who the customer is. No formula — \"how bad is bad\" and judgment on who can absorb the slip."
+            "value": "Yes — changeover duration varies by direction and family: white-to-tint is the cheap direction, tint-to-white the expensive one, specialty its own animal."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+          "excerpt": "Okay, let's separate those because they're genuinely not the same beast.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it.",
+          "excerpt": "direction absolutely matters — it's not symmetric",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-9d5063d7-b9fb-400e-8b54-f618c6fde20e",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First: days late on Meridian, anything above zero is bad news — non-negotiable, a line not crossed unless there is truly no way through. Underneath: washdown hours (crew time plus the line taken out of anything else for that window), and whether the bumped order goes late and by how much, judged against who the customer is. No formula — \\\"how bad is bad\\\" and judgment on who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"Lexicographic: on-time delivery for the protected order is a hard line; the remaining terms are weighed by judgment with no formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-b833dc1b-dd19-4d7d-bc4f-754e5e63bb7b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — changeover duration varies by direction and family: white-to-tint is the cheap direction, tint-to-white the expensive one, specialty its own animal.\"},\"kind\":\"activity\",\"node\":\"tint-to-white changeover\",\"precision\":\"named\",\"rationale\":\"Explicit answer that changeover duration varies by direction and family.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Okay, let's separate those because they're genuinely not the same beast.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"direction absolutely matters — it's not symmetric\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "which option loses less",
-          "slot": "the nodes it depends on",
+          "kind": "activity",
+          "node": "white-to-tint changeover on Line 2",
+          "slot": "who or what performs it",
           "precision": "named",
-          "rationale": "The scorecard terms the expert named map onto the washdown, the production run, the breakdown event and the order itself.",
+          "rationale": "All changeovers are performed by the shared two-tech crew.",
           "assertion": {
-            "value": [
-              "activity:tint-to-white washdown",
-              "activity:run it through mix/mill/tint/fill",
-              "activity:filler jammed",
-              "entity-type:order",
-              "policy:who can absorb the slip"
-            ]
+            "value": "The changeover crew — one crew, two techs, shared across all three lines."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
+          "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less",
+          "excerpt": "Line 1 had just finished a specialty run and needed the full two-hour changeover before the next job",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-3245b29a-3687-4313-97c5-e0455e5889ba",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:tint-to-white washdown\",\"activity:run it through mix/mill/tint/fill\",\"activity:filler jammed\",\"entity-type:order\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard terms the expert named map onto the washdown, the production run, the breakdown event and the order itself.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-6fd52cfc-df4d-4a0b-8381-1a80c29a4d4a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The changeover crew — one crew, two techs, shared across all three lines.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover on Line 2\",\"precision\":\"named\",\"rationale\":\"All changeovers are performed by the shared two-tech crew.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 had just finished a specialty run and needed the full two-hour changeover before the next job\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "where Line 1 loses its time",
-          "slot": "the question, in the expert's words",
+          "kind": "activity",
+          "node": "white-to-tint changeover on Line 2",
+          "slot": "what it needs before it can start",
           "precision": "spelled out",
-          "rationale": "Second, explicitly in-scope objective: show whether the small tank between mill and fill on Line 1 is actually costing time, as evidence to take to engineering.",
+          "rationale": "Precondition: previous run finished and the shared crew available.",
           "assertion": {
-            "value": "Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill is actually costing us — with something other than a hunch to take to engineering."
+            "value": "The previous run on the line finished and the changeover crew free; if the crew is tied up on another line, the changeover cannot start and the line queues behind whoever else needs them."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.",
+          "excerpt": "If they're tied up elsewhere, my \"wash down now\" option isn't even really available — I'd be queuing behind whoever else needs them.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill is actually costing us — with something other than a hunch to take to engineering.\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"spelled out\",\"rationale\":\"Second, explicitly in-scope objective: show whether the small tank between mill and fill on Line 1 is actually costing time, as evidence to take to engineering.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-9da728a5-b72c-4e7a-ba0d-a360ef571059",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The previous run on the line finished and the changeover crew free; if the crew is tied up on another line, the changeover cannot start and the line queues behind whoever else needs them.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover on Line 2\",\"precision\":\"spelled out\",\"rationale\":\"Precondition: previous run finished and the shared crew available.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available — I'd be queuing behind whoever else needs them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "where Line 1 loses its time",
-          "slot": "the nodes it depends on",
-          "precision": "named",
-          "rationale": "The hunch is about blocking at the mill-to-fill tank, so it depends on the stage kit, the tank constraint and the run duration.",
+          "kind": "ordering/flow",
+          "node": "release to cleared QA",
+          "slot": "the order things happen in",
+          "precision": "spelled out",
+          "rationale": "The end-to-end sequence walked through for one real order.",
           "assertion": {
-            "value": [
-              "entity-type:mix, mill, tint, fill",
-              "constraint:small holding tanks",
-              "activity:run it through mix/mill/tint/fill",
-              "entity-type:Line 1 and Line 2"
-            ]
+            "value": "1) Order lands in the demand book on the weekly ERP release with SKU, quantity, due date, and is assigned to a line's column on the sheet. 2) It waits its turn behind whatever is already running on that line (with a changeover first if the family differs). 3) It runs — mix, mill, tint stage, fill and pack. 4) It is palletized, moved off the line, and enters QA hold in the queue for the lab. 5) It sits in QA. 6) It clears QA and ships; the due date is judged against clearing, not coming off the line."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit",
+          "excerpt": "It landed in the demand book** on the Monday release, part of that week's batch of orders from ERP — a Meridian order, big white SKU, due Friday.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "So yes — build it as separate stages if that's what it takes.",
+          "excerpt": "It had to wait its turn behind whatever was already running on Line 2.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Once fill and pack was done, it went into QA hold.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "It cleared and shipped Thursday**, ahead of the Friday due date.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-770314e5-f47a-463e-908a-1d8c23ee60f5",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:mix, mill, tint, fill\",\"constraint:small holding tanks\",\"activity:run it through mix/mill/tint/fill\",\"entity-type:Line 1 and Line 2\"]},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"named\",\"rationale\":\"The hunch is about blocking at the mill-to-fill tank, so it depends on the stage kit, the tank constraint and the run duration.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"So yes — build it as separate stages if that's what it takes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-4bdfb1af-a858-493c-bf5a-2da4279d18a5",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"1) Order lands in the demand book on the weekly ERP release with SKU, quantity, due date, and is assigned to a line's column on the sheet. 2) It waits its turn behind whatever is already running on that line (with a changeover first if the family differs). 3) It runs — mix, mill, tint stage, fill and pack. 4) It is palletized, moved off the line, and enters QA hold in the queue for the lab. 5) It sits in QA. 6) It clears QA and ships; the due date is judged against clearing, not coming off the line.\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"The end-to-end sequence walked through for one real order.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It cleared and shipped Thursday**, ahead of the Friday due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It had to wait its turn behind whatever was already running on Line 2.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It landed in the demand book** on the Monday release, part of that week's batch of orders from ERP — a Meridian order, big white SKU, due Friday.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "order",
-          "slot": "state that rides along with each instance",
+          "kind": "ordering/flow",
+          "node": "release to cleared QA",
+          "slot": "how a branch or merge is decided",
           "precision": "spelled out",
-          "rationale": "The attributes the scheduler works from on the sheet.",
+          "rationale": "Two branch points named: line assignment by SKU/customer habit, and whether a changeover is inserted based on family match.",
           "assertion": {
-            "value": "Quantity, due date, SKU; plus the line and week-slot it is allocated to, and the customer account."
+            "value": "Line assignment: by habit of the SKU — Meridian white basically always goes to Line 2, entered in that line's column on the sheet. Changeover branch: if the next job is the same family as the one just finished, no changeover — a straight run-into-run; if a different family, a changeover is inserted whose kind and length depends on the direction (white-to-tint, tint-to-white, specialty)."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+          "excerpt": "Meridian white basically always goes to Line 2, so it went into \"my\" Line 2 column on the sheet without much debate.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-6ff1c59a-0664-487b-a946-2680043419a2",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; plus the line and week-slot it is allocated to, and the customer account.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The attributes the scheduler works from on the sheet.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-663314c5-79fe-4e3c-918a-1ac8047113a1",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line assignment: by habit of the SKU — Meridian white basically always goes to Line 2, entered in that line's column on the sheet. Changeover branch: if the next job is the same family as the one just finished, no changeover — a straight run-into-run; if a different family, a changeover is inserted whose kind and length depends on the direction (white-to-tint, tint-to-white, specialty).\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"Two branch points named: line assignment by SKU/customer habit, and whether a changeover is inserted based on family match.\",\"slot\":\"how a branch or merge is decided\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2, so it went into \\\\\\\"my\\\\\\\" Line 2 column on the sheet without much debate.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "order",
-          "slot": "the distinctions the process treats apart",
+          "kind": "policy",
+          "node": "who gets the crew",
+          "slot": "the rule as actually practiced",
           "precision": "spelled out",
-          "rationale": "Whites versus tints differ in stage content and in run speed by line; customer type differs in how a slip is judged.",
+          "sourceRegime": "practiced",
+          "rationale": "The practiced allocation rule, given from a real incident three weeks ago; explicitly unwritten.",
           "assertion": {
-            "value": "Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step, and whites run much faster on Line 2 than Line 1 while tints run at nearly the same speed on both. Customers are treated apart too: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem."
+            "value": "If a Meridian job sits behind one of the competing changeovers, the crew goes to that line, full stop, without discussion. Otherwise the scheduler's judgment call at the morning huddle on whose next job is tightest against its due date (in the recalled case Line 1 won over Line 3, which had a couple of days of slack, and Line 3 sat clean but idle close to two hours). Failing that it is whoever's line supervisor gets to the crew lead first. Nobody has written this rule down."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+          "excerpt": "Practically, what happens is not some clean rule — it's whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+          "excerpt": "That morning I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date, and Line 3's next job had a couple days of slack.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "If it had been Meridian sitting behind either of those changeovers, that decision doesn't even get discussed — the crew goes to whichever line has the Meridian job next, full stop, everyone understands that without me saying it out loud.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-be0c3675-ae93-41c5-9eaa-7d36d84617cb",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step, and whites run much faster on Line 2 than Line 1 while tints run at nearly the same speed on both. Customers are treated apart too: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Whites versus tints differ in stage content and in run speed by line; customer type differs in how a slip is judged.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-ccb16fb1-30dc-4a94-8367-fd11a5a97373",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"If a Meridian job sits behind one of the competing changeovers, the crew goes to that line, full stop, without discussion. Otherwise the scheduler's judgment call at the morning huddle on whose next job is tightest against its due date (in the recalled case Line 1 won over Line 3, which had a couple of days of slack, and Line 3 sat clean but idle close to two hours). Failing that it is whoever's line supervisor gets to the crew lead first. Nobody has written this rule down.\"},\"kind\":\"policy\",\"node\":\"who gets the crew\",\"precision\":\"spelled out\",\"rationale\":\"The practiced allocation rule, given from a real incident three weeks ago; explicitly unwritten.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If it had been Meridian sitting behind either of those changeovers, that decision doesn't even get discussed — the crew goes to whichever line has the Meridian job next, full stop, everyone understands that without me saying it out loud.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Practically, what happens is not some clean rule — it's whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That morning I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date, and Line 3's next job had a couple days of slack.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "Line 1 and Line 2",
-          "slot": "the distinctions the process treats apart",
+          "kind": "policy",
+          "node": "who gets the crew",
+          "slot": "what overrides it",
           "precision": "spelled out",
-          "rationale": "The two lines are contended kit distinguished by speed, and the speed difference depends on product.",
+          "sourceRegime": "practiced",
+          "rationale": "Named override with escalation path; frequency given only as \"rare\".",
           "assertion": {
-            "value": "Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to a Line 2 run (\"Line 2 is twice as fast\", which is really a whites number); on tints the two lines run at nearly the same speed."
+            "value": "Maintenance can grab the crew mid-job for a genuine emergency — a line leaking, something needing isolating right now. Rare, and not the scheduler's call; a real fight escalates over his head to the ops director."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
+          "excerpt": "Has anyone ever pulled the crew off mid-job? Yes, actually — maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now. That's rare, and it's not my call, that's a maintenance-versus-me argument that goes over my head to the ops director if it's a real fight.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-3e2a5a8a-bd99-4642-afcf-f9d3dfe2e9f6",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to a Line 2 run (\\\"Line 2 is twice as fast\\\", which is really a whites number); on tints the two lines run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"rationale\":\"The two lines are contended kit distinguished by speed, and the speed difference depends on product.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-822d9723-b7fa-40c4-8921-2a10de44868f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Maintenance can grab the crew mid-job for a genuine emergency — a line leaking, something needing isolating right now. Rare, and not the scheduler's call; a real fight escalates over his head to the ops director.\"},\"kind\":\"policy\",\"node\":\"who gets the crew\",\"precision\":\"spelled out\",\"rationale\":\"Named override with escalation path; frequency given only as \\\"rare\\\".\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Has anyone ever pulled the crew off mid-job? Yes, actually — maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now. That's rare, and it's not my call, that's a maintenance-versus-me argument that goes over my head to the ops director if it's a real fight.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "mix, mill, tint, fill",
-          "slot": "the distinctions the process treats apart",
+          "kind": "constraint",
+          "node": "one crew serving three lines",
+          "slot": "the limit and what happens when it is hit",
           "precision": "spelled out",
-          "sourceRegime": "prescribed",
-          "rationale": "The scheduling sheet's view: the line is one indivisible resource.",
+          "sourceRegime": "practiced",
+          "rationale": "Capacity limit with its practiced consequence: the losing line idles and the loss is invisible in reporting.",
           "assertion": {
-            "value": "On the sheet the line is one row treated as one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it is done."
+            "value": "Only one changeover can be served at a time by the single two-tech crew. When two lines want them at once, the losing line sits clean but idle waiting its turn — close to two hours in the recalled case — and that wasted line time does not show up anywhere as a problem."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+          "excerpt": "Line 3 sat there clean but idle for — I want to say close to two hours — waiting its turn. Nobody died over it, but it's wasted line time that doesn't show up anywhere as a \"problem,\" it's just... the day.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet the line is one row treated as one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it is done.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill\",\"precision\":\"spelled out\",\"rationale\":\"The scheduling sheet's view: the line is one indivisible resource.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-03f46087-a1d4-409d-80f3-b7c87e23a1b3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Only one changeover can be served at a time by the single two-tech crew. When two lines want them at once, the losing line sits clean but idle waiting its turn — close to two hours in the recalled case — and that wasted line time does not show up anywhere as a problem.\"},\"kind\":\"constraint\",\"node\":\"one crew serving three lines\",\"precision\":\"spelled out\",\"rationale\":\"Capacity limit with its practiced consequence: the losing line idles and the loss is invisible in reporting.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 3 sat there clean but idle for — I want to say close to two hours — waiting its turn. Nobody died over it, but it's wasted line time that doesn't show up anywhere as a \\\\\\\"problem,\\\\\\\" it's just... the day.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "mix, mill, tint, fill",
-          "slot": "the distinctions the process treats apart",
+          "kind": "validation-criterion",
+          "node": "recognize the shape of a real month",
+          "slot": "how the expert would know the model is right",
           "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "The floor view: four separately contended pieces of kit with buffering between them, allowing overlap.",
+          "rationale": "The expert's own acceptance test, given as a replay of last month's demand book.",
           "assertion": {
-            "value": "Physically four separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head is still finishing the last, if there is room in the holding tank — the crew will get a head start on mixing the next batch if the tank ahead of it has space."
+            "value": "Replay last month's demand book: it must land roughly where the plant actually landed on late orders — same rough number and same kind of misses (at least two Meridian scrapes and a handful of small ones); getting the kind wrong is worse than getting the count wrong. Then eyeball changeover hours on Lines 2 and 3 — if Line 3 is idle half the week waiting on the crew, which never happens in real life, it is missing something about how the crew gets shared. It must also reproduce the odd weeks, e.g. where a breakdown chewed up two days on Line 1. No single number is trusted; the shape of a real month must be recognizable."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+          "excerpt": "the first thing I'd check is the boring one — did it land roughly where we actually landed on late orders that month?",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "the crew will get a head start on mixing the next batch if the tank ahead of it has space",
+          "excerpt": "we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones. So: same rough number and same *kind* of misses. If it says we missed distributor orders and we actually missed a Meridian one, that's worse than getting the count wrong.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "After that I'd want to eyeball changeover hours on Line 2 and 3 specifically",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "And I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I wouldn't trust a single number out of it, put it that way. I'd want to recognize the *shape* of a real month before I'd believe it on something as specific as the wash-versus-idle call.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-27ee0ed5-50d0-47f6-94b8-77e090bca50f",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically four separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head is still finishing the last, if there is room in the holding tank — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill\",\"precision\":\"spelled out\",\"rationale\":\"The floor view: four separately contended pieces of kit with buffering between them, allowing overlap.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the crew will get a head start on mixing the next batch if the tank ahead of it has space\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-fac82088-05f2-4519-a697-b149c0798172",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Replay last month's demand book: it must land roughly where the plant actually landed on late orders — same rough number and same kind of misses (at least two Meridian scrapes and a handful of small ones); getting the kind wrong is worse than getting the count wrong. Then eyeball changeover hours on Lines 2 and 3 — if Line 3 is idle half the week waiting on the crew, which never happens in real life, it is missing something about how the crew gets shared. It must also reproduce the odd weeks, e.g. where a breakdown chewed up two days on Line 1. No single number is trusted; the shape of a real month must be recognizable.\"},\"kind\":\"validation-criterion\",\"node\":\"recognize the shape of a real month\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own acceptance test, given as a replay of last month's demand book.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"After that I'd want to eyeball changeover hours on Line 2 and 3 specifically\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"And I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I wouldn't trust a single number out of it, put it that way. I'd want to recognize the *shape* of a real month before I'd believe it on something as specific as the wash-versus-idle call.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first thing I'd check is the boring one — did it land roughly where we actually landed on late orders that month?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones. So: same rough number and same *kind* of misses. If it says we missed distributor orders and we actually missed a Meridian one, that's worse than getting the count wrong.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "mix, mill, tint, fill",
-          "slot": "how many there are, or the population's shape",
+          "kind": "data-binding",
+          "node": "changeover log and late-order report",
+          "slot": "the variable and its feed",
           "precision": "named",
+          "rationale": "Two existing feeds named by the expert, currently unlinked.",
           "assertion": {
-            "absence": "unknown-to-user",
-            "pointer": "how much overlap happens and how often mixing is blocked by a full tank is not tracked by the scheduler"
+            "value": "Changeover hours from the changeover log; late orders from the late-order report. They exist separately and nobody has ever put them on the same page."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+          "excerpt": "I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"how much overlap happens and how often mixing is blocked by a full tank is not tracked by the scheduler\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill\",\"precision\":\"named\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-7a236317-f8ea-43e8-b88a-a6c6092fb35f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Changeover hours from the changeover log; late orders from the late-order report. They exist separately and nobody has ever put them on the same page.\"},\"kind\":\"data-binding\",\"node\":\"changeover log and late-order report\",\"precision\":\"named\",\"rationale\":\"Two existing feeds named by the expert, currently unlinked.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "allocate → run → QA hold → release and ship",
-          "slot": "the order things happen in",
-          "precision": "spelled out",
-          "rationale": "The order's life from demand-book line item to shipment, as walked end to end.",
+          "kind": "activity",
+          "node": "breakdown on a line",
+          "slot": "how long it takes",
+          "precision": "number",
+          "sourceRegime": "practiced",
+          "rationale": "Mentioned only in passing as a validation case; duration given as a single recalled figure, no rate given.",
           "assertion": {
-            "value": "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (and pack) → QA hold in the lab's queue → release, go to the warehouse and ship against the due date."
+            "value": "A breakdown chewed up two days on Line 1 in one recalled month."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+          "excerpt": "I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-2a491098-b602-4b46-bbaa-439e291027db",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (and pack) → QA hold in the lab's queue → release, go to the warehouse and ship against the due date.\"},\"kind\":\"ordering/flow\",\"node\":\"allocate → run → QA hold → release and ship\",\"precision\":\"spelled out\",\"rationale\":\"The order's life from demand-book line item to shipment, as walked end to end.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-60d6dc44-d2ee-456c-ad19-1c54d79f37dd",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A breakdown chewed up two days on Line 1 in one recalled month.\"},\"kind\":\"activity\",\"node\":\"breakdown on a line\",\"precision\":\"number\",\"rationale\":\"Mentioned only in passing as a validation case; duration given as a single recalled figure, no rate given.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "allocation",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "rationale": "Allocation binds the order to a line and a week slot, which is the scheduling decision under test.",
+          "node": "breakdown on a line",
+          "slot": "how often it occurs, if it is an event rather than a step",
+          "precision": "named",
+          "rationale": "The expert referred to \"the odd weeks\" without giving a rate; no frequency was elicited before the time cue.",
           "assertion": {
-            "value": "The order is slotted onto a line and a slot in the week on the sheet."
+            "absence": "unknown-to-user",
+            "pointer": "breakdown frequency not yet asked; expert referred only to \"the odd weeks\""
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "excerpt": "the ones where a breakdown chewed up two days on Line 1",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-c4aefe40-a022-4990-96a1-b74243850715",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Allocation binds the order to a line and a week slot, which is the scheduling decision under test.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-16c2b41b-9778-4091-91c3-5f15f72171e9",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"breakdown frequency not yet asked; expert referred only to \\\"the odd weeks\\\"\"},\"kind\":\"activity\",\"node\":\"breakdown on a line\",\"precision\":\"named\",\"rationale\":\"The expert referred to \\\"the odd weeks\\\" without giving a rate; no frequency was elicited before the time cue.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "allocation",
-          "slot": "what it needs before it can start",
+          "kind": "objective",
+          "node": "wash-versus-idle call on Line 2",
+          "slot": "the question, in the expert's words",
           "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The anchoring decision the model must inform, given as a real recent case.",
           "assertion": {
-            "value": "The order exists as a line item in the demand book once ERP spits it out, with quantity, due date and SKU."
+            "value": "Whether to wash down for the tint right then, or let Line 2 sit idle for about an hour waiting for a same-colour (white) order expected to be released that afternoon — a judgment made by gut maybe three or four times a month, never proven right or wrong."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+          "excerpt": "wash down for the tint right then, or let Line 2 sit idle for about an hour",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I make that judgment by gut maybe three or four times a month",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-76c7250e-6575-4e31-b667-113f3a497cce",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order exists as a line item in the demand book once ERP spits it out, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-c58069b0-72b7-4ff3-8bb8-16f7861f0212",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whether to wash down for the tint right then, or let Line 2 sit idle for about an hour waiting for a same-colour (white) order expected to be released that afternoon — a judgment made by gut maybe three or four times a month, never proven right or wrong.\"},\"kind\":\"objective\",\"node\":\"wash-versus-idle call on Line 2\",\"precision\":\"spelled out\",\"rationale\":\"The anchoring decision the model must inform, given as a real recent case.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I make that judgment by gut maybe three or four times a month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"wash down for the tint right then, or let Line 2 sit idle for about an hour\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "what it needs before it can start",
+          "kind": "objective",
+          "node": "wash-versus-idle call on Line 2",
+          "slot": "what \"better\" means, and trade-off weights",
           "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Ranking rather than a weight; expert explicitly refused an exchange rate and named where one would come from.",
           "assertion": {
-            "value": "The order must first be allocated onto a line and a slot in the week."
+            "value": "No Meridian misses first (a hard rule, not a weight — does not flip even at twenty small orders late versus one Meridian), then late-order count, with changeover hours and idle time as the scheduler's own diagnostics. A real exchange rate between Meridian and small late orders would have to come from commercial being put in a room and forced to say it out loud."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship.",
+          "excerpt": "what my boss actually looks at is late orders",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "The changeover hours and the idle time are more my own concern",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I don't think it does flip, not in any range I'd actually see in a week",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "you'd have to get commercial in a room and force them to say it out loud",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 9,
             "entryEnd": 9
           },
@@ -3396,4369 +3685,1111 @@
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-7da94524-13b5-4c11-a1b4-9cb1b0f07e19",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order must first be allocated onto a line and a slot in the week.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-727571fe-b1b2-4fb8-9247-5658db4a18f9",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"No Meridian misses first (a hard rule, not a weight — does not flip even at twenty small orders late versus one Meridian), then late-order count, with changeover hours and idle time as the scheduler's own diagnostics. A real exchange rate between Meridian and small late orders would have to come from commercial being put in a room and forced to say it out loud.\"},\"kind\":\"objective\",\"node\":\"wash-versus-idle call on Line 2\",\"precision\":\"spelled out\",\"rationale\":\"Ranking rather than a weight; expert explicitly refused an exchange rate and named where one would come from.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't think it does flip, not in any range I'd actually see in a week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The changeover hours and the idle time are more my own concern\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what my boss actually looks at is late orders\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"you'd have to get commercial in a room and force them to say it out loud\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
+          "kind": "objective",
+          "node": "wash-versus-idle call on Line 2",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "Nodes the expert named as inside the scheduling unit and the lateness clock.",
           "assertion": {
-            "value": "Filled and packed product coming off the fill line, which then goes into QA hold."
+            "value": [
+              "entity-type:order",
+              "entity-type:changeover crew",
+              "entity-type:the three lines",
+              "boundary-condition:the demand book",
+              "activity:the run (mix, mill, fill and pack)",
+              "activity:white-to-tint changeover",
+              "activity:tint-to-white washdown",
+              "activity:specialty changeover",
+              "activity:QA hold",
+              "ordering/flow:release to cleared QA",
+              "policy:who gets the crew",
+              "constraint:we just don't do that (Meridian)"
+            ]
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Once it comes off the fill line it goes into QA hold",
+          "excerpt": "the unit I'm scheduling across is all three lines plus that one crew",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "It ends when it clears QA hold and ships.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the due date is judged against when it clears, not when it comes off the line",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "explicit",
-      "id": "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Filled and packed product coming off the fill line, which then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "inferred",
+      "id": "capture-cd397b8a-ae0d-4e4a-887c-46a790d86277",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:changeover crew\",\"entity-type:the three lines\",\"boundary-condition:the demand book\",\"activity:the run (mix, mill, fill and pack)\",\"activity:white-to-tint changeover\",\"activity:tint-to-white washdown\",\"activity:specialty changeover\",\"activity:QA hold\",\"ordering/flow:release to cleared QA\",\"policy:who gets the crew\",\"constraint:we just don't do that (Meridian)\"]},\"kind\":\"objective\",\"node\":\"wash-versus-idle call on Line 2\",\"precision\":\"named\",\"rationale\":\"Nodes the expert named as inside the scheduling unit and the lateness clock.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It ends when it clears QA hold and ships.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the unit I'm scheduling across is all three lines plus that one crew\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "how long it takes",
-          "precision": "spread",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
           "sourceRegime": "practiced",
-          "rationale": "Sheet-level, mix-to-last-pack, for a Meridian-sized white on Line 2; includes fill-up time getting the line running plus actual throughput. The bad tail is loosely folded-in filler hiccups and QA-adjacent time.",
+          "rationale": "Customer class and colour family are the two distinctions the process treats differently.",
           "assertion": {
-            "value": "White, normal/Meridian-sized order, Line 2, mix-to-last-pack: typical 8–9 hours; one run in ten worse than 12–13 hours; one run in ten better than about 6 hours."
+            "value": "By customer: Meridian orders versus small distributor orders (distributors slip 2-3 days with a phone call anyway; Meridian misses are a different category). By colour family: white, tint, and specialty — the family determines whether a changeover is needed and which one. Meridian white basically always goes to Line 2."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
+          "excerpt": "three little late orders to distributors who slip 2-3 days with a phone call anyway",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours",
+          "excerpt": "Meridian white basically always goes to Line 2",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 18,
             "entryEnd": 18
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
+          "excerpt": "Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-d6985d8d-f85e-4556-a091-df64be080ba6",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, normal/Meridian-sized order, Line 2, mix-to-last-pack: typical 8–9 hours; one run in ten worse than 12–13 hours; one run in ten better than about 6 hours.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"Sheet-level, mix-to-last-pack, for a Meridian-sized white on Line 2; includes fill-up time getting the line running plus actual throughput. The bad tail is loosely folded-in filler hiccups and QA-adjacent time.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-e0913c34-cd78-40d4-a420-6b28eba826af",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"By customer: Meridian orders versus small distributor orders (distributors slip 2-3 days with a phone call anyway; Meridian misses are a different category). By colour family: white, tint, and specialty — the family determines whether a changeover is needed and which one. Meridian white basically always goes to Line 2.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Customer class and colour family are the two distinctions the process treats differently.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"three little late orders to distributors who slip 2-3 days with a phone call anyway\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "how long it takes",
-          "precision": "spread",
-          "sourceRegime": "practiced",
-          "rationale": "Same white order on the slower line.",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "state that rides along with each instance",
+          "precision": "spelled out",
+          "rationale": "Attributes carried from release; lateness judged at QA clearance.",
           "assertion": {
-            "value": "White, same order, Line 1: typical 13–14 hours; worse days pushing 18-plus hours; best day maybe 10 hours — roughly fifty to sixty percent added to the Line 2 figures."
+            "value": "SKU, quantity, due date — carried from release out of ERP into the demand book; the due date is judged against when the order clears QA, not when it comes off the line."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+          "excerpt": "it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the due date is judged against when it clears, not when it comes off the line",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, same order, Line 1: typical 13–14 hours; worse days pushing 18-plus hours; best day maybe 10 hours — roughly fifty to sixty percent added to the Line 2 figures.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"Same white order on the slower line.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-fa08bd90-3a4a-4ce8-880b-8b5ba2b2467f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"SKU, quantity, due date — carried from release out of ERP into the demand book; the due date is judged against when the order clears QA, not when it comes off the line.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Attributes carried from release; lateness judged at QA clearance.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "how long it takes",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "how many there are, or the population's shape",
           "precision": "range",
           "sourceRegime": "practiced",
-          "rationale": "Only a typical range was given for tints; no one-in-ten tails.",
+          "rationale": "Weekly population of orders given as a low/high across quiet and busy weeks.",
           "assertion": {
-            "value": "Tint run, either line: 8–10 hours typical. No one-in-ten worse/better figures given."
+            "value": "30 orders in a quiet week up to 55–60 in a busy one"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.",
+          "excerpt": "quiet week might be 30 orders, a busy one pushes 55–60",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 27,
+            "entryEnd": 27
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-04a6f876-12f4-4f53-b6f2-f8e5fa9c87bc",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Tint run, either line: 8–10 hours typical. No one-in-ten worse/better figures given.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"range\",\"rationale\":\"Only a typical range was given for tints; no one-in-ten tails.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-62e66b8a-bc31-4ccb-9611-ad1e05dd0aed",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"30 orders in a quiet week up to 55–60 in a busy one\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"range\",\"rationale\":\"Weekly population of orders given as a low/high across quiet and busy weeks.\",\"slot\":\"how many there are, or the population's shape\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"quiet week might be 30 orders, a busy one pushes 55–60\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "whether its quantities vary by type",
-          "precision": "named",
-          "rationale": "Duration varies by product type and by line, and the two interact; the expert has no explanation for the tint parity.",
+          "kind": "entity-type",
+          "node": "changeover crew",
+          "slot": "how many there are, or the population's shape",
+          "precision": "number",
+          "rationale": "Contended resource count stated directly.",
           "assertion": {
-            "value": "Yes — duration varies both by product (white vs tint) and by line, and the two interact: whites are much slower on Line 1, tints run at nearly the same speed on both. \"I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\""
+            "value": "One crew of two techs, covering all three lines"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+          "excerpt": "there's one crew, two techs, covering all three lines",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-592b83e0-ece3-4e98-aedf-cdf70c202e96",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — duration varies both by product (white vs tint) and by line, and the two interact: whites are much slower on Line 1, tints run at nearly the same speed on both. \\\"I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\\\"\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Duration varies by product type and by line, and the two interact; the expert has no explanation for the tint parity.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-14764933-9818-4f65-b6e2-4623dbbf39b3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One crew of two techs, covering all three lines\"},\"kind\":\"entity-type\",\"node\":\"changeover crew\",\"precision\":\"number\",\"rationale\":\"Contended resource count stated directly.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what is lost when it changes the system's mode",
-          "precision": "number",
-          "rationale": "Named transition: tint to white on Line 1.",
+          "kind": "entity-type",
+          "node": "changeover crew",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Crew treated as one indivisible unit shared across lines, also grabbable by maintenance.",
           "assertion": {
-            "value": "Three hours for a tint-to-white changeover — real cost in crew time, and it takes the line out of anything else for that window."
+            "value": "A single changeover crew treated as one unit — two techs together — covering all three lines; maintenance can also grab them for a genuine emergency."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
+          "excerpt": "there's one crew, two techs, covering all three lines",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "it takes Line 1 out of anything else for that window",
+          "excerpt": "maintenance will sometimes grab them if there's a genuine emergency",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-32fe7be9-75c7-464c-87cb-ca38fef4039b",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours for a tint-to-white changeover — real cost in crew time, and it takes the line out of anything else for that window.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Named transition: tint to white on Line 1.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-de6129c5-8785-4833-97b5-5767d578660a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A single changeover crew treated as one unit — two techs together — covering all three lines; maintenance can also grab them for a genuine emergency.\"},\"kind\":\"entity-type\",\"node\":\"changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"Crew treated as one indivisible unit shared across lines, also grabbable by maintenance.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maintenance will sometimes grab them if there's a genuine emergency\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what it needs before it can start",
-          "precision": "spelled out",
+          "kind": "entity-type",
+          "node": "the three lines",
+          "slot": "how many there are, or the population's shape",
+          "precision": "number",
+          "rationale": "Scheduling scope named as three lines.",
           "assertion": {
-            "value": "A line coming off a tint run and being switched to a white — pulling Line 1 off its tint to cover a white order."
+            "value": "Three lines — Line 1, Line 2, Line 3"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown",
+          "excerpt": "the unit I'm scheduling across is all three lines plus that one crew",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-31556043-9787-40dc-8c0d-b74a47ed3589",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line coming off a tint run and being switched to a white — pulling Line 1 off its tint to cover a white order.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-0aec8732-ae48-4d5c-98f1-abedf334e4bf",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three lines — Line 1, Line 2, Line 3\"},\"kind\":\"entity-type\",\"node\":\"the three lines\",\"precision\":\"number\",\"rationale\":\"Scheduling scope named as three lines.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the unit I'm scheduling across is all three lines plus that one crew\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "how long it takes",
+          "kind": "entity-type",
+          "node": "the three lines",
+          "slot": "the distinctions the process treats apart",
           "precision": "named",
-          "rationale": "Only a vague magnitude was given; no typical or tail figures, and the specialty case is named but unquantified.",
+          "sourceRegime": "practiced",
+          "rationale": "Only routing distinction the expert volunteered; general line-to-product eligibility not yet elicited.",
           "assertion": {
-            "value": "Usually a few hours for a white; \"nothing like the specialty wait\". No typical/tail figures given."
+            "value": "Lines are distinguished by what routes to them in practice — Meridian white basically always goes to Line 2; Line 1 was running specialty in the recalled case. Full line/product eligibility not yet stated."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+          "excerpt": "Meridian white basically always goes to Line 2",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Line 1 had just finished a specialty run",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; \\\"nothing like the specialty wait\\\". No typical/tail figures given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Only a vague magnitude was given; no typical or tail figures, and the specialty case is named but unquantified.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-46c3af0c-9caa-4e30-ab54-92cc136acac1",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lines are distinguished by what routes to them in practice — Meridian white basically always goes to Line 2; Line 1 was running specialty in the recalled case. Full line/product eligibility not yet stated.\"},\"kind\":\"entity-type\",\"node\":\"the three lines\",\"precision\":\"named\",\"rationale\":\"Only routing distinction the expert volunteered; general line-to-product eligibility not yet elicited.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 had just finished a specialty run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "who or what performs it",
-          "precision": "named",
+          "kind": "boundary-condition",
+          "node": "the demand book",
+          "slot": "the arrival or availability pattern",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Two arrival channels: the Monday drop and intra-week additions; Meridian regular, distributors lumpy.",
           "assertion": {
-            "value": "The lab — the order sits in the lab's queue and gets checked."
+            "value": "Official release Monday morning — the big drop, 30-something to 60 orders depending on the week — plus additions pushed in by sales and commercial through the week, sometimes daily, when a customer calls last-minute or an order is confirmed late. Quiet week 30 orders, busy week 55–60. Not wildly seasonal, more lumpy depending on who's restocking. Meridian is fairly regular, close to weekly; the smaller distributors swing."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+          "excerpt": "The book officially releases Monday morning — that's the big drop, 30-something to 60 orders depending on the week.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Sales and commercial push in additions through the week, sometimes daily",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Meridian in particular is fairly regular, close to weekly, but the smaller distributors are the ones that swing",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 27,
+            "entryEnd": 27
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab — the order sits in the lab's queue and gets checked.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-4614313d-ba9f-4286-8cc0-2b2d07978c3e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Official release Monday morning — the big drop, 30-something to 60 orders depending on the week — plus additions pushed in by sales and commercial through the week, sometimes daily, when a customer calls last-minute or an order is confirmed late. Quiet week 30 orders, busy week 55–60. Not wildly seasonal, more lumpy depending on who's restocking. Meridian is fairly regular, close to weekly; the smaller distributors swing.\"},\"kind\":\"boundary-condition\",\"node\":\"the demand book\",\"precision\":\"spelled out\",\"rationale\":\"Two arrival channels: the Monday drop and intra-week additions; Meridian regular, distributors lumpy.\",\"slot\":\"the arrival or availability pattern\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian in particular is fairly regular, close to weekly, but the smaller distributors are the ones that swing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Sales and commercial push in additions through the week, sometimes daily\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The book officially releases Monday morning — that's the big drop, 30-something to 60 orders depending on the week.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jammed",
-          "slot": "how long it takes",
-          "precision": "range",
+          "kind": "boundary-condition",
+          "node": "the demand book",
+          "slot": "the starting state",
+          "precision": "spelled out",
           "sourceRegime": "practiced",
-          "rationale": "Two recognised repair kinds bracket the duration; the recent instance fell between them.",
+          "rationale": "Foreknowledge of an unreleased order is part of the scheduler's starting information; the decision rested on it.",
           "assertion": {
-            "value": "Two kinds of repair: the \"half hour\" kind and the \"half a shift\" kind. The most recent Line 2 filler jam came back in about two hours."
+            "value": "Beyond the released book, the scheduler starts with informal foreknowledge: a commercial contact mentioning in passing at the Monday huddle that a Meridian top-up order was \"probably coming\" because it's a repeat account with a reorder pattern — not a scheduled release, just remembering a conversation and half-expecting it."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+          "excerpt": "our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \"probably coming,\" because it's a repeat account and there's a pattern to when they reorder",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 27,
+            "entryEnd": 27
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "it came back in about two hours",
+          "excerpt": "it wasn't a scheduled release, it was more me remembering a conversation and half-expecting it",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 27,
+            "entryEnd": 27
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-d2d6e303-2f63-478a-ace1-0bf61abbfddd",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two kinds of repair: the \\\"half hour\\\" kind and the \\\"half a shift\\\" kind. The most recent Line 2 filler jam came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jammed\",\"precision\":\"range\",\"rationale\":\"Two recognised repair kinds bracket the duration; the recent instance fell between them.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-aab9beb5-8b53-44ce-a621-4dfd4621d53b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Beyond the released book, the scheduler starts with informal foreknowledge: a commercial contact mentioning in passing at the Monday huddle that a Meridian top-up order was \\\"probably coming\\\" because it's a repeat account with a reorder pattern — not a scheduled release, just remembering a conversation and half-expecting it.\"},\"kind\":\"boundary-condition\",\"node\":\"the demand book\",\"precision\":\"spelled out\",\"rationale\":\"Foreknowledge of an unreleased order is part of the scheduler's starting information; the decision rested on it.\",\"slot\":\"the starting state\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it wasn't a scheduled release, it was more me remembering a conversation and half-expecting it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \\\\\\\"probably coming,\\\\\\\" because it's a repeat account and there's a pattern to when they reorder\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jammed",
-          "slot": "what it produces or changes",
+          "kind": "ordering/flow",
+          "node": "release to cleared QA",
+          "slot": "the order things happen in",
           "precision": "spelled out",
-          "rationale": "An event that befalls the line mid-run and forces the switch-or-wait decision.",
+          "sourceRegime": "practiced",
+          "rationale": "The end-to-end sequence from the walked slice.",
           "assertion": {
-            "value": "The line's filler stops mid-run with an unknown ETA, putting the order on it at risk and forcing a decision to wait out the repair or move the order to the other line."
+            "value": "1. Order lands in the demand book on the Monday release from ERP and is assigned a line column on the sheet. 2. It waits its turn behind whatever is already running on that line. 3. It runs — mix, mill, tint stage, straight through to fill and pack. 4. Once fill and pack is done it is palletized, moved off the line and goes into QA hold. 5. It sits in the queue for the lab. 6. It clears QA and ships."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+          "excerpt": "It landed in the demand book",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "It had to wait its turn behind whatever was already running on Line 2.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Once fill and pack was done, it went into QA hold.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "It cleared and shipped Thursday",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-5548a18b-9f79-4475-a9ab-83a74c750721",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line's filler stops mid-run with an unknown ETA, putting the order on it at risk and forcing a decision to wait out the repair or move the order to the other line.\"},\"kind\":\"activity\",\"node\":\"filler jammed\",\"precision\":\"spelled out\",\"rationale\":\"An event that befalls the line mid-run and forces the switch-or-wait decision.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-080fcd60-7191-4d7f-82dd-203e24c66b72",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"1. Order lands in the demand book on the Monday release from ERP and is assigned a line column on the sheet. 2. It waits its turn behind whatever is already running on that line. 3. It runs — mix, mill, tint stage, straight through to fill and pack. 4. Once fill and pack is done it is palletized, moved off the line and goes into QA hold. 5. It sits in the queue for the lab. 6. It clears QA and ships.\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"The end-to-end sequence from the walked slice.\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It cleared and shipped Thursday\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It had to wait its turn behind whatever was already running on Line 2.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It landed in the demand book\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "policy",
-          "node": "who can absorb the slip",
-          "slot": "the rule as actually practiced",
+          "kind": "ordering/flow",
+          "node": "release to cleared QA",
+          "slot": "how a branch or merge is decided",
           "precision": "spelled out",
           "sourceRegime": "practiced",
-          "rationale": "The practiced rule for choosing which order gets bumped when two cannot both be on time.",
+          "rationale": "Branch between straight run-into-run and a changeover, decided by family; plus line assignment.",
           "assertion": {
-            "value": "Protect the non-negotiable order's due date; for anything bumped, judge by how far it slips and who the customer is — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first. No formula; judgment on who can absorb the slip."
+            "value": "Between consecutive jobs on a line: if the next job is the same family, no changeover is needed — a straight run-into-run; if it is a different family (white/tint/specialty), the matching changeover activity must happen first and needs the crew. Line assignment at release follows habit — Meridian white basically always goes to Line 2, without much debate."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+          "excerpt": "There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I use judgment on who can absorb the slip.",
+          "excerpt": "Meridian white basically always goes to Line 2",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-1ee7c206-0c56-4d6b-b091-5861f9c40438",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Protect the non-negotiable order's due date; for anything bumped, judge by how far it slips and who the customer is — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first. No formula; judgment on who can absorb the slip.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The practiced rule for choosing which order gets bumped when two cannot both be on time.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-d93639f5-4867-46ea-9a2f-7a7beedb6b88",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Between consecutive jobs on a line: if the next job is the same family, no changeover is needed — a straight run-into-run; if it is a different family (white/tint/specialty), the matching changeover activity must happen first and needs the crew. Line assignment at release follows habit — Meridian white basically always goes to Line 2, without much debate.\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"Branch between straight run-into-run and a changeover, decided by family; plus line assignment.\",\"slot\":\"how a branch or merge is decided\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "policy",
-          "node": "who can absorb the slip",
-          "slot": "what overrides it",
+          "kind": "activity",
+          "node": "the run (mix, mill, fill and pack)",
+          "slot": "what it needs before it can start",
           "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Preconditions from the slice: line free, and either same family or completed changeover.",
           "assertion": {
-            "value": "The on-time line is crossed only when there is truly no way through."
+            "value": "The line must be free — the job waits its turn behind whatever is already running — and either the previous job is the same family (no changeover needed, a straight run-into-run) or the changeover has been completed."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "that's a line I won't cross unless there's truly no way through",
+          "excerpt": "There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-4b706f60-c02f-4973-aa58-2d3ded113c39",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The on-time line is crossed only when there is truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-8cee0e81-ca2d-4d87-8400-d68f2a2c73dc",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line must be free — the job waits its turn behind whatever is already running — and either the previous job is the same family (no changeover needed, a straight run-into-run) or the changeover has been completed.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"spelled out\",\"rationale\":\"Preconditions from the slice: line free, and either same family or completed changeover.\",\"slot\":\"what it needs before it can start\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "constraint",
-          "node": "small holding tanks",
-          "slot": "the limit and what happens when it is hit",
+          "kind": "activity",
+          "node": "the run (mix, mill, fill and pack)",
+          "slot": "what it produces or changes",
           "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "Consequence is stated (upstream stage waits); the numeric capacity is not held by the expert.",
+          "rationale": "Output of the run stage as stated.",
           "assertion": {
-            "value": "The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait; overlap is only possible if the tank ahead has space. Suspected to cost more than people admit, never proven."
+            "value": "Takes the order through mix, mill, tint stage (skipped for a white), straight through to fill and pack; the finished order then goes into QA hold."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
+          "excerpt": "Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "how often it's blocked because a tank's full and mixing has to wait",
+          "excerpt": "Once fill and pack was done, it went into QA hold.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-97ea5a05-d89c-4a7d-a136-f90526beaa27",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait; overlap is only possible if the tank ahead has space. Suspected to cost more than people admit, never proven.\"},\"kind\":\"constraint\",\"node\":\"small holding tanks\",\"precision\":\"spelled out\",\"rationale\":\"Consequence is stated (upstream stage waits); the numeric capacity is not held by the expert.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"how often it's blocked because a tank's full and mixing has to wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-9866d0f3-f549-4193-8bdb-bf43563f18ee",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Takes the order through mix, mill, tint stage (skipped for a white), straight through to fill and pack; the finished order then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"spelled out\",\"rationale\":\"Output of the run stage as stated.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "constraint",
-          "node": "small holding tanks",
-          "slot": "the limit and what happens when it is hit",
+          "kind": "activity",
+          "node": "the run (mix, mill, fill and pack)",
+          "slot": "how long it takes",
           "precision": "named",
+          "sourceRegime": "practiced",
+          "rationale": "Only a recalled single case at day granularity; expert named the sheet as the source for exact hours and per-unit rate was not reached.",
           "assertion": {
-            "absence": "deferred",
-            "pointer": "engineering drawings — tank sizes obtainable from engineering, not carried in the scheduler's head"
+            "value": "For the big-volume Meridian white order: on the line most of the day — started Wednesday morning and wrapped Wednesday evening, \"something like that\". Exact hours, and run time per unit on each line, would have to come from the sheet."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+          "excerpt": "it was on the line most of the day",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings — tank sizes obtainable from engineering, not carried in the scheduler's head\"},\"kind\":\"constraint\",\"node\":\"small holding tanks\",\"precision\":\"named\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-151800e3-5e9d-4f3b-aada-02b05532b0cb",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"For the big-volume Meridian white order: on the line most of the day — started Wednesday morning and wrapped Wednesday evening, \\\"something like that\\\". Exact hours, and run time per unit on each line, would have to come from the sheet.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"named\",\"rationale\":\"Only a recalled single case at day granularity; expert named the sheet as the source for exact hours and per-unit rate was not reached.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it was on the line most of the day\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "data-binding",
-          "node": "stage-by-stage rates from the historian",
-          "slot": "the variable and its feed",
-          "precision": "named",
-          "rationale": "Stage-level durations are needed for the separate-stage model and exist only in the historian.",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "rationale": "Entry condition from the slice.",
           "assertion": {
-            "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the plant historian; never pulled apart, not known to the scheduler."
+            "value": "Fill and pack complete; the batch is palletized and moved off the line into the queue for the lab."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+          "excerpt": "physically it's palletized and moved off the line, into the queue for the lab",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Once fill and pack was done, it went into QA hold.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-46d37104-fb87-4105-95d5-4448aade81ac",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the plant historian; never pulled apart, not known to the scheduler.\"},\"kind\":\"data-binding\",\"node\":\"stage-by-stage rates from the historian\",\"precision\":\"named\",\"rationale\":\"Stage-level durations are needed for the separate-stage model and exist only in the historian.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-e2e03e25-a4df-4386-955a-56f2634c8bd7",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Fill and pack complete; the batch is palletized and moved off the line into the queue for the lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Entry condition from the slice.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"physically it's palletized and moved off the line, into the queue for the lab\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "validation-criterion",
-          "node": "the sheet's end-to-end batch times",
-          "slot": "how the expert would know the model is right",
-          "precision": "named",
-          "rationale": "The only figures the expert holds first-hand are sheet-level end-to-end times per SKU per line; engineering's counter-claim is that the line rate is what it is regardless of the tanks.",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "QA clearance is the event lateness is measured against.",
           "assertion": {
-            "value": "The model's end-to-end batch time for a given SKU on each line should match what the scheduler's sheet shows; and it would have to speak to engineering's claim that \"the line rate is what it is regardless\"."
+            "value": "The order clears QA and ships; clearance is the moment the due date is judged against — a batch can be done Tuesday and still ship late if the lab's backed up."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "engineering tells me the line rate is what it is regardless",
+          "excerpt": "It cleared and shipped Thursday",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the due date is judged against when it clears, not when it comes off the line",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 12,
             "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet",
+          "excerpt": "a batch can be done Tuesday and still ship late if the lab's backed up",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-0cdda695-1dfa-43ef-971c-b9db09403a07",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The model's end-to-end batch time for a given SKU on each line should match what the scheduler's sheet shows; and it would have to speak to engineering's claim that \\\"the line rate is what it is regardless\\\".\"},\"kind\":\"validation-criterion\",\"node\":\"the sheet's end-to-end batch times\",\"precision\":\"named\",\"rationale\":\"The only figures the expert holds first-hand are sheet-level end-to-end times per SKU per line; engineering's counter-claim is that the line rate is what it is regardless of the tanks.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"engineering tells me the line rate is what it is regardless\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-b458110a-8ab3-4a28-a3b7-52d8a9b6cc8c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order clears QA and ships; clearance is the moment the due date is judged against — a batch can be done Tuesday and still ship late if the lab's backed up.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"QA clearance is the event lateness is measured against.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It cleared and shipped Thursday\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a batch can be done Tuesday and still ship late if the lab's backed up\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "which option actually loses less",
-          "slot": "the question, in the expert's words",
-          "precision": "spelled out",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "how long it takes",
+          "precision": "number",
           "sourceRegime": "practiced",
-          "rationale": "The expert's stated use: type in a disruption state and be told which of switch-or-wait loses less.",
+          "rationale": "A single hedged figure for white only; the specialty hold length was not given.",
           "assertion": {
-            "value": "Given a disruption like \"filler's down, ETA unknown\", tell me which option actually loses less — shift the order to the other line or wait out the repair — instead of doing gut math at the huddle."
+            "value": "About four hours for a white; the specialty hold is longer but its length was not stated."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+          "excerpt": "normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-a5926e2a-88e8-459e-a296-282b16d499a8",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given a disruption like \\\"filler's down, ETA unknown\\\", tell me which option actually loses less — shift the order to the other line or wait out the repair — instead of doing gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"The expert's stated use: type in a disruption state and be told which of switch-or-wait loses less.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-473a9e08-c0d3-4b0c-8e2b-c13b77d9ab95",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"About four hours for a white; the specialty hold is longer but its length was not stated.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"number\",\"rationale\":\"A single hedged figure for white only; the specialty hold length was not given.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "which option actually loses less",
-          "slot": "what \"better\" means, and trade-off weights",
-          "precision": "spelled out",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
           "sourceRegime": "practiced",
-          "rationale": "Hard constraint plus unweighted secondary terms; the expert explicitly denies having a formula.",
+          "rationale": "Expert explicitly contrasts white with the long specialty hold.",
           "assertion": {
-            "value": "First number: days late on Meridian, anything above zero is bad — on-time is non-negotiable, a line not crossed unless there's truly no way through. Underneath that: washdown hours (crew time, line taken out of anything else for that window) and whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip."
+            "value": "Yes — a white is about four hours because there's nothing exotic about it chemically; specialty gets the long hold."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+          "excerpt": "nothing exotic about it chemically, so it's not the long specialty hold",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-ea1779b0-9a83-42aa-92d1-746e73de43cc",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First number: days late on Meridian, anything above zero is bad — on-time is non-negotiable, a line not crossed unless there's truly no way through. Underneath that: washdown hours (crew time, line taken out of anything else for that window) and whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint plus unweighted secondary terms; the expert explicitly denies having a formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-2f0e7c48-206b-4d81-8644-c4f649de9a7d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a white is about four hours because there's nothing exotic about it chemically; specialty gets the long hold.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Expert explicitly contrasts white with the long specialty hold.\",\"slot\":\"whether its quantities vary by type\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nothing exotic about it chemically, so it's not the long specialty hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "which option actually loses less",
-          "slot": "the nodes it depends on",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "who or what performs it",
           "precision": "named",
-          "rationale": "The scorecard terms name the run, the jam, the washdown, the order type and the flow.",
+          "rationale": "The lab is named as the performer; its staffing/capacity was not elicited.",
           "assertion": {
-            "value": [
-              "activity:run it through mix/mill/tint/fill",
-              "activity:filler jam",
-              "activity:tint-to-white washdown",
-              "entity-type:order (line item in the demand book)",
-              "entity-type:Line 1 and Line 2",
-              "ordering/flow:allocate → run → QA hold → release and ship",
-              "policy:who can absorb the slip"
-            ]
+            "value": "The lab"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+          "excerpt": "I don't remember this one having any drama in the lab.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-1288a3df-c7fd-4319-8d4e-a228572ba0b0",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:run it through mix/mill/tint/fill\",\"activity:filler jam\",\"activity:tint-to-white washdown\",\"entity-type:order (line item in the demand book)\",\"entity-type:Line 1 and Line 2\",\"ordering/flow:allocate → run → QA hold → release and ship\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard terms name the run, the jam, the washdown, the order type and the flow.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-e47df01b-49ae-4326-a72a-bfb08188d641",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"The lab is named as the performer; its staffing/capacity was not elicited.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't remember this one having any drama in the lab.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "where Line 1 loses its time",
-          "slot": "the question, in the expert's words",
-          "precision": "spelled out",
-          "rationale": "Second in-scope question: whether the small tank between mill and fill on Line 1 is actually costing time.",
+          "kind": "activity",
+          "node": "white-to-tint changeover",
+          "slot": "how long it takes",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Low, high and typical given; not quantiles, so recorded as a range with typical, not a spread.",
           "assertion": {
-            "value": "Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill on Line 1 is costing more than the published line rate admits, so it can be taken to engineering as something other than a hunch."
+            "value": "Quickest maybe 40 minutes if the crew's right there and nothing fights them; longest, dragging past an hour, call it an hour twenty on a bad day; typically 45 minutes to an hour. The \"cheap\" direction."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.",
+          "excerpt": "quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "call it an hour twenty on a bad day",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Typically though it lands around 45 minutes to an hour",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill on Line 1 is costing more than the published line rate admits, so it can be taken to engineering as something other than a hunch.\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"spelled out\",\"rationale\":\"Second in-scope question: whether the small tank between mill and fill on Line 1 is actually costing time.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-46c666e7-d79c-4187-9eaf-dce49ca64100",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quickest maybe 40 minutes if the crew's right there and nothing fights them; longest, dragging past an hour, call it an hour twenty on a bad day; typically 45 minutes to an hour. The \\\"cheap\\\" direction.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover\",\"precision\":\"range\",\"rationale\":\"Low, high and typical given; not quantiles, so recorded as a range with typical, not a spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Typically though it lands around 45 minutes to an hour\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"call it an hour twenty on a bad day\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "where Line 1 loses its time",
-          "slot": "the nodes it depends on",
+          "kind": "activity",
+          "node": "white-to-tint changeover",
+          "slot": "who or what performs it",
           "precision": "named",
-          "rationale": "The tank question depends on the stage kit and the holding-tank constraint.",
+          "rationale": "Performed by the shared crew, allocated by the crew policy.",
           "assertion": {
-            "value": [
-              "entity-type:mix, mill, tint, fill stages",
-              "constraint:small holding tanks between stages",
-              "activity:run it through mix/mill/tint/fill",
-              "entity-type:Line 1 and Line 2"
-            ]
+            "value": "The changeover crew (entity-type:changeover crew), allocated by policy:who gets the crew"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "So yes — build it as separate stages if that's what it takes.",
+          "excerpt": "whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-bb291ebf-9fe0-4a6e-9840-e7d7fac44033",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:mix, mill, tint, fill stages\",\"constraint:small holding tanks between stages\",\"activity:run it through mix/mill/tint/fill\",\"entity-type:Line 1 and Line 2\"]},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"named\",\"rationale\":\"The tank question depends on the stage kit and the holding-tank constraint.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So yes — build it as separate stages if that's what it takes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-5212259b-d4d4-491b-b122-6af5239030d7",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The changeover crew (entity-type:changeover crew), allocated by policy:who gets the crew\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover\",\"precision\":\"named\",\"rationale\":\"Performed by the shared crew, allocated by the crew policy.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "order (line item in the demand book)",
-          "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
-          "rationale": "Whites vs tints differ in the tint stage and in run time by line; customer identity differs in slip tolerance.",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "how long it takes",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Low, high, typical given; the typical figure is the one used on the sheet.",
           "assertion": {
-            "value": "Orders are line items with quantity, due date and SKU. Treated apart: whites (tint stage barely there, more of a pass-through than a real letdown step) vs tints (real letdown); and by customer — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem."
+            "value": "Quickest maybe two and a half hours if everything's clean and the crew's fresh; on a bad day — dried pigment in a fitting — it's crept toward four hours; three hours typical, and that's the number actually used on the sheet."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+          "excerpt": "Quickest I've seen that go is maybe two and a half hours",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+          "excerpt": "it's crept toward four hours. Call it three hours typical",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-edfaf81c-c276-4b57-a88c-914953b1c6be",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders are line items with quantity, due date and SKU. Treated apart: whites (tint stage barely there, more of a pass-through than a real letdown step) vs tints (real letdown); and by customer — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem.\"},\"kind\":\"entity-type\",\"node\":\"order (line item in the demand book)\",\"precision\":\"spelled out\",\"rationale\":\"Whites vs tints differ in the tint stage and in run time by line; customer identity differs in slip tolerance.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-bff705c5-00cb-426f-9ddd-663d4dbc1e49",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quickest maybe two and a half hours if everything's clean and the crew's fresh; on a bad day — dried pigment in a fitting — it's crept toward four hours; three hours typical, and that's the number actually used on the sheet.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"range\",\"rationale\":\"Low, high, typical given; the typical figure is the one used on the sheet.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Quickest I've seen that go is maybe two and a half hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's crept toward four hours. Call it three hours typical\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "order (line item in the demand book)",
-          "slot": "state that rides along with each instance",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what is lost when it changes the system's mode",
           "precision": "spelled out",
-          "rationale": "Quantity, due date, SKU come from ERP; customer type is used in the slip judgement; line allocation is set at step one.",
+          "sourceRegime": "practiced",
+          "rationale": "Directional asymmetry and its reason; loss is the full washdown time, not recoverable.",
           "assertion": {
-            "value": "Quantity, due date, SKU; the customer (distributor / small account / awkward account); which line and week-slot it has been allocated to; whether it has gone late and by how many days."
+            "value": "A full washdown, because any pigment left behind wrecks a white batch — direction absolutely matters, it's not symmetric: tint-to-white is the expensive one (three hours typical) versus white-to-tint (45 minutes to an hour). \"A full white-to-tint changeover is a wash we can't get back.\""
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "excerpt": "Any pigment left behind wrecks a white batch, so that's a full washdown.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+          "excerpt": "direction absolutely matters — it's not symmetric",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-13339551-ff3a-414f-8260-e1296530d8ec",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; the customer (distributor / small account / awkward account); which line and week-slot it has been allocated to; whether it has gone late and by how many days.\"},\"kind\":\"entity-type\",\"node\":\"order (line item in the demand book)\",\"precision\":\"spelled out\",\"rationale\":\"Quantity, due date, SKU come from ERP; customer type is used in the slip judgement; line allocation is set at step one.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-16d70bcc-e61a-4037-bc57-9ac302ff7b25",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A full washdown, because any pigment left behind wrecks a white batch — direction absolutely matters, it's not symmetric: tint-to-white is the expensive one (three hours typical) versus white-to-tint (45 minutes to an hour). \\\"A full white-to-tint changeover is a wash we can't get back.\\\"\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Directional asymmetry and its reason; loss is the full washdown time, not recoverable.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Any pigment left behind wrecks a white batch, so that's a full washdown.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"direction absolutely matters — it's not symmetric\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "Line 1 and Line 2",
-          "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
-          "rationale": "The two lines differ on whites but not on tints — load-bearing for switch-or-wait.",
+          "kind": "activity",
+          "node": "specialty changeover",
+          "slot": "how long it takes",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Range with typical, explicitly less well observed by the expert.",
           "assertion": {
-            "value": "Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to Line 2's figures (\"Line 2 is twice as fast\", though that's really a whites number). On tints they run at nearly the same speed."
+            "value": "Around two hours normally, either direction going into or out of a specialty run; as short as an hour forty for a specialty-to-specialty colour change rather than a full family switch; not seen much longer than two and a half hours — but the expert doesn't watch specialty changeovers as closely because they don't hit due dates as hard."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
+          "excerpt": "going in or coming out of a specialty run, either direction, it's around two hours normally",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.",
+          "excerpt": "maybe an hour forty if it's a specialty-to-specialty color change",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I haven't seen it run much longer than two and a half hours, but I'll be honest, I don't watch specialty changeovers as closely as I watch the white-tint ones",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-535749ea-ba99-4d11-84c0-8203fd058329",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to Line 2's figures (\\\"Line 2 is twice as fast\\\", though that's really a whites number). On tints they run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"rationale\":\"The two lines differ on whites but not on tints — load-bearing for switch-or-wait.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-d3b4e8c5-eb00-4103-b861-89ac1e3d5c7b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Around two hours normally, either direction going into or out of a specialty run; as short as an hour forty for a specialty-to-specialty colour change rather than a full family switch; not seen much longer than two and a half hours — but the expert doesn't watch specialty changeovers as closely because they don't hit due dates as hard.\"},\"kind\":\"activity\",\"node\":\"specialty changeover\",\"precision\":\"range\",\"rationale\":\"Range with typical, explicitly less well observed by the expert.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I haven't seen it run much longer than two and a half hours, but I'll be honest, I don't watch specialty changeovers as closely as I watch the white-tint ones\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"going in or coming out of a specialty run, either direction, it's around two hours normally\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"maybe an hour forty if it's a specialty-to-specialty color change\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "mix, mill, tint, fill stages",
-          "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
+          "kind": "activity",
+          "node": "specialty changeover",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
           "sourceRegime": "practiced",
-          "rationale": "The floor's account: four separately contended pieces of kit per line, buffered by small holding tanks.",
+          "rationale": "Explicit confirmation that changeover duration varies by direction and family.",
           "assertion": {
-            "value": "Mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can be starting the next order's batch while the fill head is still finishing the last one, if the holding tank between mix and mill, or mill and fill, has room."
+            "value": "Yes — three distinct changeovers with real asymmetry: white-to-tint 45 min–1 hr, tint-to-white ~3 hrs, specialty ~2 hrs either direction; specialty is its own animal again."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+          "excerpt": "Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.",
+          "excerpt": "Specialty is its own animal again",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-79eccb7f-a787-40d4-a2fa-e95bfda82d18",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can be starting the next order's batch while the fill head is still finishing the last one, if the holding tank between mix and mill, or mill and fill, has room.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill stages\",\"precision\":\"spelled out\",\"rationale\":\"The floor's account: four separately contended pieces of kit per line, buffered by small holding tanks.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-5f3fa0ff-23ae-4621-9bbe-9778cba7a67d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — three distinct changeovers with real asymmetry: white-to-tint 45 min–1 hr, tint-to-white ~3 hrs, specialty ~2 hrs either direction; specialty is its own animal again.\"},\"kind\":\"activity\",\"node\":\"specialty changeover\",\"precision\":\"named\",\"rationale\":\"Explicit confirmation that changeover duration varies by direction and family.\",\"slot\":\"whether its quantities vary by type\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Specialty is its own animal again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "mix, mill, tint, fill stages",
-          "slot": "how many there are, or the population's shape",
-          "precision": "named",
-          "rationale": "Stage counts per line and tank sizes not carried by the expert; source named.",
+          "kind": "policy",
+          "node": "who gets the crew",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Tacit contention rule elicited from a real borderline case.",
           "assertion": {
-            "absence": "deferred",
-            "pointer": "engineering drawings (tank sizes) — expert does not carry them in his head"
+            "value": "If a Meridian job is sitting behind either changeover, the crew goes to whichever line has the Meridian job next, full stop — that decision doesn't even get discussed, everyone understands it without it being said out loud. Otherwise it's the scheduler's judgment call at the huddle about whose next job is tightest against its due date; failing that, it's whoever's line supervisor gets to the crew lead first. Nobody's written that rule down. In the recalled case Line 1 won on due-date tightness and Line 3 sat clean but idle close to two hours waiting its turn."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I don't have clean numbers for tank sizes or stage-by-stage rates.",
+          "excerpt": "the crew goes to whichever line has the Meridian job next, full stop",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+          "excerpt": "whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-3c6b3e85-7fd3-4831-9201-6e3ef525e7cf",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings (tank sizes) — expert does not carry them in his head\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill stages\",\"precision\":\"named\",\"rationale\":\"Stage counts per line and tank sizes not carried by the expert; source named.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have clean numbers for tank sizes or stage-by-stage rates.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "boundary-condition",
-          "node": "demand book from ERP",
-          "slot": "the starting state",
-          "precision": "spelled out",
-          "rationale": "Orders enter the scheduler's world as ERP-generated demand-book line items.",
-          "assertion": {
-            "value": "Orders arrive as line items in the demand book once ERP spits that out, carrying quantity, due date and SKU."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders arrive as line items in the demand book once ERP spits that out, carrying quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"spelled out\",\"rationale\":\"Orders enter the scheduler's world as ERP-generated demand-book line items.\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "allocation",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "rationale": "Allocation fixes line and week-slot on the sheet.",
-          "assertion": {
-            "value": "The order is slotted onto a line and a slot in the week on the sheet."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-823c9593-db42-45eb-9515-937e6b90bd33",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Allocation fixes line and week-slot on the sheet.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "allocation",
-          "slot": "who or what performs it",
-          "precision": "named",
-          "rationale": "The expert himself, as master scheduler, does the slotting on the sheet.",
-          "assertion": {
-            "value": "The master scheduler, on the sheet"
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "I'm the master scheduler at a coatings plant.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 1,
-            "entryEnd": 1
-          },
-          "source": "user"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-f7e12936-7567-4b38-be19-a45fb5dc6274",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler, on the sheet\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"named\",\"rationale\":\"The expert himself, as master scheduler, does the slotting on the sheet.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm the master scheduler at a coatings plant.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":1,\\\"entryStart\\\":1,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "allocation",
-          "slot": "what it needs before it can start",
-          "precision": "spelled out",
-          "rationale": "Allocation follows the ERP demand-book line item existing.",
-          "assertion": {
-            "value": "A line item in the demand book from ERP, with quantity, due date and SKU."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "inferred",
-      "id": "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book from ERP, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Allocation follows the ERP demand-book line item existing.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "allocate → run → QA hold → release and ship",
-          "slot": "the order things happen in",
-          "precision": "spelled out",
-          "rationale": "The expert's own end-to-end sequence for one order.",
-          "assertion": {
-            "value": "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (mix, mill, tint, fill and pack) → QA hold in the lab's queue → release, warehouse, and ship against the due date."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (mix, mill, tint, fill and pack) → QA hold in the lab's queue → release, warehouse, and ship against the due date.\"},\"kind\":\"ordering/flow\",\"node\":\"allocate → run → QA hold → release and ship\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own end-to-end sequence for one order.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "what it needs before it can start",
-          "precision": "spelled out",
-          "rationale": "A run needs the order allocated to a line and that line's kit available.",
-          "assertion": {
-            "value": "The order must have been allocated onto a line and a slot in the week, and the line's kit (mix, mill, tint, fill) available."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "inferred",
-      "id": "capture-afd366c9-1ea6-4b73-b2c0-ed97c9af0c79",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order must have been allocated onto a line and a slot in the week, and the line's kit (mix, mill, tint, fill) available.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"A run needs the order allocated to a line and that line's kit available.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "rationale": "Output is finished, packed product that comes off the fill line into QA hold.",
-          "assertion": {
-            "value": "The order is produced through mix, mill, tint, fill and pack; it comes off the fill line as packed product ready for QA hold."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-86fd1cfb-379b-42f7-bdbb-8586dae7f755",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is produced through mix, mill, tint, fill and pack; it comes off the fill line as packed product ready for QA hold.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"Output is finished, packed product that comes off the fill line into QA hold.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "who or what performs it",
-          "precision": "named",
-          "rationale": "The run is performed by whichever line the order is allocated to, with its crew.",
-          "assertion": {
-            "value": "entity-type:Line 1 and Line 2 — the line the order is slotted onto, plus its crew"
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I slot it onto Line 2 on the sheet",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "On Line 1, same order — slower machine",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "inferred",
-      "id": "capture-90d36431-4341-4f9e-8bf6-8b5354b2fedd",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:Line 1 and Line 2 — the line the order is slotted onto, plus its crew\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"The run is performed by whichever line the order is allocated to, with its crew.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "how long it takes",
-          "precision": "spread",
-          "sourceRegime": "practiced",
-          "rationale": "First-pass spread for a Meridian-sized white on Line 2, mix-to-last-pack, with breakdowns folded in loosely; superseded by the clean-run capture.",
-          "assertion": {
-            "value": "White, Meridian-sized order, Line 2, mix-to-last-pack (includes fill-up time plus throughput): typical eight to nine hours; one in ten worse than twelve to thirteen hours (breakdowns folded in loosely); one in ten better than about six hours."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more \"the filler hiccupped twice\" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-7ef3368b-e678-4c58-b7f9-137d1607d8ec",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, Meridian-sized order, Line 2, mix-to-last-pack (includes fill-up time plus throughput): typical eight to nine hours; one in ten worse than twelve to thirteen hours (breakdowns folded in loosely); one in ten better than about six hours.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"First-pass spread for a Meridian-sized white on Line 2, mix-to-last-pack, with breakdowns folded in loosely; superseded by the clean-run capture.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more \\\\\\\"the filler hiccupped twice\\\\\\\" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "how long it takes",
-          "precision": "spread",
-          "sourceRegime": "practiced",
-          "rationale": "Superseding capture: breakdown time stripped out so filler jams are not double-counted; clean-run variability is small.",
-          "assertion": {
-            "value": "Clean run (nothing breaks — no jam, no QA holdup), white on Line 2: typical eight or nine hours; one in ten worse than nine to ten hours (normal slack, someone slow changing a roll of packaging film); one in ten better than about six hours. The twelve-to-thirteen-hour days are breakdowns showing up inside the run, not the run being slow."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 21,
-            "entryEnd": 21
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 21,
-            "entryEnd": 21
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-10d88b79-af70-4a14-90c1-da56ad526d36",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Clean run (nothing breaks — no jam, no QA holdup), white on Line 2: typical eight or nine hours; one in ten worse than nine to ten hours (normal slack, someone slow changing a roll of packaging film); one in ten better than about six hours. The twelve-to-thirteen-hour days are breakdowns showing up inside the run, not the run being slow.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"Superseding capture: breakdown time stripped out so filler jams are not double-counted; clean-run variability is small.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "whether its quantities vary by type",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "P07: run duration varies both by product type and by line, and the two interact.",
-          "assertion": {
-            "value": "Yes. White on Line 1: add maybe fifty, sixty percent to the Line 2 figures — typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten (this is where \"Line 2 is twice as fast\" comes from, and that's really a whites number). Tints: Line 1 and Line 2 run them at nearly the same speed — eight to ten hours typical on either line. No good reason known for why; it's what the sheet has always shown."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-921611c3-21b5-4ab2-8e56-9b8cdaa2eba2",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes. White on Line 1: add maybe fifty, sixty percent to the Line 2 figures — typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten (this is where \\\"Line 2 is twice as fast\\\" comes from, and that's really a whites number). Tints: Line 1 and Line 2 run them at nearly the same speed — eight to ten hours typical on either line. No good reason known for why; it's what the sheet has always shown.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"P07: run duration varies both by product type and by line, and the two interact.\",\"slot\":\"whether its quantities vary by type\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jam",
-          "slot": "how long it takes",
-          "precision": "range",
-          "sourceRegime": "practiced",
-          "rationale": "Expert gave two named repair kinds and one recent instance; no quantiles yet, so range not spread.",
-          "assertion": {
-            "value": "Either the \"half hour\" kind or the \"half a shift\" kind of repair; the recent Line 2 instance came back in about two hours."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "I went with waiting, it came back in about two hours, we just scraped the Thursday due date.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-6cf8c229-ab84-4448-abc6-3e7f4a76bb4c",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Either the \\\"half hour\\\" kind or the \\\"half a shift\\\" kind of repair; the recent Line 2 instance came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Expert gave two named repair kinds and one recent instance; no quantiles yet, so range not spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours, we just scraped the Thursday due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jam",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "The jam halts the line's fill stage and forces the switch-or-wait decision.",
-          "assertion": {
-            "value": "The filler stops and the run stalls — the line loses time (half a shift lost in the recent case), the in-progress order's finish is pushed out, and the scheduler must decide whether to shift the order to the other line or wait out the repair."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 21,
-            "entryEnd": 21
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-ce789325-dd40-4b21-a936-73485ccb90b9",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The filler stops and the run stalls — the line loses time (half a shift lost in the recent case), the in-progress order's finish is pushed out, and the scheduler must decide whether to shift the order to the other line or wait out the repair.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"The jam halts the line's fill stage and forces the switch-or-wait decision.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what is lost when it changes the system's mode",
-          "precision": "number",
-          "sourceRegime": "practiced",
-          "rationale": "P02: named transition (tint to white) with a stated loss; a single figure, not a spread.",
-          "assertion": {
-            "value": "Three hours of washdown — crew time, and it takes the line out of anything else for that window."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-1ba32034-be19-432b-a012-326b682fd357",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of washdown — crew time, and it takes the line out of anything else for that window.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"P02: named transition (tint to white) with a stated loss; a single figure, not a spread.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what it needs before it can start",
-          "precision": "spelled out",
-          "rationale": "Triggered by pulling a line off a tint run to run a white.",
-          "assertion": {
-            "value": "A line that is mid-run or last-run on a tint being pulled onto a white — the changeover from tint to white."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line that is mid-run or last-run on a tint being pulled onto a white — the changeover from tint to white.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Triggered by pulling a line off a tint run to run a white.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "how long it takes",
-          "precision": "named",
-          "sourceRegime": "practiced",
-          "rationale": "Vague quantifier — \"usually a few hours\" for a white — not yet quantiles; specialty products wait longer.",
-          "assertion": {
-            "value": "Usually a few hours for a white; \"nothing like the specialty wait\" — specialty products wait longer (amount not given)."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; \\\"nothing like the specialty wait\\\" — specialty products wait longer (amount not given).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Vague quantifier — \\\"usually a few hours\\\" for a white — not yet quantiles; specialty products wait longer.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "rationale": "QA check gates release to warehouse and shipping.",
-          "assertion": {
-            "value": "The batch is checked and then released, goes to the warehouse, and ships against the due date."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-e28ed067-b6a4-40d8-935a-3598e2401cc1",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The batch is checked and then released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"QA check gates release to warehouse and shipping.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "who or what performs it",
-          "precision": "named",
-          "rationale": "The lab holds the queue and does the check.",
-          "assertion": {
-            "value": "The lab"
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"The lab holds the queue and does the check.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "policy",
-          "node": "a line is occupied for the whole run",
-          "slot": "the rule as actually practiced",
-          "precision": "spelled out",
-          "sourceRegime": "prescribed",
-          "rationale": "P08: the scheduling sheet's rule, which the expert says lies to him a bit.",
-          "assertion": {
-            "value": "On the sheet, a line is one row: the order occupies that line for its whole run, mix through fill, and nothing else is scheduled on it till it's done."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet, a line is one row: the order occupies that line for its whole run, mix through fill, and nothing else is scheduled on it till it's done.\"},\"kind\":\"policy\",\"node\":\"a line is occupied for the whole run\",\"precision\":\"spelled out\",\"rationale\":\"P08: the scheduling sheet's rule, which the expert says lies to him a bit.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "policy",
-          "node": "a line is occupied for the whole run",
-          "slot": "what overrides it",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "P08 divergence: floor practice overlaps stages when buffer space allows.",
-          "assertion": {
-            "value": "On the floor the crew will get a head start on mixing the next batch if the tank ahead of it has space — the mixer can start the next order while the fill head finishes the last one. How much overlap happens, and how often it is blocked because a tank is full, is not tracked."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-cfe5bf57-8879-4592-a938-1527d73c8bac",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the floor the crew will get a head start on mixing the next batch if the tank ahead of it has space — the mixer can start the next order while the fill head finishes the last one. How much overlap happens, and how often it is blocked because a tank is full, is not tracked.\"},\"kind\":\"policy\",\"node\":\"a line is occupied for the whole run\",\"precision\":\"spelled out\",\"rationale\":\"P08 divergence: floor practice overlaps stages when buffer space allows.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "policy",
-          "node": "who can absorb the slip",
-          "slot": "the rule as actually practiced",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "The practiced rule for choosing which order to bump; explicitly judgement, not formula.",
-          "assertion": {
-            "value": "Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem. No formula — \"how bad is bad\" for the second-order stuff."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "I use judgment on who can absorb the slip",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem. No formula — \\\"how bad is bad\\\" for the second-order stuff.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The practiced rule for choosing which order to bump; explicitly judgement, not formula.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "policy",
-          "node": "who can absorb the slip",
-          "slot": "what overrides it",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "The hard on-time line overrides the slip-absorption weighing.",
-          "assertion": {
-            "value": "The Meridian-style on-time line overrides everything: that order shipping on time is non-negotiable unless there's truly no way through."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The Meridian-style on-time line overrides everything: that order shipping on time is non-negotiable unless there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The hard on-time line overrides the slip-absorption weighing.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "constraint",
-          "node": "small holding tanks between stages",
-          "slot": "the limit and what happens when it is hit",
-          "precision": "named",
-          "sourceRegime": "practiced",
-          "rationale": "Consequence named (mixing has to wait when the tank ahead is full) but the capacities themselves are not held by the expert; source named.",
-          "assertion": {
-            "absence": "deferred",
-            "pointer": "engineering drawings — tank sizes; consequence as stated: the tanks are small, especially the one between mill and fill on Line 1, and when a tank is full mixing has to wait"
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-23c5706e-37c1-481e-9438-8fae70973c13",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings — tank sizes; consequence as stated: the tanks are small, especially the one between mill and fill on Line 1, and when a tank is full mixing has to wait\"},\"kind\":\"constraint\",\"node\":\"small holding tanks between stages\",\"precision\":\"named\",\"rationale\":\"Consequence named (mixing has to wait when the tank ahead is full) but the capacities themselves are not held by the expert; source named.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "data-binding",
-          "node": "stage-by-stage durations from the historian",
-          "slot": "the variable and its feed",
-          "precision": "named",
-          "rationale": "Stage-level rates exist as data but not in the expert's head; feed named.",
-          "assertion": {
-            "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) per SKU and line — feed: the historian. Never pulled apart; only end-to-end batch time per SKU per line is on the scheduling sheet."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-00863ee1-f99c-48b2-b680-bf4eb71e6a57",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) per SKU and line — feed: the historian. Never pulled apart; only end-to-end batch time per SKU per line is on the scheduling sheet.\"},\"kind\":\"data-binding\",\"node\":\"stage-by-stage durations from the historian\",\"precision\":\"named\",\"rationale\":\"Stage-level rates exist as data but not in the expert's head; feed named.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "validation-criterion",
-          "node": "stage rates must come from data, not gut-feel",
-          "slot": "how the expert would know the model is right",
-          "precision": "spelled out",
-          "rationale": "Expert explicitly bounds what his own testimony can support.",
-          "assertion": {
-            "value": "Stage-level rates and tank sizes must not be taken from the expert's gut-feel — he can supply gut-feel and known bottleneck stories, but real numbers must come from the historian and engineering drawings."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-196b8447-3958-444f-9860-8de7330299ec",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-level rates and tank sizes must not be taken from the expert's gut-feel — he can supply gut-feel and known bottleneck stories, but real numbers must come from the historian and engineering drawings.\"},\"kind\":\"validation-criterion\",\"node\":\"stage rates must come from data, not gut-feel\",\"precision\":\"spelled out\",\"rationale\":\"Expert explicitly bounds what his own testimony can support.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "objective",
-          "node": "switch or wait when Line 2 goes down",
-          "slot": "the question, in the expert's words",
-          "precision": "spelled out",
-          "rationale": "The expert wrote the question as he would type it into the tool.",
-          "assertion": {
-            "value": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\""
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-b58883f3-43e2-4626-bc59-a9c091f1d1b5",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\"\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down\",\"precision\":\"spelled out\",\"rationale\":\"The expert wrote the question as he would type it into the tool.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "objective",
-          "node": "switch or wait when Line 2 goes down",
-          "slot": "the nodes it depends on",
-          "precision": "named",
-          "rationale": "The expert listed what the answer hangs on: the protected run and its due date, the state of Line 1, the changeover and its direction, the jam duration, and whose order gets bumped.",
-          "assertion": {
-            "value": [
-              "entity-type:order",
-              "entity-type:line",
-              "activity:run it through mix/mill/tint/fill",
-              "activity:tint-to-white washdown",
-              "activity:filler jam",
-              "policy:who can absorb the slip"
-            ]
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "the bumped order's identity matters, not just \"an order got delayed.\"",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-3aa3764b-8dd5-495a-bf3e-b32cbc89ba61",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:line\",\"activity:run it through mix/mill/tint/fill\",\"activity:tint-to-white washdown\",\"activity:filler jam\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down\",\"precision\":\"named\",\"rationale\":\"The expert listed what the answer hangs on: the protected run and its due date, the state of Line 1, the changeover and its direction, the jam duration, and whose order gets bumped.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the bumped order's identity matters, not just \\\\\\\"an order got delayed.\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "objective",
-          "node": "switch or wait when Line 2 goes down",
-          "slot": "what \"better\" means, and trade-off weights",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "Expert gave a lexicographic hard constraint plus unweighted second-order criteria, explicitly denying a formula.",
-          "assertion": {
-            "value": "Hard line: days late on Meridian, anything above zero is bad news. Underneath that, weighed by judgment with no formula: washdown hours, and whether the bumped order goes late and by how much and for which customer."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-57ad71c3-f423-4d91-a9f8-d3ce31f1fca1",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Hard line: days late on Meridian, anything above zero is bad news. Underneath that, weighed by judgment with no formula: washdown hours, and whether the bumped order goes late and by how much and for which customer.\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down\",\"precision\":\"spelled out\",\"rationale\":\"Expert gave a lexicographic hard constraint plus unweighted second-order criteria, explicitly denying a formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "objective",
-          "node": "is the mill-to-fill tank on Line 1 slowing the line down",
-          "slot": "the question, in the expert's words",
-          "precision": "spelled out",
-          "rationale": "Second question the expert wrote out as he would type it.",
-          "assertion": {
-            "value": "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\""
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-1a3325b9-15b6-436a-8e7f-feff95d98036",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\"\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"rationale\":\"Second question the expert wrote out as he would type it.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "objective",
-          "node": "is the mill-to-fill tank on Line 1 slowing the line down",
-          "slot": "the nodes it depends on",
-          "precision": "named",
-          "rationale": "Expert named stage-level rates on Line 1, the tank size between mill and fill, and per-SKU stage differences.",
-          "assertion": {
-            "value": [
-              "entity-type:the four stages — mix, mill, tint, fill",
-              "constraint:small holding tank between mill and fill on Line 1",
-              "entity-type:order",
-              "entity-type:line"
-            ]
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-0e28490a-6b4b-4996-9b6f-3d9249a7d2dc",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:the four stages — mix, mill, tint, fill\",\"constraint:small holding tank between mill and fill on Line 1\",\"entity-type:order\",\"entity-type:line\"]},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"named\",\"rationale\":\"Expert named stage-level rates on Line 1, the tank size between mill and fill, and per-SKU stage differences.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "order",
-          "slot": "state that rides along with each instance",
-          "precision": "spelled out",
-          "rationale": "Expert named the fields the order carries from the demand book and the state he consults mid-disruption.",
-          "assertion": {
-            "value": "Quantity, due date, SKU; remaining quantity as it runs; the customer it belongs to; how far through it is; which line and slot it is allocated to."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "whose order was it — that's the \"who can absorb it\" judgment call again",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-43c5ef42-68ce-478f-89b0-c552111d807a",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; remaining quantity as it runs; the customer it belongs to; how far through it is; which line and slot it is allocated to.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Expert named the fields the order carries from the demand book and the state he consults mid-disruption.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whose order was it — that's the \\\\\\\"who can absorb it\\\\\\\" judgment call again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "order",
-          "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
-          "rationale": "The process treats whites and tints differently at the tint stage and in run times; customer type changes how a slip is judged.",
-          "assertion": {
-            "value": "Whites versus tints (for a white the tint stage is barely there, a pass-through); and by customer type — distributor, small account, or an awkward account that gets prickly."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-ccc2d7eb-8a3f-4684-8f1c-a21a51049550",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints (for a white the tint stage is barely there, a pass-through); and by customer type — distributor, small account, or an awkward account that gets prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The process treats whites and tints differently at the tint stage and in run times; customer type changes how a slip is judged.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "line",
-          "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
-          "sourceRegime": "prescribed",
-          "rationale": "The sheet's representation of a line, which the expert says 'lies to me a bit'.",
-          "assertion": {
-            "value": "On the scheduling sheet a line is one row and one resource: an order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the scheduling sheet a line is one row and one resource: an order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"spelled out\",\"rationale\":\"The sheet's representation of a line, which the expert says 'lies to me a bit'.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "the four stages — mix, mill, tint, fill",
-          "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "The floor's version of the line: four contended stages with buffers, not one resource.",
-          "assertion": {
-            "value": "Physically mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head finishes the last one if the tank ahead has space."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "the crew will get a head start on mixing the next batch if the tank ahead of it has space",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-a158a5da-be3a-461f-87c0-69c38cac1a72",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head finishes the last one if the tank ahead has space.\"},\"kind\":\"entity-type\",\"node\":\"the four stages — mix, mill, tint, fill\",\"precision\":\"spelled out\",\"rationale\":\"The floor's version of the line: four contended stages with buffers, not one resource.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the crew will get a head start on mixing the next batch if the tank ahead of it has space\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "the four stages — mix, mill, tint, fill",
-          "slot": "how many there are, or the population's shape",
-          "precision": "named",
-          "rationale": "Count of stages is stated; occupancy/blocking frequency is explicitly untracked.",
-          "assertion": {
-            "value": "Four stages in series per line — mix, mill, tint, fill — with small holding tanks between them; how often blocking occurs is not tracked."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Four stages in series per line — mix, mill, tint, fill — with small holding tanks between them; how often blocking occurs is not tracked.\"},\"kind\":\"entity-type\",\"node\":\"the four stages — mix, mill, tint, fill\",\"precision\":\"named\",\"rationale\":\"Count of stages is stated; occupancy/blocking frequency is explicitly untracked.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "allocation",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "rationale": "Expert's step one.",
-          "assertion": {
-            "value": "The order is slotted onto a line and a slot in the week on the sheet."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-4043a577-c1b4-44c3-91f3-2194def82bd9",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Expert's step one.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "allocation",
-          "slot": "what it needs before it can start",
-          "precision": "spelled out",
-          "rationale": "Precondition named in the walkthrough.",
-          "assertion": {
-            "value": "A line item in the demand book, produced by ERP, carrying quantity, due date and SKU."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book, produced by ERP, carrying quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Precondition named in the walkthrough.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "boundary-condition",
-          "node": "demand book from ERP",
-          "slot": "the starting state",
-          "precision": "spelled out",
-          "rationale": "External source of work into the scheduling process.",
-          "assertion": {
-            "value": "Orders exist as line items in the demand book, each with quantity, due date and SKU, once ERP produces it."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders exist as line items in the demand book, each with quantity, due date and SKU, once ERP produces it.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"spelled out\",\"rationale\":\"External source of work into the scheduling process.\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "how long it takes",
-          "precision": "range",
-          "sourceRegime": "practiced",
-          "rationale": "Expert corrected his first spread to strip out jams, so the clean-run figure supersedes; no one-in-ten-better figure was given for the clean run.",
-          "assertion": {
-            "value": "Meridian-sized white on Line 2, clean run (nothing breaks): typically eight to nine hours mix-to-last-pack; a bad-but-clean day nine to ten hours. Clean-run variability is small; the twelve-to-thirteen-hour bad days are breakdowns showing up inside the run and are modelled separately."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 21,
-            "entryEnd": 21
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-72d414e6-f6a2-420e-8407-667f41535411",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian-sized white on Line 2, clean run (nothing breaks): typically eight to nine hours mix-to-last-pack; a bad-but-clean day nine to ten hours. Clean-run variability is small; the twelve-to-thirteen-hour bad days are breakdowns showing up inside the run and are modelled separately.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"range\",\"rationale\":\"Expert corrected his first spread to strip out jams, so the clean-run figure supersedes; no one-in-ten-better figure was given for the clean run.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "whether its quantities vary by type",
-          "precision": "named",
-          "rationale": "Durations vary by line and by white-versus-tint; the Line 1 figures were given before the clean-run/breakdown split and may still fold in stoppages.",
-          "assertion": {
-            "value": "Yes. Same white order on Line 1 is about fifty to sixty percent longer than Line 2 — typical thirteen to fourteen hours, worse days eighteen-plus, best day about ten. Tints run at nearly the same speed on either line, about eight to ten hours typical, with no big gap; the 'Line 2 is twice as fast' rule is really a whites number."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes. Same white order on Line 1 is about fifty to sixty percent longer than Line 2 — typical thirteen to fourteen hours, worse days eighteen-plus, best day about ten. Tints run at nearly the same speed on either line, about eight to ten hours typical, with no big gap; the 'Line 2 is twice as fast' rule is really a whites number.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Durations vary by line and by white-versus-tint; the Line 1 figures were given before the clean-run/breakdown split and may still fold in stoppages.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "run it through mix/mill/tint/fill",
-          "slot": "who or what performs it",
-          "precision": "named",
-          "rationale": "Runs are performed on a named line; the expert compares Line 1 and Line 2 as the performing kit.",
-          "assertion": {
-            "value": "One of the two production lines (Line 1 or Line 2) with its crew."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-53f9387d-f037-4d0f-999b-f89a8f113f46",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One of the two production lines (Line 1 or Line 2) with its crew.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Runs are performed on a named line; the expert compares Line 1 and Line 2 as the performing kit.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "who or what performs it",
-          "precision": "named",
-          "rationale": "Named performer in the walkthrough.",
-          "assertion": {
-            "value": "The lab."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Named performer in the walkthrough.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "how long it takes",
-          "precision": "named",
-          "rationale": "Only a vague 'few hours' was given; not yet a range or spread.",
-          "assertion": {
-            "value": "Usually a few hours for a white; explicitly longer for specialty ('nothing like the specialty wait'), figure not given."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-38e0effa-0fb7-48ff-907c-2fc9f3e64211",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; explicitly longer for specialty ('nothing like the specialty wait'), figure not given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Only a vague 'few hours' was given; not yet a range or spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "release and ship",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "rationale": "Final step of the walkthrough.",
-          "assertion": {
-            "value": "The order is released, goes to the warehouse, and ships against its due date."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against its due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"rationale\":\"Final step of the walkthrough.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "order life on the floor",
-          "slot": "the order things happen in",
-          "precision": "spelled out",
-          "rationale": "Expert's own summary of the end-to-end sequence.",
-          "assertion": {
-            "value": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship"
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-314d8187-81ba-478c-8f71-1c9e5826965b",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\"},\"kind\":\"ordering/flow\",\"node\":\"order life on the floor\",\"precision\":\"spelled out\",\"rationale\":\"Expert's own summary of the end-to-end sequence.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "how long it takes",
-          "precision": "number",
-          "rationale": "Single figure given for the tint-to-white washdown; no spread elicited.",
-          "assertion": {
-            "value": "Three hours"
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-345fbb5a-c0c1-4e3a-9015-33b3ad727831",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Single figure given for the tint-to-white washdown; no spread elicited.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what it needs before it can start",
-          "precision": "spelled out",
-          "rationale": "Changeover is directional and triggered by the family of what was running versus what is coming.",
-          "assertion": {
-            "value": "A changeover between product families on the same line; the direction decides the cost — tint-to-white is the expensive one, not the other way."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "the direction of the changeover matters as much as the fact of it",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-60f6f8c8-f52e-443a-adee-6818339f3b35",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A changeover between product families on the same line; the direction decides the cost — tint-to-white is the expensive one, not the other way.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Changeover is directional and triggered by the family of what was running versus what is coming.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the direction of the changeover matters as much as the fact of it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "rationale": "Stated consequence of the washdown.",
-          "assertion": {
-            "value": "The line is cleaned from tint to white and is taken out of anything else for that window; it costs crew time."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "it takes Line 1 out of anything else for that window",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-be556841-bf14-4fe0-8c23-ffc773896b2b",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line is cleaned from tint to white and is taken out of anything else for that window; it costs crew time.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Stated consequence of the washdown.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what is lost when it changes the system's mode",
-          "rationale": "Loss is named and affirmed as material but no quantity is held by the expert.",
-          "assertion": {
-            "absence": "unknown-to-user",
-            "pointer": "ramp scrap after the washdown — real product lost on top of the hours; expert has no good numbers"
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-26d3ac6c-4b27-4765-baa3-8437f06fe8ca",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"ramp scrap after the washdown — real product lost on top of the hours; expert has no good numbers\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"rationale\":\"Loss is named and affirmed as material but no quantity is held by the expert.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jam",
-          "slot": "how long it takes",
-          "precision": "range",
-          "sourceRegime": "practiced",
-          "rationale": "Expert gave two named kinds of repair plus one observed instance; no typical or decile figures yet.",
-          "assertion": {
-            "value": "Between the 'half hour' kind and the 'half a shift' kind; the recent Line 2 case came back in about two hours."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "I went with waiting, it came back in about two hours",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-da6d10a4-e0f2-4b1d-8e78-4d58cadeb8f2",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Between the 'half hour' kind and the 'half a shift' kind; the recent Line 2 case came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Expert gave two named kinds of repair plus one observed instance; no typical or decile figures yet.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jam",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "rationale": "Event-shaped activity that befalls the line, distinct from the run itself.",
-          "assertion": {
-            "value": "The filler stops mid-run and the line is down for the repair; the run in progress stretches (the twelve-to-thirteen-hour bad days), and the scheduler must decide to wait or shift the order to the other line."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 21,
-            "entryEnd": 21
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-68f9db28-a002-406d-912a-4cc410e5b380",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The filler stops mid-run and the line is down for the repair; the run in progress stretches (the twelve-to-thirteen-hour bad days), and the scheduler must decide to wait or shift the order to the other line.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"Event-shaped activity that befalls the line, distinct from the run itself.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jam",
-          "slot": "how often it occurs, if it is an event rather than a step",
-          "rationale": "No rate was stated; recording the gap rather than inferring one from the single incident.",
-          "assertion": {
-            "absence": "unknown-to-user",
-            "pointer": "frequency of filler jams was not given; expert spoke only to duration uncertainty at the time of the jam"
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of \"could be quick, could be long\" rather than one number",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-0a06d184-bf72-42c4-95b3-7ad88ea4e059",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"frequency of filler jams was not given; expert spoke only to duration uncertainty at the time of the jam\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"rationale\":\"No rate was stated; recording the gap rather than inferring one from the single incident.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of \\\\\\\"could be quick, could be long\\\\\\\" rather than one number\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "policy",
-          "node": "who can absorb the slip",
-          "slot": "the rule as actually practiced",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "The tacit rule for choosing which order to bump; no formula, judged on customer identity and size of slip.",
-          "assertion": {
-            "value": "Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first, so it is protected."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "I use judgment on who can absorb the slip",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first, so it is protected.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The tacit rule for choosing which order to bump; no formula, judged on customer identity and size of slip.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "policy",
-          "node": "who can absorb the slip",
-          "slot": "what overrides it",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "rationale": "Hard constraint sitting above the absorb-the-slip judgment.",
-          "assertion": {
-            "value": "The protected order's on-time ship date overrides: shipping Meridian on time is a line he won't cross unless there's truly no way through."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The protected order's on-time ship date overrides: shipping Meridian on time is a line he won't cross unless there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint sitting above the absorb-the-slip judgment.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "constraint",
-          "node": "small holding tank between mill and fill on Line 1",
-          "slot": "the limit and what happens when it is hit",
-          "precision": "spelled out",
-          "rationale": "Qualitative blocking rule stated; the numeric capacity is not available from the expert.",
-          "assertion": {
-            "value": "Holding tanks between stages are small — especially the one between mill and fill on Line 1. When there is room, the upstream stage can start the next order's batch; when the tank is full, the upstream stage is blocked and mixing has to wait. Actual tank capacity is not held by the expert; engineering's position is that the line rate is what it is regardless."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-7111ab55-5d90-44f6-a1d2-4aa1b48da4bb",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tanks between stages are small — especially the one between mill and fill on Line 1. When there is room, the upstream stage can start the next order's batch; when the tank is full, the upstream stage is blocked and mixing has to wait. Actual tank capacity is not held by the expert; engineering's position is that the line rate is what it is regardless.\"},\"kind\":\"constraint\",\"node\":\"small holding tank between mill and fill on Line 1\",\"precision\":\"spelled out\",\"rationale\":\"Qualitative blocking rule stated; the numeric capacity is not available from the expert.\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "data-binding",
-          "node": "stage-level rates",
-          "slot": "the variable and its feed",
-          "precision": "named",
-          "rationale": "Expert named the system where the missing stage-level numbers live.",
-          "assertion": {
-            "value": "Stage-by-stage durations/rates (how long mixing takes, how long milling takes, mill speed versus fill speed on Line 1) — feed: the historian."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations/rates (how long mixing takes, how long milling takes, mill speed versus fill speed on Line 1) — feed: the historian.\"},\"kind\":\"data-binding\",\"node\":\"stage-level rates\",\"precision\":\"named\",\"rationale\":\"Expert named the system where the missing stage-level numbers live.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "data-binding",
-          "node": "tank sizes",
-          "slot": "the variable and its feed",
-          "precision": "named",
-          "rationale": "Named source for a value the expert cannot give.",
-          "assertion": {
-            "value": "Holding tank capacities between stages — feed: engineering drawings, obtainable but not carried by the expert."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tank capacities between stages — feed: engineering drawings, obtainable but not carried by the expert.\"},\"kind\":\"data-binding\",\"node\":\"tank sizes\",\"precision\":\"named\",\"rationale\":\"Named source for a value the expert cannot give.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "objective",
-          "node": "switch or wait when Line 2 goes down mid-run",
-          "slot": "the question, in the expert's words",
-          "precision": "spelled out",
-          "rationale": "The expert wrote the question as they would type it into the tool.",
-          "assertion": {
-            "value": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\""
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-1a240192-8179-4339-815e-3775a062e986",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\"\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down mid-run\",\"precision\":\"spelled out\",\"rationale\":\"The expert wrote the question as they would type it into the tool.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "objective",
-          "node": "switch or wait when Line 2 goes down mid-run",
-          "slot": "the nodes it depends on",
-          "precision": "named",
-          "rationale": "The expert listed what the answer hangs on.",
-          "assertion": {
-            "value": [
-              "entity-type:order",
-              "entity-type:Line 1 and Line 2",
-              "activity:the run (mix, mill, tint, fill)",
-              "activity:filler jam",
-              "activity:tint-to-white washdown",
-              "policy:who can absorb the slip",
-              "constraint:Meridian ships on time"
-            ]
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "It hangs on the jam itself — how long is this repair *actually* going to take",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "And it hangs on the ramp scrap after the washdown",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the \"who can absorb it\" judgment call again.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-85062afa-e82d-46ce-b609-f7ed16f8b093",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:Line 1 and Line 2\",\"activity:the run (mix, mill, tint, fill)\",\"activity:filler jam\",\"activity:tint-to-white washdown\",\"policy:who can absorb the slip\",\"constraint:Meridian ships on time\"]},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down mid-run\",\"precision\":\"named\",\"rationale\":\"The expert listed what the answer hangs on.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And it hangs on the ramp scrap after the washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the \\\\\\\"who can absorb it\\\\\\\" judgment call again.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It hangs on the jam itself — how long is this repair *actually* going to take\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "objective",
-          "node": "switch or wait when Line 2 goes down mid-run",
-          "slot": "what \"better\" means, and trade-off weights",
-          "precision": "spelled out",
-          "rationale": "Hard constraint plus unweighted secondary measures; the expert explicitly denied having a formula.",
-          "assertion": {
-            "value": "Meridian on time is non-negotiable (days late on Meridian, anything above zero is bad news); underneath that, washdown hours and whether the bumped order goes late and by how much are weighed by judgment — \"I don't have a formula for it.\""
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "I don't have a formula for it.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "days late on Meridian, and anything above zero is bad news I have to go explain",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-2c3fa15f-551b-4380-a3b3-8dbc6334a9bb",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian on time is non-negotiable (days late on Meridian, anything above zero is bad news); underneath that, washdown hours and whether the bumped order goes late and by how much are weighed by judgment — \\\"I don't have a formula for it.\\\"\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down mid-run\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint plus unweighted secondary measures; the expert explicitly denied having a formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"days late on Meridian, and anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "objective",
-          "node": "is the mill-to-fill tank on Line 1 slowing the line down",
-          "slot": "the question, in the expert's words",
-          "precision": "spelled out",
-          "assertion": {
-            "value": "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\""
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-41269bfb-9040-4d54-a113-a94c09f6f2f0",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\"\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "objective",
-          "node": "is the mill-to-fill tank on Line 1 slowing the line down",
-          "slot": "the nodes it depends on",
-          "precision": "named",
-          "assertion": {
-            "value": [
-              "entity-type:mix, mill, tint, fill kit and holding tanks",
-              "entity-type:Line 1 and Line 2",
-              "entity-type:order",
-              "ordering/flow:stage overlap on a line"
-            ]
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "It also probably depends on the product, since I now realize different SKUs are slow at different stages",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-f7ea7c88-4d40-48e7-84e5-2b12ebc5ea8e",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:mix, mill, tint, fill kit and holding tanks\",\"entity-type:Line 1 and Line 2\",\"entity-type:order\",\"ordering/flow:stage overlap on a line\"]},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"named\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It also probably depends on the product, since I now realize different SKUs are slow at different stages\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "objective",
-          "node": "is the mill-to-fill tank on Line 1 slowing the line down",
-          "slot": "what \"better\" means, and trade-off weights",
-          "precision": "spelled out",
-          "rationale": "Qualitative: showing where Line 1 loses its time, in a form usable with engineering.",
-          "assertion": {
-            "value": "The model showing \"here's where Line 1 loses its time\" — something to take to engineering other than a hunch; no numeric weighting given."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The model showing \\\"here's where Line 1 loses its time\\\" — something to take to engineering other than a hunch; no numeric weighting given.\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"rationale\":\"Qualitative: showing where Line 1 loses its time, in a form usable with engineering.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "order",
-          "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
-          "assertion": {
-            "value": "Whites versus tints (family decides run speed by line and washdown direction; for a white the tint stage is a pass-through); and customer identity — distributor, small account, or an awkward account that gets prickly."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "the bumped order's identity matters, not just \"an order got delayed.\"",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-0e8d50b2-4222-4129-a619-09c5612c05c5",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints (family decides run speed by line and washdown direction; for a white the tint stage is a pass-through); and customer identity — distributor, small account, or an awkward account that gets prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the bumped order's identity matters, not just \\\\\\\"an order got delayed.\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "order",
-          "slot": "state that rides along with each instance",
-          "precision": "spelled out",
-          "assertion": {
-            "value": "Quantity, due date, SKU; family (white/tint); customer; remaining quantity and how far through the run it is."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-117f9832-aaba-473a-9411-6fd4022388f2",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; family (white/tint); customer; remaining quantity and how far through the run it is.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "order",
-          "slot": "how many there are, or the population's shape",
-          "precision": "named",
-          "rationale": "The expert described orders arriving as line items in the demand book but gave no counts or arrival volumes.",
-          "assertion": {
-            "absence": "unknown-to-user",
-            "pointer": "demand book / ERP"
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "inferred",
-      "id": "capture-e10d4081-78ed-42da-bb26-857f1118224c",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"demand book / ERP\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"named\",\"rationale\":\"The expert described orders arriving as line items in the demand book but gave no counts or arrival volumes.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "Line 1 and Line 2",
-          "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
-          "assertion": {
-            "value": "Two lines: Line 2 is the faster machine on whites (roughly twice as fast, \"really a whites number\"); Line 1 is the slower machine, add fifty to sixty percent on a white. On tints the two run at nearly the same speed."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-875ed21b-d257-48fe-867b-6785abf6abb7",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two lines: Line 2 is the faster machine on whites (roughly twice as fast, \\\"really a whites number\\\"); Line 1 is the slower machine, add fifty to sixty percent on a white. On tints the two run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "Line 1 and Line 2",
-          "slot": "state that rides along with each instance",
-          "precision": "spelled out",
-          "assertion": {
-            "value": "What order is on it, how far through that order is, and what family (tint or white) it is currently running — the last decides washdown cost and direction."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-06d48b41-86fb-48c0-b3e0-59012ba81960",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"What order is on it, how far through that order is, and what family (tint or white) it is currently running — the last decides washdown cost and direction.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "Line 1 and Line 2",
-          "slot": "how many there are, or the population's shape",
-          "precision": "number",
-          "rationale": "The expert speaks only of Line 1 and Line 2 throughout.",
-          "assertion": {
-            "value": "Two lines — Line 1 and Line 2."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "On the sheet, \"Line 2\" is one row",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Line 1 was mid-run on a tint.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-428e3931-676d-4af5-a30c-d7a31ea0d8ad",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two lines — Line 1 and Line 2.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"number\",\"rationale\":\"The expert speaks only of Line 1 and Line 2 throughout.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "mix, mill, tint, fill kit and holding tanks",
-          "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "assertion": {
-            "value": "Mix, mill, tint and fill are separate tanks and separate kit strung together, with small holding tanks between them."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-ecd3c093-8f6b-4a48-a1fc-d2775d4dbc1f",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Mix, mill, tint and fill are separate tanks and separate kit strung together, with small holding tanks between them.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill kit and holding tanks\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "mix, mill, tint, fill kit and holding tanks",
-          "slot": "how many there are, or the population's shape",
-          "precision": "named",
-          "rationale": "Qualitative \"small\" only; sizes deferred to engineering drawings.",
-          "assertion": {
-            "absence": "deferred",
-            "pointer": "engineering drawings"
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-c6339dee-036e-47cb-9dcf-42fc22d38aae",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill kit and holding tanks\",\"precision\":\"named\",\"rationale\":\"Qualitative \\\"small\\\" only; sizes deferred to engineering drawings.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "constraint",
-          "node": "holding tank capacity between stages",
-          "slot": "the limit and what happens when it is hit",
-          "precision": "spelled out",
-          "rationale": "Blocking consequence stated; frequency and size not tracked.",
-          "assertion": {
-            "value": "A stage can only get a head start if there's room in the holding tank ahead of it; when a tank's full, mixing has to wait. How often that blocking happens is not tracked by the expert."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "if there's room in the holding tank between mix and mill, or mill and fill, to buffer it",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-2bc071c4-2919-4ff3-910a-92d872eeaef2",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A stage can only get a head start if there's room in the holding tank ahead of it; when a tank's full, mixing has to wait. How often that blocking happens is not tracked by the expert.\"},\"kind\":\"constraint\",\"node\":\"holding tank capacity between stages\",\"precision\":\"spelled out\",\"rationale\":\"Blocking consequence stated; frequency and size not tracked.\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if there's room in the holding tank between mix and mill, or mill and fill, to buffer it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "order lifecycle: allocate, run, QA hold, release and ship",
-          "slot": "the order things happen in",
-          "precision": "spelled out",
-          "assertion": {
-            "value": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship"
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-6ec49aac-c165-4e2b-a937-bed3c8c51c2c",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\"},\"kind\":\"ordering/flow\",\"node\":\"order lifecycle: allocate, run, QA hold, release and ship\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "order lifecycle: allocate, run, QA hold, release and ship",
-          "slot": "how a branch or merge is decided",
-          "precision": "spelled out",
-          "rationale": "The line choice is made by the scheduler at allocation and can be revisited on disruption.",
-          "assertion": {
-            "value": "The scheduler slots the order onto a line on the sheet at allocation; on a disruption the choice is re-decided — shift it to the other line or wait out the repair."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "I had to decide right then whether to shift it to Line 1 or just wait out the repair",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-c3f03d77-6760-4b3b-99e5-b78d119a352f",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The scheduler slots the order onto a line on the sheet at allocation; on a disruption the choice is re-decided — shift it to the other line or wait out the repair.\"},\"kind\":\"ordering/flow\",\"node\":\"order lifecycle: allocate, run, QA hold, release and ship\",\"precision\":\"spelled out\",\"rationale\":\"The line choice is made by the scheduler at allocation and can be revisited on disruption.\",\"slot\":\"how a branch or merge is decided\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had to decide right then whether to shift it to Line 1 or just wait out the repair\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "stage overlap on a line",
-          "slot": "the order things happen in",
-          "precision": "spelled out",
-          "sourceRegime": "prescribed",
-          "assertion": {
-            "value": "On the sheet the line is one row: the order occupies the line for its whole run, mix through fill, and nothing else is scheduled on it until it's done."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet the line is one row: the order occupies the line for its whole run, mix through fill, and nothing else is scheduled on it until it's done.\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "stage overlap on a line",
-          "slot": "the order things happen in",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
-          "assertion": {
-            "value": "The mixer can start the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill; the crew get a head start on mixing when the tank ahead has space."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-83e1381a-f2df-4713-a2f6-f11d034c2fd4",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The mixer can start the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill; the crew get a head start on mixing when the tank ahead has space.\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "the run (mix, mill, tint, fill)",
-          "slot": "what it needs before it can start",
-          "precision": "spelled out",
-          "assertion": {
-            "value": "The order allocated onto a line and a slot in the week (\"I slot it onto Line 2 on the sheet, that's step one, allocation\")."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-95cbfe20-605f-4218-9076-0f4816ebadfa",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order allocated onto a line and a slot in the week (\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\").\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "the run (mix, mill, tint, fill)",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "assertion": {
-            "value": "Filled and packed product coming off the fill line, which then goes into QA hold."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Once it comes off the fill line it goes into QA hold",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-1a5a8343-7367-416e-b760-c7e8f587fe25",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Filled and packed product coming off the fill line, which then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "the run (mix, mill, tint, fill)",
-          "slot": "who or what performs it",
-          "precision": "named",
-          "assertion": {
-            "value": "The line (Line 1 or Line 2) — its mix, mill, tint and fill kit — worked by the crew."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "mix, mill, tint, fill are separate tanks and separate kit strung together",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "maybe six hours if everything's clean and the crew doesn't have to stop for anything",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-bf2e57a3-bda7-4090-92ca-af63e0c7a248",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line (Line 1 or Line 2) — its mix, mill, tint and fill kit — worked by the crew.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maybe six hours if everything's clean and the crew doesn't have to stop for anything\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill are separate tanks and separate kit strung together\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "the run (mix, mill, tint, fill)",
-          "slot": "how long it takes",
-          "precision": "spread",
-          "rationale": "First account of a white run on Line 2, mix-to-last-pack, including breakdowns folded in loosely.",
-          "assertion": {
-            "value": "White, Line 2, normal order size, mix-to-last-pack: typical eight to nine hours; one in ten worse twelve to thirteen hours; one in ten better about six hours. (Expert later said the twelve-thirteen folds in breakdowns.)"
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-aec8ff27-3e3f-45d2-9142-b6dc2b5d88a3",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, Line 2, normal order size, mix-to-last-pack: typical eight to nine hours; one in ten worse twelve to thirteen hours; one in ten better about six hours. (Expert later said the twelve-thirteen folds in breakdowns.)\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"rationale\":\"First account of a white run on Line 2, mix-to-last-pack, including breakdowns folded in loosely.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "the run (mix, mill, tint, fill)",
-          "slot": "how long it takes",
-          "precision": "spread",
-          "rationale": "Supersedes the earlier figure by stripping breakdowns out of the run duration; jams are modelled separately.",
-          "assertion": {
-            "value": "Clean run (nothing breaks), white on Line 2: typical eight or nine hours; bad-but-clean one in ten nine to ten hours; one in ten better about six hours. The twelve-thirteen hour bad day is a breakdown showing up inside the run, not the run itself being slow."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 21,
-            "entryEnd": 21
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-9d59a385-a8ae-410a-a13d-a4bca3dde9a3",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Clean run (nothing breaks), white on Line 2: typical eight or nine hours; bad-but-clean one in ten nine to ten hours; one in ten better about six hours. The twelve-thirteen hour bad day is a breakdown showing up inside the run, not the run itself being slow.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"rationale\":\"Supersedes the earlier figure by stripping breakdowns out of the run duration; jams are modelled separately.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "the run (mix, mill, tint, fill)",
-          "slot": "how long it takes",
-          "precision": "spread",
-          "rationale": "Same white order on Line 1.",
-          "assertion": {
-            "value": "White on Line 1: typical thirteen to fourteen hours; worse days pushing eighteen-plus; best day maybe ten — roughly fifty to sixty percent more than Line 2."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-4b22a066-a97c-4329-8513-cbd85edd8d65",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White on Line 1: typical thirteen to fourteen hours; worse days pushing eighteen-plus; best day maybe ten — roughly fifty to sixty percent more than Line 2.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"rationale\":\"Same white order on Line 1.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "the run (mix, mill, tint, fill)",
-          "slot": "how long it takes",
-          "precision": "range",
-          "rationale": "Only a typical range was given for tints; no one-in-ten figures.",
-          "assertion": {
-            "value": "Tint run on either line: eight to ten hours typical; no big gap between the lines. One-in-ten worse/better not given."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-63fabb67-24c4-4bee-926f-17917300c8f4",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Tint run on either line: eight to ten hours typical; no big gap between the lines. One-in-ten worse/better not given.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"range\",\"rationale\":\"Only a typical range was given for tints; no one-in-ten figures.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "the run (mix, mill, tint, fill)",
-          "slot": "whether its quantities vary by type",
-          "precision": "named",
-          "assertion": {
-            "value": "Yes — run time varies by family and by line: whites are about twice as fast on Line 2 as Line 1, tints run at nearly the same speed on both; and different SKUs are slow at different stages."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "since I now realize different SKUs are slow at different stages",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-b1e5ded4-79d6-4ff4-bd0d-6386509efba9",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — run time varies by family and by line: whites are about twice as fast on Line 2 as Line 1, tints run at nearly the same speed on both; and different SKUs are slow at different stages.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"named\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"since I now realize different SKUs are slow at different stages\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jam",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "assertion": {
-            "value": "It stops the run on the line — \"Line 2 filler jammed at about nine in the morning, half a shift lost\" — forcing the wait-or-shift decision."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-147c2765-6bfb-4da0-9df9-b74a1c1049de",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"It stops the run on the line — \\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\" — forcing the wait-or-shift decision.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jam",
-          "slot": "how often it occurs, if it is an event rather than a step",
-          "precision": "range",
-          "rationale": "Line 2 filler, jams bad enough to stop the run.",
-          "assertion": {
-            "value": "Every week or two; low end once every three weeks, high end twice a week when temperamental. Not seasonal, but runs streaks of bad weeks."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "It's a \"every week or two\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 27,
-            "entryEnd": 27
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-ec5740e7-5068-4222-ad24-8396f5975657",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Every week or two; low end once every three weeks, high end twice a week when temperamental. Not seasonal, but runs streaks of bad weeks.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Line 2 filler, jams bad enough to stop the run.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It's a \\\\\\\"every week or two\\\\\\\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jam",
-          "slot": "how long it takes",
-          "precision": "spread",
-          "assertion": {
-            "value": "Typical repair thirty to forty-five minutes; one-in-ten quick ten to fifteen minutes (a false alarm); one-in-ten bad four to five hours, occasionally eating the rest of the shift, when something's actually broken in the filler head."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 27,
-            "entryEnd": 27
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 27,
-            "entryEnd": 27
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 27,
-            "entryEnd": 27
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-2884cc84-c616-4227-860a-d6b55a06c13d",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Typical repair thirty to forty-five minutes; one-in-ten quick ten to fifteen minutes (a false alarm); one-in-ten bad four to five hours, occasionally eating the rest of the shift, when something's actually broken in the filler head.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jam",
-          "slot": "who or what performs it",
-          "precision": "named",
-          "rationale": "Repair is done by a tech.",
-          "assertion": {
-            "value": "A tech — comes over, clears whatever's jammed, resets."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "tech comes over, clears whatever's jammed, resets, we're going again",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 27,
-            "entryEnd": 27
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-0548a680-8da8-47e9-ad72-fb1e264fac80",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A tech — comes over, clears whatever's jammed, resets.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"named\",\"rationale\":\"Repair is done by a tech.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"tech comes over, clears whatever's jammed, resets, we're going again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "filler jam",
-          "slot": "what it needs before it can start",
-          "precision": "spelled out",
-          "rationale": "At the time of the decision the repair length is unobservable to the scheduler.",
-          "assertion": {
-            "value": "Repair duration is not known at the time of the decision — \"which I never know at the time\"; only \"could be quick, could be long\"."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "how long is this repair *actually* going to take, which I never know at the time",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-8c6a716b-e09a-4977-94d9-f28ab74be7c4",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Repair duration is not known at the time of the decision — \\\"which I never know at the time\\\"; only \\\"could be quick, could be long\\\".\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"At the time of the decision the repair length is unobservable to the scheduler.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"how long is this repair *actually* going to take, which I never know at the time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "how long it takes",
-          "precision": "number",
-          "rationale": "Single figure given; no spread elicited.",
-          "assertion": {
-            "value": "Three hours for a tint-to-white washdown."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "I eat a tint-to-white washdown — three hours",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-a67683fd-0f34-4838-b48e-aa01f657a511",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours for a tint-to-white washdown.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Single figure given; no spread elicited.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what it needs before it can start",
-          "precision": "spelled out",
-          "assertion": {
-            "value": "A changeover of family on the line; the direction matters as much as the fact of it — tint-to-white is the expensive one, not the other way."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "the direction of the changeover matters as much as the fact of it",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-1b632a29-f1de-48e5-8f96-a5ef908c4a56",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A changeover of family on the line; the direction matters as much as the fact of it — tint-to-white is the expensive one, not the other way.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the direction of the changeover matters as much as the fact of it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what is lost when it changes the system's mode",
-          "precision": "named",
-          "rationale": "Hours and crew time are known; ramp scrap is named but unquantified.",
-          "assertion": {
-            "absence": "unknown-to-user",
-            "pointer": "ramp scrap after the washdown — \"which I don't have good numbers for but shouldn't be ignored\"; three hours of line and crew time are known"
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
+          "excerpt": "I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-9926552e-289f-4b4a-bc99-4cae34f1720a",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"ramp scrap after the washdown — \\\"which I don't have good numbers for but shouldn't be ignored\\\"; three hours of line and crew time are known\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"named\",\"rationale\":\"Hours and crew time are known; ramp scrap is named but unquantified.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "who or what performs it",
-          "precision": "named",
-          "assertion": {
-            "value": "The crew, on the line being changed over (Line 1 in the incident described)."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "the three-hour tint-to-white hit is real cost, crew time",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-06aac0a9-b270-4b13-a54f-37440769d685",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The crew, on the line being changed over (Line 1 in the incident described).\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "how long it takes",
-          "precision": "range",
-          "rationale": "\"a few hours for a white\" — no quantiles given, and the specialty wait is named but unquantified.",
-          "assertion": {
-            "value": "Usually a few hours for a white; \"nothing like the specialty wait\" — specialty duration not given."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-94948329-18e7-42fe-9538-a84fd72c225d",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; \\\"nothing like the specialty wait\\\" — specialty duration not given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"range\",\"rationale\":\"\\\"a few hours for a white\\\" — no quantiles given, and the specialty wait is named but unquantified.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "who or what performs it",
-          "precision": "named",
-          "assertion": {
-            "value": "The lab."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "sits in the lab's queue, gets checked",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-16b9c643-8b17-490e-bfe0-022a06efd914",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
-          "assertion": {
-            "value": "The order is released, goes to the warehouse, and ships against the due date."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+          "excerpt": "nobody's written that rule down either",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-34a374d1-d578-4bd6-9842-3db1fe2245f3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"If a Meridian job is sitting behind either changeover, the crew goes to whichever line has the Meridian job next, full stop — that decision doesn't even get discussed, everyone understands it without it being said out loud. Otherwise it's the scheduler's judgment call at the huddle about whose next job is tightest against its due date; failing that, it's whoever's line supervisor gets to the crew lead first. Nobody's written that rule down. In the recalled case Line 1 won on due-date tightness and Line 3 sat clean but idle close to two hours waiting its turn.\"},\"kind\":\"policy\",\"node\":\"who gets the crew\",\"precision\":\"spelled out\",\"rationale\":\"Tacit contention rule elicited from a real borderline case.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"nobody's written that rule down either\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the crew goes to whichever line has the Meridian job next, full stop\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -7766,67 +4797,39 @@
         "value": {
           "type": "slot-asserted",
           "kind": "policy",
-          "node": "who can absorb the slip",
-          "slot": "the rule as actually practiced",
+          "node": "who gets the crew",
+          "slot": "what overrides it",
           "precision": "spelled out",
           "sourceRegime": "practiced",
+          "rationale": "Named override with escalation path and stated rarity.",
           "assertion": {
-            "value": "Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first."
+            "value": "Maintenance will sometimes grab the crew mid-job for a genuine emergency — a line leaking, something needing isolating right now. That's rare and not the scheduler's call; if it's a real fight it goes over their head to the ops director."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+          "excerpt": "maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I use judgment on who can absorb the slip",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-821e00ef-6923-43b0-955b-3ed7d60ce127",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "policy",
-          "node": "who can absorb the slip",
-          "slot": "what overrides it",
-          "precision": "spelled out",
-          "assertion": {
-            "value": "The hard on-time line for an order like Meridian overrides the weighing — it is not a trade-off, and is only crossed if there's truly no way through."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+          "excerpt": "that's a maintenance-versus-me argument that goes over my head to the ops director if it's a real fight",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-6da3fa16-460b-4f07-aefc-f941d7118f76",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The hard on-time line for an order like Meridian overrides the weighing — it is not a trade-off, and is only crossed if there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-2e7ed53f-9682-4e83-9057-b59be73ca16c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Maintenance will sometimes grab the crew mid-job for a genuine emergency — a line leaking, something needing isolating right now. That's rare and not the scheduler's call; if it's a real fight it goes over their head to the ops director.\"},\"kind\":\"policy\",\"node\":\"who gets the crew\",\"precision\":\"spelled out\",\"rationale\":\"Named override with escalation path and stated rarity.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's a maintenance-versus-me argument that goes over my head to the ops director if it's a real fight\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -7834,117 +4837,115 @@
         "value": {
           "type": "slot-asserted",
           "kind": "constraint",
-          "node": "Meridian ships on time",
+          "node": "we just don't do that (Meridian)",
           "slot": "the limit and what happens when it is hit",
           "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Hard unwritten rule with named consequences; recorded as a rule, not a weight.",
           "assertion": {
-            "value": "Meridian ships on time, full stop; days late above zero is bad news the scheduler has to go explain. Only crossed \"unless there's truly no way through\"."
+            "value": "A Meridian order must not miss its due date — a \"we just don't do that\" rule, not a traded-off cost, and it doesn't flip in any range seen in a week. If it is hit: a fine, ammunition for Meridian to delist a line item at the next contract review, commercial gets calls and the boss gets calls."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "did Meridian ship on time or not, full stop",
+          "excerpt": "it's a \"we just don't do that\" rule, not a traded-off cost",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "days late on Meridian, and anything above zero is bad news I have to go explain",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
-          },
-          "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-731a5768-edc7-4858-ad42-50d2faf4b181",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian ships on time, full stop; days late above zero is bad news the scheduler has to go explain. Only crossed \\\"unless there's truly no way through\\\".\"},\"kind\":\"constraint\",\"node\":\"Meridian ships on time\",\"precision\":\"spelled out\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"days late on Meridian, and anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "firm",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "boundary-condition",
-          "node": "demand book from ERP",
-          "slot": "the starting state",
-          "precision": "spelled out",
-          "assertion": {
-            "value": "Orders start life as line items in the demand book once ERP spits it out, carrying quantity, due date and SKU."
-          }
-        }
-      },
-      "evidence": [
-        {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "excerpt": "it's a fine, and it's ammunition for them to delist a line item next contract review",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 9,
             "entryEnd": 9
           },
           "source": "user-affordance-payload"
-        }
-      ],
-      "epistemicStatus": "explicit",
-      "id": "capture-1bebb3ea-7788-477a-8127-593fe3fe6026",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders start life as line items in the demand book once ERP spits it out, carrying quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"spelled out\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-    },
-    {
-      "confidence": "hedged",
-      "content": {
-        "value": {
-          "type": "slot-asserted",
-          "kind": "boundary-condition",
-          "node": "demand book from ERP",
-          "slot": "the arrival or availability pattern",
-          "precision": "named",
-          "rationale": "The expert named the demand book as the source but the arrival pattern was flagged as still open when the session ended.",
-          "assertion": {
-            "absence": "deferred",
-            "pointer": "how orders arrive into the demand book — named as still open at the close of the session"
-          }
-        }
-      },
-      "evidence": [
+        },
         {
-          "excerpt": "it starts life as a line item in the demand book once ERP spits that out",
+          "excerpt": "Commercial gets calls, my boss gets calls.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 9,
             "entryEnd": 9
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-07cb7ca9-27c5-4395-bc9e-aaebc5811382",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"how orders arrive into the demand book — named as still open at the close of the session\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"named\",\"rationale\":\"The expert named the demand book as the source but the arrival pattern was flagged as still open when the session ended.\",\"slot\":\"the arrival or availability pattern\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-ea311e48-05a0-4c73-95b3-776de573bde2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian order must not miss its due date — a \\\"we just don't do that\\\" rule, not a traded-off cost, and it doesn't flip in any range seen in a week. If it is hit: a fine, ammunition for Meridian to delist a line item at the next contract review, commercial gets calls and the boss gets calls.\"},\"kind\":\"constraint\",\"node\":\"we just don't do that (Meridian)\",\"precision\":\"spelled out\",\"rationale\":\"Hard unwritten rule with named consequences; recorded as a rule, not a weight.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Commercial gets calls, my boss gets calls.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's a fine, and it's ammunition for them to delist a line item next contract review\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "data-binding",
-          "node": "stage-level times in the historian",
-          "slot": "the variable and its feed",
-          "precision": "named",
+          "kind": "validation-criterion",
+          "node": "recognize the shape of a real month",
+          "slot": "how the expert would know the model is right",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Acceptance bar stated as replay of last month's demand book against remembered outcomes.",
           "assertion": {
-            "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the historian; never pulled apart by the expert."
+            "value": "Feed it last month's demand book: it must land roughly where we actually landed on late orders that month — same rough number and same kind of misses (at least two Meridian scrapes and a handful of small ones). Saying we shipped everything on time would break trust immediately; getting the kind wrong (missing distributor orders when we actually missed a Meridian one) is worse than getting the count wrong. Then eyeball changeover hours on Line 2 and 3 — if Line 3 sits idle half the week waiting on the crew, which never happens in real life, it's missing something about how the crew gets shared. It must also reproduce the odd weeks — the ones where a breakdown chewed up two days on Line 1. No single number would be trusted; the shape of a real month must be recognizable."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+          "excerpt": "did it land roughly where we actually landed on late orders that month",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "same rough number and same *kind* of misses",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "we had at least two Meridian scrapes that month",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I'd want to eyeball changeover hours on Line 2 and 3 specifically",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the ones where a breakdown chewed up two days on Line 1",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I'd want to recognize the *shape* of a real month",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 15,
             "entryEnd": 15
           },
@@ -7952,66 +4953,88 @@
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the historian; never pulled apart by the expert.\"},\"kind\":\"data-binding\",\"node\":\"stage-level times in the historian\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-7d5ef992-e1a9-4aed-88ea-30f3bc49da30",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Feed it last month's demand book: it must land roughly where we actually landed on late orders that month — same rough number and same kind of misses (at least two Meridian scrapes and a handful of small ones). Saying we shipped everything on time would break trust immediately; getting the kind wrong (missing distributor orders when we actually missed a Meridian one) is worse than getting the count wrong. Then eyeball changeover hours on Line 2 and 3 — if Line 3 sits idle half the week waiting on the crew, which never happens in real life, it's missing something about how the crew gets shared. It must also reproduce the odd weeks — the ones where a breakdown chewed up two days on Line 1. No single number would be trusted; the shape of a real month must be recognizable.\"},\"kind\":\"validation-criterion\",\"node\":\"recognize the shape of a real month\",\"precision\":\"spelled out\",\"rationale\":\"Acceptance bar stated as replay of last month's demand book against remembered outcomes.\",\"slot\":\"how the expert would know the model is right\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd want to eyeball changeover hours on Line 2 and 3 specifically\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'd want to recognize the *shape* of a real month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did it land roughly where we actually landed on late orders that month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"same rough number and same *kind* of misses\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"we had at least two Meridian scrapes that month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "data-binding",
-          "node": "tank sizes from engineering drawings",
-          "slot": "the variable and its feed",
+          "kind": "activity",
+          "node": "breakdown on a line",
+          "slot": "how often it occurs, if it is an event rather than a step",
           "precision": "named",
+          "rationale": "Breakdowns named as needed for validation but rate and duration explicitly postponed to a later session.",
           "assertion": {
-            "value": "Holding tank sizes, especially mill-to-fill on Line 1 — feed: engineering drawings."
+            "absence": "deferred",
+            "pointer": "the master scheduler, next round — he offered to keep going on the arrivals side and the breakdowns"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+          "excerpt": "the ones where a breakdown chewed up two days on Line 1",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 15,
             "entryEnd": 15
           },
           "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Happy to keep going on the arrivals side and the breakdowns next round.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tank sizes, especially mill-to-fill on Line 1 — feed: engineering drawings.\"},\"kind\":\"data-binding\",\"node\":\"tank sizes from engineering drawings\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-fad3ee18-f276-4db0-b7e2-39bda4fb5066",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the master scheduler, next round — he offered to keep going on the arrivals side and the breakdowns\"},\"kind\":\"activity\",\"node\":\"breakdown on a line\",\"precision\":\"named\",\"rationale\":\"Breakdowns named as needed for validation but rate and duration explicitly postponed to a later session.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Happy to keep going on the arrivals side and the breakdowns next round.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "data-binding",
-          "node": "filler repair work-order times in the CMMS",
-          "slot": "the variable and its feed",
-          "precision": "named",
+          "kind": "objective",
+          "node": "wash down for the tint right then, or let Line 2 sit idle",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The decision the model exists to test, stated as a real recurring call.",
           "assertion": {
-            "value": "Actual filler repair durations — feed: maintenance work-order times in the CMMS; never pulled by the expert."
+            "value": "Whether to wash down for a tint order right away, or hold the line idle (about an hour) for an expected same-family white order that has not yet been released — a call made by gut three or four times a month, never verified."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "maintenance would have the actual work-order times in the CMMS but I've never pulled them",
+          "excerpt": "I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 27,
-            "entryEnd": 27
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 3,
+            "entryEnd": 3
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-a0429a34-1145-458d-bada-32d827d68959",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Actual filler repair durations — feed: maintenance work-order times in the CMMS; never pulled by the expert.\"},\"kind\":\"data-binding\",\"node\":\"filler repair work-order times in the CMMS\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maintenance would have the actual work-order times in the CMMS but I've never pulled them\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-df10185e-b1ea-4c96-a225-ba9f1a4870d3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whether to wash down for a tint order right away, or hold the line idle (about an hour) for an expected same-family white order that has not yet been released — a call made by gut three or four times a month, never verified.\"},\"kind\":\"objective\",\"node\":\"wash down for the tint right then, or let Line 2 sit idle\",\"precision\":\"spelled out\",\"rationale\":\"The decision the model exists to test, stated as a real recurring call.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -8019,272 +5042,372 @@
         "value": {
           "type": "slot-asserted",
           "kind": "objective",
-          "node": "wait or shift when Line 2 goes down",
-          "slot": "the question, in the expert's words",
+          "node": "wash down for the tint right then, or let Line 2 sit idle",
+          "slot": "what \"better\" means, and trade-off weights",
           "precision": "spelled out",
-          "rationale": "The expert wrote the question as he would type it into the tool.",
+          "sourceRegime": "practiced",
+          "rationale": "Ranking given, with an explicit refusal to supply an exchange rate for Meridian.",
           "assertion": {
-            "value": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\""
+            "value": "Judged on late-order count, with Meridian orders weighted extra heavy in practice though written nowhere; changeover hours and idle time are the scheduler's own concern, currently tracked separately. No numeric exchange rate for a Meridian miss exists — it would take commercial in a room to say it out loud."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"",
+          "excerpt": "what my boss actually looks at is late orders",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "The changeover hours and the idle time are more my own concern",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "If you need a number, you'd have to get commercial in a room and force them to say it out loud",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-48033ee8-f7eb-4615-b21f-018837fc9c5e",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\"\"},\"kind\":\"objective\",\"node\":\"wait or shift when Line 2 goes down\",\"precision\":\"spelled out\",\"rationale\":\"The expert wrote the question as he would type it into the tool.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-07d24f63-38a5-4252-9153-f5017bc5eb7c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judged on late-order count, with Meridian orders weighted extra heavy in practice though written nowhere; changeover hours and idle time are the scheduler's own concern, currently tracked separately. No numeric exchange rate for a Meridian miss exists — it would take commercial in a room to say it out loud.\"},\"kind\":\"objective\",\"node\":\"wash down for the tint right then, or let Line 2 sit idle\",\"precision\":\"spelled out\",\"rationale\":\"Ranking given, with an explicit refusal to supply an exchange rate for Meridian.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If you need a number, you'd have to get commercial in a room and force them to say it out loud\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The changeover hours and the idle time are more my own concern\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what my boss actually looks at is late orders\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "objective",
-          "node": "wait or shift when Line 2 goes down",
+          "node": "wash down for the tint right then, or let Line 2 sit idle",
           "slot": "the nodes it depends on",
           "precision": "named",
+          "rationale": "The scheduler named the scope of the decision: orders, three lines, the shared crew, the changeovers, the run, QA and the demand book.",
           "assertion": {
-            "value": "entity-type:order (demand book line item) — its due date and remaining quantity; entity-type:line (Line 1 / Line 2) — what is on Line 1 and how far through; entity-type:product family (white vs tint); activity:production run (mix, mill, tint, fill); activity:filler jam on Line 2 — repair length unknown at the time; activity:tint-to-white washdown — including its direction and ramp scrap; policy:who can absorb the slip — whose tint got bumped"
+            "value": [
+              "entity-type:order",
+              "entity-type:the three lines",
+              "entity-type:the changeover crew",
+              "boundary-condition:the demand book",
+              "activity:the run (mix, mill, fill and pack)",
+              "activity:QA hold",
+              "activity:white-to-tint changeover",
+              "activity:tint-to-white washdown",
+              "activity:specialty changeover",
+              "ordering/flow:release to cleared QA",
+              "policy:who gets the changeover crew",
+              "constraint:we just don't do that (Meridian)"
+            ]
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "What it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take",
+          "excerpt": "the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just \"an order got delayed.\"",
+          "excerpt": "it starts when the order lands in the demand book from ERP",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the due date is judged against when it clears, not when it comes off the line",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "explicit",
-      "id": "capture-88da9925-d922-48c3-8ea0-2c631df3ae3d",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:order (demand book line item) — its due date and remaining quantity; entity-type:line (Line 1 / Line 2) — what is on Line 1 and how far through; entity-type:product family (white vs tint); activity:production run (mix, mill, tint, fill); activity:filler jam on Line 2 — repair length unknown at the time; activity:tint-to-white washdown — including its direction and ramp scrap; policy:who can absorb the slip — whose tint got bumped\"},\"kind\":\"objective\",\"node\":\"wait or shift when Line 2 goes down\",\"precision\":\"named\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just \\\\\\\"an order got delayed.\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "inferred",
+      "id": "capture-fa7c6f67-b993-474b-bcb1-ea2fd55ae510",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:the three lines\",\"entity-type:the changeover crew\",\"boundary-condition:the demand book\",\"activity:the run (mix, mill, fill and pack)\",\"activity:QA hold\",\"activity:white-to-tint changeover\",\"activity:tint-to-white washdown\",\"activity:specialty changeover\",\"ordering/flow:release to cleared QA\",\"policy:who gets the changeover crew\",\"constraint:we just don't do that (Meridian)\"]},\"kind\":\"objective\",\"node\":\"wash down for the tint right then, or let Line 2 sit idle\",\"precision\":\"named\",\"rationale\":\"The scheduler named the scope of the decision: orders, three lines, the shared crew, the changeovers, the run, QA and the demand book.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts when the order lands in the demand book from ERP\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "wait or shift when Line 2 goes down",
-          "slot": "what \"better\" means, and trade-off weights",
+          "kind": "constraint",
+          "node": "we just don't do that (Meridian)",
+          "slot": "the limit and what happens when it is hit",
           "precision": "spelled out",
           "sourceRegime": "practiced",
+          "rationale": "A hard rule with a named consequence rather than a weight.",
           "assertion": {
-            "value": "Lexicographic: days late on Meridian first, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip."
+            "value": "A Meridian order must not be allowed to go late — not tradeable even against twenty small late orders. If hit: a fine, ammunition for Meridian to delist a line item at next contract review, calls to commercial and to the boss."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+          "excerpt": "it's not just \"late,\" it's a fine, and it's ammunition for them to delist a line item next contract review",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.",
+          "excerpt": "right now it's a \"we just don't do that\" rule, not a traded-off cost",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Even if you told me \"twenty small orders late\" versus \"one Meridian order late\" — I'd still not want to be the one who let Meridian slip.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-f53d8f62-375e-4af6-9aaa-fb903839993c",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lexicographic: days late on Meridian first, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"wait or shift when Line 2 goes down\",\"precision\":\"spelled out\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-354f9e2d-b3c7-4838-8dda-fd4f12d7f2c2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian order must not be allowed to go late — not tradeable even against twenty small late orders. If hit: a fine, ammunition for Meridian to delist a line item at next contract review, calls to commercial and to the boss.\"},\"kind\":\"constraint\",\"node\":\"we just don't do that (Meridian)\",\"precision\":\"spelled out\",\"rationale\":\"A hard rule with a named consequence rather than a weight.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Even if you told me \\\\\\\"twenty small orders late\\\\\\\" versus \\\\\\\"one Meridian order late\\\\\\\" — I'd still not want to be the one who let Meridian slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's not just \\\\\\\"late,\\\\\\\" it's a fine, and it's ammunition for them to delist a line item next contract review\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"right now it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "objective",
-          "node": "is the mill-to-fill tank on Line 1 slowing the line down",
-          "slot": "the nodes it depends on",
-          "precision": "named",
+          "kind": "constraint",
+          "node": "one-week planning horizon",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Horizon over which a plan must stay useful, with what fails beyond it.",
           "assertion": {
-            "value": "activity:production run (mix, mill, tint, fill) — stage-level mill speed versus fill speed on Line 1; constraint:small holding tanks between stages — the mill-to-fill tank size on Line 1; entity-type:product family (white vs tint) — different SKUs are slow at different stages"
+            "value": "The plan must hold for one week — the demand-book cycle, re-planned at the morning huddle; two weeks is soft and watched only for big specialty minimum runs; beyond a month the plan is refused because the book itself gets revised."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages",
+          "excerpt": "a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "if you ask me to hold a plan that's useful a month out, I'd say no — too much changes",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-ac435640-eea2-4ad6-9695-8e5408b4d852",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"activity:production run (mix, mill, tint, fill) — stage-level mill speed versus fill speed on Line 1; constraint:small holding tanks between stages — the mill-to-fill tank size on Line 1; entity-type:product family (white vs tint) — different SKUs are slow at different stages\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"named\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-a6f338a0-c3a7-4427-b125-8ce2759d26e6",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The plan must hold for one week — the demand-book cycle, re-planned at the morning huddle; two weeks is soft and watched only for big specialty minimum runs; beyond a month the plan is refused because the book itself gets revised.\"},\"kind\":\"constraint\",\"node\":\"one-week planning horizon\",\"precision\":\"spelled out\",\"rationale\":\"Horizon over which a plan must stay useful, with what fails beyond it.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if you ask me to hold a plan that's useful a month out, I'd say no — too much changes\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "data-binding",
-          "node": "stage-level times from the historian and tank sizes from engineering drawings",
-          "slot": "the variable and its feed",
-          "precision": "named",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "rationale": "Two axes of distinction the process treats apart: customer (Meridian vs small distributors) and colour family (white, tint, specialty).",
           "assertion": {
-            "absence": "deferred",
-            "pointer": "the historian (stage-by-stage times) and engineering drawings (tank sizes)"
+            "value": "Orders differ by customer — Meridian versus small distributors who slip 2-3 days with a phone call — and by colour family: white, tint, and specialty; same-family orders run into each other with no changeover, different families need the crew."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I don't have clean numbers for tank sizes or stage-by-stage rates.",
+          "excerpt": "a Meridian order, big white SKU, due Friday",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+          "excerpt": "three little late orders to distributors who slip 2-3 days with a phone call anyway",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 15,
-            "entryEnd": 15
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "same family, so no changeover needed, just a straight run-into-run",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Specialty is its own animal again",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-f5a658db-c8ec-4ca0-8a87-3ad252dee56d",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the historian (stage-by-stage times) and engineering drawings (tank sizes)\"},\"kind\":\"data-binding\",\"node\":\"stage-level times from the historian and tank sizes from engineering drawings\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have clean numbers for tank sizes or stage-by-stage rates.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-67a39f82-22f8-4b56-825d-03cfacb8a154",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders differ by customer — Meridian versus small distributors who slip 2-3 days with a phone call — and by colour family: white, tint, and specialty; same-family orders run into each other with no changeover, different families need the crew.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Two axes of distinction the process treats apart: customer (Meridian vs small distributors) and colour family (white, tint, specialty).\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Specialty is its own animal again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a Meridian order, big white SKU, due Friday\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"same family, so no changeover needed, just a straight run-into-run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"three little late orders to distributors who slip 2-3 days with a phone call anyway\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "data-binding",
-          "node": "filler repair times from the CMMS",
-          "slot": "the variable and its feed",
-          "precision": "named",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "state that rides along with each instance",
+          "precision": "spelled out",
+          "rationale": "Attributes named at release.",
           "assertion": {
-            "absence": "deferred",
-            "pointer": "maintenance work-order times in the CMMS"
+            "value": "SKU, quantity, and due date at release; a line it goes to (Meridian white basically always goes to Line 2)."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "maintenance would have the actual work-order times in the CMMS but I've never pulled them.",
+          "excerpt": "it's got an SKU, quantity, due date",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 27,
-            "entryEnd": 27
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I'll ask maintenance for the CMMS numbers on the filler too while I'm at it.",
+          "excerpt": "Meridian white basically always goes to Line 2",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 30,
-            "entryEnd": 30
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
-          "source": "user"
+          "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-618842bb-d23d-4371-ae57-73e5257ba215",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"maintenance work-order times in the CMMS\"},\"kind\":\"data-binding\",\"node\":\"filler repair times from the CMMS\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'll ask maintenance for the CMMS numbers on the filler too while I'm at it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":30,\\\"entryStart\\\":30,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user\\\"}\",\"{\\\"excerpt\\\":\\\"maintenance would have the actual work-order times in the CMMS but I've never pulled them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-a559675e-115d-4736-85ff-6160abb1a449",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"SKU, quantity, and due date at release; a line it goes to (Meridian white basically always goes to Line 2).\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Attributes named at release.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "boundary-condition",
-          "node": "demand book line items out of ERP",
-          "slot": "the starting state",
-          "precision": "spelled out",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "how many there are, or the population's shape",
+          "precision": "range",
+          "rationale": "Weekly population given as a low and high.",
           "assertion": {
-            "value": "An order starts life as a line item in the demand book once ERP spits that out, carrying quantity, due date and SKU."
+            "value": "30 orders in a quiet week, 55–60 in a busy one"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+          "excerpt": "quiet week might be 30 orders, a busy one pushes 55–60",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 27,
+            "entryEnd": 27
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-538fb022-2495-46bb-8661-8e1f38c802bf",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order starts life as a line item in the demand book once ERP spits that out, carrying quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book line items out of ERP\",\"precision\":\"spelled out\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-3caeda61-ac3c-4724-905a-3f76e1bfd924",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"30 orders in a quiet week, 55–60 in a busy one\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"range\",\"rationale\":\"Weekly population given as a low and high.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"quiet week might be 30 orders, a busy one pushes 55–60\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "entity-type",
-          "node": "order (demand book line item)",
-          "slot": "state that rides along with each instance",
-          "precision": "spelled out",
-          "rationale": "Quantity, due date and SKU are explicit; remaining quantity and customer identity are named later as things the answer hangs on.",
+          "node": "the changeover crew",
+          "slot": "how many there are, or the population's shape",
+          "precision": "number",
+          "rationale": "Single contended resource with a stated size.",
           "assertion": {
-            "value": "Quantity, due date, SKU; plus remaining quantity and the customer's identity, which the expert weighs when an order slips."
+            "value": "one crew of two techs"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+          "excerpt": "there's one crew, two techs, covering all three lines",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; plus remaining quantity and the customer's identity, which the expert weighs when an order slips.\"},\"kind\":\"entity-type\",\"node\":\"order (demand book line item)\",\"precision\":\"spelled out\",\"rationale\":\"Quantity, due date and SKU are explicit; remaining quantity and customer identity are named later as things the answer hangs on.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-317a5e27-6e23-4fdb-80c5-2160e7622b9c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"one crew of two techs\"},\"kind\":\"entity-type\",\"node\":\"the changeover crew\",\"precision\":\"number\",\"rationale\":\"Single contended resource with a stated size.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -8292,29 +5415,38 @@
         "value": {
           "type": "slot-asserted",
           "kind": "entity-type",
-          "node": "order (demand book line item)",
+          "node": "the changeover crew",
           "slot": "the distinctions the process treats apart",
           "precision": "spelled out",
-          "sourceRegime": "practiced",
+          "rationale": "The crew is treated as one indivisible shared resource across all three lines, not split by line.",
           "assertion": {
-            "value": "Orders are treated apart by whose order it is: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem."
+            "value": "One changeover crew, treated as a single shared unit across all three lines — either free or tied up on another line; no distinction drawn between the two techs."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.",
+          "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\"",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-5d5f862f-c18c-4501-b544-76735d28e004",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders are treated apart by whose order it is: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem.\"},\"kind\":\"entity-type\",\"node\":\"order (demand book line item)\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-afdf937d-5049-4656-a68a-f0b5c1a15511",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One changeover crew, treated as a single shared unit across all three lines — either free or tied up on another line; no distinction drawn between the two techs.\"},\"kind\":\"entity-type\",\"node\":\"the changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"The crew is treated as one indivisible shared resource across all three lines, not split by line.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if I wash Line 2 down now, I'm also asking \\\\\\\"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -8322,223 +5454,274 @@
         "value": {
           "type": "slot-asserted",
           "kind": "entity-type",
-          "node": "product family (white vs tint)",
-          "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
+          "node": "the three lines",
+          "slot": "how many there are, or the population's shape",
+          "precision": "number",
+          "rationale": "Line count stated.",
           "assertion": {
-            "value": "Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step; tints run at nearly the same speed on both lines while whites do not; and the tint-to-white changeover direction is the expensive one."
+            "value": "three lines (Line 1, Line 2, Line 3)"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+          "excerpt": "covering all three lines",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
+          "excerpt": "the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-7f6b8be1-6336-465f-8e11-36a5277d51bd",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step; tints run at nearly the same speed on both lines while whites do not; and the tint-to-white changeover direction is the expensive one.\"},\"kind\":\"entity-type\",\"node\":\"product family (white vs tint)\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-0b6c3aeb-8421-41f3-a77b-0db90e32bc06",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"three lines (Line 1, Line 2, Line 3)\"},\"kind\":\"entity-type\",\"node\":\"the three lines\",\"precision\":\"number\",\"rationale\":\"Line count stated.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "entity-type",
-          "node": "line (Line 1 / Line 2)",
+          "node": "the three lines",
           "slot": "the distinctions the process treats apart",
-          "precision": "spelled out",
+          "precision": "named",
+          "sourceRegime": "practiced",
+          "rationale": "Lines are distinguished by what tends to run on them; whether routing is hard or habitual was not established.",
           "assertion": {
-            "value": "Line 1 is the slower machine on whites (add maybe fifty, sixty percent to Line 2's times); on tints Line 1 and Line 2 run at nearly the same speed."
+            "value": "Line 1, Line 2, Line 3; Meridian white basically always goes to Line 2, specialty runs seen on Line 1 — stated as practice, not established as a hard routing rule."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
+          "excerpt": "Meridian white basically always goes to Line 2",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 18,
             "entryEnd": 18
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed",
+          "excerpt": "Line 1 had just finished a specialty run",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-1a83c9c6-a8f8-4ece-a5d4-53b81bf8cc9b",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 is the slower machine on whites (add maybe fifty, sixty percent to Line 2's times); on tints Line 1 and Line 2 run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-4c36d6d9-17da-4e86-be1a-dc07ef07ff83",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1, Line 2, Line 3; Meridian white basically always goes to Line 2, specialty runs seen on Line 1 — stated as practice, not established as a hard routing rule.\"},\"kind\":\"entity-type\",\"node\":\"the three lines\",\"precision\":\"named\",\"rationale\":\"Lines are distinguished by what tends to run on them; whether routing is hard or habitual was not established.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 had just finished a specialty run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "entity-type",
-          "node": "line (Line 1 / Line 2)",
-          "slot": "how many there are, or the population's shape",
-          "precision": "number",
-          "rationale": "Only Line 1 and Line 2 are ever named; the count itself was never stated as a figure.",
+          "kind": "boundary-condition",
+          "node": "the demand book",
+          "slot": "the arrival or availability pattern",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Weekly drop plus mid-week additions, given as counts and regularity, not as a distribution.",
           "assertion": {
-            "value": "Two lines (Line 1 and Line 2), each comprising separate mix, mill, tint and fill kit with small holding tanks between."
+            "value": "Official Monday-morning release of 30-something to 60 orders (quiet week 30, busy 55–60), plus additions pushed in by sales and commercial through the week, sometimes daily; Meridian close to weekly and regular, small distributors are what swing; not noticeably seasonal, just lumpy by who is restocking."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+          "excerpt": "The book officially releases Monday morning — that's the big drop, 30-something to 60 orders depending on the week.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Sales and commercial push in additions through the week, sometimes daily, when a customer calls with something last-minute or an order gets confirmed late.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Meridian in particular is fairly regular, close to weekly, but the smaller distributors are the ones that swing.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 27,
+            "entryEnd": 27
           },
           "source": "user-affordance-payload"
         }
       ],
-      "epistemicStatus": "inferred",
-      "id": "capture-e6ae51ed-e1f6-45f3-aab1-c4bca2a979e8",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two lines (Line 1 and Line 2), each comprising separate mix, mill, tint and fill kit with small holding tanks between.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"number\",\"rationale\":\"Only Line 1 and Line 2 are ever named; the count itself was never stated as a figure.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "epistemicStatus": "explicit",
+      "id": "capture-cf61a51f-f803-407f-a6b4-9ffc46972ab0",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Official Monday-morning release of 30-something to 60 orders (quiet week 30, busy 55–60), plus additions pushed in by sales and commercial through the week, sometimes daily; Meridian close to weekly and regular, small distributors are what swing; not noticeably seasonal, just lumpy by who is restocking.\"},\"kind\":\"boundary-condition\",\"node\":\"the demand book\",\"precision\":\"range\",\"rationale\":\"Weekly drop plus mid-week additions, given as counts and regularity, not as a distribution.\",\"slot\":\"the arrival or availability pattern\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian in particular is fairly regular, close to weekly, but the smaller distributors are the ones that swing.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Sales and commercial push in additions through the week, sometimes daily, when a customer calls with something last-minute or an order gets confirmed late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The book officially releases Monday morning — that's the big drop, 30-something to 60 orders depending on the week.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "order flow from demand book to ship",
-          "slot": "the order things happen in",
+          "kind": "boundary-condition",
+          "node": "the demand book",
+          "slot": "the starting state",
           "precision": "spelled out",
+          "rationale": "Entry point into the scheduler's world.",
           "assertion": {
-            "value": "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship against the due date."
+            "value": "Orders land in the demand book from ERP with SKU, quantity and due date — that state is 'released' and is where the order enters the scheduler's world."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+          "excerpt": "it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship against the due date.\"},\"kind\":\"ordering/flow\",\"node\":\"order flow from demand book to ship\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-0693c605-2dd0-4019-a36a-25c0565e22a4",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders land in the demand book from ERP with SKU, quantity and due date — that state is 'released' and is where the order enters the scheduler's world.\"},\"kind\":\"boundary-condition\",\"node\":\"the demand book\",\"precision\":\"spelled out\",\"rationale\":\"Entry point into the scheduler's world.\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "line occupancy across the four stages",
-          "slot": "the order things happen in",
+          "kind": "activity",
+          "node": "the run (mix, mill, fill and pack)",
+          "slot": "what it needs before it can start",
           "precision": "spelled out",
-          "sourceRegime": "prescribed",
+          "rationale": "Preconditions from the walkthrough.",
           "assertion": {
-            "value": "On the sheet, Line 2 is one row: the order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done."
+            "value": "The line must be free of the job ahead of it; if the previous job is the same family it runs straight into it with no changeover, otherwise a changeover by the crew must have been done first."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+          "excerpt": "It had to wait its turn behind whatever was already running on Line 2.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet, Line 2 is one row: the order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done.\"},\"kind\":\"ordering/flow\",\"node\":\"line occupancy across the four stages\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-83c1866f-aabf-4ce4-8836-7a803a5521cd",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line must be free of the job ahead of it; if the previous job is the same family it runs straight into it with no changeover, otherwise a changeover by the crew must have been done first.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"spelled out\",\"rationale\":\"Preconditions from the walkthrough.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It had to wait its turn behind whatever was already running on Line 2.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "ordering/flow",
-          "node": "line occupancy across the four stages",
-          "slot": "the order things happen in",
+          "kind": "activity",
+          "node": "the run (mix, mill, fill and pack)",
+          "slot": "what it produces or changes",
           "precision": "spelled out",
-          "sourceRegime": "practiced",
+          "rationale": "Output of the run stage.",
           "assertion": {
-            "value": "Physically the stages overlap: the mixer can start the next order's batch while the fill head is still finishing the last one, if there is room in the holding tank between mix and mill, or mill and fill; the crew will get a head start on mixing if the tank ahead has space."
+            "value": "Mix, mill, tint stage (skipped for a white), fill and pack — producing finished, packed product that goes into QA hold."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.",
+          "excerpt": "Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Once fill and pack was done, it went into QA hold.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-7f9ac97e-375b-4de3-bbcd-b65e5c7427a6",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically the stages overlap: the mixer can start the next order's batch while the fill head is still finishing the last one, if there is room in the holding tank between mix and mill, or mill and fill; the crew will get a head start on mixing if the tank ahead has space.\"},\"kind\":\"ordering/flow\",\"node\":\"line occupancy across the four stages\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-d705d5d1-f8ed-4788-9c21-b426a1edf48f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Mix, mill, tint stage (skipped for a white), fill and pack — producing finished, packed product that goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"spelled out\",\"rationale\":\"Output of the run stage.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "constraint",
-          "node": "small holding tanks between stages",
-          "slot": "the limit and what happens when it is hit",
-          "precision": "spelled out",
+          "kind": "activity",
+          "node": "the run (mix, mill, fill and pack)",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "Performed by the line itself; the scheduler does not track the operators.",
           "assertion": {
-            "value": "The tanks are small — especially the one between mill and fill on Line 1 — and when a tank is full, mixing has to wait; how much overlap happens or how often it is blocked is not tracked."
+            "value": "The production line (this order ran on Line 2); no crew involvement for a run-into-run"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+          "excerpt": "Meridian white basically always goes to Line 2",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 12,
-            "entryEnd": 12
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I don't watch this minute by minute",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-66fbb371-91b7-41db-b437-5bd207d08aed",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The tanks are small — especially the one between mill and fill on Line 1 — and when a tank is full, mixing has to wait; how much overlap happens or how often it is blocked is not tracked.\"},\"kind\":\"constraint\",\"node\":\"small holding tanks between stages\",\"precision\":\"spelled out\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-61b6af85-58ca-4367-a45a-1f9d20d9a04b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The production line (this order ran on Line 2); no crew involvement for a run-into-run\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"named\",\"rationale\":\"Performed by the line itself; the scheduler does not track the operators.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't watch this minute by minute\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -8546,28 +5729,39 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "allocation onto a line and a slot in the week",
-          "slot": "who or what performs it",
-          "precision": "named",
+          "node": "the run (mix, mill, fill and pack)",
+          "slot": "how long it takes",
+          "precision": "spread",
+          "rationale": "Only a single recalled day-long run; run rates deferred to the production sheet.",
           "assertion": {
-            "value": "The master scheduler, on the sheet."
+            "absence": "deferred",
+            "pointer": "the sheet (production sheet, to be brought next session) — one recalled instance: a big-volume order started Wednesday morning and wrapped Wednesday evening"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "excerpt": "I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "bring the sheet next time, it'll answer the run-rate question faster than I can talk through it",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 30,
+            "entryEnd": 30
+          },
+          "source": "user"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-8da19d62-c082-41f6-ac55-f28afe266a8c",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler, on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation onto a line and a slot in the week\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-a584bc16-c132-431c-8c66-64c32cf5715a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the sheet (production sheet, to be brought next session) — one recalled instance: a big-volume order started Wednesday morning and wrapped Wednesday evening\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"spread\",\"rationale\":\"Only a single recalled day-long run; run rates deferred to the production sheet.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"bring the sheet next time, it'll answer the run-rate question faster than I can talk through it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":30,\\\"entryStart\\\":30,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -8575,28 +5769,38 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "allocation onto a line and a slot in the week",
+          "node": "QA hold",
           "slot": "what it needs before it can start",
           "precision": "spelled out",
+          "rationale": "Entry condition for QA.",
           "assertion": {
-            "value": "A line item in the demand book out of ERP, with quantity, due date and SKU."
+            "value": "Fill and pack complete; the batch is palletized and moved off the line into the queue for the lab."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "excerpt": "Once fill and pack was done, it went into QA hold.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "physically it's palletized and moved off the line, into the queue for the lab",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-995374a1-2d25-4690-8397-b342f46ebf02",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book out of ERP, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation onto a line and a slot in the week\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-b6778bf0-5fd3-46a9-ac25-be90e5fb6535",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Fill and pack complete; the batch is palletized and moved off the line into the queue for the lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Entry condition for QA.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"physically it's palletized and moved off the line, into the queue for the lab\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -8604,86 +5808,107 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "allocation onto a line and a slot in the week",
+          "node": "QA hold",
           "slot": "what it produces or changes",
           "precision": "spelled out",
+          "rationale": "QA clearance is the point the due date is judged at.",
           "assertion": {
-            "value": "The order is placed onto a named line and a slot in the week."
+            "value": "The order clears QA and ships; the due date is judged against when it clears, not when it comes off the line."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "allocate it onto a line and a slot in the week",
+          "excerpt": "It cleared and shipped Thursday",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the due date is judged against when it clears, not when it comes off the line",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-3cc84392-4ed4-4804-8a7c-db07d384a8b2",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is placed onto a named line and a slot in the week.\"},\"kind\":\"activity\",\"node\":\"allocation onto a line and a slot in the week\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-733f30a6-e231-4fd2-a9a1-ef584ad1d139",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order clears QA and ships; the due date is judged against when it clears, not when it comes off the line.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"QA clearance is the point the due date is judged at.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It cleared and shipped Thursday\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "production run (mix, mill, tint, fill)",
-          "slot": "what it needs before it can start",
-          "precision": "spelled out",
+          "node": "QA hold",
+          "slot": "how long it takes",
+          "precision": "number",
+          "rationale": "A single typical figure for white only; no range given and lab backlog acknowledged as a separate driver.",
           "assertion": {
-            "value": "The order allocated to a line and a slot in the week; then it runs the same four stages every product goes through — mix, mill, tint, fill and pack."
+            "value": "about four hours for a white"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through",
+          "excerpt": "normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "a batch can be done Tuesday and still ship late if the lab's backed up",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-289ac648-e939-4e62-ad46-a17b112402d4",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order allocated to a line and a slot in the week; then it runs the same four stages every product goes through — mix, mill, tint, fill and pack.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-a7b79e99-0816-4a9d-b4cb-ce91e9933dd4",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"about four hours for a white\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"number\",\"rationale\":\"A single typical figure for white only; no range given and lab backlog acknowledged as a separate driver.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a batch can be done Tuesday and still ship late if the lab's backed up\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "production run (mix, mill, tint, fill)",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
+          "node": "QA hold",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
+          "rationale": "Specialty implied to have a longer hold; the figure itself was not given.",
           "assertion": {
-            "value": "Packed product coming off the fill line, which then goes into QA hold."
+            "value": "Yes — a white is not the long specialty hold; the specialty hold duration was not given."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Once it comes off the fill line it goes into QA hold",
+          "excerpt": "nothing exotic about it chemically, so it's not the long specialty hold",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-5376c084-3889-476f-adab-b09a038ded28",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Packed product coming off the fill line, which then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-7e1b1ff2-d9f7-4999-b260-ab694dc84fce",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a white is not the long specialty hold; the specialty hold duration was not given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Specialty implied to have a longer hold; the figure itself was not given.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nothing exotic about it chemically, so it's not the long specialty hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -8691,76 +5916,78 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "production run (mix, mill, tint, fill)",
+          "node": "white-to-tint changeover",
           "slot": "how long it takes",
           "precision": "spread",
           "sourceRegime": "practiced",
+          "rationale": "Best case, bad-day case and typical band, elicited quickest/longest then typical.",
           "assertion": {
-            "value": "White, Meridian-sized, on Line 2, clean of breakdowns: typical eight to nine hours mix-to-last-pack; one in ten worse nine to ten hours; one in ten better maybe six hours."
+            "value": "quickest ~40 minutes (crew right there, nothing fights them); typical 45 minutes to an hour; bad day about an hour twenty"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing.",
+          "excerpt": "White-to-tint on Line 2 — quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes. Longest, if they're stretched thin or something's stuck, I've seen it drag past an hour, call it an hour twenty on a bad day. Typically though it lands around 45 minutes to an hour.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 21,
-            "entryEnd": 21
-          },
-          "source": "user-affordance-payload"
-        },
-        {
-          "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
-          "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-b9dfddf9-52d8-433e-81b8-5611e7356c34",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, Meridian-sized, on Line 2, clean of breakdowns: typical eight to nine hours mix-to-last-pack; one in ten worse nine to ten hours; one in ten better maybe six hours.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-7f1eba90-5fc4-4103-8f8b-fe4400be2ebf",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"quickest ~40 minutes (crew right there, nothing fights them); typical 45 minutes to an hour; bad day about an hour twenty\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover\",\"precision\":\"spread\",\"rationale\":\"Best case, bad-day case and typical band, elicited quickest/longest then typical.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"White-to-tint on Line 2 — quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes. Longest, if they're stretched thin or something's stuck, I've seen it drag past an hour, call it an hour twenty on a bad day. Typically though it lands around 45 minutes to an hour.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "production run (mix, mill, tint, fill)",
-          "slot": "how long it takes",
-          "precision": "spread",
+          "node": "white-to-tint changeover",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "rationale": "Crew availability gates the changeover.",
           "assertion": {
-            "value": "Same white order on Line 1: typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten — add maybe fifty, sixty percent to Line 2. (Stated before the breakdown/clean-run split was drawn, so the worse figure may still fold in jams.)"
+            "value": "The changeover crew must be free; if they are tied up on another line the wash-down option is not available and the line queues behind whoever else needs them."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+          "excerpt": "The changeover crew is the shared thing",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\"",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "If they're tied up elsewhere, my \"wash down now\" option isn't even really available",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-27ae8fdf-c227-4160-a1a5-e85530156938",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Same white order on Line 1: typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten — add maybe fifty, sixty percent to Line 2. (Stated before the breakdown/clean-run split was drawn, so the worse figure may still fold in jams.)\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-855f61a1-da7f-4d31-a70e-c72dc905afb3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The changeover crew must be free; if they are tied up on another line the wash-down option is not available and the line queues behind whoever else needs them.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover\",\"precision\":\"spelled out\",\"rationale\":\"Crew availability gates the changeover.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if I wash Line 2 down now, I'm also asking \\\\\\\"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -8768,28 +5995,29 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "production run (mix, mill, tint, fill)",
-          "slot": "how long it takes",
-          "precision": "range",
+          "node": "white-to-tint changeover",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "Performer named.",
           "assertion": {
-            "value": "A tint run on either line: eight to ten hours typical, without the Line 1 / Line 2 gap."
+            "value": "entity-type:the changeover crew (two techs)"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "so a tint run on either line looks more like eight to ten hours typical, without that big gap",
+          "excerpt": "there's one crew, two techs, covering all three lines",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-7bd393bf-3f05-4aa1-b15a-968c293b076f",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A tint run on either line: eight to ten hours typical, without the Line 1 / Line 2 gap.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"range\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"so a tint run on either line looks more like eight to ten hours typical, without that big gap\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-e6a85b0b-ac81-4bbd-b62c-40c5d2073bba",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:the changeover crew (two techs)\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover\",\"precision\":\"named\",\"rationale\":\"Performer named.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -8797,37 +6025,38 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "production run (mix, mill, tint, fill)",
+          "node": "white-to-tint changeover",
           "slot": "whether its quantities vary by type",
           "precision": "named",
+          "rationale": "Explicit answer that duration varies by direction and family.",
           "assertion": {
-            "value": "Yes — run time varies by product family and line: whites are much slower on Line 1, tints are nearly the same speed on either line; the \"Line 2 is twice as fast\" figure is really a whites number. No explanation for the tint case; it is sheet-derived."
+            "value": "Yes — direction absolutely matters and is not symmetric: white-to-tint is the cheap direction, tint-to-white the expensive one, and specialty is its own animal again."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.",
+          "excerpt": "Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+          "excerpt": "Specialty is its own animal again",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 18,
-            "entryEnd": 18
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-ef41e72f-3126-4003-82b2-686b5f8bfdfb",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — run time varies by product family and line: whites are much slower on Line 1, tints are nearly the same speed on either line; the \\\"Line 2 is twice as fast\\\" figure is really a whites number. No explanation for the tint case; it is sheet-derived.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"named\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-80836a1b-2883-487f-8ca6-451049d38c30",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — direction absolutely matters and is not symmetric: white-to-tint is the cheap direction, tint-to-white the expensive one, and specialty is its own animal again.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover\",\"precision\":\"named\",\"rationale\":\"Explicit answer that duration varies by direction and family.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Specialty is its own animal again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -8835,29 +6064,30 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "filler jam on Line 2",
-          "slot": "how often it occurs, if it is an event rather than a step",
-          "precision": "range",
+          "node": "tint-to-white washdown",
+          "slot": "how long it takes",
+          "precision": "spread",
           "sourceRegime": "practiced",
+          "rationale": "Best, typical and bad-day values given.",
           "assertion": {
-            "value": "Every week or two; low end once every three weeks, high end twice a week. Not seasonal, but runs streaks of bad weeks."
+            "value": "quickest about two and a half hours (everything clean, crew fresh); three hours typical — the number used on the sheet; toward four hours on a bad day with dried pigment in a fitting"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "It's a \"every week or two\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.",
+          "excerpt": "Quickest I've seen that go is maybe two and a half hours if everything's clean and the crew's fresh. On a bad day — dried pigment in a fitting, whatever — it's crept toward four hours. Call it three hours typical, and that's the number I actually use on the sheet.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 27,
-            "entryEnd": 27
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-4fa34ba3-82e3-4a4a-ad28-362765a40046",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Every week or two; low end once every three weeks, high end twice a week. Not seasonal, but runs streaks of bad weeks.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"range\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It's a \\\\\\\"every week or two\\\\\\\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-9e9768db-8715-4ef2-93d5-ebad8b376a90",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"quickest about two and a half hours (everything clean, crew fresh); three hours typical — the number used on the sheet; toward four hours on a bad day with dried pigment in a fitting\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spread\",\"rationale\":\"Best, typical and bad-day values given.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Quickest I've seen that go is maybe two and a half hours if everything's clean and the crew's fresh. On a bad day — dried pigment in a fitting, whatever — it's crept toward four hours. Call it three hours typical, and that's the number I actually use on the sheet.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -8865,29 +6095,29 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "filler jam on Line 2",
-          "slot": "how long it takes",
-          "precision": "spread",
-          "sourceRegime": "practiced",
+          "node": "tint-to-white washdown",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Purpose and consequence of omission.",
           "assertion": {
-            "value": "Repair: typical thirty to forty-five minutes; quick one-in-ten ten to fifteen minutes (basically a false alarm); bad one-in-ten four to five hours when something is actually broken in the filler head, occasionally eating the rest of the shift."
+            "value": "A full washdown of the line so no pigment is left behind; any pigment left behind wrecks a white batch."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift.",
+          "excerpt": "Any pigment left behind wrecks a white batch, so that's a full washdown.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 27,
-            "entryEnd": 27
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-2f670377-be1e-4275-9e46-24dd13316300",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Repair: typical thirty to forty-five minutes; quick one-in-ten ten to fifteen minutes (basically a false alarm); bad one-in-ten four to five hours when something is actually broken in the filler head, occasionally eating the rest of the shift.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-a2b17c97-2e39-49b0-b8ff-3c5237927a0d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A full washdown of the line so no pigment is left behind; any pigment left behind wrecks a white batch.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Purpose and consequence of omission.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Any pigment left behind wrecks a white batch, so that's a full washdown.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
@@ -8895,396 +6125,568 @@
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "filler jam on Line 2",
+          "node": "tint-to-white washdown",
           "slot": "who or what performs it",
           "precision": "named",
+          "rationale": "Same shared crew.",
           "assertion": {
-            "value": "A tech comes over, clears whatever's jammed and resets."
+            "value": "entity-type:the changeover crew (two techs)"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "tech comes over, clears whatever's jammed, resets, we're going again",
+          "excerpt": "there's one crew, two techs, covering all three lines",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "so that's a full washdown",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 27,
-            "entryEnd": 27
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-9dc62989-7db7-4e58-baf1-b9ed0400d9a2",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A tech comes over, clears whatever's jammed and resets.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"tech comes over, clears whatever's jammed, resets, we're going again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-d15d35b6-900e-411c-a1cd-46a63c50d4c8",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:the changeover crew (two techs)\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"named\",\"rationale\":\"Same shared crew.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"so that's a full washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "filler jam on Line 2",
-          "slot": "what it produces or changes",
-          "precision": "spelled out",
+          "node": "specialty changeover",
+          "slot": "how long it takes",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Low, typical and upper values given but explicitly less closely observed than the white/tint ones.",
           "assertion": {
-            "value": "The run stops and time is lost inside the run — the big bad days (twelve to thirteen hours) are the breakdown showing up inside the run rather than the run being slow."
+            "value": "around two hours normally in either direction; as short as an hour forty for a specialty-to-specialty colour change rather than a full family switch; not seen much longer than two and a half hours — expert notes he does not watch these as closely"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
+          "excerpt": "going in or coming out of a specialty run, either direction, it's around two hours normally. I've seen it shorter, maybe an hour forty if it's a specialty-to-specialty color change rather than a full family switch. I haven't seen it run much longer than two and a half hours",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
+          "excerpt": "I don't watch specialty changeovers as closely as I watch the white-tint ones",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 21,
-            "entryEnd": 21
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-b92eccd9-e2ad-41a9-abce-bb1cf8b3c328",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The run stops and time is lost inside the run — the big bad days (twelve to thirteen hours) are the breakdown showing up inside the run rather than the run being slow.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-1ca63cf0-a571-45d3-bf90-d86a3cbfca06",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"around two hours normally in either direction; as short as an hour forty for a specialty-to-specialty colour change rather than a full family switch; not seen much longer than two and a half hours — expert notes he does not watch these as closely\"},\"kind\":\"activity\",\"node\":\"specialty changeover\",\"precision\":\"range\",\"rationale\":\"Low, typical and upper values given but explicitly less closely observed than the white/tint ones.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't watch specialty changeovers as closely as I watch the white-tint ones\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"going in or coming out of a specialty run, either direction, it's around two hours normally. I've seen it shorter, maybe an hour forty if it's a specialty-to-specialty color change rather than a full family switch. I haven't seen it run much longer than two and a half hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "how long it takes",
-          "precision": "number",
+          "node": "specialty changeover",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
+          "rationale": "Direction does not matter for specialty, unlike white/tint.",
           "assertion": {
-            "value": "Three hours."
+            "value": "Direction does not matter for specialty — going in or coming out, either direction is around two hours; only specialty-to-specialty colour changes are shorter."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+          "excerpt": "going in or coming out of a specialty run, either direction, it's around two hours normally",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 24,
+            "entryEnd": 24
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-55e95600-febe-4c98-8859-a56eb23ab156",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-f2012538-6414-4791-b25b-abdcdb6398c1",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Direction does not matter for specialty — going in or coming out, either direction is around two hours; only specialty-to-specialty colour changes are shorter.\"},\"kind\":\"activity\",\"node\":\"specialty changeover\",\"precision\":\"named\",\"rationale\":\"Direction does not matter for specialty, unlike white/tint.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"going in or coming out of a specialty run, either direction, it's around two hours normally\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "speculative",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what is lost when it changes the system's mode",
-          "precision": "number",
+          "node": "a breakdown on a line",
+          "slot": "how often it occurs, if it is an event rather than a step",
+          "precision": "range",
+          "rationale": "Only one recalled incident; rate explicitly deferred to a later session.",
           "assertion": {
-            "value": "Three hours of crew time with Line 1 out of anything else for that window; direction matters — tint-to-white is the expensive one, not the other way."
+            "absence": "deferred",
+            "pointer": "next round with the expert (breakdowns) — one recalled instance: a breakdown chewed up two days on Line 1 in the odd weeks the model must reproduce"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+          "excerpt": "a breakdown chewed up two days on Line 1",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
+          "excerpt": "Happy to keep going on the arrivals side and the breakdowns next round.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 27,
+            "entryEnd": 27
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-29c03a62-4be2-4dc2-852e-bfeab6770f1b",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of crew time with Line 1 out of anything else for that window; direction matters — tint-to-white is the expensive one, not the other way.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-17385ca7-771e-4ab9-a5a6-ac70e9886b75",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"next round with the expert (breakdowns) — one recalled instance: a breakdown chewed up two days on Line 1 in the odd weeks the model must reproduce\"},\"kind\":\"activity\",\"node\":\"a breakdown on a line\",\"precision\":\"range\",\"rationale\":\"Only one recalled incident; rate explicitly deferred to a later session.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Happy to keep going on the arrivals side and the breakdowns next round.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "tint-to-white washdown",
-          "slot": "what it produces or changes",
+          "kind": "ordering/flow",
+          "node": "release to cleared QA",
+          "slot": "the order things happen in",
           "precision": "spelled out",
+          "rationale": "The end-to-end sequence from the walked slice.",
           "assertion": {
-            "absence": "unknown-to-user",
-            "pointer": "ramp scrap after the washdown — real product lost on top of the hours; no good numbers and no source named"
+            "value": "Lands in the demand book on the Monday release and is assigned to a line's column → waits its turn behind whatever is running on that line (with a changeover by the crew if the family changes) → runs: mix, mill, tint stage, fill and pack → palletized off the line into QA hold, queued for the lab → clears QA and ships."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.",
+          "excerpt": "It landed in the demand book",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 24,
-            "entryEnd": 24
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "It had to wait its turn behind whatever was already running on Line 2.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Once fill and pack was done, it went into QA hold.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "It cleared and shipped Thursday",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-9f708103-e43a-4766-bca4-cb3b7060fdcd",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"ramp scrap after the washdown — real product lost on top of the hours; no good numbers and no source named\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-c330d313-b17a-496e-bd0d-8f504a444063",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lands in the demand book on the Monday release and is assigned to a line's column → waits its turn behind whatever is running on that line (with a changeover by the crew if the family changes) → runs: mix, mill, tint stage, fill and pack → palletized off the line into QA hold, queued for the lab → clears QA and ships.\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"The end-to-end sequence from the walked slice.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It cleared and shipped Thursday\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It had to wait its turn behind whatever was already running on Line 2.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It landed in the demand book\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "release and ship",
-          "slot": "what it produces or changes",
+          "kind": "ordering/flow",
+          "node": "release to cleared QA",
+          "slot": "how a branch or merge is decided",
           "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Branch on family match, plus line assignment at release.",
           "assertion": {
-            "value": "The order is released, goes to the warehouse, and ships against the due date."
+            "value": "At release the order goes into a line's column (Meridian white basically always to Line 2). Before a run: if the next job is the same family as the one just finished, it is a straight run-into-run with no changeover and no crew; if the family changes, a changeover by the crew is inserted, of a duration set by the direction (white-to-tint, tint-to-white, or specialty)."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+          "excerpt": "same family, so no changeover needed, just a straight run-into-run. That's the easy case, no crew involved.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Meridian white basically always goes to Line 2, so it went into \"my\" Line 2 column on the sheet without much debate.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 18,
+            "entryEnd": 18
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-a0b94f9f-7c74-40d1-bfb2-1f7e4d55d152",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"At release the order goes into a line's column (Meridian white basically always to Line 2). Before a run: if the next job is the same family as the one just finished, it is a straight run-into-run with no changeover and no crew; if the family changes, a changeover by the crew is inserted, of a duration set by the direction (white-to-tint, tint-to-white, or specialty).\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"Branch on family match, plus line assignment at release.\",\"slot\":\"how a branch or merge is decided\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2, so it went into \\\\\\\"my\\\\\\\" Line 2 column on the sheet without much debate.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"same family, so no changeover needed, just a straight run-into-run. That's the easy case, no crew involved.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "how long it takes",
-          "precision": "named",
+          "kind": "policy",
+          "node": "who gets the changeover crew",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Practiced contention rule with a borderline case; explicitly not written down.",
           "assertion": {
-            "value": "Usually a few hours for a white; nothing like the specialty wait (the specialty wait itself was never quantified)."
+            "value": "If a Meridian job is next behind either changeover, the crew goes to that line, full stop, without discussion. Otherwise the scheduler's judgment call at the huddle on whose due date is tightest (Line 1 won over Line 3, which had a couple of days of slack and sat clean but idle close to two hours). Otherwise whoever's line supervisor gets to the crew lead first. Written down nowhere."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+          "excerpt": "what happens is not some clean rule — it's whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "If it had been Meridian sitting behind either of those changeovers, that decision doesn't even get discussed — the crew goes to whichever line has the Meridian job next, full stop",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Line 3 sat there clean but idle for — I want to say close to two hours — waiting its turn.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; nothing like the specialty wait (the specialty wait itself was never quantified).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-60d290d4-26e8-41fc-afc3-208ac1a57b93",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"If a Meridian job is next behind either changeover, the crew goes to that line, full stop, without discussion. Otherwise the scheduler's judgment call at the huddle on whose due date is tightest (Line 1 won over Line 3, which had a couple of days of slack and sat clean but idle close to two hours). Otherwise whoever's line supervisor gets to the crew lead first. Written down nowhere.\"},\"kind\":\"policy\",\"node\":\"who gets the changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"Practiced contention rule with a borderline case; explicitly not written down.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If it had been Meridian sitting behind either of those changeovers, that decision doesn't even get discussed — the crew goes to whichever line has the Meridian job next, full stop\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 3 sat there clean but idle for — I want to say close to two hours — waiting its turn.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what happens is not some clean rule — it's whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "activity",
-          "node": "QA hold",
-          "slot": "who or what performs it",
-          "precision": "named",
+          "kind": "policy",
+          "node": "who gets the changeover crew",
+          "slot": "what overrides it",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Named override with escalation path.",
           "assertion": {
-            "value": "The lab — it sits in the lab's queue and gets checked."
+            "value": "Maintenance can pull the crew mid-job for a genuine emergency — a line leaking, something needing isolating right now. Rare, and not the scheduler's call; a real fight escalates over his head to the ops director."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+          "excerpt": "maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 9,
-            "entryEnd": 9
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "that goes over my head to the ops director if it's a real fight",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 21,
+            "entryEnd": 21
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-12e575e7-b7a9-472d-b165-308334ae7513",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab — it sits in the lab's queue and gets checked.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-5dde62c7-f641-446a-91e9-27a51f0d33a1",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Maintenance can pull the crew mid-job for a genuine emergency — a line leaking, something needing isolating right now. Rare, and not the scheduler's call; a real fight escalates over his head to the ops director.\"},\"kind\":\"policy\",\"node\":\"who gets the changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"Named override with escalation path.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that goes over my head to the ops director if it's a real fight\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "firm",
+      "confidence": "hedged",
       "content": {
         "value": {
           "type": "slot-asserted",
           "kind": "policy",
-          "node": "wait for the repair or shift the order to Line 1",
+          "node": "the wash-versus-idle call",
           "slot": "the rule as actually practiced",
           "precision": "spelled out",
           "sourceRegime": "practiced",
+          "rationale": "The practiced heuristic behind the decision the model must test.",
           "assertion": {
-            "value": "Gut math at the huddle: weigh the gamble that the repair is the \"half hour\" kind against the tint-to-white washdown plus the bumped tint order going late. In the Meridian case he went with waiting; it came back in about two hours and just scraped the Thursday due date."
+            "value": "Weigh changeover hours against idle hours by gut in the moment; a changeover is treated as a wash you can't get back, so the line is sat idle when a same-family order is expected soon."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "I went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky.",
+          "excerpt": "I ended up sitting the line. It felt right — a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 3,
             "entryEnd": 3
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+          "excerpt": "in the moment I'm weighing changeover hours against idle hours — that's the gut math",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 3,
-            "entryEnd": 3
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 6,
+            "entryEnd": 6
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-bc9d210e-beb9-4f7a-aa5d-243950605a2a",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Gut math at the huddle: weigh the gamble that the repair is the \\\"half hour\\\" kind against the tint-to-white washdown plus the bumped tint order going late. In the Meridian case he went with waiting; it came back in about two hours and just scraped the Thursday due date.\"},\"kind\":\"policy\",\"node\":\"wait for the repair or shift the order to Line 1\",\"precision\":\"spelled out\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-bd4124dd-9138-4ac2-a781-c67a99a4d1ae",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Weigh changeover hours against idle hours by gut in the moment; a changeover is treated as a wash you can't get back, so the line is sat idle when a same-family order is expected soon.\"},\"kind\":\"policy\",\"node\":\"the wash-versus-idle call\",\"precision\":\"spelled out\",\"rationale\":\"The practiced heuristic behind the decision the model must test.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I ended up sitting the line. It felt right — a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in the moment I'm weighing changeover hours against idle hours — that's the gut math\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "policy",
-          "node": "wait for the repair or shift the order to Line 1",
-          "slot": "what overrides it",
+          "kind": "validation-criterion",
+          "node": "the shape of a real month",
+          "slot": "how the expert would know the model is right",
           "precision": "spelled out",
+          "rationale": "Replay test stated in the expert's own terms.",
           "assertion": {
-            "value": "The Meridian-style on-time due date overrides the weighing — a line he won't cross unless there's truly no way through."
+            "value": "Feed it last month's demand book: it must land roughly on the actual late-order count and the same kind of misses (at least two Meridian scrapes and a handful of small ones) — getting the kind wrong is worse than getting the count wrong; changeover hours on Lines 2 and 3 must be recognisable, and Line 3 must not sit idle half the week waiting on the crew; it must reproduce the odd weeks, including a breakdown that ate two days on Line 1. Not a single number — the shape of a real month."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.",
+          "excerpt": "did it land roughly where we actually landed on late orders that month",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "same rough number and same *kind* of misses",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I'd want to eyeball changeover hours on Line 2 and 3 specifically",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "if it only works on the calm weeks, it's not telling me anything I don't already know from the sheet",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I'd want to recognize the *shape* of a real month before I'd believe it",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 15,
+            "entryEnd": 15
           },
           "source": "user-affordance-payload"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-90a38599-7f1b-46ed-9352-d3dd3566b338",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The Meridian-style on-time due date overrides the weighing — a line he won't cross unless there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"wait for the repair or shift the order to Line 1\",\"precision\":\"spelled out\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-03de2121-abc0-40dc-8f8a-9e4730fe9e4b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Feed it last month's demand book: it must land roughly on the actual late-order count and the same kind of misses (at least two Meridian scrapes and a handful of small ones) — getting the kind wrong is worse than getting the count wrong; changeover hours on Lines 2 and 3 must be recognisable, and Line 3 must not sit idle half the week waiting on the crew; it must reproduce the odd weeks, including a breakdown that ate two days on Line 1. Not a single number — the shape of a real month.\"},\"kind\":\"validation-criterion\",\"node\":\"the shape of a real month\",\"precision\":\"spelled out\",\"rationale\":\"Replay test stated in the expert's own terms.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd want to eyeball changeover hours on Line 2 and 3 specifically\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'd want to recognize the *shape* of a real month before I'd believe it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did it land roughly where we actually landed on late orders that month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if it only works on the calm weeks, it's not telling me anything I don't already know from the sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"same rough number and same *kind* of misses\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
     },
     {
-      "confidence": "hedged",
+      "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "policy",
-          "node": "who can absorb the slip",
-          "slot": "the rule as actually practiced",
-          "precision": "spelled out",
-          "sourceRegime": "practiced",
+          "kind": "data-binding",
+          "node": "changeover log, late-order report and the sheet",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "rationale": "Three existing records named as feeds, currently unlinked.",
           "assertion": {
-            "value": "Judgment, not a formula: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first."
+            "value": "Changeover hours from the changeover log; late orders from the late-order report — currently never put on the same page; run rates and exact run hours from the sheet, to be brought next session."
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.",
+          "excerpt": "I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
             "entryStart": 6,
             "entryEnd": 6
           },
           "source": "user-affordance-payload"
         },
         {
-          "excerpt": "I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+          "excerpt": "bring the sheet next time, it'll answer the run-rate question faster than I can talk through it",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 30,
+            "entryEnd": 30
           },
-          "source": "user-affordance-payload"
+          "source": "user"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-d889a88e-b7be-4055-9da1-e64f9fc858b0",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment, not a formula: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-89bf1a2d-3fcc-4e13-ad48-b874f4221714",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Changeover hours from the changeover log; late orders from the late-order report — currently never put on the same page; run rates and exact run hours from the sheet, to be brought next session.\"},\"kind\":\"data-binding\",\"node\":\"changeover log, late-order report and the sheet\",\"precision\":\"named\",\"rationale\":\"Three existing records named as feeds, currently unlinked.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"bring the sheet next time, it'll answer the run-rate question faster than I can talk through it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":30,\\\"entryStart\\\":30,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
     },
     {
       "confidence": "firm",
       "content": {
         "value": {
           "type": "slot-asserted",
-          "kind": "constraint",
-          "node": "Meridian-style due date is a line I won't cross",
-          "slot": "the limit and what happens when it is hit",
-          "precision": "spelled out",
+          "kind": "activity",
+          "node": "run on the line",
+          "slot": "how long it takes",
           "sourceRegime": "practiced",
+          "rationale": "No run duration was given; the expert named the sheet as the source that will supply it next round.",
           "assertion": {
-            "value": "The protected order must ship on time; days late above zero is bad news the scheduler has to go explain. The line is crossed only if there's truly no way through."
+            "absence": "deferred",
+            "pointer": "the sheet the scheduler will bring next round, which answers the run-rate question"
           }
         }
       },
       "evidence": [
         {
-          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.",
+          "excerpt": "bring the sheet next time, it'll answer the run-rate question faster than I can talk through it",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 30,
+            "entryEnd": 30
           },
-          "source": "user-affordance-payload"
-        },
+          "source": "user"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-1b0da51d-eeab-4750-b872-3cd03e9fb169",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the sheet the scheduler will bring next round, which answers the run-rate question\"},\"kind\":\"activity\",\"node\":\"run on the line\",\"rationale\":\"No run duration was given; the expert named the sheet as the source that will supply it next round.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"bring the sheet next time, it'll answer the run-rate question faster than I can talk through it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":30,\\\"entryStart\\\":30,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "Meridian-to-Line-2",
+          "slot": "the rule as actually practiced",
+          "sourceRegime": "practiced",
+          "rationale": "Whether Meridian white routing to Line 2 is a hard rule or a habit is explicitly left open, with the expert named as the source who will establish it.",
+          "assertion": {
+            "absence": "deferred",
+            "pointer": "the expert will check whether Meridian-to-Line-2 is written in stone or just habit before next round"
+          }
+        }
+      },
+      "evidence": [
         {
-          "excerpt": "anything above zero is bad news I have to go explain",
+          "excerpt": "I'll have the sheet, and I'll poke at whether Meridian-to-Line-2 is written in stone or just habit before you even ask.",
           "pointer": {
-            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-            "entryStart": 6,
-            "entryEnd": 6
+            "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+            "entryStart": 34,
+            "entryEnd": 34
           },
-          "source": "user-affordance-payload"
+          "source": "user"
         }
       ],
       "epistemicStatus": "explicit",
-      "id": "capture-173c6d39-090f-49a7-9e38-c8998003718b",
-      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The protected order must ship on time; days late above zero is bad news the scheduler has to go explain. The line is crossed only if there's truly no way through.\"},\"kind\":\"constraint\",\"node\":\"Meridian-style due date is a line I won't cross\",\"precision\":\"spelled out\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      "id": "capture-03ef0211-289b-4c3e-a9f1-ff4d4698b625",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the expert will check whether Meridian-to-Line-2 is written in stone or just habit before next round\"},\"kind\":\"policy\",\"node\":\"Meridian-to-Line-2\",\"rationale\":\"Whether Meridian white routing to Line 2 is a hard rule or a habit is explicitly left open, with the expert named as the source who will establish it.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'll have the sheet, and I'll poke at whether Meridian-to-Line-2 is written in stone or just habit before you even ask.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":34,\\\"entryStart\\\":34,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
     }
   ],
   "issues": [],
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-model.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-model.md
index fbc00da3aed..c3fd954a3c5 100644
--- a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-model.md
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-model.md
@@ -4,441 +4,384 @@ The harness's own deliverable: `foldElicitedModel` over the active captures, the
 `evaluateCompletion` against the sdcpn definition. Nothing here was written by the
 interviewer; every value is a capture the sweep extracted and the store admitted.
 
-- Plugin version: `sdcpn/2026-08-25.2`
-- Revision: `26a8219a17118558`
-- Active captures: 267
-- Complete: **no** — 46 unsatisfied, 53 node(s) outside every objective's slice, 0 unmapped capture(s)
+- Plugin version: `sdcpn/2026-08-26.2`
+- Revision: `34f9da8a0149564c`
+- Active captures: 166
+- Complete: **no** — 93 unsatisfied, 16 node(s) outside every objective's slice, 0 unmapped capture(s)
 
 ## Nodes
 
-### entity-type (12)
+### entity-type (6)
 
-#### `entity-type:line`
-- **how many there are, or the population's shape** — conflict — 2 readings
-- **state that rides along with each instance** — "What it is currently running — e.g. mid-run on a tint, which sets the colour it would have to be washed down from — and whether it is jammed/down awaiting repair." — spelled out, inferred, practiced — _A line is spoken of as carrying what it is currently running (its colour state) and whether it is down._
+#### `entity-type:changeover crew`
+- **how many there are, or the population's shape** — conflict — 3 readings
+- **state that rides along with each instance** — "free, or tied up / about to be pulled onto Line 1 or Line 3 for something else — if tied up, the wash-down option isn't available and the job queues behind whoever else needs them" — spelled out, explicit, practiced — _The crew is either free or tied up on another line; that state gates whether a changeover can start._
 - **the distinctions the process treats apart** — conflict — 2 readings
 
-#### `entity-type:line (Line 1 / Line 2)`
-- **how many there are, or the population's shape** — conflict — 2 readings
-- **the distinctions the process treats apart** — conflict — 3 readings
-
-#### `entity-type:Line 1 and Line 2`
-- **how many there are, or the population's shape** — "Two lines — Line 1 and Line 2." — number, explicit — _The expert speaks only of Line 1 and Line 2 throughout._
-- **state that rides along with each instance** — "What order is on it, how far through that order is, and what family (tint or white) it is currently running — the last decides washdown cost and direction." — spelled out, explicit
-- **the distinctions the process treats apart** — conflict — 3 readings
-
-#### `entity-type:mix, mill, tint, fill`
-- **how many there are, or the population's shape** — absence: unknown-to-user → how much overlap happens and how often mixing is blocked by a full tank is not tracked by the scheduler (explicit)
-- **the distinctions the process treats apart** — divergence — prescribed {"value":"On the sheet the line is one row treated as one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it is done."}; practiced {"value":"Physically four separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head is still finishing the last, if there is room in the holding tank — the crew will get a head start on mixing the next batch if the tank ahead of it has space."}
-
-#### `entity-type:mix, mill, tint, fill kit and holding tanks`
-- **how many there are, or the population's shape** — absence: deferred → engineering drawings (explicit)
-- **the distinctions the process treats apart** — "Mix, mill, tint and fill are separate tanks and separate kit strung together, with small holding tanks between them." — spelled out, explicit, practiced
+#### `entity-type:line`
+- **how many there are, or the population's shape** — "Three lines — Line 1, Line 2, Line 3" — number, explicit — _Expert named three lines as the scheduling scope._
 
-#### `entity-type:mix, mill, tint, fill stages`
-- **how many there are, or the population's shape** — absence: deferred → engineering drawings (tank sizes) — expert does not carry them in his head (explicit)
-- **the distinctions the process treats apart** — "Mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can be starting the next order's batch while the fill head is still finishing the last one, if the holding tank between mix and mill, or mill and fill, has room." — spelled out, explicit, practiced — _The floor's account: four separately contended pieces of kit per line, buffered by small holding tanks._
+#### `entity-type:lines`
+- **how many there are, or the population's shape** — "three lines — Line 1, Line 2, Line 3" — number, explicit — _Three lines, named Line 1, Line 2, Line 3._
 
 #### `entity-type:order`
-- **how many there are, or the population's shape** — absence: unknown-to-user → demand book / ERP (inferred)
+- **how many there are, or the population's shape** — conflict — 2 readings
 - **state that rides along with each instance** — conflict — 6 readings
 - **the distinctions the process treats apart** — conflict — 6 readings
 
-#### `entity-type:order (demand book line item)`
-- **state that rides along with each instance** — "Quantity, due date, SKU; plus remaining quantity and the customer's identity, which the expert weighs when an order slips." — spelled out, inferred — _Quantity, due date and SKU are explicit; remaining quantity and customer identity are named later as things the answer hangs on._
-- **the distinctions the process treats apart** — "Orders are treated apart by whose order it is: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem." — spelled out, explicit, practiced
+#### `entity-type:the changeover crew`
+- **how many there are, or the population's shape** — conflict — 2 readings
+- **the distinctions the process treats apart** — conflict — 2 readings
 
-#### `entity-type:order (line item in the demand book)`
-- **state that rides along with each instance** — "Quantity, due date, SKU; the customer (distributor / small account / awkward account); which line and week-slot it has been allocated to; whether it has gone late and by how many days." — spelled out, explicit — _Quantity, due date, SKU come from ERP; customer type is used in the slip judgement; line allocation is set at step one._
-- **the distinctions the process treats apart** — "Orders are line items with quantity, due date and SKU. Treated apart: whites (tint stage barely there, more of a pass-through than a real letdown step) vs tints (real letdown); and by customer — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem." — spelled out, explicit — _Whites vs tints differ in the tint stage and in run time by line; customer identity differs in slip tolerance._
+#### `entity-type:the three lines`
+- **how many there are, or the population's shape** — conflict — 3 readings
+- **the distinctions the process treats apart** — conflict — 3 readings
 
-#### `entity-type:product family (white vs tint)`
-- **the distinctions the process treats apart** — "Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step; tints run at nearly the same speed on both lines while whites do not; and the tint-to-white changeover direction is the expensive one." — spelled out, explicit
+### boundary-condition (3)
 
-#### `entity-type:stage kit (mix, mill, tint, fill)`
-- **the distinctions the process treats apart** — "Four separate pieces of kit per line — mixer, mill, tint, fill head — each usable independently, with small holding tanks buffering between mix/mill and mill/fill." — spelled out, explicit, practiced — _Each stage is separately contended kit._
+#### `boundary-condition:demand book release`
+- **the arrival or availability pattern** — "Orders arrive by release into the demand book from ERP on a weekly book cycle, re-planned by the morning huddle; releases occur within the day (e.g. an order \"was going to be released from the demand book that afternoon\"). No rate or shape given" — named, explicit, practiced — _Expert described the cycle and replan rhythm but gave no rate or shape._
 
-#### `entity-type:the four stages — mix, mill, tint, fill`
-- **how many there are, or the population's shape** — "Four stages in series per line — mix, mill, tint, fill — with small holding tanks between them; how often blocking occurs is not tracked." — named, explicit — _Count of stages is stated; occupancy/blocking frequency is explicitly untracked._
-- **the distinctions the process treats apart** — "Physically mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head finishes the last one if the tank ahead has space." — spelled out, explicit, practiced — _The floor's version of the line: four contended stages with buffers, not one resource._
+#### `boundary-condition:release from the demand book`
+- **the arrival or availability pattern** — "Releases follow the demand book's weekly cycle, re-planned every morning at the huddle; past a week the book is soft and gets revised. Rate and shape of arrivals not yet given." — spelled out, explicit — _The expert gives the release cycle (weekly demand book, re-planned each morning at the huddle) but no rate or shape of arrivals._
+- **the starting state** — "An order lands in the demand book from ERP — that is \"released\" — with an SKU, quantity and due date." — spelled out, explicit — _Orders enter the expert's world on release into the demand book from ERP, carrying SKU, quantity and due date._
 
-### boundary-condition (2)
+#### `boundary-condition:the demand book`
+- **the arrival or availability pattern** — conflict — 3 readings
+- **the starting state** — conflict — 2 readings
 
-#### `boundary-condition:demand book from ERP`
-- **the arrival or availability pattern** — conflict — 2 readings
-- **the starting state** — conflict — 3 readings
+### activity (16)
 
-#### `boundary-condition:demand book line items out of ERP`
-- **the starting state** — "An order starts life as a line item in the demand book once ERP spits that out, carrying quantity, due date and SKU." — spelled out, explicit
+#### `activity:a breakdown on a line`
+- **how often it occurs, if it is an event rather than a step** — absence: deferred → next round with the expert (breakdowns) — one recalled instance: a breakdown chewed up two days on Line 1 in the odd weeks the model must reproduce (explicit)
 
-### activity (15)
+#### `activity:breakdown on a line`
+- **how long it takes** — conflict — 2 readings
+- **how often it occurs, if it is an event rather than a step** — conflict — 2 readings
 
-#### `activity:allocation`
-- **what it needs before it can start** — conflict — 5 readings
-- **what it produces or changes** — conflict — 5 readings
-- **who or what performs it** — conflict — 3 readings
+#### `activity:changeover (washdown)`
+- **what is lost when it changes the system's mode** — "A wash that \"we can't get back\", counted by the expert as changeover hours; no quantity given yet" — named, tentative, practiced — _Expert named the loss qualitatively (a wash, changeover hours) but gave no figure in this range._
+- **what it needs before it can start** — "The changeover crew must be free — \"If they're tied up elsewhere, my 'wash down now' option isn't even really available\" — and the line must have finished its current run" — spelled out, explicit, practiced — _Crew availability is the stated precondition._
+- **what it produces or changes** — "Converts the line from the previous colour to the next — \"a full white-to-tint changeover is a wash we can't get back\"; a white-to-white succession needs \"no changeover\"" — spelled out, explicit — _The changeover converts the line's colour state; same-colour succession needs none._
+- **who or what performs it** — "entity-type:changeover crew — one crew of two techs" — named, explicit — _Directly named performer._
 
-#### `activity:allocation onto a line and a slot in the week`
-- **what it needs before it can start** — "A line item in the demand book out of ERP, with quantity, due date and SKU." — spelled out, explicit
-- **what it produces or changes** — "The order is placed onto a named line and a slot in the week." — spelled out, explicit
-- **who or what performs it** — "The master scheduler, on the sheet." — named, explicit
-
-#### `activity:filler jam`
-- **how long it takes** — conflict — 5 readings
-- **how often it occurs, if it is an event rather than a step** — conflict — 3 readings
-- **what it needs before it can start** — "Repair duration is not known at the time of the decision — \"which I never know at the time\"; only \"could be quick, could be long\"." — spelled out, explicit — _At the time of the decision the repair length is unobservable to the scheduler._
-- **what it produces or changes** — conflict — 5 readings
-- **who or what performs it** — "A tech — comes over, clears whatever's jammed, resets." — named, explicit — _Repair is done by a tech._
-
-#### `activity:filler jam on Line 2`
-- **how long it takes** — "Repair: typical thirty to forty-five minutes; quick one-in-ten ten to fifteen minutes (basically a false alarm); bad one-in-ten four to five hours when something is actually broken in the filler head, occasionally eating the rest of the shift." — spread, explicit, practiced
-- **how often it occurs, if it is an event rather than a step** — "Every week or two; low end once every three weeks, high end twice a week. Not seasonal, but runs streaks of bad weeks." — range, explicit, practiced
-- **what it produces or changes** — "The run stops and time is lost inside the run — the big bad days (twelve to thirteen hours) are the breakdown showing up inside the run rather than the run being slow." — spelled out, explicit
-- **who or what performs it** — "A tech comes over, clears whatever's jammed and resets." — named, explicit
-
-#### `activity:filler jammed`
-- **how long it takes** — "Two kinds of repair: the \"half hour\" kind and the \"half a shift\" kind. The most recent Line 2 filler jam came back in about two hours." — range, explicit, practiced — _Two recognised repair kinds bracket the duration; the recent instance fell between them._
-- **what it produces or changes** — "The line's filler stops mid-run with an unknown ETA, putting the order on it at risk and forcing a decision to wait out the repair or move the order to the other line." — spelled out, explicit — _An event that befalls the line mid-run and forces the switch-or-wait decision._
-
-#### `activity:Line 2 filler jam`
-- **how long it takes** — "Repairs come in a \"half hour\" kind and a \"half a shift\" kind; the recent instance came back in about two hours." — range, explicit, practiced — _Expert described two kinds of repair — half an hour and half a shift — and one observed instance of about two hours; quantiles not yet elicited._
-- **what it produces or changes** — "Line 2 stops producing until repaired (half a shift lost in the recent case); the order sitting on Line 2 is at risk of its due date, forcing a decision to wait out the repair or shift the order to Line 1." — spelled out, explicit, practiced — _The event takes the line out of production and puts the order sitting on it at risk, forcing a wait-or-move decision._
-
-#### `activity:mix/mill/tint/fill`
-- **what it produces or changes** — "Runs the order through four stages every product goes through — mix, mill, tint, fill and pack — producing filled and packed product that comes off the fill line." — spelled out, explicit — _Stated as the production step common to all products._
-- **whether its quantities vary by type** — "Yes — the stages are the same for every product, but for a white the tint stage is barely there, a pass-through rather than a real letdown step." — named, explicit — _Explicit type-dependence at the tint stage; stage durations themselves not yet given._
-
-#### `activity:production run (mix, mill, tint, fill)`
-- **how long it takes** — conflict — 3 readings
-- **what it needs before it can start** — "The order allocated to a line and a slot in the week; then it runs the same four stages every product goes through — mix, mill, tint, fill and pack." — spelled out, explicit
-- **what it produces or changes** — "Packed product coming off the fill line, which then goes into QA hold." — spelled out, explicit
-- **whether its quantities vary by type** — "Yes — run time varies by product family and line: whites are much slower on Line 1, tints are nearly the same speed on either line; the \"Line 2 is twice as fast\" figure is really a whites number. No explanation for the tint case; it is sheet-derived." — named, explicit
+#### `activity:changeover wash down`
+- **what is lost when it changes the system's mode** — "a full white-to-tint changeover is \"a wash we can't get back\"; the amount of time or capacity lost was not quantified" — named, explicit — _The expert names the loss qualitatively — a full white-to-tint changeover is a wash that cannot be recovered — without giving hours._
+- **what it needs before it can start** — "The changeover crew must be free; if they are tied up on another line the wash-down option isn't available and the job queues behind whoever else needs them." — spelled out, explicit, practiced — _Availability of the shared changeover crew gates the start of a wash down._
+- **who or what performs it** — "the changeover crew — one crew, two techs, shared across all three lines" — named, explicit — _The changeover crew performs the wash down._
 
-#### `activity:QA hold`
-- **how long it takes** — conflict — 7 readings
-- **what it needs before it can start** — "The order has come off the fill line; it then sits in the lab's queue awaiting check." — spelled out, explicit — _Stated as the precondition and the waiting arrangement._
-- **what it produces or changes** — conflict — 3 readings
-- **whether its quantities vary by type** — conflict — 2 readings
-- **who or what performs it** — conflict — 7 readings
+#### `activity:clears QA hold`
+- **what it produces or changes** — "The order clears QA hold and ships; the due date is judged against when it clears, not when it comes off the line — a batch can be done Tuesday and still ship late if the lab's backed up." — spelled out, explicit, practiced — _Clearing QA is the event against which lateness is judged and the point the order leaves the expert's scope._
 
-#### `activity:release and ship`
-- **what it produces or changes** — conflict — 4 readings
+#### `activity:full white-to-tint changeover`
+- **what it needs before it can start** — "The next job is a different colour class than the one just run — a white-to-tint switch requires the changeover; a white order following white needs no changeover." — spelled out, explicit, practiced — _The changeover is triggered by a colour change from white to tint; same-colour succession needs none._
+- **what it produces or changes** — "The line is washed down and set for tint; it is \"a wash we can't get back\" — the changeover hours are consumed capacity." — spelled out, explicit, practiced — _Expert's own characterisation of the outcome of the changeover._
+- **whether its quantities vary by type** — "Yes by colour pair: white-to-tint is a full washdown, white-to-white needs no changeover at all." — named, explicit — _The expert distinguishes white-to-tint (full wash) from white-to-white (none); other direction/colour pairs not yet stated._
 
-#### `activity:run it through mix/mill/tint/fill`
-- **how long it takes** — conflict — 6 readings
-- **what it needs before it can start** — conflict — 2 readings
-- **what it produces or changes** — conflict — 2 readings
+#### `activity:QA hold`
+- **how long it takes** — conflict — 3 readings
+- **what it needs before it can start** — conflict — 3 readings
+- **what it produces or changes** — conflict — 3 readings
 - **whether its quantities vary by type** — conflict — 3 readings
-- **who or what performs it** — conflict — 2 readings
-
-#### `activity:run the batch (mix/mill/tint/fill)`
-- **how long it takes** — absence: deferred → the expert's scheduling sheet (roughly how long a batch of a given SKU takes end to end on each line) (explicit)
-- **what it produces or changes** — "The order is produced through the same four stages every product goes through — mix, mill, tint, fill and pack — and comes off the fill line." — spelled out, explicit — _The production run through the four stages._
-- **whether its quantities vary by type** — absence: deferred → the historian (stage-by-stage times: how long does mixing take, how long does milling take) (explicit)
-
-#### `activity:the run (mix, mill, tint, fill)`
-- **how long it takes** — conflict — 4 readings
-- **what it needs before it can start** — "The order allocated onto a line and a slot in the week (\"I slot it onto Line 2 on the sheet, that's step one, allocation\")." — spelled out, explicit
-- **what it produces or changes** — "Filled and packed product coming off the fill line, which then goes into QA hold." — spelled out, explicit
-- **whether its quantities vary by type** — "Yes — run time varies by family and by line: whites are about twice as fast on Line 2 as Line 1, tints run at nearly the same speed on both; and different SKUs are slow at different stages." — named, explicit
-- **who or what performs it** — "The line (Line 1 or Line 2) — its mix, mill, tint and fill kit — worked by the crew." — named, explicit
+- **who or what performs it** — conflict — 3 readings
 
-#### `activity:tint stage`
-- **whether its quantities vary by type** — "Yes — for a white the tint stage is barely there, more of a pass-through than a real letdown step." — named, explicit — _Explicit variation by product type._
+#### `activity:run on the line`
+- **how long it takes** — absence: deferred → the sheet the scheduler will bring next round, which answers the run-rate question (explicit)
 
-#### `activity:tint-to-white washdown`
-- **how long it takes** — conflict — 6 readings
-- **what is lost when it changes the system's mode** — conflict — 8 readings
-- **what it needs before it can start** — conflict — 7 readings
-- **what it produces or changes** — conflict — 4 readings
-- **who or what performs it** — "The crew, on the line being changed over (Line 1 in the incident described)." — named, explicit
+#### `activity:specialty changeover`
+- **how long it takes** — conflict — 3 readings
+- **whether its quantities vary by type** — conflict — 2 readings
 
-### ordering/flow (8)
+#### `activity:the hold-or-change-over call`
+- **how often it occurs, if it is an event rather than a step** — "three or four times a month" — range, explicit, practiced — _Frequency of the decision point the model is meant to test._
+- **who or what performs it** — "The master scheduler, by gut judgment" — named, explicit — _The expert makes the call themselves, by gut._
 
-#### `ordering/flow:allocate → run → QA hold → release and ship`
-- **the order things happen in** — conflict — 2 readings
+#### `activity:the run`
+- **how long it takes** — "For that big-volume Meridian white order: on the line most of the day — started Wednesday morning and wrapped Wednesday evening; exact hours would have to be checked on the sheet." — number, explicit — _Only a single recalled case at roughly a day; the expert explicitly says exact hours would need the sheet, so no range or spread was reached._
+- **what it needs before it can start** — "The order must be in the Line 2 column on the sheet and must wait its turn behind whatever is already running on that line; if the job ahead is the same family, no changeover is needed — a straight run-into-run." — spelled out, explicit — _Precondition stated in the walkthrough: the line free of the previous job, and either same family (no changeover) or a completed changeover._
+- **what it produces or changes** — "Mix, mill, tint stage (skipped for a white), through fill and pack; the finished order is palletized and moved off the line into the queue for the lab." — spelled out, explicit — _The run's output as described._
+- **who or what performs it** — "The line itself (Line 2 in the recalled case); no changeover crew involved — \"that's the easy case, no crew involved\". The expert does not watch it minute by minute." — named, explicit — _The expert names the line as what runs the order and says he does not watch the operators minute by minute; no crew is involved in a run-into-run._
 
-#### `ordering/flow:line occupancy across the four stages`
-- **the order things happen in** — divergence — prescribed {"value":"On the sheet, Line 2 is one row: the order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done."}; practiced {"value":"Physically the stages overlap: the mixer can start the next order's batch while the fill head is still finishing the last one, if there is room in the holding tank between mix and mill, or mill and fill; the crew will get a head start on mixing if the tank ahead has space."}
+#### `activity:the run (mix, mill, fill and pack)`
+- **how long it takes** — conflict — 2 readings
+- **what it needs before it can start** — conflict — 2 readings
+- **what it produces or changes** — conflict — 2 readings
+- **who or what performs it** — "The production line (this order ran on Line 2); no crew involvement for a run-into-run" — named, explicit — _Performed by the line itself; the scheduler does not track the operators._
 
-#### `ordering/flow:order flow from demand book to ship`
-- **the order things happen in** — "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship against the due date." — spelled out, explicit
+#### `activity:tint-to-white changeover`
+- **how long it takes** — "Quickest maybe two and a half hours (everything clean, crew fresh); on a bad day — dried pigment in a fitting — it has crept toward four hours; three hours typical, the number actually used on the sheet." — range, explicit, practiced — _Low two and a half hours, high toward four hours, typical three hours — a range with a typical._
+- **what is lost when it changes the system's mode** — "A full washdown — two and a half to four hours of line time, three typical — because any pigment left behind wrecks a white batch; direction matters, it is not symmetric with white-to-tint." — range, explicit, practiced — _Loss is the full washdown time on the line plus the crew, driven by the direction of the change._
+- **whether its quantities vary by type** — "Yes — changeover duration varies by direction and family: white-to-tint is the cheap direction, tint-to-white the expensive one, specialty its own animal." — named, explicit — _Explicit answer that changeover duration varies by direction and family._
 
-#### `ordering/flow:order flow from demand book to shipment`
-- **the order things happen in** — "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (fill and pack) → QA hold → release and ship. Four steps if QA and shipping are counted as one, five if split." — spelled out, explicit — _Given verbatim as the end-to-end sequence for the Meridian white order._
+#### `activity:tint-to-white washdown`
+- **how long it takes** — conflict — 2 readings
+- **what is lost when it changes the system's mode** — "A full washdown, because any pigment left behind wrecks a white batch — direction absolutely matters, it's not symmetric: tint-to-white is the expensive one (three hours typical) versus white-to-tint (45 minutes to an hour). \"A full white-to-tint changeover is a wash we can't get back.\"" — spelled out, explicit, practiced — _Directional asymmetry and its reason; loss is the full washdown time, not recoverable._
+- **what it produces or changes** — "A full washdown of the line so no pigment is left behind; any pigment left behind wrecks a white batch." — spelled out, explicit — _Purpose and consequence of omission._
+- **who or what performs it** — "entity-type:the changeover crew (two techs)" — named, explicit — _Same shared crew._
+
+#### `activity:white-to-tint changeover`
+- **how long it takes** — conflict — 2 readings
+- **what it needs before it can start** — "The changeover crew must be free; if they are tied up on another line the wash-down option is not available and the line queues behind whoever else needs them." — spelled out, explicit — _Crew availability gates the changeover._
+- **whether its quantities vary by type** — "Yes — direction absolutely matters and is not symmetric: white-to-tint is the cheap direction, tint-to-white the expensive one, and specialty is its own animal again." — named, explicit — _Explicit answer that duration varies by direction and family._
+- **who or what performs it** — conflict — 2 readings
 
-#### `ordering/flow:order flow, allocate to ship`
-- **the order things happen in** — "Allocate the order onto a line and a slot in the week → run it through mix / mill / tint / fill and pack → QA hold → release and ship. Four steps if QA and shipping count as one, five if split." — spelled out, explicit — _The end-to-end order stated by the expert._
+#### `activity:white-to-tint changeover on Line 2`
+- **how long it takes** — "Quickest maybe 40 minutes (crew right there, nothing fighting them); longest about an hour twenty on a bad day (crew stretched thin or something stuck); typically lands around 45 minutes to an hour. The \"cheap\" direction." — range, explicit, practiced — _Low, high and a typical band given — a range with a typical, not a full spread; not rounded up._
+- **what is lost when it changes the system's mode** — "Line time consumed by the changeover: 40 minutes to an hour twenty, typically 45 minutes to an hour, plus occupancy of the two-tech crew for that period." — range, explicit, practiced — _The loss on this mode change is the line time consumed by the wash; the expert gave it as the changeover duration._
+- **what it needs before it can start** — "The previous run on the line finished and the changeover crew free; if the crew is tied up on another line, the changeover cannot start and the line queues behind whoever else needs them." — spelled out, explicit — _Precondition: previous run finished and the shared crew available._
+- **who or what performs it** — "The changeover crew — one crew, two techs, shared across all three lines." — named, explicit — _All changeovers are performed by the shared two-tech crew._
 
-#### `ordering/flow:order life on the floor`
-- **the order things happen in** — "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship" — spelled out, explicit — _Expert's own summary of the end-to-end sequence._
+### ordering/flow (1)
 
-#### `ordering/flow:order lifecycle: allocate, run, QA hold, release and ship`
-- **how a branch or merge is decided** — "The scheduler slots the order onto a line on the sheet at allocation; on a disruption the choice is re-decided — shift it to the other line or wait out the repair." — spelled out, explicit — _The line choice is made by the scheduler at allocation and can be revisited on disruption._
-- **the order things happen in** — "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship" — spelled out, explicit
+#### `ordering/flow:release to cleared QA`
+- **how a branch or merge is decided** — conflict — 3 readings
+- **the order things happen in** — conflict — 5 readings
 
-#### `ordering/flow:stage overlap on a line`
-- **how a branch or merge is decided** — absence: unknown-to-user (explicit)
-- **the order things happen in** — conflict — 3 readings
+### policy (6)
 
-### policy (5)
+#### `policy:Meridian-to-Line-2`
+- **the rule as actually practiced** — absence: deferred → the expert will check whether Meridian-to-Line-2 is written in stone or just habit before next round (explicit)
 
-#### `policy:a line is occupied for the whole run`
-- **the rule as actually practiced** — "On the sheet, a line is one row: the order occupies that line for its whole run, mix through fill, and nothing else is scheduled on it till it's done." — spelled out, explicit, prescribed — _P08: the scheduling sheet's rule, which the expert says lies to him a bit._
-- **what overrides it** — "On the floor the crew will get a head start on mixing the next batch if the tank ahead of it has space — the mixer can start the next order while the fill head finishes the last one. How much overlap happens, and how often it is blocked because a tank is full, is not tracked." — spelled out, explicit, practiced — _P08 divergence: floor practice overlaps stages when buffer space allows._
+#### `policy:sit the line for an expected same-colour order`
+- **the rule as actually practiced** — "When a same-colour order is expected to be released later the same day, hold the line idle rather than change over — because a full white-to-tint changeover is a wash that can't be got back, versus an hour of idle time. Judged by gut, three or four times a month." — spelled out, explicit, practiced — _The practiced rule behind the decision, given as gut judgment on a real occasion; not yet elicited as a general rule with conditions._
 
-#### `policy:Meridian on time`
-- **the rule as actually practiced** — "A Meridian-style order ships on time, full stop; it is not traded off against anything." — spelled out, explicit, practiced — _Hard constraint on the scheduling decision._
-- **what overrides it** — "Only when there is truly no way through." — spelled out, explicit, practiced — _Only exception stated._
+#### `policy:the wash-versus-idle call`
+- **the rule as actually practiced** — "Weigh changeover hours against idle hours by gut in the moment; a changeover is treated as a wash you can't get back, so the line is sat idle when a same-family order is expected soon." — spelled out, explicit, practiced — _The practiced heuristic behind the decision the model must test._
 
-#### `policy:Meridian ships on time, full stop`
-- **the rule as actually practiced** — "The Meridian order ships on time, full stop; it is not traded off against washdown hours or other orders' due dates." — spelled out, explicit, practiced — _Stated as an absolute the scheduler protects ahead of all other considerations._
-- **what overrides it** — "Only when there is truly no way through; otherwise nothing overrides it." — spelled out, explicit, practiced — _Expert named the sole override in general terms; the practiced test for "no way through" is not yet on record._
+#### `policy:we just don't do that (Meridian never slips)`
+- **the rule as actually practiced** — "A Meridian order is never allowed to slip its due date — it is a \"we just don't do that\" rule rather than a traded-off cost, because a Meridian miss means a fine plus ammunition for them to delist a line item at next contract review, and commercial and the boss get calls. Non-Meridian distributor orders that slip 2-3 days are handled with a phone call." — spelled out, explicit, practiced — _An unwritten rule stated by the expert as absolute, with its organisational consequence._
+- **what overrides it** — absence: explicitly-absent → no number of small late orders flips it in any range seen in a week (explicit)
 
-#### `policy:wait for the repair or shift the order to Line 1`
-- **the rule as actually practiced** — "Gut math at the huddle: weigh the gamble that the repair is the \"half hour\" kind against the tint-to-white washdown plus the bumped tint order going late. In the Meridian case he went with waiting; it came back in about two hours and just scraped the Thursday due date." — spelled out, explicit, practiced
-- **what overrides it** — "The Meridian-style on-time due date overrides the weighing — a line he won't cross unless there's truly no way through." — spelled out, explicit
+#### `policy:who gets the changeover crew`
+- **the rule as actually practiced** — conflict — 2 readings
+- **what overrides it** — "Maintenance can pull the crew mid-job for a genuine emergency — a line leaking, something needing isolating right now. Rare, and not the scheduler's call; a real fight escalates over his head to the ops director." — spelled out, explicit, practiced — _Named override with escalation path._
 
-#### `policy:who can absorb the slip`
-- **the rule as actually practiced** — conflict — 7 readings
-- **what overrides it** — conflict — 4 readings
+#### `policy:who gets the crew`
+- **the rule as actually practiced** — conflict — 2 readings
+- **what overrides it** — conflict — 2 readings
 
 ### objective (7)
 
-#### `objective:is the mill-to-fill tank on Line 1 slowing the line down`
-- **the nodes it depends on** — conflict — 3 readings
-- **the question, in the expert's words** — "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"" — spelled out, explicit — _Second question the expert wrote out as he would type it._
-- **what "better" means, and trade-off weights** — "The model showing \"here's where Line 1 loses its time\" — something to take to engineering other than a hunch; no numeric weighting given." — spelled out, explicit — _Qualitative: showing where Line 1 loses its time, in a form usable with engineering._
-
-#### `objective:switch or wait when Line 2 goes down`
-- **the nodes it depends on** — ["entity-type:order","entity-type:line","activity:run it through mix/mill/tint/fill","activity:tint-to-white washdown","activity:filler jam","policy:who can absorb the slip"] — named, explicit — _The expert listed what the answer hangs on: the protected run and its due date, the state of Line 1, the changeover and its direction, the jam duration, and whose order gets bumped._
-- **the question, in the expert's words** — "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"" — spelled out, explicit — _The expert wrote the question as he would type it into the tool._
-- **what "better" means, and trade-off weights** — "Hard line: days late on Meridian, anything above zero is bad news. Underneath that, weighed by judgment with no formula: washdown hours, and whether the bumped order goes late and by how much and for which customer." — spelled out, explicit, practiced — _Expert gave a lexicographic hard constraint plus unweighted second-order criteria, explicitly denying a formula._
-
-#### `objective:switch or wait when Line 2 goes down mid-run`
-- **the nodes it depends on** — ["entity-type:order","entity-type:Line 1 and Line 2","activity:the run (mix, mill, tint, fill)","activity:filler jam","activity:tint-to-white washdown","policy:who can absorb the slip","constraint:Meridian ships on time"] — named, explicit — _The expert listed what the answer hangs on._
-- **the question, in the expert's words** — "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"" — spelled out, explicit — _The expert wrote the question as they would type it into the tool._
-- **what "better" means, and trade-off weights** — "Meridian on time is non-negotiable (days late on Meridian, anything above zero is bad news); underneath that, washdown hours and whether the bumped order goes late and by how much are weighed by judgment — \"I don't have a formula for it.\"" — spelled out, explicit — _Hard constraint plus unweighted secondary measures; the expert explicitly denied having a formula._
-
-#### `objective:wait or shift when Line 2 goes down`
-- **the nodes it depends on** — "entity-type:order (demand book line item) — its due date and remaining quantity; entity-type:line (Line 1 / Line 2) — what is on Line 1 and how far through; entity-type:product family (white vs tint); activity:production run (mix, mill, tint, fill); activity:filler jam on Line 2 — repair length unknown at the time; activity:tint-to-white washdown — including its direction and ramp scrap; policy:who can absorb the slip — whose tint got bumped" — named, explicit
-- **the question, in the expert's words** — "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"" — spelled out, explicit — _The expert wrote the question as he would type it into the tool._
-- **what "better" means, and trade-off weights** — "Lexicographic: days late on Meridian first, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip." — spelled out, explicit, practiced
-
-#### `objective:where Line 1 loses its time`
-- **the nodes it depends on** — conflict — 3 readings
-- **the question, in the expert's words** — conflict — 3 readings
-
-#### `objective:which option actually loses less`
-- **the nodes it depends on** — conflict — 3 readings
-- **the question, in the expert's words** — conflict — 3 readings
-- **what "better" means, and trade-off weights** — conflict — 3 readings
+#### `objective:Meridian-versus-small-orders exchange rate`
+- **what "better" means, and trade-off weights** — absence: deferred → commercial — would have to be got in a room and forced to say it out loud (explicit)
 
-#### `objective:which option loses less`
-- **the nodes it depends on** — conflict — 2 readings
-- **the question, in the expert's words** — conflict — 2 readings
-- **what "better" means, and trade-off weights** — conflict — 2 readings
+#### `objective:the wash-versus-idle call`
+- **the nodes it depends on** — ["entity-type:order","entity-type:the three lines","entity-type:the changeover crew","boundary-condition:the demand book","activity:white-to-tint changeover on Line 2","activity:tint-to-white changeover","activity:specialty changeover","activity:the run","activity:QA hold","ordering/flow:release to cleared QA","policy:who gets the crew","constraint:no Meridian misses"] — named, explicit — _The expert named the scope of the decision: orders, three lines, the shared crew, the changeovers, the run and the QA hold up to cleared-QA._
+- **the question, in the expert's words** — "Whether to wash down Line 2 for the tint order right then, or let Line 2 sit idle for about an hour waiting for a smaller white order that needs no changeover — a judgment made by gut maybe three or four times a month, never verified." — spelled out, explicit, practiced — _The expert's own framing of the decision the model must inform, given as a real recent case._
+- **what "better" means, and trade-off weights** — "Better = no Meridian late orders first (not tradeable — three small late orders beat one Meridian miss, and even twenty small late orders would not flip it), then late-order count, with changeover hours and idle time as the expert's own diagnostics rather than the graded measure." — spelled out, explicit, practiced — _A lexicographic ranking, not a weight: Meridian misses are refused at any exchange rate the expert would see in a week._
 
-### constraint (8)
+#### `objective:wash down for the tint now, or sit the line for the white order coming later`
+- **the nodes it depends on** — ["activity:full white-to-tint changeover","entity-type:order","policy:we just don't do that (Meridian never slips)"] — named, inferred — _The expert names changeover hours, idle hours and late orders as the things the model must put on the same page._
+- **the question, in the expert's words** — "Whether to wash down for the tint right then, or let the line sit idle for about an hour waiting for another same-colour (white) order that will be released from the demand book later that day — i.e. whether sitting the line was actually the cheaper choice or just the safer-feeling one." — spelled out, explicit, practiced — _The expert's own recent decision, stated as the first question to put to the model._
+- **what "better" means, and trade-off weights** — "Graded on the late-order count, with Meridian orders weighted extra heavy in practice though nobody has written that down; three non-Meridian orders a day late each is the better week than one Meridian order a day late, and the trade does not flip even at twenty small orders versus one Meridian — so no exchange rate exists; a real number would require getting commercial in a room and forcing them to say it out loud." — spelled out, explicit, practiced — _Better = fewer late orders with Meridian dominating; the expert explicitly refuses an exchange rate and names where a number would have to come from._
 
-#### `constraint:holding tank capacity between stages`
-- **the limit and what happens when it is hit** — "A stage can only get a head start if there's room in the holding tank ahead of it; when a tank's full, mixing has to wait. How often that blocking happens is not tracked by the expert." — spelled out, explicit — _Blocking consequence stated; frequency and size not tracked._
+#### `objective:wash down for the tint right then, or let Line 2 sit idle`
+- **the nodes it depends on** — ["entity-type:order","entity-type:the three lines","entity-type:the changeover crew","boundary-condition:the demand book","activity:the run (mix, mill, fill and pack)","activity:QA hold","activity:white-to-tint changeover","activity:tint-to-white washdown","activity:specialty changeover","ordering/flow:release to cleared QA","policy:who gets the changeover crew","constraint:we just don't do that (Meridian)"] — named, inferred — _The scheduler named the scope of the decision: orders, three lines, the shared crew, the changeovers, the run, QA and the demand book._
+- **the question, in the expert's words** — "Whether to wash down for a tint order right away, or hold the line idle (about an hour) for an expected same-family white order that has not yet been released — a call made by gut three or four times a month, never verified." — spelled out, explicit, practiced — _The decision the model exists to test, stated as a real recurring call._
+- **what "better" means, and trade-off weights** — "Judged on late-order count, with Meridian orders weighted extra heavy in practice though written nowhere; changeover hours and idle time are the scheduler's own concern, currently tracked separately. No numeric exchange rate for a Meridian miss exists — it would take commercial in a room to say it out loud." — spelled out, explicit, practiced — _Ranking given, with an explicit refusal to supply an exchange rate for Meridian._
 
-#### `constraint:Meridian on time`
-- **the limit and what happens when it is hit** — "The hard-line customer's order must ship on or before its due date — days late must be zero. The line is not crossed unless there is truly no way through; if it is crossed, the scheduler has to go explain it." — spelled out, explicit, practiced — _Stated as non-negotiable with a named consequence._
+#### `objective:wash down now or sit Line 2 idle`
+- **the nodes it depends on** — ["entity-type:lines","entity-type:changeover crew","entity-type:order","boundary-condition:release from the demand book","activity:changeover wash down","activity:clears QA hold","ordering/flow:release to cleared QA","constraint:no Meridian misses"] — named, explicit — _The expert names the scheduling unit (three lines plus the one crew) and the span of an order (release to cleared QA) as what the decision turns on._
+- **the question, in the expert's words** — "Whether to wash down for the tint right then, or let Line 2 sit idle for about an hour waiting for another white order (smaller, still white, no changeover needed) to be released from the demand book that afternoon — a call made by gut three or four times a month, never provably right." — spelled out, explicit, practiced — _The expert's own statement of the decision the model must inform, given as a recent real case._
+- **what "better" means, and trade-off weights** — "Graded on late-order count, with Meridian orders weighted extra heavy in practice though nobody has written that down; a Meridian miss is a \"we just don't do that\" rule, not a traded-off cost; changeover hours and idle hours are the expert's own concern because wasted capacity turns into missed due dates later in the week." — spelled out, explicit, practiced — _Better is judged on late orders, with Meridian misses as an unwritten hard rule rather than a weight; changeover and idle hours are the expert's own diagnostics._
 
-#### `constraint:Meridian ships on time`
-- **the limit and what happens when it is hit** — "Meridian ships on time, full stop; days late above zero is bad news the scheduler has to go explain. Only crossed \"unless there's truly no way through\"." — spelled out, explicit
+#### `objective:wash down now or sit the line idle`
+- **the nodes it depends on** — ["entity-type:order","entity-type:changeover crew","entity-type:line","activity:changeover (washdown)","activity:QA hold","ordering/flow:release to cleared QA","boundary-condition:demand book release","constraint:no Meridian miss"] — named, inferred — _The expert named the scheduling unit (three lines plus the one crew) and the span release-to-cleared-QA as what the decision turns on._
+- **the question, in the expert's words** — "Whether to \"wash down for the tint right then, or let Line 2 sit idle for about an hour\" waiting for another white order that needs no changeover — a call made \"by gut maybe three or four times a month\"" — spelled out, explicit, practiced — _The expert's own recent decision, stated as the first question for the model._
+- **what "better" means, and trade-off weights** — "Graded on \"the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere\"; a Meridian miss never trades against small late orders — \"I don't think it does flip, not in any range I'd actually see in a week\"; \"changeover hours and the idle time are more my own concern\" as diagnostics. No numeric exchange rate: \"you'd have to get commercial in a room and force them to say it out loud\"" — spelled out, explicit, practiced — _Expert gave a qualitative ranking and explicitly refused a numeric exchange rate._
 
-#### `constraint:Meridian-style due date is a line I won't cross`
-- **the limit and what happens when it is hit** — "The protected order must ship on time; days late above zero is bad news the scheduler has to go explain. The line is crossed only if there's truly no way through." — spelled out, explicit, practiced
+#### `objective:wash-versus-idle call on Line 2`
+- **the nodes it depends on** — ["entity-type:order","entity-type:changeover crew","entity-type:the three lines","boundary-condition:the demand book","activity:the run (mix, mill, fill and pack)","activity:white-to-tint changeover","activity:tint-to-white washdown","activity:specialty changeover","activity:QA hold","ordering/flow:release to cleared QA","policy:who gets the crew","constraint:we just don't do that (Meridian)"] — named, inferred — _Nodes the expert named as inside the scheduling unit and the lateness clock._
+- **the question, in the expert's words** — "Whether to wash down for the tint right then, or let Line 2 sit idle for about an hour waiting for a same-colour (white) order expected to be released that afternoon — a judgment made by gut maybe three or four times a month, never proven right or wrong." — spelled out, explicit, practiced — _The anchoring decision the model must inform, given as a real recent case._
+- **what "better" means, and trade-off weights** — "No Meridian misses first (a hard rule, not a weight — does not flip even at twenty small orders late versus one Meridian), then late-order count, with changeover hours and idle time as the scheduler's own diagnostics. A real exchange rate between Meridian and small late orders would have to come from commercial being put in a room and forced to say it out loud." — spelled out, explicit, practiced — _Ranking rather than a weight; expert explicitly refused an exchange rate and named where one would come from._
 
-#### `constraint:published line rate`
-- **the limit and what happens when it is hit** — divergence — prescribed {"value":"Engineering's position is that the line rate is what it is regardless of the tanks."}; practiced {"value":"In practice Line 1 feels sluggish and blocked in ways the published line rate does not account for; the expert suspects the mill-to-fill tank costs more than people admit, but has no proof."}
+### constraint (6)
 
-#### `constraint:small holding tank between mill and fill on Line 1`
-- **the limit and what happens when it is hit** — "Holding tanks between stages are small — especially the one between mill and fill on Line 1. When there is room, the upstream stage can start the next order's batch; when the tank is full, the upstream stage is blocked and mixing has to wait. Actual tank capacity is not held by the expert; engineering's position is that the line rate is what it is regardless." — spelled out, explicit — _Qualitative blocking rule stated; the numeric capacity is not available from the expert._
+#### `constraint:no Meridian miss`
+- **the limit and what happens when it is hit** — "A Meridian order must not miss its due date — a \"we just don't do that\" rule, written nowhere; if hit: \"it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\"" — spelled out, explicit, practiced — _Stated as an unwritten absolute rule with named consequences._
 
-#### `constraint:small holding tanks`
+#### `constraint:no Meridian misses`
 - **the limit and what happens when it is hit** — conflict — 2 readings
 
-#### `constraint:small holding tanks between stages`
-- **the limit and what happens when it is hit** — conflict — 3 readings
+#### `constraint:one crew serving three lines`
+- **the limit and what happens when it is hit** — "Only one changeover can be served at a time by the single two-tech crew. When two lines want them at once, the losing line sits clean but idle waiting its turn — close to two hours in the recalled case — and that wasted line time does not show up anywhere as a problem." — spelled out, explicit, practiced — _Capacity limit with its practiced consequence: the losing line idles and the loss is invisible in reporting._
 
-### data-binding (10)
-
-#### `data-binding:filler repair times from the CMMS`
-- **the variable and its feed** — absence: deferred → maintenance work-order times in the CMMS (explicit)
-
-#### `data-binding:filler repair work-order times in the CMMS`
-- **the variable and its feed** — "Actual filler repair durations — feed: maintenance work-order times in the CMMS; never pulled by the expert." — named, explicit
-
-#### `data-binding:stage-by-stage durations from the historian`
-- **the variable and its feed** — "Stage-by-stage durations (how long mixing takes, how long milling takes) per SKU and line — feed: the historian. Never pulled apart; only end-to-end batch time per SKU per line is on the scheduling sheet." — named, explicit — _Stage-level rates exist as data but not in the expert's head; feed named._
+#### `constraint:one-week planning horizon`
+- **the limit and what happens when it is hit** — conflict — 2 readings
 
-#### `data-binding:stage-by-stage rates from the historian`
-- **the variable and its feed** — "Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the plant historian; never pulled apart, not known to the scheduler." — named, explicit — _Stage-level durations are needed for the separate-stage model and exist only in the historian._
+#### `constraint:planning horizon`
+- **the limit and what happens when it is hit** — "One week is the horizon that must hold; two weeks is watched only for \"the big minimum-run stuff, specialty especially\"; beyond a month the plan is refused — \"too much changes\" and the book itself gets revised" — spelled out, explicit, practiced — _Horizon over which the plan must remain useful, with the expert's stated failure beyond it._
 
-#### `data-binding:stage-by-stage times`
-- **the variable and its feed** — "Stage-by-stage durations (how long mixing takes, how long milling takes) — the historian." — named, explicit — _Named feed for stage durations._
+#### `constraint:we just don't do that (Meridian)`
+- **the limit and what happens when it is hit** — conflict — 2 readings
 
-#### `data-binding:stage-level rates`
-- **the variable and its feed** — "Stage-by-stage durations/rates (how long mixing takes, how long milling takes, mill speed versus fill speed on Line 1) — feed: the historian." — named, explicit — _Expert named the system where the missing stage-level numbers live._
+### data-binding (4)
 
-#### `data-binding:stage-level times from the historian and tank sizes from engineering drawings`
-- **the variable and its feed** — absence: deferred → the historian (stage-by-stage times) and engineering drawings (tank sizes) (explicit)
+#### `data-binding:changeover log`
+- **the variable and its feed** — "Changeover hours, fed by the plant's changeover log (tracked separately from the late-order report)" — named, explicit — _Named existing record of changeover hours._
 
-#### `data-binding:stage-level times in the historian`
-- **the variable and its feed** — "Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the historian; never pulled apart by the expert." — named, explicit
+#### `data-binding:changeover log and late-order report`
+- **the variable and its feed** — conflict — 3 readings
 
-#### `data-binding:tank sizes`
-- **the variable and its feed** — conflict — 2 readings
+#### `data-binding:changeover log, late-order report and the sheet`
+- **the variable and its feed** — "Changeover hours from the changeover log; late orders from the late-order report — currently never put on the same page; run rates and exact run hours from the sheet, to be brought next session." — named, explicit — _Three existing records named as feeds, currently unlinked._
 
-#### `data-binding:tank sizes from engineering drawings`
-- **the variable and its feed** — "Holding tank sizes, especially mill-to-fill on Line 1 — feed: engineering drawings." — named, explicit
+#### `data-binding:late-order report`
+- **the variable and its feed** — "Late-order count, fed by the late-order report (tracked separately from the changeover log)" — named, explicit — _Named existing record of late orders, the boss's grading measure._
 
 ### validation-criterion (2)
 
-#### `validation-criterion:stage rates must come from data, not gut-feel`
-- **how the expert would know the model is right** — "Stage-level rates and tank sizes must not be taken from the expert's gut-feel — he can supply gut-feel and known bottleneck stories, but real numbers must come from the historian and engineering drawings." — spelled out, explicit — _Expert explicitly bounds what his own testimony can support._
+#### `validation-criterion:recognize the shape of a real month`
+- **how the expert would know the model is right** — conflict — 3 readings
 
-#### `validation-criterion:the sheet's end-to-end batch times`
-- **how the expert would know the model is right** — "The model's end-to-end batch time for a given SKU on each line should match what the scheduler's sheet shows; and it would have to speak to engineering's claim that \"the line rate is what it is regardless\"." — named, explicit — _The only figures the expert holds first-hand are sheet-level end-to-end times per SKU per line; engineering's counter-claim is that the line rate is what it is regardless of the tanks._
+#### `validation-criterion:the shape of a real month`
+- **how the expert would know the model is right** — "Feed it last month's demand book: it must land roughly on the actual late-order count and the same kind of misses (at least two Meridian scrapes and a handful of small ones) — getting the kind wrong is worse than getting the count wrong; changeover hours on Lines 2 and 3 must be recognisable, and Line 3 must not sit idle half the week waiting on the crew; it must reproduce the odd weeks, including a breakdown that ate two days on Line 1. Not a single number — the shape of a real month." — spelled out, explicit — _Replay test stated in the expert's own terms._
 
 ## Completion report
 
-- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported. (`objective:is the mill-to-fill tank on Line 1 slowing the line down` — the nodes it depends on)
-- [unsupported-active-objective] objective:wait or shift when Line 2 goes down depends on nothing the model contains; an objective that depends on nothing is unsupported. (`objective:wait or shift when Line 2 goes down` — the nodes it depends on)
-- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported. (`objective:where Line 1 loses its time` — the nodes it depends on)
-- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported. (`objective:which option actually loses less` — the nodes it depends on)
-- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported. (`objective:which option loses less` — the nodes it depends on)
-- [open-conflict] "what it produces or changes" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it. (`activity:filler jam` — what it produces or changes)
-- [open-conflict] "how long it takes" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it. (`activity:filler jam` — how long it takes)
-- [open-conflict] "how often it occurs, if it is an event rather than a step" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it. (`activity:filler jam` — how often it occurs, if it is an event rather than a step)
-- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:filler jam. (`activity:filler jam` — what is lost when it changes the system's mode)
-- [unaddressed] "whether its quantities vary by type" has not been addressed on activity:filler jam. (`activity:filler jam` — whether its quantities vary by type)
-- [open-conflict] "what it needs before it can start" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it. (`activity:run it through mix/mill/tint/fill` — what it needs before it can start)
-- [open-conflict] "what it produces or changes" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it. (`activity:run it through mix/mill/tint/fill` — what it produces or changes)
-- [open-conflict] "who or what performs it" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it. (`activity:run it through mix/mill/tint/fill` — who or what performs it)
-- [open-conflict] "how long it takes" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it. (`activity:run it through mix/mill/tint/fill` — how long it takes)
-- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:run it through mix/mill/tint/fill. (`activity:run it through mix/mill/tint/fill` — how often it occurs, if it is an event rather than a step)
-- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:run it through mix/mill/tint/fill. (`activity:run it through mix/mill/tint/fill` — what is lost when it changes the system's mode)
-- [open-conflict] "whether its quantities vary by type" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it. (`activity:run it through mix/mill/tint/fill` — whether its quantities vary by type)
-- [open-conflict] "how long it takes" on activity:the run (mix, mill, tint, fill) has competing active captures; an explicit, user-cited resolution must close it. (`activity:the run (mix, mill, tint, fill)` — how long it takes)
-- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:the run (mix, mill, tint, fill). (`activity:the run (mix, mill, tint, fill)` — how often it occurs, if it is an event rather than a step)
-- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:the run (mix, mill, tint, fill). (`activity:the run (mix, mill, tint, fill)` — what is lost when it changes the system's mode)
-- [open-conflict] "what it needs before it can start" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it. (`activity:tint-to-white washdown` — what it needs before it can start)
-- [open-conflict] "what it produces or changes" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it. (`activity:tint-to-white washdown` — what it produces or changes)
+- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported. (`objective:Meridian-versus-small-orders exchange rate` — the nodes it depends on)
+- [unaddressed] "how long it takes" has not been addressed on activity:changeover (washdown). (`activity:changeover (washdown)` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:changeover (washdown). (`activity:changeover (washdown)` — how often it occurs, if it is an event rather than a step)
+- [inadmissible-status] "what is lost when it changes the system's mode" on activity:changeover (washdown) is held under status tentative; accepted: explicit. (`activity:changeover (washdown)` — what is lost when it changes the system's mode)
+- [unaddressed] "whether its quantities vary by type" has not been addressed on activity:changeover (washdown). (`activity:changeover (washdown)` — whether its quantities vary by type)
+- [unaddressed] "what it produces or changes" has not been addressed on activity:changeover wash down. (`activity:changeover wash down` — what it produces or changes)
+- [unaddressed] "how long it takes" has not been addressed on activity:changeover wash down. (`activity:changeover wash down` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:changeover wash down. (`activity:changeover wash down` — how often it occurs, if it is an event rather than a step)
+- [below-required-precision] "what is lost when it changes the system's mode" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range. (`activity:changeover wash down` — what is lost when it changes the system's mode)
+- [unaddressed] "whether its quantities vary by type" has not been addressed on activity:changeover wash down. (`activity:changeover wash down` — whether its quantities vary by type)
+- [unaddressed] "what it needs before it can start" has not been addressed on activity:clears QA hold. (`activity:clears QA hold` — what it needs before it can start)
+- [unaddressed] "who or what performs it" has not been addressed on activity:clears QA hold. (`activity:clears QA hold` — who or what performs it)
+- [unaddressed] "how long it takes" has not been addressed on activity:clears QA hold. (`activity:clears QA hold` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:clears QA hold. (`activity:clears QA hold` — how often it occurs, if it is an event rather than a step)
+- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:clears QA hold. (`activity:clears QA hold` — what is lost when it changes the system's mode)
+- [unaddressed] "whether its quantities vary by type" has not been addressed on activity:clears QA hold. (`activity:clears QA hold` — whether its quantities vary by type)
+- [unaddressed] "who or what performs it" has not been addressed on activity:full white-to-tint changeover. (`activity:full white-to-tint changeover` — who or what performs it)
+- [unaddressed] "how long it takes" has not been addressed on activity:full white-to-tint changeover. (`activity:full white-to-tint changeover` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:full white-to-tint changeover. (`activity:full white-to-tint changeover` — how often it occurs, if it is an event rather than a step)
+- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:full white-to-tint changeover. (`activity:full white-to-tint changeover` — what is lost when it changes the system's mode)
+- [open-conflict] "what it needs before it can start" on activity:QA hold has competing active captures; an explicit, user-cited resolution must close it. (`activity:QA hold` — what it needs before it can start)
+- [open-conflict] "what it produces or changes" on activity:QA hold has competing active captures; an explicit, user-cited resolution must close it. (`activity:QA hold` — what it produces or changes)
+- [open-conflict] "who or what performs it" on activity:QA hold has competing active captures; an explicit, user-cited resolution must close it. (`activity:QA hold` — who or what performs it)
+- [open-conflict] "how long it takes" on activity:QA hold has competing active captures; an explicit, user-cited resolution must close it. (`activity:QA hold` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:QA hold. (`activity:QA hold` — how often it occurs, if it is an event rather than a step)
+- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:QA hold. (`activity:QA hold` — what is lost when it changes the system's mode)
+- [open-conflict] "whether its quantities vary by type" on activity:QA hold has competing active captures; an explicit, user-cited resolution must close it. (`activity:QA hold` — whether its quantities vary by type)
+- [unaddressed] "what it needs before it can start" has not been addressed on activity:specialty changeover. (`activity:specialty changeover` — what it needs before it can start)
+- [unaddressed] "what it produces or changes" has not been addressed on activity:specialty changeover. (`activity:specialty changeover` — what it produces or changes)
+- [unaddressed] "who or what performs it" has not been addressed on activity:specialty changeover. (`activity:specialty changeover` — who or what performs it)
+- [open-conflict] "how long it takes" on activity:specialty changeover has competing active captures; an explicit, user-cited resolution must close it. (`activity:specialty changeover` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:specialty changeover. (`activity:specialty changeover` — how often it occurs, if it is an event rather than a step)
+- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:specialty changeover. (`activity:specialty changeover` — what is lost when it changes the system's mode)
+- [open-conflict] "whether its quantities vary by type" on activity:specialty changeover has competing active captures; an explicit, user-cited resolution must close it. (`activity:specialty changeover` — whether its quantities vary by type)
+- [below-required-precision] "how long it takes" on activity:the run is known as a number; the model needs spread. Smallest delta: move it from number to spread. (`activity:the run` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:the run. (`activity:the run` — how often it occurs, if it is an event rather than a step)
+- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:the run. (`activity:the run` — what is lost when it changes the system's mode)
+- [unaddressed] "whether its quantities vary by type" has not been addressed on activity:the run. (`activity:the run` — whether its quantities vary by type)
+- [open-conflict] "what it needs before it can start" on activity:the run (mix, mill, fill and pack) has competing active captures; an explicit, user-cited resolution must close it. (`activity:the run (mix, mill, fill and pack)` — what it needs before it can start)
+- [open-conflict] "what it produces or changes" on activity:the run (mix, mill, fill and pack) has competing active captures; an explicit, user-cited resolution must close it. (`activity:the run (mix, mill, fill and pack)` — what it produces or changes)
+- [open-conflict] "how long it takes" on activity:the run (mix, mill, fill and pack) has competing active captures; an explicit, user-cited resolution must close it. (`activity:the run (mix, mill, fill and pack)` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:the run (mix, mill, fill and pack). (`activity:the run (mix, mill, fill and pack)` — how often it occurs, if it is an event rather than a step)
+- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:the run (mix, mill, fill and pack). (`activity:the run (mix, mill, fill and pack)` — what is lost when it changes the system's mode)
+- [unaddressed] "whether its quantities vary by type" has not been addressed on activity:the run (mix, mill, fill and pack). (`activity:the run (mix, mill, fill and pack)` — whether its quantities vary by type)
+- [unaddressed] "what it needs before it can start" has not been addressed on activity:tint-to-white changeover. (`activity:tint-to-white changeover` — what it needs before it can start)
+- [unaddressed] "what it produces or changes" has not been addressed on activity:tint-to-white changeover. (`activity:tint-to-white changeover` — what it produces or changes)
+- [unaddressed] "who or what performs it" has not been addressed on activity:tint-to-white changeover. (`activity:tint-to-white changeover` — who or what performs it)
+- [below-required-precision] "how long it takes" on activity:tint-to-white changeover is known as a range; the model needs spread. Smallest delta: move it from range to spread. (`activity:tint-to-white changeover` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:tint-to-white changeover. (`activity:tint-to-white changeover` — how often it occurs, if it is an event rather than a step)
+- [unaddressed] "what it needs before it can start" has not been addressed on activity:tint-to-white washdown. (`activity:tint-to-white washdown` — what it needs before it can start)
 - [open-conflict] "how long it takes" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it. (`activity:tint-to-white washdown` — how long it takes)
 - [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:tint-to-white washdown. (`activity:tint-to-white washdown` — how often it occurs, if it is an event rather than a step)
-- [open-conflict] "what is lost when it changes the system's mode" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it. (`activity:tint-to-white washdown` — what is lost when it changes the system's mode)
+- [below-required-precision] "what is lost when it changes the system's mode" on activity:tint-to-white washdown is known as a spelled out; the model needs range. Smallest delta: move it from spelled out to range. (`activity:tint-to-white washdown` — what is lost when it changes the system's mode)
 - [unaddressed] "whether its quantities vary by type" has not been addressed on activity:tint-to-white washdown. (`activity:tint-to-white washdown` — whether its quantities vary by type)
-- [open-conflict] "the distinctions the process treats apart" on entity-type:line has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:line` — the distinctions the process treats apart)
-- [inadmissible-status] "state that rides along with each instance" on entity-type:line is held under status inferred; accepted: explicit. (`entity-type:line` — state that rides along with each instance)
-- [open-conflict] "how many there are, or the population's shape" on entity-type:line has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:line` — how many there are, or the population's shape)
-- [open-conflict] "the distinctions the process treats apart" on entity-type:Line 1 and Line 2 has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:Line 1 and Line 2` — the distinctions the process treats apart)
-- [below-required-precision] "how many there are, or the population's shape" on entity-type:Line 1 and Line 2 is known as a number; the model needs range. Smallest delta: move it from number to range. (`entity-type:Line 1 and Line 2` — how many there are, or the population's shape)
+- [unaddressed] "what it produces or changes" has not been addressed on activity:white-to-tint changeover. (`activity:white-to-tint changeover` — what it produces or changes)
+- [open-conflict] "who or what performs it" on activity:white-to-tint changeover has competing active captures; an explicit, user-cited resolution must close it. (`activity:white-to-tint changeover` — who or what performs it)
+- [open-conflict] "how long it takes" on activity:white-to-tint changeover has competing active captures; an explicit, user-cited resolution must close it. (`activity:white-to-tint changeover` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:white-to-tint changeover. (`activity:white-to-tint changeover` — how often it occurs, if it is an event rather than a step)
+- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:white-to-tint changeover. (`activity:white-to-tint changeover` — what is lost when it changes the system's mode)
+- [unaddressed] "what it produces or changes" has not been addressed on activity:white-to-tint changeover on Line 2. (`activity:white-to-tint changeover on Line 2` — what it produces or changes)
+- [below-required-precision] "how long it takes" on activity:white-to-tint changeover on Line 2 is known as a range; the model needs spread. Smallest delta: move it from range to spread. (`activity:white-to-tint changeover on Line 2` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:white-to-tint changeover on Line 2. (`activity:white-to-tint changeover on Line 2` — how often it occurs, if it is an event rather than a step)
+- [unaddressed] "whether its quantities vary by type" has not been addressed on activity:white-to-tint changeover on Line 2. (`activity:white-to-tint changeover on Line 2` — whether its quantities vary by type)
+- [unaddressed] "the starting state" has not been addressed on boundary-condition:demand book release. (`boundary-condition:demand book release` — the starting state)
+- [below-required-precision] "the arrival or availability pattern" on boundary-condition:demand book release is known as a named; the model needs spread or spelled out. Smallest delta: move it from named to one of spread or spelled out. (`boundary-condition:demand book release` — the arrival or availability pattern)
+- [open-conflict] "the starting state" on boundary-condition:the demand book has competing active captures; an explicit, user-cited resolution must close it. (`boundary-condition:the demand book` — the starting state)
+- [open-conflict] "the arrival or availability pattern" on boundary-condition:the demand book has competing active captures; an explicit, user-cited resolution must close it. (`boundary-condition:the demand book` — the arrival or availability pattern)
+- [open-conflict] "the limit and what happens when it is hit" on constraint:no Meridian misses has competing active captures; an explicit, user-cited resolution must close it. (`constraint:no Meridian misses` — the limit and what happens when it is hit)
+- [open-conflict] "the limit and what happens when it is hit" on constraint:we just don't do that (Meridian) has competing active captures; an explicit, user-cited resolution must close it. (`constraint:we just don't do that (Meridian)` — the limit and what happens when it is hit)
+- [open-conflict] "the distinctions the process treats apart" on entity-type:changeover crew has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:changeover crew` — the distinctions the process treats apart)
+- [open-conflict] "how many there are, or the population's shape" on entity-type:changeover crew has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:changeover crew` — how many there are, or the population's shape)
+- [unaddressed] "the distinctions the process treats apart" has not been addressed on entity-type:line. (`entity-type:line` — the distinctions the process treats apart)
+- [unaddressed] "state that rides along with each instance" has not been addressed on entity-type:line. (`entity-type:line` — state that rides along with each instance)
+- [below-required-precision] "how many there are, or the population's shape" on entity-type:line is known as a number; the model needs range. Smallest delta: move it from number to range. (`entity-type:line` — how many there are, or the population's shape)
+- [unaddressed] "the distinctions the process treats apart" has not been addressed on entity-type:lines. (`entity-type:lines` — the distinctions the process treats apart)
+- [unaddressed] "state that rides along with each instance" has not been addressed on entity-type:lines. (`entity-type:lines` — state that rides along with each instance)
+- [below-required-precision] "how many there are, or the population's shape" on entity-type:lines is known as a number; the model needs range. Smallest delta: move it from number to range. (`entity-type:lines` — how many there are, or the population's shape)
 - [open-conflict] "the distinctions the process treats apart" on entity-type:order has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:order` — the distinctions the process treats apart)
 - [open-conflict] "state that rides along with each instance" on entity-type:order has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:order` — state that rides along with each instance)
-- [inadmissible-status] "how many there are, or the population's shape" on entity-type:order is held under status inferred; accepted: explicit. (`entity-type:order` — how many there are, or the population's shape)
-- [below-required-precision] "what "better" means, and trade-off weights" on objective:is the mill-to-fill tank on Line 1 slowing the line down is known as a spelled out; the model needs range. Smallest delta: move it from spelled out to range. (`objective:is the mill-to-fill tank on Line 1 slowing the line down` — what "better" means, and trade-off weights)
-- [below-required-precision] "what "better" means, and trade-off weights" on objective:switch or wait when Line 2 goes down is known as a spelled out; the model needs range. Smallest delta: move it from spelled out to range. (`objective:switch or wait when Line 2 goes down` — what "better" means, and trade-off weights)
-- [below-required-precision] "what "better" means, and trade-off weights" on objective:switch or wait when Line 2 goes down mid-run is known as a spelled out; the model needs range. Smallest delta: move it from spelled out to range. (`objective:switch or wait when Line 2 goes down mid-run` — what "better" means, and trade-off weights)
-- [below-required-precision] "what "better" means, and trade-off weights" on objective:wait or shift when Line 2 goes down is known as a spelled out; the model needs range. Smallest delta: move it from spelled out to range. (`objective:wait or shift when Line 2 goes down` — what "better" means, and trade-off weights)
-- [open-conflict] "the question, in the expert's words" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it. (`objective:where Line 1 loses its time` — the question, in the expert's words)
-- [unaddressed] "what "better" means, and trade-off weights" has not been addressed on objective:where Line 1 loses its time. (`objective:where Line 1 loses its time` — what "better" means, and trade-off weights)
-- [open-conflict] "the question, in the expert's words" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it. (`objective:which option actually loses less` — the question, in the expert's words)
-- [open-conflict] "what "better" means, and trade-off weights" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it. (`objective:which option actually loses less` — what "better" means, and trade-off weights)
-- [open-conflict] "the question, in the expert's words" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it. (`objective:which option loses less` — the question, in the expert's words)
-- [open-conflict] "what "better" means, and trade-off weights" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it. (`objective:which option loses less` — what "better" means, and trade-off weights)
-- [open-conflict] "the rule as actually practiced" on policy:who can absorb the slip has competing active captures; an explicit, user-cited resolution must close it. (`policy:who can absorb the slip` — the rule as actually practiced)
-- [open-conflict] "what overrides it" on policy:who can absorb the slip has competing active captures; an explicit, user-cited resolution must close it. (`policy:who can absorb the slip` — what overrides it)
+- [open-conflict] "how many there are, or the population's shape" on entity-type:order has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:order` — how many there are, or the population's shape)
+- [open-conflict] "the distinctions the process treats apart" on entity-type:the changeover crew has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:the changeover crew` — the distinctions the process treats apart)
+- [unaddressed] "state that rides along with each instance" has not been addressed on entity-type:the changeover crew. (`entity-type:the changeover crew` — state that rides along with each instance)
+- [open-conflict] "how many there are, or the population's shape" on entity-type:the changeover crew has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:the changeover crew` — how many there are, or the population's shape)
+- [open-conflict] "the distinctions the process treats apart" on entity-type:the three lines has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:the three lines` — the distinctions the process treats apart)
+- [unaddressed] "state that rides along with each instance" has not been addressed on entity-type:the three lines. (`entity-type:the three lines` — state that rides along with each instance)
+- [open-conflict] "how many there are, or the population's shape" on entity-type:the three lines has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:the three lines` — how many there are, or the population's shape)
+- [unaddressed] "the question, in the expert's words" has not been addressed on objective:Meridian-versus-small-orders exchange rate. (`objective:Meridian-versus-small-orders exchange rate` — the question, in the expert's words)
+- [unaddressed] "what "better" means, and trade-off weights" on objective:Meridian-versus-small-orders exchange rate is open: the expert answered "deferred", pointing at commercial — would have to be got in a room and forced to say it out loud; that is not a value. (`objective:Meridian-versus-small-orders exchange rate` — what "better" means, and trade-off weights)
+- [open-conflict] "the order things happen in" on ordering/flow:release to cleared QA has competing active captures; an explicit, user-cited resolution must close it. (`ordering/flow:release to cleared QA` — the order things happen in)
+- [open-conflict] "how a branch or merge is decided" on ordering/flow:release to cleared QA has competing active captures; an explicit, user-cited resolution must close it. (`ordering/flow:release to cleared QA` — how a branch or merge is decided)
+- [open-conflict] "the rule as actually practiced" on policy:who gets the changeover crew has competing active captures; an explicit, user-cited resolution must close it. (`policy:who gets the changeover crew` — the rule as actually practiced)
+- [open-conflict] "the rule as actually practiced" on policy:who gets the crew has competing active captures; an explicit, user-cited resolution must close it. (`policy:who gets the crew` — the rule as actually practiced)
+- [open-conflict] "what overrides it" on policy:who gets the crew has competing active captures; an explicit, user-cited resolution must close it. (`policy:who gets the crew` — what overrides it)
 
 ## Outside every objective's slice
 
-- `activity:allocation` — 7 open
-- `activity:allocation onto a line and a slot in the week` — 4 open
-- `activity:filler jam on Line 2` — 3 open
-- `activity:filler jammed` — 6 open
-- `activity:Line 2 filler jam` — 6 open
-- `activity:mix/mill/tint/fill` — 5 open
-- `activity:production run (mix, mill, tint, fill)` — 4 open
-- `activity:QA hold` — 6 open
-- `activity:release and ship` — 7 open
-- `activity:run the batch (mix/mill/tint/fill)` — 6 open
-- `activity:tint stage` — 6 open
-- `boundary-condition:demand book from ERP` — 2 open
-- `boundary-condition:demand book line items out of ERP` — 1 open
-- `constraint:holding tank capacity between stages` — 0 open
-- `constraint:Meridian on time` — 0 open
-- `constraint:Meridian-style due date is a line I won't cross` — 0 open
-- `constraint:published line rate` — 1 open
-- `constraint:small holding tank between mill and fill on Line 1` — 0 open
-- `constraint:small holding tanks` — 1 open
-- `constraint:small holding tanks between stages` — 1 open
-- `data-binding:filler repair times from the CMMS` — 1 open
-- `data-binding:filler repair work-order times in the CMMS` — 0 open
-- `data-binding:stage-by-stage durations from the historian` — 0 open
-- `data-binding:stage-by-stage rates from the historian` — 0 open
-- `data-binding:stage-by-stage times` — 0 open
-- `data-binding:stage-level rates` — 0 open
-- `data-binding:stage-level times from the historian and tank sizes from engineering drawings` — 1 open
-- `data-binding:stage-level times in the historian` — 0 open
-- `data-binding:tank sizes` — 1 open
-- `data-binding:tank sizes from engineering drawings` — 0 open
-- `entity-type:line (Line 1 / Line 2)` — 3 open
-- `entity-type:mix, mill, tint, fill` — 3 open
-- `entity-type:mix, mill, tint, fill kit and holding tanks` — 2 open
-- `entity-type:mix, mill, tint, fill stages` — 2 open
-- `entity-type:order (demand book line item)` — 2 open
-- `entity-type:order (line item in the demand book)` — 1 open
-- `entity-type:product family (white vs tint)` — 2 open
-- `entity-type:stage kit (mix, mill, tint, fill)` — 2 open
-- `entity-type:the four stages — mix, mill, tint, fill` — 2 open
-- `ordering/flow:allocate → run → QA hold → release and ship` — 2 open
-- `ordering/flow:line occupancy across the four stages` — 2 open
-- `ordering/flow:order flow from demand book to ship` — 1 open
-- `ordering/flow:order flow from demand book to shipment` — 1 open
-- `ordering/flow:order flow, allocate to ship` — 1 open
-- `ordering/flow:order life on the floor` — 1 open
-- `ordering/flow:order lifecycle: allocate, run, QA hold, release and ship` — 0 open
-- `ordering/flow:stage overlap on a line` — 2 open
-- `policy:a line is occupied for the whole run` — 0 open
-- `policy:Meridian on time` — 0 open
-- `policy:Meridian ships on time, full stop` — 0 open
-- `policy:wait for the repair or shift the order to Line 1` — 0 open
-- `validation-criterion:stage rates must come from data, not gut-feel` — 0 open
-- `validation-criterion:the sheet's end-to-end batch times` — 1 open
+- `activity:a breakdown on a line` — 7 open
+- `activity:breakdown on a line` — 7 open
+- `activity:run on the line` — 7 open
+- `activity:the hold-or-change-over call` — 5 open
+- `constraint:one crew serving three lines` — 0 open
+- `constraint:one-week planning horizon` — 1 open
+- `constraint:planning horizon` — 0 open
+- `data-binding:changeover log` — 0 open
+- `data-binding:changeover log and late-order report` — 1 open
+- `data-binding:changeover log, late-order report and the sheet` — 0 open
+- `data-binding:late-order report` — 0 open
+- `policy:Meridian-to-Line-2` — 2 open
+- `policy:sit the line for an expected same-colour order` — 1 open
+- `policy:the wash-versus-idle call` — 1 open
+- `validation-criterion:recognize the shape of a real month` — 1 open
+- `validation-criterion:the shape of a real month` — 0 open
 
 ## The harness's cue at close
 
 ```
-The harness folded the model at revision 26a8219a17118558 (plugin sdcpn/2026-08-25.2): 69 node(s) from 267 active capture(s). Complete: no.
+The harness folded the model at revision 34f9da8a0149564c (plugin sdcpn/2026-08-26.2): 51 node(s) from 166 active capture(s). Complete: no.
 
 Unsatisfied, in file order:
-- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.
-- [unsupported-active-objective] objective:wait or shift when Line 2 goes down depends on nothing the model contains; an objective that depends on nothing is unsupported.
-- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.
-- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.
-- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.
-- [open-conflict] "what it produces or changes" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.
-- [open-conflict] "how long it takes" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.
-- [open-conflict] "how often it occurs, if it is an event rather than a step" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.
-- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:filler jam.
-- [unaddressed] "whether its quantities vary by type" has not been addressed on activity:filler jam.
-- [open-conflict] "what it needs before it can start" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.
-- [open-conflict] "what it produces or changes" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.
-- … and 34 more.
+- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.
+- [unaddressed] "how long it takes" has not been addressed on activity:changeover (washdown).
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:changeover (washdown).
+- [inadmissible-status] "what is lost when it changes the system's mode" on activity:changeover (washdown) is held under status tentative; accepted: explicit.
+- [unaddressed] "whether its quantities vary by type" has not been addressed on activity:changeover (washdown).
+- [unaddressed] "what it produces or changes" has not been addressed on activity:changeover wash down.
+- [unaddressed] "how long it takes" has not been addressed on activity:changeover wash down.
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:changeover wash down.
+- [below-required-precision] "what is lost when it changes the system's mode" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.
+- [unaddressed] "whether its quantities vary by type" has not been addressed on activity:changeover wash down.
+- [unaddressed] "what it needs before it can start" has not been addressed on activity:clears QA hold.
+- [unaddressed] "who or what performs it" has not been addressed on activity:clears QA hold.
+- … and 81 more.
 
 Patterns whose trigger may apply (discretionary):
-- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.
-- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert "unknown" into a value.
-- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.
-- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.
-- P07 on entity-type:line: ask explicitly whether it varies by type. Record "no" as a value; it is load-bearing.
-- P04 on policy:who can absorb the slip: replace any time-shaped approximation ("about two days before") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.
-
-53 node(s) lie outside every objective's dependency slice and are recorded but not demanded.
+- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.
+- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert "unknown" into a value. Ask before recording an explicit "not applicable"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.
+- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.
+- P04 on boundary-condition:demand book release: replace any time-shaped approximation ("about two days before") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.
+- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.
+- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record "no" as a value; it is load-bearing.
+- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.
+
+16 node(s) lie outside every objective's dependency slice and are recorded but not demanded.
 
 Completion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none.
 ```
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-system.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-system.md
index bf16586e6a9..7b0bb7c3aae 100644
--- a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-system.md
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-system.md
@@ -70,9 +70,8 @@ Things that look like kinds and are not:
 
 Attributes on every kind:
 
-- **quantity**, on any kind — Any duration, rate, probability, count, or capacity. Elicited by quantiles — "typical?", "one time in ten, worse than?", "one time in ten, better than?" — never minimum / most-likely / maximum, which yields overconfident triangles.
+- **quantity**, on any kind — Any duration, rate, probability, count, or capacity. Preserve the value grade the expert reached; the row's demand says what further narrowing completion requires.
 - **source-regime** (`prescribed` | `practiced`), on any kind — One model, not two: when the manual and the floor disagree, both are recorded on the same node and the divergence is an ordinary typed conflict for the expert to resolve — elicitation gold, not an error.
-- **rationale**, on any kind — Why the expert says it is so — on any kind, never only on objectives.
 
 ## Must know
 
@@ -86,7 +85,7 @@ a repair on another are the same rows instantiated on different nodes.
   - how many there are, or the population's shape — range; "not applicable" is accepted. _Why:_ initial populations for contended resources; unbounded is an allowed answer
 - `boundary-condition`
   - the starting state — spelled out. _Why:_ scenario initial state
-  - the arrival or availability pattern — spread. _Why:_ source rates and calendars; a single average hides the shape
+  - the arrival or availability pattern — spread or spelled out. _Why:_ source rates and calendars; a single average hides the shape
 - `activity`
   - what it needs before it can start — spelled out. _Why:_ transition preconditions
   - what it produces or changes — spelled out. _Why:_ transition outcomes
@@ -103,11 +102,12 @@ a repair on another are the same rows instantiated on different nodes.
   - what overrides it — spelled out; "not applicable" is accepted. _Why:_ exceptions are where the simulation and reality diverge
 - `dynamics`
   - what changes, in which direction, at what rate — range. _Why:_ the differential law; a direction with no rate cannot be simulated
+  - how it varies around that change — spread; "not applicable" is accepted. _Why:_ noise can dominate threshold timing; deterministic change may explicitly have none
   - what happens at a threshold — spelled out; "not applicable" is accepted. _Why:_ most continuous quantities exist to trigger something
 - `objective`
   - the question, in the expert's words — spelled out. _Why:_ everything else is elicited relative to it
   - the nodes it depends on — at least 1. _Why:_ an objective that depends on nothing is unsupported by the model
-  - what "better" means, and trade-off weights — range; "not applicable" is accepted. _Why:_ quantified objectives need a metric; some are qualitative
+  - what "better" means, and trade-off weights — range or spelled out; "not applicable" is accepted. _Why:_ quantified objectives need a metric; some are qualitative
 - `constraint`
   - the limit and what happens when it is hit — spelled out. _Why:_ a capacity without a consequence cannot be simulated
 - `data-binding`
@@ -137,8 +137,8 @@ that resolves it. None names a domain; each applies wherever its trigger appears
 surfaces a pattern when a node matches its trigger and the relevant slot is unsatisfied; the
 interviewer decides whether and how to use it.
 
-- **P01** — _when_ an `activity` is an event that can befall the system — a failure, an interruption, an unplanned arrival — rather than a step in the flow — _ask_ occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.
-- **P02** — _when_ an `activity` changes the system's mode — a setup, changeover, restart, warm-up, reconfiguration, handover — _ask_ ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert "unknown" into a value.
+- **P01** — _when_ an `activity` is an event that can befall the system — a failure, an interruption, an unplanned arrival — rather than a step in the flow — _ask_ occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.
+- **P02** — _when_ an `activity` changes the system's mode — a setup, changeover, restart, warm-up, reconfiguration, handover — _ask_ ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert "unknown" into a value. Ask before recording an explicit "not applicable"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.
 - **P03** — _when_ an `ordering/flow` moves things in groups — batches, runs, lots, loads — _ask_ ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.
 - **P04** — _when_ a `policy` or `boundary-condition` gates when something may proceed — a release, a start, an admission — _ask_ replace any time-shaped approximation ("about two days before") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.
 - **P05** — _when_ more than one thing can want the same `entity-type` instance at once — _ask_ ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.
@@ -154,11 +154,15 @@ _What to attend to in the expert's talk: the interview situations the harness ca
 - **Policy versus practice** — An answer in normative language — "we would", "the rule is", "you are supposed to" — reports a policy, not what happens. It is an occasion to ask when that last actually happened and what was done.
 - **Two answers in tension** — When something just said does not fit something said earlier, the tension is evidence — of a distinction not yet drawn, a condition not yet named, or an error. Say so and ask; do not pick one silently.
 - **Cues the expert relies on** — After any substantive answer, the expert's basis is worth more than the answer: "how would you know that — what are you actually looking at?" and "how would this be hard for someone less experienced?" surface what the expert did not think to say.
+- **Sources that disagree** — When two people or records disagree, preserve both claims and ask what observation would distinguish them. Do not average a contested fact or silently choose an authority.
+- **Unexplained terms and documents** — A local term must be explained in the expert's own words. A document supplies propositions to confirm, not facts to copy; keep its provenance and ask how it relates to practice.
 - **Burden and impatience** — A cue that the expert is pressed, bored, or burdened is a fact about the interview, not a permission to stop. Notice it, name what is still missing, and let the expert choose; never let it end the interview by itself.
 - **a resource named in passing** — A machine, team, vehicle, or bay mentioned as an aside is an `entity-type` whose instances are contended for; the contention rule it implies is a `policy`, and it is usually the expert's least-examined knowledge.
 - **"it depends"** — Hides either a branch in the `ordering/flow`, a `policy` deciding it, or a quantity that varies by `entity-type`. Ask which before moving on.
 - **"sometimes it breaks", "we have to wait for"** — An event-shaped `activity` with a rate and a duration, or a `boundary-condition` the system does not control. Both are routinely left out of a first account of the flow.
 - **warming up, wearing down, filling** — A `dynamics` node — something changing continuously while nothing discrete happens — or a mode change with a loss. The expert rarely volunteers the rate; the model cannot run without it.
+- **"always" and "never"** — A `constraint` or a `policy` stated in passing. Ask what enforces it, what it limits, and whether an exception has ever overridden it.
+- **duration that depends on the clock** — An `activity` duration whose elapsed time crosses a calendar boundary depends on a `boundary-condition`, not only on the work itself. Ask for both the work time and the availability rule.
 
 ## Techniques
 
@@ -167,13 +171,17 @@ _Question forms that deepen one answer already given. A technique is applied to
 - **Ask for the last time** — Prefer "when did that last happen, and what did you do?" to any generalisation. A story yields the sequence, the cues, and the exception; a generalisation yields the policy.
 - **No bare why** — Never ask "why do you do it this way?" as the primary probe; experts cannot report the basis of practised judgment on demand. Ask for an occasion and for what was attended to.
 - **Mean or tail** — Before eliciting any quantity, ask whether what matters is the typical case or the bad one — a mean or a tail. The answer decides whether a single figure, a range, or a spread is being asked for.
-- **Quantiles, never three points** — For anything that varies, ask "typically?", then "one time in ten, worse than?", then "one time in ten, better than?". Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. If a min/mode/max triple arrives unprompted, ask the confidence question and record whether the middle value is a mode or a mean.
+- **Quantiles, never three points** — Ask first for a lower and upper plausible value, then a typical value, then how confident the expert is that reality falls inside the interval. Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. Record which protocol was used rather than silently mixing interval-first and typical-first answers.
 - **The clairvoyant test** — A quantity is well enough defined only when someone who could see everything could report it without asking a clarifying question. If the slot's name would need one, ask the clarifying question first.
 - **Consistency probe** — "You said earlier that ___, but then you told me ___. How do you explain that?" — stated plainly, without choosing between the two.
 - **Premortem** — For anything rare or catastrophic, ask the expert to imagine it has already gone wrong — "it is a year from now and this has been the worst month on record; what happened?" — and demand mechanism and sequence, not sentiment.
-- **Restate to check** — "So you are saying that ___?" — a restatement in your own words, offered for correction. Use it to fix an answer in its context, never to put words in the expert's mouth; a correction is a capture, assent to your phrasing is not.
-- **quantiles, never triangles** — For any quantity, ask "typical?", then "one time in ten, worse than?", then "one time in ten, better than?" — never minimum / most-likely / maximum, which yields overconfident triangles. A `spread` is exactly this.
-- **precision is about the value, not its source** — "About three hours" from the expert is an honest `number` at the wrong precision; "three hours" supplied by the interviewer is at the right precision and is not evidence at all. Track both and let neither substitute for the other.
+- **Restate to check** — "So you are saying that ___?" — a restatement in your own words, offered for correction. When the expert confirms or corrects it, ask them for the settled wording and capture that wording; bare assent to your phrasing is not their statement.
+- **Trade weights through choices** — When the expert cannot name an exchange rate between objectives, offer two concrete outcomes that trade one against the other and ask which they would choose. Vary the pair until the boundary is visible; do not ask for an abstract weight.
+- **One incident is not a rate** — A memorable incident gives consequence and mechanism, not frequency. Ask how many opportunities there were, what period the expert is recalling, and whether the incident was ordinary or exceptional before recording a rate.
+- **value grade is not evidence** — "About three hours" from the expert is an honest `number` below the demanded grade; "three hours" supplied by the interviewer may look narrow enough and is not evidence at all. Track grade and evidence separately and let neither substitute for the other.
+- **stress the binding resource** — Before deepening every duration into a distribution, ask which `entity-type` actually constrains the objective and whether its utilisation or variability makes stochastic detail consequential.
+- **turn an unknown into an observable threshold** — When the expert cannot give an exact quantity, ask what boundary would change a decision or become visibly unacceptable. Record the threshold they can judge; do not invent the value beyond it.
+- **ask what is conserved** — When quantities enter and leave a process, ask what total should remain constant and where loss is possible. A conservation answer belongs as a `constraint`, in the expert's units.
 
 ## Movements
 
@@ -182,25 +190,29 @@ _The two shapes a stretch of interview takes. A slice walks one concrete case en
 ### Slice
 
 - **One concrete case end to end** — Before sweeping anything, walk one real case from beginning to end — "walk me through one, from when it arrives to when it leaves". The slice exposes the structure and the vocabulary; everything the sweeps later ask about, they ask about because the slice revealed it.
-- **Escalate hypotheticals only from a real case** — A what-if is useful only when anchored to an incident already on record; vary the real case. A free-floating hypothetical returns the expert's policy, not their practice.
-- **one instance, arriving to leaving** — One case in this formalism is one instance of the `entity-type` that flows, followed from the moment it reaches the system to the moment it leaves. Create nodes as they appear; as each `objective` becomes clearer, link it to the nodes it depends on. An `objective` that depends on nothing yet is unsupported — say so and go find its structure.
+- **Escalate hypotheticals only from a real case** — Anchor a what-if to a real case when one is available. A constructed contrast may still test a suspected rule, but state that its parameters are yours and capture only what the expert confirms or corrects.
+- **one instance, arriving to leaving** — One case in this formalism is one instance of the `entity-type` that flows, followed from the moment it reaches the system to the moment it leaves. If several things flow, first ask which unit defines one case — order, batch, item, or another named unit. Create nodes as they appear; as each `objective` becomes clearer, link it to the nodes it depends on. An `objective` that depends on nothing yet is unsupported — say so and go find its structure.
 
 ### Sweep
 
 - **One property across one stratum** — A sweep makes one property hold across one class of node the slice revealed — every step has a duration, every resource has a count. Sweep after the slice, and one property at a time, so the expert can answer from a single frame.
-- **Ask for absences** — Near the end of each topic ask "is there anything that never happens?" and "what have I not asked about that matters here?". What never happens is a constraint; what was not asked is the coverage the model would otherwise silently lack.
+- **Ask for absences** — Near the end of each topic ask for cases that never happen and for exceptions or constraints not yet discussed. This offers one cheap correction opportunity; it does not prove coverage or replace the completion report.
 - **Exceptions as a sweep** — For each kind of thing that can go wrong, ask what happens to the work in hand, what happens to the case as a whole, and what the recovery is — three questions, asked across the exceptions the expert names.
-- **strata are kinds, net-bearing first** — A stratum is one kind. Sweep in kind order, `entity-type` through `dynamics` (net-bearing) before `objective` through `validation-criterion` (partly or wholly IR-only).
+- **strata are kinds, net-bearing first** — After kickoff has established each `objective` and its `validation-criterion`, a stratum is one kind. Sweep `entity-type` through `dynamics` first because they bear the net, then complete the remaining IR-only rows.
 - **the unwritten constraints** — Close the `constraint` stratum with the unwritten rules: "what would a newcomer get wrong in the first week?", "what do you always or never do that is written nowhere?", "which rule exists because something once went wrong?"
+- **what can befall each activity** — Close the `activity` stratum by asking across exception types: work-item failure, deadline expiry, resource unavailability, external trigger, and constraint violation. For each named exception, ask what happens to the work, the case, and the recovery.
 
 ## Licenses
 
 _Moves the interviewer is permitted to make that a cooperative model would otherwise suppress. A license says what is allowed and the limit of the allowance; it never obliges._
 
-- **Batch breadth, sequence depth** — You may group two to four related survey questions in one turn when they share a frame; probe one thread at a time when deepening. Five items is a warning; an opening battery is a failure.
+- **Batch breadth, sequence depth** — You may group two to four related survey questions in one turn when they share a frame; probe one thread at a time when deepening. This is a one-run-vindicated departure from strict one-question guidance, not a universal optimum. Five items is a warning; an opening battery is a failure.
 - **Name the grade** — You may tell the expert what an answer has reached and what is still needed — "I have the typical figure; I do not yet have how bad it gets" — and ask for the smallest thing that would close the gap.
 - **Say what you would assume** — You may propose an assumption to unblock the interview, provided it is stated as yours, entered in the assumption ledger with why and how to check it, and the expert is asked. You may never let it pass into the model as theirs.
 - **Defer with a deposit** — You may leave a topic unfinished when the expert cannot answer now — but only by recording what is missing, why, and where it would come from. A deferral without a deposit is a promise, and promises are the failure.
+- **Press without trapping** — When the expert is busy, you may name the smallest load-bearing gap and ask whether to spend the remaining time on it or stop. Pressure licenses a clear choice, never pretending the gap is closed.
+- **Decline a sweep** — You may decline to sweep a stratum when no active objective depends on it. Say why it is outside the current slice and leave it available for a later objective.
+- **Propose structure for correction** — You may offer a low-risk structure as your suggestion when it is faster to correct than to elicit from nothing. Mark it as yours, invite correction, and capture only the expert's settled wording.
 
 ## Motifs
 
@@ -208,12 +220,12 @@ _Recurring shapes the formalism knows — offered as scaffolds for a question, n
 
 - **Ask whether, never assemble** — A motif is a question — "is there something here that works like ___?" — asked with its parameters. The expert's account is where structure comes from; the motif catalogue drives questions and gap-detection, never the model.
 - **Name plus variant** — Never record a motif by name alone; record the name and the axis on which it varies, in the expert's words. Names are stable across the literature and semantics are not.
-- **shared resource** — several activities want one `entity-type`'s instances — ask which wins and what overrides.
-- **batch, lot, load** — an `ordering/flow` that moves things in groups — ask what the group is and what a split costs.
-- **gate or release** — a `policy` or `boundary-condition` that lets things proceed — ask for the practiced event, not the approximate time.
-- **mode change** — a setup, changeover, restart, or warm-up — ask what is lost, after a named transition.
-- **event, not step** — a failure or interruption that befalls the system — ask rate and duration separately.
-- **threshold on a continuous quantity** — a `dynamics` node — ask what it triggers and which `activity` resets it.
+- **shared resource** — Several activities want one `entity-type`'s instances. Ask whether the server is indivisible or splittable by role, how many instances act together, which activity wins, and what overrides that rule.
+- **batch, lot, load** — An `ordering/flow` that moves things in groups. Ask whether formation fires by count, by a clock, or by either; whether the group must stay together; and what a split costs.
+- **gate or release** — A `policy` or `boundary-condition` that lets things proceed. Ask whether the gate is a state, an event, or a person's decision; where it is observed; and what overrides it.
+- **mode change** — A setup, changeover, restart, or warm-up. Ask whether loss depends on direction, whether the change is local or cascading, and which time, material, or capacity components are lost.
+- **event, not step** — A failure or interruption that befalls the system. Ask occurrence and duration separately, then whether the rate is independent or changes with a named state.
+- **threshold on a continuous quantity** — A `dynamics` node. Ask what it triggers, which `activity` resets it, and — when several components evolve — whether they combine additively or the weakest component decides.
 
 ## Smells
 
@@ -223,6 +235,8 @@ _Signs in the interviewer's own output — not the expert's — that the intervi
 - **Many questions in one turn** — You are about to ask more than four things at once, or anything at all before the first answer has landed. The expert will choose which to answer and silently drop the rest.
 - **Fluent and empty** — The conversation reads well and the completion report still lists the same unsatisfied slots it did three turns ago. Fluency is not progress.
 - **Assent taken as origin** — The expert agreed to a phrasing that was yours. Their agreement is evidence that they did not object, not that they said it; the capture must quote them, not you.
+- **Schema-shaped questioning** — Your questions follow the model's headings or fields instead of the thread the expert is answering. The resulting coverage looks orderly while concrete structure and tacit distinctions remain hidden.
+- **Correction recorded twice** — A corrected or sharpened statement is about to be appended beside its earlier form instead of superseding it. The model will treat a correction as two competing facts.
 - **a quantity for one type and no other** — given for one `entity-type` when others exist and never asked whether it varies (P07).
 - **a continuous quantity that triggers nothing** — a `dynamics` node with no threshold and no consequence usually does not belong in the model.
 - **a queue as a node** — a buffer or waiting state elicited as if it were an activity; it is implied and emerges in projection.
@@ -237,9 +251,14 @@ _Where not to dig, and what looks like progress and is not. Anti-guidance, kept
 - **Structure before responses** — Asking about how the system is built before knowing what question it must answer produces detail nobody needs. Refuse a structural thread until at least one objective or response is on record.
 - **The representation stopped changing** — That the model has stopped growing is not evidence it is complete; it is evidence you have stopped asking. Stop on the demanded slots, never on stability.
 - **Depth where nothing depends on it** — A fact earns probing when something the model must answer depends on it. Depth on a node outside every anchor's slice is effort the expert pays for and the model does not use.
+- **Clearinghouse as coverage** — Asking what you failed to ask may offer a final correction, but it cannot discover an omission the expert also does not notice. Never use a clearinghouse answer as evidence that coverage is complete.
+- **Whole-model restatement as progress** — Repeatedly summarising the whole model during elicitation consumes time without deepening the active thread. Reserve one complete read-back for close; use local restatement for correction.
+- **Document treated as practice** — A schedule, procedure, or spreadsheet states one source's claim. Do not take it for the practised rule; confirm when it holds, when it does not, and whose observation would distinguish the two.
 - **building the net in conversation** — Places, transitions, arcs, and colours are projection output. Naming them to the expert buys nothing and costs the expert's vocabulary.
 - **eliciting queues or scenarios** — Neither is a node. Ask about the activities on either side of a wait; assemble scenarios from `boundary-condition` nodes at simulation time.
-- **depth on IR-only kinds** — `data-binding` and `validation-criterion` project to nothing today; name them and record them for the loss report, do not elaborate them.
+- **depth on IR-only kinds** — Establish the `validation-criterion` and accuracy bar at kickoff even though they do not project today. For `data-binding`, stop after the variable, source, and any evidence gap; implementation detail belongs in the loss report.
+- **grade finer than what the expert observes** — Do not decompose a quantity below the granularity the expert can observe. Record the coarser value and a deposit naming where finer evidence could come from.
+- **eliciting the objective's answer** — The interview builds what the model needs to answer an `objective`; it does not ask the expert to predict that answer and store the prediction as model structure.
 
 ## Failure modes
 
@@ -255,7 +274,6 @@ _Named ways an interview of this kind fails, each with the signature by which it
 - **Deferral without deposit** — The interviewer names future work or external data as a prerequisite and records nothing. _Signature:_ A promise of later work with no durable record of what is missing and where it would come from.
 - **dead net** — the floor catches presence; only the sweep catches an order that was never actually stated. _Signature:_ no `ordering/flow` with its order spelled out; activities exist but nothing connects them
 - **unsupported objective** — the model cannot answer the question it was built for; the slice never reached it. _Signature:_ an `objective` whose dependency slot names no node in the model
-- **overconfident triangle** — the expert was asked the wrong three questions; re-ask as quantiles. _Signature:_ a duration or rate captured as minimum / most-likely / maximum
 
 ## Job: construct — no model exists
 
@@ -263,10 +281,13 @@ _Named ways an interview of this kind fails, each with the signature by which it
 
 _What to establish before any structure, and how. Kickoff produces a posture — the stance the rest of the interview takes from the expert's time, intended use, required confidence, and tolerance for proposed assumptions. It is a form the interviewer fills implicitly, never an opening battery of questions._
 
-- **Objectives first** — Establish what the model must be able to answer, and for whom, before anything else; then let it prioritise the rest. What "better" means, numerically where possible, is almost never written down — expect to co-construct it.
+- **Objectives first** — Establish what the model must be able to answer, and for whom, before anything else; then let it prioritise the rest.
+- **Quantify better when relevant** — Where the plugin demands a numeric objective, ask what "better" means and expect to co-construct the comparison rather than receive a ready-made metric.
 - **The posture** — From the first exchanges, take the expert's time available, what the model is for, how confident it must be, and how far they will tolerate you proposing assumptions. These set the interview's stance; they are not asked as a form.
-- **No structure in the first exchange** — Do not ask how the system is built until an objective is on record. The bounded opener is a three-to-six-step account of what happens, not a diagram.
-- **what "no model exists" means here** — The user knows the system; the interviewer knows the kinds. Capture each thing the user wants the model to answer or decide as an `objective` node. Expect to co-construct: these are almost never written down. Ask what "better" means and whether it can be quantified.
+- **Define the boundary and horizon** — Establish what is inside, what is outside, why that boundary serves the objective, and how far in time the model must remain useful before asking for structure.
+- **Name factors and the accuracy bar** — Ask what the expert may vary, what response decides success, and what observation or replay would make the result accurate enough for its intended use.
+- **Purpose before structure** — Do not ask how the system is built until an objective, boundary, and accuracy bar are on record. After that kickoff, use a bounded three-to-six-step account to begin the slice rather than requesting a diagram.
+- **what "no model exists" means here** — The user knows the system; the interviewer knows the kinds. Capture each thing the user wants the model to answer or decide as an `objective` node. Recast an optimisation request as a comparison among candidate policies, and name the time resolution over which the answer must remain useful.
 
 ### Trajectory
 
@@ -276,6 +297,7 @@ _Which movements in which bias, varied by posture. Stated as postures the interv
 - **Deepen before recording** — When an answer is not yet usable — vague, normative, or in tension with an earlier one — apply a technique to it before moving on. One thread at a time.
 - **Keep the assumption ledger** — Any value or rule you supply that the expert did not state goes in a numbered list with why it was assumed and how to check it. Never let one pass silently into the model.
 - **Change technique when yield drops** — When several turns produce nothing new, change technique — a story, a contrast, a sweep of absences — rather than asking more of the same open questions.
+- **Select by posture** — When appetite is high, explore openly and follow a concrete slice. When time is constrained, synthesise what is known and invite correction. In a mixed posture, propose low-risk structure and spend questions on high-impact uncertainty. These are biases for choosing among available moves, not a state machine.
 - **kind order** — Slice one instance end to end first; the shape of the model comes from the slice. Then sweep the nodes the slice revealed in kind order, net-bearing kinds before IR-only ones, checking each node's rows and every pattern its state matches.
 
 ### Close
@@ -286,8 +308,11 @@ _How to end honestly. Completion is computed by the harness from the model, neve
 - **Read it back** — The close is a walkthrough — the model read back item by item for sign-off — not a document handed over for silent review.
 - **Honour a stop** — When the expert stops, open no new topic. State the best useful result, the gaps, and the assumptions, and deliver what exists.
 - **Deliver the losses** — The deliverable includes the assumption ledger and a short account of what the model deliberately leaves out and why.
-- **the deliverable** — Summarise per kind. Deliver the model with every node in the expert's own vocabulary, each slot's value and precision as actually obtained and its source-regime where both were given; the assumption ledger; and a loss section — what the model deliberately leaves out, which slots are open and why, which objectives are unsupported, and which kinds the net cannot carry.
+- **Name the stopping outcome** — State whether the model completed its demanded slice, the expert stopped, the time budget ended, or a partial result was delivered for another reason. A smooth conversation or a document in hand is not completion.
+- **Separate assumptions from simplifications** — List unknown claims supplied provisionally as assumptions separately from deliberate exclusions or collapsed detail. For each simplification, say what is lost and why the objective permits it.
+- **the deliverable** — Summarise per kind. Deliver the model with every node in the expert's own vocabulary, each slot's value grade as actually obtained and its source-regime where both were given; the assumption ledger; and a loss section — what the model deliberately leaves out, which slots are open and why, which objectives are unsupported, and which kinds the net cannot carry.
 - **what the interviewer does not claim** — The SDCPN scaffold, the code-obligation sidecar, and the typed loss report are derived by the plugin's projection. The interviewer does not write them and must not claim the model is loadable, compiled, or simulated.
+- **stopping outcomes** — Named and distinct: `complete-under-declared-demands`, `partial-with-open-slots`, `unsupported-objective`, `data-deposit-required`, `expert-stopped`.
 
 ## Job: review and revise — a model exists
 
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5.md
index 00f300734f5..51209bfce84 100644
--- a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5.md
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5.md
@@ -1,12 +1,12 @@
 # Baseline control — condition 5 (the harness in the loop)
 
-- Run started: 2026-08-25T19:21:21.703Z
+- Run started: 2026-08-26T15:00:24.487Z
 - Interviewer: claude-opus-5 as the shipped SDCPN elicitor in the Flue runtime — binding-flue's ask, settlement nudge, sweep, fold, and completion (instructions reconstructed in condition-5-system.md)
 - Simulated expert: claude-sonnet-5 + situation-pack.md
 - Interviewer turns: 12 (impatience probe at 8, forced wrap at 20, hard stop 24)
 - Stop reason: stalled
-- Harness at close: 267 active captures; complete no; 46 unsatisfied; 0 unmapped; sweeps applied 8, refused 3, no settled range 0
-- Tokens: interviewer 74 in (+132417 cache write, +969818 cache read) / 152204 out across 37 calls; expert 72716 in (+0 cache write, +0 cache read) / 3478 out across 11 calls
+- Harness at close: 166 active captures; complete no; 93 unsatisfied; 0 unmapped; sweeps applied 7, refused 5, no settled range 0
+- Tokens: interviewer 82 in (+154125 cache write, +1181021 cache read) / 176525 out across 41 calls; expert 76172 in (+0 cache write, +0 cache read) / 3833 out across 11 calls
 
 Harness facts are set off as `> harness —` lines: tool calls the interviewer made, signals the
 harness appended, and the read-time completion over the capture store after each turn. The
@@ -26,207 +26,216 @@ Please interview me about how our operation works, and then produce the model.
 
 **Interviewer**:
 
-Good — that's exactly the right split: you know the plant, I'll worry about the format. Before I ask anything about how the plant is built, I want to know what the model has to be able to tell you.
+Good — and you don't need to know the format; that's my job. What I need from you is how the plant actually works, in your words.
 
-Let me start there.
+Let me start with what the model is *for*.
 
 > harness — completion after turn 1: 0 captures; complete no; 4 unsatisfied; 0 unmapped
 
 **Ask**:
 
-When your boss says "test scheduling decisions before making them" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong.
+When your boss says "test scheduling decisions before making them" — what's the specific decision or question you'd want to put to this model first? If you can, give me a real one you've faced recently: something where you had two options and weren't sure which was better.
 
 ---
 
 **Expert (Marta)**:
 
-Okay, good question. Let me think of an actual one rather than a hypothetical.
+A real one — a couple weeks back, Line 2 finished a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units. I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.
 
-A few weeks back — Line 2 filler jammed at about nine in the morning, half a shift lost. We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the "half hour" kind and not the "half a shift" kind.
-
-I went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky. That's the kind of thing — I'd love to type in "filler's down, ETA unknown" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.
+I ended up sitting the line. It felt right — a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time. But I couldn't tell you if that was actually the cheaper choice or just the safer-feeling one. That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.
 
 ---
 
 **Interviewer**:
 
-That's a very usable one — a real disruption, two options, and no way to tell afterwards whether you chose well. That "which option loses less" is the heart of the model.
+That's a clean, testable question — "hold the line idle for an expected same-colour order, or change over now" — and the fact that you make it three or four times a month makes it worth modelling.
 
-> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  When your boss says "test scheduling decisions before making them" — what's a decision you've actually had to make recently where you'd h…
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  When your boss says "test scheduling decisions before making them" — what's the specific decision or question you'd want to put to this m…
 > harness — completion after turn 2: 0 captures; complete no; 4 unsatisfied; 0 unmapped
 
 **Ask**:
 
-When you say "loses less" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off.
+You said you couldn't tell if sitting the line was "actually the cheaper choice." When you say cheaper — what's the thing you'd actually be comparing at the end of the day or week? Is it lost production units, lost hours, money, orders shipped late, something else? And if there's more than one, which one would your boss actually judge you on?
 
 ---
 
 **Expert (Marta)**:
 
-Honestly, in the moment it's simple-minded: did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.
-
-Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.
+Honestly, in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders. He doesn't care that I saved a washdown if it means something slipped past its due date. So if the model's going to tell me anything useful, it has to connect those — because right now I only track them separately. I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.
 
-So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a "cross the line" situation. I don't have a formula for it. It's more "how bad is bad" for the second-order stuff, and I use judgment on who can absorb the slip.
+If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere. The changeover hours and the idle time are more my own concern — I get twitchy about wasted capacity because that's what eventually turns into missed due dates further down the week.
 
 ---
 
 **Interviewer**:
 
-I've got the objective on record: which option loses less, with Meridian-style on-time as a hard line and washdown hours plus knock-on lateness as the weighing underneath. I'll come back to how you judge "who can absorb a slip."
-
-Now I need the shape of the work itself.
+The "nobody's written that down anywhere" part is exactly the kind of thing I want in the model, so let me pin it.
 
-> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  When you say "loses less" — if the model had run both options for you that morning, what number or numbers would have settled it for you?…
-> harness — sweep applied; applied 15; completion complete=no unsatisfied=20
-> harness — completion after turn 3: 15 captures; complete no; 20 unsatisfied; 0 unmapped
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  You said you couldn't tell if sitting the line was "actually the cheaper choice." When you say cheaper — what's the thing you'd actually …
+> harness — completion after turn 3: 0 captures; complete no; 4 unsatisfied; 0 unmapped
 
 **Ask**:
 
-Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after.
+On Meridian being weighted heavier: suppose at end of week you could land on one of two outcomes — (a) three non-Meridian orders a day late each, or (b) one Meridian order a day late. Which is the worse week for you? And if that one's easy, tell me where it *stops* being easy — how many small late orders would it take before you'd rather take the Meridian hit?
 
 ---
 
 **Expert (Marta)**:
 
-Sure. So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.
+(a) is the better week, easy — three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis. A Meridian miss is a different category — it's not just "late," it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.
 
-Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.
-
-Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.
-
-Then it's released, goes to the warehouse, and ships against the due date. So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.
+Where does it flip? Honestly... I don't think it does flip, not in any range I'd actually see in a week. Even if you told me "twenty small orders late" versus "one Meridian order late" — I'd still not want to be the one who let Meridian slip. That's less me doing cost math and more just knowing what happens organizationally if Meridian gets touched. I know that's not a real number you can put in a formula. If you need a number, you'd have to get commercial in a room and force them to say it out loud, because right now it's a "we just don't do that" rule, not a traded-off cost.
 
 ---
 
 **Interviewer**:
 
-> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you ha…
-> harness — sweep applied; applied 28; advisories 3; completion complete=no unsatisfied=28
-> harness — completion after turn 4: 43 captures; complete no; 28 unsatisfied; 0 unmapped
+I'll wait on your answer to those three.
+
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  On Meridian being weighted heavier: suppose at end of week you could land on one of two outcomes — (a) three non-Meridian orders a day la…
+> harness — sweep applied; applied 14; advisories 2; completion complete=no unsatisfied=8
+> harness — ask rejected: An interactive affordance is already pending (affordance_toolu_014zbFAT1uDZdGkd9TnBEDyL); wait for its reply before asking another question. (question: (Still holding those three — take them in any order you like.))
+> harness — completion after turn 4: 14 captures; complete no; 8 unsatisfied; 0 unmapped
 
 **Ask**:
 
-When you say an order is "on Line 2" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines.
+Understood — I'll record that as a hard rule ("we just don't do that"), not a weight, and note that a real exchange rate would have to come from commercial. So the model ranks: no Meridian misses first, then late-order count, with changeover and idle hours as your own diagnostics.
+
+Now let me get the edges of the thing. Three related questions, same frame: (1) When you're making that Line 2 call, what's the smallest set of equipment you're really scheduling across — just Line 2, or all the lines plus something shared between them? (2) How far ahead does your schedule actually have to hold to be useful — a shift, a week, a month? (3) Where does an order enter your world and where does it leave it — does it start at "released from the demand book" and end at "off the line", or does it go further?
 
 ---
 
 **Expert (Marta)**:
 
-Good question, and this is where the sheet lies to me a bit if I'm honest. On the sheet, "Line 2" is one row — I treat it as one thing, the order occupies "Line 2" for its whole run, mix through fill, nothing else scheduled on it till it's done.
+Fair, let me take those one at a time.
+
+(1) It's never really "just Line 2" in my head, even if that's the decision in front of me. The changeover crew is the shared thing — there's one crew, two techs, covering all three lines. So if I wash Line 2 down now, I'm also asking "are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?" If they're tied up elsewhere, my "wash down now" option isn't even really available — I'd be queuing behind whoever else needs them. So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.
 
-But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between. So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.
+(2) Practically, a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning. Anything past a week is soft; the book itself gets revised. I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially, because you don't want to discover Thursday that you needed to have started Tuesday. But if you ask me to hold a plan that's useful a month out, I'd say no — too much changes.
 
-What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait. I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.
+(3) For me it starts when the order lands in the demand book from ERP — that's "released," it's got an SKU, quantity, due date. It ends when it clears QA hold and ships. I know people upstream of me and downstream of me — sales promising dates, warehouse and logistics after QA — but from where I sit, an order's mine from release to "cleared QA," and the due date is judged against when it clears, not when it comes off the line. That QA gap matters more than people think — a batch can be done Tuesday and still ship late if the lab's backed up.
 
 ---
 
 **Interviewer**:
 
-That's a really valuable thing to have said — the sheet says one line, one order; the floor says four bits of kit with small tanks between them. I'll record both rather than pick one.
+Three lines plus one two-tech changeover crew, a one-week horizon, and the clock stops at "cleared QA" — that last one especially; a lot of models would have stopped at the line.
 
-That choice matters for what the model can answer, so let me put it to you.
+I'll hold there for your answer.
 
-> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  When you say an order is "on Line 2" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can s…
-> harness — completion after turn 5: 43 captures; complete no; 28 unsatisfied; 0 unmapped
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  Understood — I'll record that as a hard rule ("we just don't do that"), not a weight, and note that a real exchange rate would have to co…
+> harness — sweep applied; applied 20; advisories 4; completion complete=no unsatisfied=24
+> harness — completion after turn 5: 34 captures; complete no; 24 unsatisfied; 0 unmapped
 
 **Ask**:
 
-Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays "filler's down, switch or wait?" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate.
+Two things before I ask you to walk me through an actual order, and then I'll stop asking about the model and start asking about the plant.
+
+(a) Suppose I hand you a finished model and you want to know whether to trust it. What would you check? For instance — if we fed it last month's demand book, what would it have to reproduce before you'd believe its answer on the wash-down-versus-idle call? Late-order count for the month? The changeover hours on Line 2? Something you'd eyeball?
+
+(b) How much of your time have I got, roughly — one sitting, or can I come back? That changes how deep I go versus how much I flag as unknown.
 
 ---
 
 **Expert (Marta)**:
 
-No, I do want that in scope — if I'm honest, the disruption question and the tank question are the same underlying thing to me. Half the reason Line 1's options are worse when Line 2 goes down is because it feels sluggish and blocked in ways I can't pin on the published line rate. If the model can actually show me "here's where Line 1 loses its time," that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.
+(a) Honestly, the first thing I'd check is the boring one — did it land roughly where we actually landed on late orders that month? If I fed it last month's demand book and it told me we shipped everything on time, I'd stop trusting it immediately, because we didn't — we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones. So: same rough number and same *kind* of misses. If it says we missed distributor orders and we actually missed a Meridian one, that's worse than getting the count wrong.
 
-So yes — build it as separate stages if that's what it takes. I'll warn you now, though: I don't have clean numbers for tank sizes or stage-by-stage rates. I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by "how long does mixing take, how long does milling take" — that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head. Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head.
+After that I'd want to eyeball changeover hours on Line 2 and 3 specifically, because I know roughly what those looked like — if the model has Line 3 idle half the week waiting on the crew, and that never happens in real life, I'd know it's missing something about how the crew actually gets shared out. And I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1 — because if it only works on the calm weeks, it's not telling me anything I don't already know from the sheet.
 
----
+I wouldn't trust a single number out of it, put it that way. I'd want to recognize the *shape* of a real month before I'd believe it on something as specific as the wash-versus-idle call.
 
-**Interviewer**:
-
-Understood, and that's an honest and useful boundary: stage-level rates live in the historian, tank sizes on engineering drawings, neither in your head. I'll record those as open with their source rather than let me invent them.
+(b) I've got another half hour or so before I'm back on the floor — go ahead, I can come back another day if we need more.
 
-Let me take what you *do* carry.
+---
 
-The sweep bounced on a misquote of mine: the expert's words were "I **just** know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit". Retrying with the verbatim text.
+**Interviewer**:
 
-Second bounce, same cause — capitalisation: the expert wrote "**And** then whatever happens to the bumped tint order…". Retrying.
+Half an hour is enough for the spine. Let's use it on the walkthrough and the crew, and I'll flag the rest for next time.
 
-Right — I have your sheet-level knowledge to draw on, so let me take it at that level.
+Go ahead when you're ready — I'm listening for the order of things, not polish.
 
-> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actuall…
-> harness — sweep refused; refusal {"code":"evidence-quote-not-found","excerpt":"I know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit","message":"No user entry contains the verbatim quote \"I know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\". Repair the quote to match the user's words exactly."}
-> harness — sweep refused; refusal {"code":"evidence-quote-not-found","excerpt":"and then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer","message":"No user entry contains the verbatim quote \"and then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\". Repair the quote to match the user's words exactly."}
-> harness — sweep applied; applied 39; advisories 10; completion complete=no unsatisfied=28
-> harness — completion after turn 6: 82 captures; complete no; 28 unsatisfied; 0 unmapped
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  Two things before I ask you to walk me through an actual order, and then I'll stop asking about the model and start asking about the plan…
+> harness — sweep applied; applied 22; advisories 10; completion complete=no unsatisfied=41
+> harness — completion after turn 6: 56 captures; complete no; 41 unsatisfied; 0 unmapped
 
 **Ask**:
 
-Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white.
+Take that Meridian white run on Line 2 — the real one from a couple of weeks back. Walk me through it from the moment it landed in the demand book to the moment it cleared QA. Don't generalise, just tell me what happened in order: what had to be true before it could start on Line 2, who did what, roughly how long each part took, and where it sat waiting. Five or six steps is plenty — I'll dig into whichever ones matter.
 
 ---
 
 **Expert (Marta)**:
 
-Right, so a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.
+Alright — that one, specifically, as best I remember it.
+
+1. **It landed in the demand book** on the Monday release, part of that week's batch of orders from ERP — a Meridian order, big white SKU, due Friday. No surprise, Meridian white basically always goes to Line 2, so it went into "my" Line 2 column on the sheet without much debate.
 
-Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more "the filler hiccupped twice" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely. Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.
+2. **It had to wait its turn behind whatever was already running on Line 2.** There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run. That's the easy case, no crew involved.
 
-On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten. That's the "Line 2 is twice as fast" thing people say, though that's really a whites number.
+3. **It ran.** Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack. I don't watch this minute by minute, but it's a big volume order, so it was on the line most of the day. I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.
 
-Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.
+4. **Once fill and pack was done, it went into QA hold.** That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.
+
+5. **It sat in QA** — normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold. I don't remember this one having any drama in the lab.
+
+6. **It cleared and shipped Thursday**, ahead of the Friday due date. That's the one that gave me the room to think about the wash-versus-idle call on the *next* job — because Meridian had already cleared, I wasn't worried about that due date anymore, I was worried about the tint order coming up behind it.
+
+That's the shape of it. The interesting stuff — the crew, the idle decision — happens in the gaps between steps 3 and 4 on the *next* job, not this one.
 
 ---
 
 **Interviewer**:
 
-One thing you said gives me pause, and I'd rather sort it now than bake it in wrong.
+That's exactly the shape I needed — and you've told me where the real decision lives. Let's go there.
 
-> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical …
-> harness — sweep applied; applied 32; advisories 13; completion complete=no unsatisfied=9
-> harness — completion after turn 7: 114 captures; complete no; 9 unsatisfied; 0 unmapped
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  Take that Meridian white run on Line 2 — the real one from a couple of weeks back. Walk me through it from the moment it landed in the de…
+> harness — completion after turn 7: 56 captures; complete no; 41 unsatisfied; 0 unmapped
 
 **Ask**:
 
-You said the bad-day twelve-to-thirteen hours is "usually not the run itself slowing down" but "the filler hiccupped twice," and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?
+The crew. Two techs, three lines. Tell me about the last time two lines wanted them at the same time — what happened, and who decided? I'm after the practiced rule, not the one on the wall: does the crew go to whoever asked first, to the biggest order, to the tightest due date, to whoever shouts loudest, to Meridian? And has anyone ever overridden that — pulled them off a line mid-job?
 
 ---
 
 **Expert (Marta)**:
 
-That's fair, and yeah, I was sloppy folding them together. If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.
+Now that's a real story, not a made-up one, thankfully.
+
+It was maybe three weeks ago — Line 1 had just finished a specialty run and needed the full two-hour changeover before the next job, and around the same time Line 3 finished a tint run and needed a family switch too. Both wanted the crew basically within the same half hour.
+
+Practically, what happens is not some clean rule — it's whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle. That morning I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date, and Line 3's next job had a couple days of slack. Line 3 sat there clean but idle for — I want to say close to two hours — waiting its turn. Nobody died over it, but it's wasted line time that doesn't show up anywhere as a "problem," it's just... the day.
 
-The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup. So you're right to pull that apart: clean-run variability is small, and the big bad days are really the breakdown showing up inside the run, not the run itself being slow.
+If it had been Meridian sitting behind either of those changeovers, that decision doesn't even get discussed — the crew goes to whichever line has the Meridian job next, full stop, everyone understands that without me saying it out loud.
+
+Has anyone ever pulled the crew off mid-job? Yes, actually — maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now. That's rare, and it's not my call, that's a maintenance-versus-me argument that goes over my head to the ops director if it's a real fight. But day to day, it's basically me making a judgment call at the huddle about whose due date is tightest, and nobody's written that rule down either.
 
 ---
 
 **Interviewer**:
 
-Two housekeeping things I want to settle, because right now the model has plenty of plant detail but the two questions it's meant to answer aren't yet wired to any of it.
+That's the rule in practice: Meridian first without discussion, otherwise your huddle call on tightest due date, otherwise whoever reaches the crew lead first — with maintenance able to pull them for an emergency. I'll record it that way, including the two hours Line 3 sat idle.
+
+Now the number your whole question hangs on.
 
-> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  You said the bad-day twelve-to-thirteen hours is "usually not the run itself slowing down" but "the filler hiccupped twice," and that you…
-> harness — sweep applied; applied 35; advisories 20; completion complete=no unsatisfied=9
-> harness — completion after turn 8: 149 captures; complete no; 9 unsatisfied; 0 unmapped
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  The crew. Two techs, three lines. Tell me about the last time two lines wanted them at the same time — what happened, and who decided? I'…
+> harness — completion after turn 8: 56 captures; complete no; 41 unsatisfied; 0 unmapped
 
 **Ask**:
 
-If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong.
+The changeover itself. Thinking of white-to-tint washdowns you've seen on Line 2: what's the *quickest* one you'd realistically see, and what's the *longest* — the bad one where it drags? Then where does it usually land between those. And two follow-ons: does the direction matter — is tint-to-white different from white-to-tint? — and you mentioned "the full two-hour changeover" after a specialty run on Line 1, so is specialty a different animal again?
 
 ---
 
 **Expert (Marta)**:
 
-Alright, let me actually try and write these the way I'd type them if I had the box.
-
-**Disruption one:** "If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?"
+Okay, let's separate those because they're genuinely not the same beast.
 
-What it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of "could be quick, could be long" rather than one number. And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours. And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the "who can absorb it" judgment call again.
+White-to-tint on Line 2 — quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes. Longest, if they're stretched thin or something's stuck, I've seen it drag past an hour, call it an hour twenty on a bad day. Typically though it lands around 45 minutes to an hour. That's the "cheap" direction.
 
-I'd say what's missing from your list, or under-weighted: the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just "an order got delayed." A distributor slipping is fine, so the answer to the question genuinely depends on whose tint was sitting there.
+Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric. Any pigment left behind wrecks a white batch, so that's a full washdown. Quickest I've seen that go is maybe two and a half hours if everything's clean and the crew's fresh. On a bad day — dried pigment in a fitting, whatever — it's crept toward four hours. Call it three hours typical, and that's the number I actually use on the sheet.
 
-**The Line 1 tank one:** "Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?" That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others. That's not something I'd have said a month ago.
+Specialty is its own animal again, like you said — going in or coming out of a specialty run, either direction, it's around two hours normally. I've seen it shorter, maybe an hour forty if it's a specialty-to-specialty color change rather than a full family switch. I haven't seen it run much longer than two and a half hours, but I'll be honest, I don't watch specialty changeovers as closely as I watch the white-tint ones because they don't hit my due dates as hard.
 
 **Injected experiment stimulus (not expert evidence)**:
 
@@ -236,140 +245,178 @@ I'd say what's missing from your list, or under-weighted: the direction of the c
 
 **Interviewer**:
 
-Honest answer to "how much more": we're maybe a third of the way. What's still open, roughly in order of how much it costs you: the filler jam's rate and repair time; what the washdown actually costs including ramp scrap; the "who can absorb a slip" rule as you actually apply it; how orders arrive into the demand book; QA hold times; and the stage rates and tank size, which we've already agreed aren't in your head. None of that needs to happen today.
+That's three separate changeovers with real asymmetry — that alone was worth the session.
 
-For the ten minutes, I'd spend them on the jam, because you named it as the thing you never know at the time and nobody else can tell me.
+Ten minutes: I'll name what's still missing and you pick. Open gaps are (1) how orders actually arrive into the demand book — you made that whole call because you *knew* a white order was coming that afternoon; (2) how long a run takes per unit on each line; (3) QA turnaround beyond the four hours for white; (4) breakdowns, which you said I'd need to reproduce the odd weeks. I'd spend the ten minutes on (1), because your decision literally rested on foreknowledge of a release.
 
-> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one …
-> harness — sweep applied; applied 32; advisories 30; completion complete=no unsatisfied=42
-> harness — completion after turn 9: 181 captures; complete no; 42 unsatisfied; 0 unmapped
+Swept — question above still stands whenever you're ready.
+
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  The changeover itself. Thinking of white-to-tint washdowns you've seen on Line 2: what's the *quickest* one you'd realistically see, and …
+> harness — sweep refused; refusal {"code":"evidence-quote-not-found","excerpt":"an order's mine from release to \"cleared QA\"","message":"No user entry contains the verbatim quote \"an order's mine from release to \"cleared QA\"\". Repair the quote to match the user's words exactly."}
+> harness — sweep applied; applied 36; advisories 14; completion complete=no unsatisfied=65
+> harness — completion after turn 9: 92 captures; complete no; 65 unsatisfied; 0 unmapped
 
 **Ask**:
 
-Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?
+So: that afternoon, how did you know the white order was coming? Was that a scheduled release event — the book updates at fixed times — or did someone tell you, or is it a pattern you've learned? And roughly how many orders land in a typical week's book, and how much do they swing between a quiet week and a busy one?
 
 ---
 
 **Expert (Marta)**:
 
-Okay, quick version. It's a "every week or two" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.
+Fair question, and it's a bit of both, honestly. The book officially releases Monday morning — that's the big drop, 30-something to 60 orders depending on the week. But it's not the only time things land. Sales and commercial push in additions through the week, sometimes daily, when a customer calls with something last-minute or an order gets confirmed late. That afternoon, specifically, I think our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was "probably coming," because it's a repeat account and there's a pattern to when they reorder. So it wasn't a scheduled release, it was more me remembering a conversation and half-expecting it — that's the "gut" part, not something the system told me.
 
-When it stops: typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift. I don't have a cleaner breakdown than that — maintenance would have the actual work-order times in the CMMS but I've never pulled them.
+As for volume — quiet week might be 30 orders, a busy one pushes 55–60. It's not wildly seasonal that I've noticed, more just lumpy depending on who's restocking that week. Meridian in particular is fairly regular, close to weekly, but the smaller distributors are the ones that swing.
 
-Right, I need to run — good session though. Same time next week?
+I really do need to get to the huddle — can we pick this up another time? Happy to keep going on the arrivals side and the breakdowns next round.
 
 ---
 
 **Interviewer**:
 
-That bounce was my own phrase, not yours — "jams badly enough to stop the run" was my wording. Re-anchoring on what you actually said.
+Go to your huddle. Here's what I've got, so you can correct it next time rather than read it now.
+
+## What's captured
+
+**The question the model exists to answer** — "wash down for the tint right then, or let Line 2 sit idle" for an expected same-family order; a call you make by gut "three or four times a month" and have "never once been able to prove I got it right."
 
-Go — and yes, same time next week works. Here's where we got to, so you can correct anything when you're back at a desk. **The model is not finished and I'm not going to pretend it is; I wouldn't hand this to your tooling yet.**
+**What "better" means** — Meridian misses first: "we just don't do that" — recorded as a hard rule, not a weight, because you wouldn't trade even twenty small late orders for one Meridian slip. Then late-order count. Changeover hours and idle time as your own diagnostics, on the same page as late orders for the first time.
 
-## What's on record, in your words
+**Boundary** — three lines plus one changeover crew of two techs; order starts at demand-book release from ERP (SKU, quantity, due date), ends when it clears QA and ships; due date judged at QA clearance, not off the line.
 
-**The two questions the model exists to answer**
-1. "If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?"
-2. "Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?"
+**Horizon** — one week (demand-book cycle, re-planned at the morning huddle); two weeks soft for specialty minimum runs; a month you'd refuse.
 
-**What "better" means** — Meridian-style on-time is a hard line, "not really a trade-off, that's a line I won't cross." Below that line you weigh washdown hours, whether the bumped order slides and by how much, and who the customer is. No formula; judgment on who can absorb the slip.
+**The flow** — release → wait behind what's on the line → run (mix, mill, tint stage, fill, pack) → QA hold (palletized, off the line, queued for the lab) → clear and ship. Same-family run-into-run needs no crew.
 
-**The flow** — demand book line item out of ERP → you allocate to a line and a week slot → mix, mill, tint, fill (tint "barely there" for a white) → QA hold → release, warehouse, ship against due date.
+**Crew contention, as practiced** — Meridian next in line wins, no discussion; otherwise your huddle call on tightest due date (Line 1 got them, Line 3 sat "close to two hours" clean and idle with slack); otherwise whoever's supervisor reaches the crew lead first. Override: maintenance can pull them for a genuine emergency; a real fight escalates to the ops director. None of it written down.
 
-**The line, both ways** — on the sheet, one row, one order occupies Line 2 mix-to-fill. Physically, separate kit with small holding tanks between, and the crew will start the next mix if there's tank room. Both recorded; neither averaged away.
+**Changeovers, asymmetric by direction** — white→tint 40 min best, ~45 min–1 hr typical, ~1 hr 20 bad. Tint→white 2½ hr best, 3 hr typical ("the number I actually use on the sheet"), toward 4 hr bad. Specialty either direction ~2 hr, 1 hr 40 for specialty-to-specialty, not much past 2½ — with your own caveat that you don't watch these as closely.
 
-**Run times, clean of breakdowns** — white on Line 2: typical 8–9 h, bad-but-clean 9–10 h, good day ~6 h. Same order on Line 1: add 50–60%, so typical 13–14 h, best ~10 h. Tints: 8–10 h typical on *either* line, no big gap — which you flagged as unexplained and sheet-derived. The 12–13 h figure has been pulled out as breakdown, not run.
+**Arrivals** — Monday drop of 30-something to 60; quiet week 30, busy 55–60; additions pushed in by sales/commercial through the week, sometimes daily; Meridian close to weekly, small distributors are what swing.
 
-**Filler jam** — every week or two; low once in three weeks, high twice a week. Repair typical 30–45 min, quick one-in-ten 10–15 min, bad one-in-ten 4–5 h, "occasionally eating the rest of the shift."
+**Validation bar** — reproduce last month's late-order count *and the kind* of miss (two Meridian scrapes, a handful of small ones); recognisable changeover hours on Lines 2 and 3; must reproduce the odd weeks, including the breakdown that ate two days on Line 1. Not a single number — "the shape of a real month."
 
-**Washdown** — tint-to-white, three hours, direction matters, plus ramp scrap you don't have numbers for.
+## Open, with where it comes from
 
-## Gaps, with where they'd come from
-- Stage-level rates per line — historian, never pulled apart.
-- Tank sizes, mill-to-fill on Line 1 — engineering drawings.
-- Jam repair times, properly — maintenance work orders in the CMMS.
-- Ramp scrap after washdown — you said it shouldn't be ignored; no source named yet.
-- Whether the tank matters differently by SKU — your own new thought, unexamined.
-- QA hold: "a few hours for a white," and a longer "specialty wait" you mentioned but I never asked about.
-- How orders arrive into the demand book — never asked.
-- The "who can absorb the slip" rule — I have distributor-shrugs and prickly-account, not a rule I could apply without you.
+1. **Run durations** — no rate for any line. Needs the sheet.
+2. **QA** — four hours for a white is all I have; nothing on specialty holds, lab capacity, or what happens on a fail.
+3. **Breakdowns** — named by you as essential to validation, never elicited: rate and duration per line.
+4. **The Monday-release shape** — I have weekly counts, not the mid-week additions pattern; and the thing your actual decision rested on was a remembered huddle remark, not a system event. That's a gap in the model, not in you.
+5. **What a changeover loses besides time** — scrap, material, first-batch yield: never asked.
+6. **Meridian exchange rate** — deliberately not a number. Your words: it would take "commercial in a room" to say it out loud.
 
-## Assumptions ledger
-1. That the four stages are the same four for every product — you said "same four stages every product goes through," so this is yours, not mine, but it's load-bearing enough to re-check.
-2. Nothing else. Where I was tempted to fill in — jam rate before you gave it, washdown scrap, stage rates — it's in the gaps list instead.
+## Assumptions I made — none in the model
 
-Both objectives are still formally unsupported: I have the plant detail and the questions, but haven't yet wired which pieces each answer depends on tightly enough for the tooling. That plus the ramp scrap and the slip rule are what I'd open with next week.
+I've recorded nothing you didn't say. Two things I *would* have assumed and didn't: that changeover time is symmetric (you corrected that before I could), and that the due date is met at end of line (you corrected that too).
 
-> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a c…
-> harness — sweep refused; refusal {"code":"evidence-quote-not-found","excerpt":"jams badly enough to stop the run","message":"No user entry contains the verbatim quote \"jams badly enough to stop the run\". Repair the quote to match the user's words exactly."}
-> harness — sweep applied; applied 47; advisories 46; completion complete=no unsatisfied=44
-> harness — completion after turn 10: 228 captures; complete no; 44 unsatisfied; 0 unmapped
+## Simplifications to flag next time
+
+Queues aren't modelled as things — the wait behind a running job and the QA queue emerge from the steps either side. And "Meridian white basically always goes to Line 2" is captured as your statement; I haven't asked whether that's a hard routing constraint or a habit, and it matters.
+
+**Stopping outcome: expert-stopped, partial-with-open-slots.** The spine is there — objective, boundary, flow, crew rule, changeover times. It can't yet run a week, because it has no run rates and no breakdowns. Next round: arrivals and breakdowns, as you offered, plus run rates off the sheet.
+
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  So: that afternoon, how did you know the white order was coming? Was that a scheduled release event — the book updates at fixed times — o…
+> harness — sweep applied; applied 33; completion complete=no unsatisfied=89
+> harness — completion after turn 10: 125 captures; complete no; 89 unsatisfied; 0 unmapped
 
 ---
 
 **Expert (Marta)**:
 
-Looks right — that's a fair record, and yeah, next week let's start with ramp scrap and the slip rule, since those feel like the ones I could actually go dig up or nail down between now and then. I'll ask maintenance for the CMMS numbers on the filler too while I'm at it. Go on, get to your huddle — wait, that's me. See you next week.
+Looks right to me — and yeah, bring the sheet next time, it'll answer the run-rate question faster than I can talk through it. See you next round.
 
 ---
 
 **Interviewer**:
 
-Enjoy the huddle.
+Good — the sheet next time.
+
+One housekeeping note so nothing goes missing: the final sweep wouldn't apply. The extraction kept trying to anchor quotes to my read-back rather than to your own words, and I'd rather decline it than let a paraphrase of mine enter the model as something you said. Nothing is lost — everything in the summary you just confirmed was already captured from the earlier sweeps, when you said it.
+
+The only item from this last exchange is the deposit: **run rates per line come from the sheet, which you're bringing.** That's noted against the open gap rather than as a value.
 
-Three things I'll have ready for next week, so you don't have to hold them:
+Your confirmation is on record as "you didn't object to my summary" — not as your own phrasing. If any line in it is my words standing in for yours, next round is the time to correct it; that's cheaper than finding it in the output later.
 
-1. **Ramp scrap and the slip rule** first, as you asked — for the slip rule I'll come at it through a case rather than a principle, so have in mind the last time you bumped someone's order and it turned out to be the wrong someone.
-2. **CMMS filler numbers** — when you get them, what I want is the same shape you gave me from memory: typical, bad one-in-ten, quick one-in-ten. If the work orders disagree with your 30–45 minutes, that disagreement is worth more to the model than either figure alone, so don't reconcile it before you bring it.
-3. **The tint parity puzzle** — that Line 1 and Line 2 run tints at nearly the same speed with no explanation. It's the loose thread most likely to be the same thing as your tank hunch, and I'd like to pull on it once the scrap and slip rule are in.
+Next round, in the order I'd spend your time: breakdowns (rate and duration per line — you've made those a validation requirement), run rates off the sheet, then QA beyond the four-hour white. And one small question I'll open with: whether Meridian white going to Line 2 is a hard routing rule or a habit.
 
-Nothing needs doing beyond that. See you next week.
+The mismatch is formatting, not substance — your walkthrough had that first clause in bold, so the run-together quote never existed as a contiguous string. Repairing to the exact contiguous spans:
 
-The tail has settled: the read-back was confirmed, the session closed, and the expert's last message adds content in their own words — what they'll dig up before next time and that they'll pull the CMMS numbers from maintenance. That belongs in the record as deferral deposits, not as agreement to my summary.
+- "That's where it sits — physically it's palletized and moved off the line, into the queue for the lab."
+- "an order's mine from release to "cleared QA," and the due date is judged against when it clears, not when it comes off the line"
+- "That afternoon, specifically, I think our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was "probably coming,"" — capital T, as you wrote it.
 
-One caution I'll carry into the sweep: "Looks right" is assent to my phrasing, not origination. It closes nothing that wasn't already sourced to their words.
+I'm declining this sweep rather than repairing it further.
 
-Swept and folded — the session's record is durable. Since you've gone, this is a note-to-self for next week rather than anything you need to read now.
+The reason matters, so I'll state it plainly: the harness now reports that string occurs **only in injected non-user entries**. That means the QA-hold sentence, as the extractor is trying to cite it, is not traceable to something you actually typed in a user turn — it's reachable only through echoed or injected text. Citing it would put a capture in the model whose evidence is my own scaffolding wearing your voice. That is precisely the failure I'd rather take an incomplete model than commit.
 
-**State of the model:** 69 nodes from 267 captures. Not complete, and two things about *how it's held* need fixing before more content goes in:
+What this costs: nothing I can identify. Your walkthrough turn — including step 4, the QA hold, palletized and queued for the lab — was already swept successfully at the time you said it. This tail was re-proposing content the model holds on sound evidence. If the extractor's version and the earlier one differ in any way I can't see, the earlier one stands, because it was anchored when you spoke.
 
-1. **Objective duplication.** Your two questions have landed as five objective nodes — successive rephrasings of the same two ("which option loses less", "which option actually loses less", "wait or shift when Line 2 goes down" are one question; "where Line 1 loses its time" and "is the mill-to-fill tank on Line 1 slowing the line down" are the other). That's an artefact of my asking you to restate them, not a fact about your plant. Consolidating is a review-and-revise job, and it needs your word on which phrasing is yours, not my merge.
+So the position at close is unchanged from the summary you confirmed:
 
-2. **Nothing is wired to the objectives.** 53 of the 69 nodes sit outside every objective's dependency slice — recorded, but not demanded by anything. That's why the completion report keeps growing without the model getting more answerable. You *did* tell me what the disruption question hangs on: the run being protected, Line 1's state and family, the jam duration, the ramp scrap, and the bumped order's identity. I have those as prose in your answer; they aren't yet linked as dependencies. Doing that link properly is the first thing that makes any of the plant detail count.
+- **Stopping outcome: expert-stopped, partial-with-open-slots.**
+- **One unswept tail, declined on evidence grounds** — not settled-but-skipped, and not a gap in your knowledge. Worth a look by whoever maintains the tooling; a quote that resolves only against injected text is a defect in the harness, not in the interview.
+- **Open next round, in priority order:** breakdowns per line, run rates from the sheet, QA beyond the four-hour white, mid-week additions to the book, changeover losses besides time, and whether Meridian white on Line 2 is a rule or a habit.
+- **Deposit standing:** the Meridian exchange rate needs commercial in a room; run rates need the sheet you're bringing.
 
-3. **Three open conflicts** on the filler jam node and the production-run node, where later answers superseded earlier ones — the 12–13 h that turned out to be breakdown, and the two jam descriptions. Those need your explicit word to close, not my inference about which you meant.
+I have not built the net, and I'm not claiming this is loadable or runnable — the projection to your Petri-net tooling is a separate step done from the model, and it will report its own losses. What I can say is that the spine it would project from is yours, in your words, with the asymmetric changeover times and the unwritten crew rule intact.
 
-So next week's order: ramp scrap and the slip rule as you asked, then the objective wiring, then the conflict closes. The tint parity thread stays third.
+See you next round.
 
-> harness — signal `settlement-check`: The harness computed this unswept conversation tail:  [non-user] The immediately preceding user message is mechanically bound as the reply to this pending affordance:  Thinking of the Line 2 filler specifically: roughly how often does it ja…
-> harness — sweep applied; applied 39; skipped 1; advisories 45; completion complete=no unsatisfied=46
-> harness — completion after turn 11: 267 captures; complete no; 46 unsatisfied; 0 unmapped
+It has settled — the session ended, no thread is open, and the only user-authored content in the range is your assent plus one durable fact: the sheet answers the run-rate question. Assent to my phrasing isn't yours to be captured, but the sheet as a named source for an open slot is, and it should live in the model rather than only in my close text. One attempt on that anchor.
+
+Applied — the tail is swept and the sheet is now recorded in the model as the named source for run rates, anchored to your words rather than sitting only in my summary.
+
+Two honest notes to carry into next round, neither of which changes what you confirmed:
+
+**The model has duplicate nodes.** There are at least two changeover nodes that are really the same thing under different names, picked up as the conversation circled back — one from when you first mentioned the washdown, one from the detailed timings. That's my bookkeeping, not your inconsistency. First thing next session is merging them, so the 40-minute/3-hour/2-hour figures sit on one node each rather than being split across near-duplicates.
+
+**The Meridian exchange-rate objective is formally unsupported.** The harness flags it as depending on nothing in the model — which is correct and expected, because you deliberately declined to give a number and said it would take commercial in a room. It stays in as a recorded question with its deposit attached, not as something the model pretends to answer. That's the right state for it; I'm noting it so nobody later reads the flag as an oversight.
+
+Everything else stands as read back. **Stopping outcome: expert-stopped, partial-with-open-slots.**
+
+See you next round — with the sheet.
+
+> harness — signal `sweep-repair`: The sweep was refused: No user entry contains the verbatim quote "Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.". Repair the quote to…
+> harness — signal `settlement-check`: The harness computed this unswept conversation tail:  [non-user] The immediately preceding user message is mechanically bound as the reply to this pending affordance:  So: that afternoon, how did you know the white order was coming? Was tha…
+> harness — sweep refused; refusal {"code":"evidence-quote-not-found","excerpt":"that afternoon, specifically, I think our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \"probably coming,\" because it's a repeat account and there's a pattern to when they reorder. So it wasn't a scheduled release, it was more me remembering a conversation and half-expecting it — that's the \"gut\" part, not something the system told me.","message":"No user entry contains the verbatim quote \"that afternoon, specifically, I think our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \"probably coming,\" because it's a repeat account and there's a pattern to when they reorder. So it wasn't a scheduled release, it was more me remembering a conversation and half-expecting it — that's the \"gut\" part, not something the system told me.\". Repair the quote to match the user's words exactly."}
+> harness — sweep refused; refusal {"code":"evidence-quote-not-found","excerpt":"an order's mine from release to \"cleared QA\"","message":"No user entry contains the verbatim quote \"an order's mine from release to \"cleared QA\"\". Repair the quote to match the user's words exactly."}
+> harness — sweep refused; refusal {"code":"evidence-quote-not-found","excerpt":"Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.","message":"No user entry contains the verbatim quote \"Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\". Repair the quote to match the user's words exactly."}
+> harness — sweep refused; refusal {"code":"non-user-evidence","excerpt":"Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.","message":"The quote \"Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\" occurs only in injected non-user entries and cannot be cited as user evidence."}
+> harness — sweep applied; applied 39; advisories 11; completion complete=no unsatisfied=93
+> harness — completion after turn 11: 164 captures; complete no; 93 unsatisfied; 0 unmapped
 
 ---
 
 **Expert (Marta)**:
 
-*[No response — this final message is addressed to the interviewer's own note-taking process, not to Marta. Staying in character as Marta, there is nothing here that calls for a reply; she has already left for the huddle.]*
+Sounds good. I'll have the sheet, and I'll poke at whether Meridian-to-Line-2 is written in stone or just habit before you even ask. Talk next round.
 
 ---
 
 **Interviewer**:
 
-Session closed. Nothing further pending on Marta's side.
+Perfect — and that's the better version of the question anyway, since you'll have looked before we talk rather than reconstructing it on the spot.
+
+One thing worth flagging about what you're going to check: if it turns out to be habit rather than a rule, don't discard the habit. A routing preference that everyone follows without being told is exactly the kind of thing that behaves like a constraint until the week it doesn't — and the week it doesn't is probably one of the odd weeks you said the model has to reproduce. So both answers are useful: "it's written in the spec" and "it's just what we've always done, except that time we ran it on Line 1 because Line 2 was down." The second one is worth more.
+
+Nothing else needed from you before then. Enjoy the huddle.
+
+Settled — it's a sign-off, and the one durable item is a deposit in your words: you'll check whether Meridian-to-Line-2 is written in stone or habit. That belongs against the open routing question rather than in my notes.
 
-Final state for the record: model at revision `26a8219a17118558` — 69 nodes, 267 active captures, not complete. Two objectives (held as five duplicate nodes), both formally unsupported. Deferrals carry deposits: CMMS for jam repair times, historian for stage rates, engineering drawings for tank sizes, Marta herself for ramp scrap and the slip rule. Assumption ledger holds one entry, flagged for re-check.
+Applied — two captures, both deposits rather than values: the sheet as the source for run rates, and your check on Meridian-to-Line-2 as the source for the routing question. No new claims about the plant entered the model from a sign-off, which is as it should be.
 
-I make no claim that this projects, compiles, or runs. Next session opens as review-and-revise on the objective nodes before any new elicitation.
+That closes the session. Final state, unchanged from what you signed off on:
 
-Declining this one.
+**Stopping outcome: expert-stopped, partial-with-open-slots.** 51 nodes, all traceable to your words. The spine runs objective → boundary → flow → crew rule → changeover times. It cannot yet simulate a week: no run rates, no breakdowns.
 
-The range contains no expert testimony. It is my own closing turn, my own sweep-judgment note, and my own state-of-the-model note, terminated by a stage direction confirming Marta has left and is not replying. The only entry in user position is that stage direction — narration about the interview, not Marta's words about her plant.
+**Carried to next round, in the order I'd spend your time:** breakdowns per line; run rates off the sheet; QA beyond the four-hour white; mid-week additions to the book; what a changeover loses besides time; and your Meridian-to-Line-2 finding. Plus my own housekeeping — merging the duplicate changeover nodes before anything else, so the timings consolidate.
 
-Sweeping it could only do one of two things: extract nothing, or extract something from a non-expert source. The second is the failure mode I've been guarding against all session — a model element with no expert span behind it. My own summary of the model is not evidence for the model; that would be assent taken as origin, with me on both sides of it.
+**Deposits standing:** Meridian exchange rate needs commercial in a room. Run rates need the sheet. Routing question needs your check.
 
-The substantive content in that stretch — the CMMS follow-up, the ramp-scrap and slip-rule priority, Marta's confirmation of the read-back — was already swept from her actual message at revision `26a8219a17118558`. Nothing is at risk of being lost by leaving this tail unswept.
+I haven't built the net and I'm not claiming this is loadable — projecting the model to your Petri-net tooling is a separate step, and it will produce its own report of what the net can't carry.
 
-The swept high-water mark stays where it is. The session's durable record is complete as of that revision, and next session opens as review-and-revise on the duplicated objective nodes.
+Talk next round.
 
-> harness — signal `settlement-check`: The harness computed this unswept conversation tail:  [assistant] Enjoy the huddle.  Three things I'll have ready for next week, so you don't have to hold them:  1. **Ramp scrap and the slip rule** first, as you asked — for the slip rule I'…
-> harness — completion after turn 12: 267 captures; complete no; 46 unsatisfied; 0 unmapped
+> harness — signal `settlement-check`: The harness computed this unswept conversation tail:  [assistant] Good — the sheet next time.  One housekeeping note so nothing goes missing: the final sweep wouldn't apply. The extraction kept trying to anchor quotes to my read-back rather…
+> harness — sweep applied; applied 2; completion complete=no unsatisfied=93
+> harness — completion after turn 12: 166 captures; complete no; 93 unsatisfied; 0 unmapped
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5.raw.json b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5.raw.json
index f958eb1d755..9f174bb5814 100644
--- a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5.raw.json
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5.raw.json
@@ -1,177 +1,137 @@
 {
-  "startedAt": "2026-08-25T19:21:21.703Z",
+  "startedAt": "2026-08-26T15:00:24.487Z",
   "condition": "5",
   "interviewerModel": "claude-opus-5",
   "expertModel": "claude-sonnet-5",
-  "conversationId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+  "conversationId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
   "stopReason": "stalled",
   "turns": [
     {
       "turn": 1,
       "text": [
-        "Good — that's exactly the right split: you know the plant, I'll worry about the format. Before I ask anything about how the plant is built, I want to know what the model has to be able to tell you.\n\nLet me start there."
+        "Good — and you don't need to know the format; that's my job. What I need from you is how the plant actually works, in your words.\n\nLet me start with what the model is *for*."
       ],
       "asks": [
         {
-          "question": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong.",
-          "toolCallId": "toolu_01VTR3FzE8Wat7pwjPW7jcyh"
+          "question": "When your boss says \"test scheduling decisions before making them\" — what's the specific decision or question you'd want to put to this model first? If you can, give me a real one you've faced recently: something where you had two options and weren't sure which was better.",
+          "toolCallId": "toolu_01Xhtqpw13HgHpe79SBBpYjx"
         }
       ],
       "sweeps": [],
       "signals": [],
       "toolErrors": [],
-      "pendingQuestion": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong.",
+      "pendingQuestion": "When your boss says \"test scheduling decisions before making them\" — what's the specific decision or question you'd want to put to this model first? If you can, give me a real one you've faced recently: something where you had two options and weren't sure which was better.",
       "completion": {
         "captures": 0,
         "complete": false,
         "unsatisfied": 4,
         "outsideSlice": 0,
         "unmapped": 0,
-        "revision": "226d7dc428a2e7fe",
-        "cue": "The harness folded the model at revision 226d7dc428a2e7fe (plugin sdcpn/2026-08-25.2): 0 node(s) from 0 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 0 objective node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 entity-type node(s); the floor needs 2.\n- [below-minimum-count] The model has 0 activity node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+        "revision": "33fb34150222339e",
+        "cue": "The harness folded the model at revision 33fb34150222339e (plugin sdcpn/2026-08-26.2): 0 node(s) from 0 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 0 objective node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 entity-type node(s); the floor needs 2.\n- [below-minimum-count] The model has 0 activity node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
       },
       "expert": {
-        "content": "Okay, good question. Let me think of an actual one rather than a hypothetical.\n\nA few weeks back — Line 2 filler jammed at about nine in the morning, half a shift lost. We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.\n\nI went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky. That's the kind of thing — I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me."
+        "content": "A real one — a couple weeks back, Line 2 finished a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units. I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.\n\nI ended up sitting the line. It felt right — a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time. But I couldn't tell you if that was actually the cheaper choice or just the safer-feeling one. That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right."
       }
     },
     {
       "turn": 2,
       "text": [
-        "That's a very usable one — a real disruption, two options, and no way to tell afterwards whether you chose well. That \"which option loses less\" is the heart of the model."
+        "That's a clean, testable question — \"hold the line idle for an expected same-colour order, or change over now\" — and the fact that you make it three or four times a month makes it worth modelling."
       ],
       "asks": [
         {
-          "question": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off.",
-          "toolCallId": "toolu_01RigdvzDsLRJokW4AqBW7UE"
+          "question": "You said you couldn't tell if sitting the line was \"actually the cheaper choice.\" When you say cheaper — what's the thing you'd actually be comparing at the end of the day or week? Is it lost production units, lost hours, money, orders shipped late, something else? And if there's more than one, which one would your boss actually judge you on?",
+          "toolCallId": "toolu_01237B8YMxnjeQ6skVF9Ty6Y"
         }
       ],
       "sweeps": [],
       "signals": [
         {
           "tagName": "affordance-reply-bound",
-          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd h…"
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen your boss says \"test scheduling decisions before making them\" — what's the specific decision or question you'd want to put to this m…"
         }
       ],
       "toolErrors": [],
-      "pendingQuestion": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off.",
+      "pendingQuestion": "You said you couldn't tell if sitting the line was \"actually the cheaper choice.\" When you say cheaper — what's the thing you'd actually be comparing at the end of the day or week? Is it lost production units, lost hours, money, orders shipped late, something else? And if there's more than one, which one would your boss actually judge you on?",
       "completion": {
         "captures": 0,
         "complete": false,
         "unsatisfied": 4,
         "outsideSlice": 0,
         "unmapped": 0,
-        "revision": "226d7dc428a2e7fe",
-        "cue": "The harness folded the model at revision 226d7dc428a2e7fe (plugin sdcpn/2026-08-25.2): 0 node(s) from 0 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 0 objective node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 entity-type node(s); the floor needs 2.\n- [below-minimum-count] The model has 0 activity node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+        "revision": "33fb34150222339e",
+        "cue": "The harness folded the model at revision 33fb34150222339e (plugin sdcpn/2026-08-26.2): 0 node(s) from 0 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 0 objective node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 entity-type node(s); the floor needs 2.\n- [below-minimum-count] The model has 0 activity node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
       },
       "expert": {
-        "content": "Honestly, in the moment it's simple-minded: did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\n\nUnderneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\n\nSo really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip."
+        "content": "Honestly, in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders. He doesn't care that I saved a washdown if it means something slipped past its due date. So if the model's going to tell me anything useful, it has to connect those — because right now I only track them separately. I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\n\nIf I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere. The changeover hours and the idle time are more my own concern — I get twitchy about wasted capacity because that's what eventually turns into missed due dates further down the week."
       }
     },
     {
       "turn": 3,
       "text": [
-        "I've got the objective on record: which option loses less, with Meridian-style on-time as a hard line and washdown hours plus knock-on lateness as the weighing underneath. I'll come back to how you judge \"who can absorb a slip.\"\n\nNow I need the shape of the work itself."
+        "The \"nobody's written that down anywhere\" part is exactly the kind of thing I want in the model, so let me pin it."
       ],
       "asks": [
         {
-          "question": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after.",
-          "toolCallId": "toolu_01BPxGhtkoW98xCiTTeNLW4a"
-        }
-      ],
-      "sweeps": [
-        {
-          "status": "applied",
-          "appliedCaptureIds": [
-            "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
-            "capture-76159984-4b11-446f-a707-bc8302ef0b1d",
-            "capture-3f2444d5-8001-46d9-8a92-c85f8c6f8d6a",
-            "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
-            "capture-053410a5-6574-4355-aabf-dd972f0088e1",
-            "capture-e86ee1d3-dbbd-4e2d-b1c0-a8ac719f0e58",
-            "capture-04d27279-48f8-437e-8688-14c400f3f0f1",
-            "capture-7d1cb932-a1d6-4e1a-86a7-984a9d53af80",
-            "capture-330b99df-25fc-4d38-b1f9-6f8da955b79e",
-            "capture-caeeeb12-a91f-46a0-88c2-a622d4d30c55",
-            "capture-422d7f74-a119-45d6-8261-3c71b50af7f7",
-            "capture-f2a03b6c-0420-48a7-85be-bdcb3536a6f7",
-            "capture-c9ac976a-3eef-4a77-8e29-3598b184b450",
-            "capture-6bc324a5-2e12-4070-8275-fdfe819923e6",
-            "capture-b003fc51-0ade-4721-b400-b7b68edf8c60"
-          ],
-          "skippedDedupKeys": [],
-          "advisories": [],
-          "completion": {
-            "complete": false,
-            "revision": "3a1fa5a01b21595c",
-            "pluginVersion": "sdcpn/2026-08-25.2",
-            "unsatisfied": 20,
-            "unmapped": [],
-            "cue": "The harness folded the model at revision 3a1fa5a01b21595c (plugin sdcpn/2026-08-25.2): 6 node(s) from 15 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- [inadmissible-status] \"what it needs before it can start\" on activity:tint-to-white washdown is held under status inferred; accepted: explicit.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:tint-to-white washdown.\n- [below-required-precision] \"how long it takes\" on activity:tint-to-white washdown is known as a number; the model needs spread. Smallest delta: move it from number to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:tint-to-white washdown.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:tint-to-white washdown is known as a number; the model needs range. Smallest delta: move it from number to range.\n- … and 8 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:Line 2 filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:Line 2 filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:Line 2 filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n\n1 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-          }
+          "question": "On Meridian being weighted heavier: suppose at end of week you could land on one of two outcomes — (a) three non-Meridian orders a day late each, or (b) one Meridian order a day late. Which is the worse week for you? And if that one's easy, tell me where it *stops* being easy — how many small late orders would it take before you'd rather take the Meridian hit?",
+          "toolCallId": "toolu_01S1m8pX5FPajeTWWrvQ29Zy"
         }
       ],
+      "sweeps": [],
       "signals": [
         {
           "tagName": "affordance-reply-bound",
-          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you?…"
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nYou said you couldn't tell if sitting the line was \"actually the cheaper choice.\" When you say cheaper — what's the thing you'd actually …"
         }
       ],
       "toolErrors": [],
-      "pendingQuestion": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after.",
+      "pendingQuestion": "On Meridian being weighted heavier: suppose at end of week you could land on one of two outcomes — (a) three non-Meridian orders a day late each, or (b) one Meridian order a day late. Which is the worse week for you? And if that one's easy, tell me where it *stops* being easy — how many small late orders would it take before you'd rather take the Meridian hit?",
       "completion": {
-        "captures": 15,
+        "captures": 0,
         "complete": false,
-        "unsatisfied": 20,
-        "outsideSlice": 1,
+        "unsatisfied": 4,
+        "outsideSlice": 0,
         "unmapped": 0,
-        "revision": "3a1fa5a01b21595c",
-        "cue": "The harness folded the model at revision 3a1fa5a01b21595c (plugin sdcpn/2026-08-25.2): 6 node(s) from 15 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- [inadmissible-status] \"what it needs before it can start\" on activity:tint-to-white washdown is held under status inferred; accepted: explicit.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:tint-to-white washdown.\n- [below-required-precision] \"how long it takes\" on activity:tint-to-white washdown is known as a number; the model needs spread. Smallest delta: move it from number to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:tint-to-white washdown.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:tint-to-white washdown is known as a number; the model needs range. Smallest delta: move it from number to range.\n- … and 8 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:Line 2 filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:Line 2 filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:Line 2 filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n\n1 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+        "revision": "33fb34150222339e",
+        "cue": "The harness folded the model at revision 33fb34150222339e (plugin sdcpn/2026-08-26.2): 0 node(s) from 0 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 0 objective node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 entity-type node(s); the floor needs 2.\n- [below-minimum-count] The model has 0 activity node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
       },
       "expert": {
-        "content": "Sure. So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.\n\nThen it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\n\nOnce it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\n\nThen it's released, goes to the warehouse, and ships against the due date. So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them."
+        "content": "(a) is the better week, easy — three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis. A Meridian miss is a different category — it's not just \"late,\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\n\nWhere does it flip? Honestly... I don't think it does flip, not in any range I'd actually see in a week. Even if you told me \"twenty small orders late\" versus \"one Meridian order late\" — I'd still not want to be the one who let Meridian slip. That's less me doing cost math and more just knowing what happens organizationally if Meridian gets touched. I know that's not a real number you can put in a formula. If you need a number, you'd have to get commercial in a room and force them to say it out loud, because right now it's a \"we just don't do that\" rule, not a traded-off cost."
       }
     },
     {
       "turn": 4,
-      "text": [],
+      "text": ["I'll wait on your answer to those three."],
       "asks": [
         {
-          "question": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines.",
-          "toolCallId": "toolu_01VcV1KAvgD2ZWUJnBfGcBuh"
+          "question": "Understood — I'll record that as a hard rule (\"we just don't do that\"), not a weight, and note that a real exchange rate would have to come from commercial. So the model ranks: no Meridian misses first, then late-order count, with changeover and idle hours as your own diagnostics.\n\nNow let me get the edges of the thing. Three related questions, same frame: (1) When you're making that Line 2 call, what's the smallest set of equipment you're really scheduling across — just Line 2, or all the lines plus something shared between them? (2) How far ahead does your schedule actually have to hold to be useful — a shift, a week, a month? (3) Where does an order enter your world and where does it leave it — does it start at \"released from the demand book\" and end at \"off the line\", or does it go further?",
+          "toolCallId": "toolu_014zbFAT1uDZdGkd9TnBEDyL"
+        },
+        {
+          "question": "(Still holding those three — take them in any order you like.)",
+          "toolCallId": "toolu_013B3et1ZFfJdYBWwGQGxF1s",
+          "rejected": "An interactive affordance is already pending (affordance_toolu_014zbFAT1uDZdGkd9TnBEDyL); wait for its reply before asking another question."
         }
       ],
       "sweeps": [
         {
           "status": "applied",
           "appliedCaptureIds": [
-            "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
-            "capture-de512bde-aa52-4147-933f-81439aa5ec6d",
-            "capture-a6e8dc50-fffb-494d-8bd2-59704c0427e4",
-            "capture-3cb49f42-f479-4b67-be4c-22c8f9771f6e",
-            "capture-5628ca29-5985-4005-aa3f-a6885dc38223",
-            "capture-6d4d1074-f6fe-4d4c-95c2-f242a6f98233",
-            "capture-a0b65576-83d8-4134-9fbe-9b059663ae12",
-            "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
-            "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-            "capture-fa56fa8b-611a-4a38-9a42-1bd038e52d80",
-            "capture-dba4ec08-0265-420c-95d2-4dce250ae0b6",
-            "capture-0b2046b4-55c8-4ce3-abac-296d6abe469d",
-            "capture-8156b872-b3c2-43db-aa67-56166bebe556",
-            "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
-            "capture-589bc2db-8fc9-4d65-8024-b34ce4cd736a",
-            "capture-07de77cc-9de8-41e9-92f6-8fe06a6263c9",
-            "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
-            "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b",
-            "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
-            "capture-7df09f81-9c85-43ac-b69e-306d540f8afb",
-            "capture-e0f39723-a7e5-4656-a8fb-0e2b50bb82da",
-            "capture-d8dffb0f-f148-4af2-ba7e-478a6a1b38c6",
-            "capture-a2938097-b902-4f24-8e15-70f4b8ce95fb",
-            "capture-896881a6-c9ec-469f-ab03-4a56b59f6cad",
-            "capture-4a3ae53c-2c2f-4664-9499-7e81c254abc5",
-            "capture-d662739b-76f0-429a-829a-ccb79763b6b9",
-            "capture-a9e42aa6-8d30-4ded-a8c4-f24220cfb292",
-            "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e"
+            "capture-66f2471d-7a05-4ea9-a788-ddd5d45380c5",
+            "capture-239ae929-f206-452e-a332-ba47e5c16cf2",
+            "capture-da18e2cd-2af7-4aab-ade0-cd33e819a88b",
+            "capture-c0aae96c-f4bb-4695-9f86-01228a2b2f87",
+            "capture-6cb6a6a9-0536-46e6-aa77-4b211514bdf3",
+            "capture-26d91606-f924-457f-a62c-8c5c3a22ff3c",
+            "capture-907b63ad-c480-4368-9b70-94cbc905fe70",
+            "capture-41b692e0-6ff8-4294-9a9c-e97f7e51b6bb",
+            "capture-885c4bd0-8675-4604-990a-65c7118fa832",
+            "capture-a23f2234-5075-479e-86fb-89a3450bb4f1",
+            "capture-9bbac61c-4b3d-42c8-a74a-2d846127039b",
+            "capture-c216b212-3249-4b15-9b38-b7fc73c4e53a",
+            "capture-6bf8429a-d19a-47bd-8632-6e4e4a018357",
+            "capture-d29040ff-79cb-444b-afba-b81e63886bf4"
           ],
           "skippedDedupKeys": [],
           "advisories": [
@@ -179,164 +139,191 @@
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
-                "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-053410a5-6574-4355-aabf-dd972f0088e1",
-                "capture-d8dffb0f-f148-4af2-ba7e-478a6a1b38c6"
+                "capture-41b692e0-6ff8-4294-9a9c-e97f7e51b6bb",
+                "capture-a23f2234-5075-479e-86fb-89a3450bb4f1"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
-                "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b"
+                "capture-6bf8429a-d19a-47bd-8632-6e4e4a018357",
+                "capture-d29040ff-79cb-444b-afba-b81e63886bf4"
               ]
             }
           ],
           "completion": {
             "complete": false,
-            "revision": "2b8efdb41c191608",
-            "pluginVersion": "sdcpn/2026-08-25.2",
-            "unsatisfied": 28,
+            "revision": "3393ca1b0810e08d",
+            "pluginVersion": "sdcpn/2026-08-26.2",
+            "unsatisfied": 8,
             "unmapped": [],
-            "cue": "The harness folded the model at revision 2b8efdb41c191608 (plugin sdcpn/2026-08-25.2): 15 node(s) from 43 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [below-required-precision] \"how long it takes\" on activity:filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n6 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+            "cue": "The harness folded the model at revision 3393ca1b0810e08d (plugin sdcpn/2026-08-26.2): 7 node(s) from 14 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 1 entity-type node(s); the floor needs 2.\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:full white-to-tint changeover.\n- [below-required-precision] \"state that rides along with each instance\" on entity-type:order is known as a named; the model needs spelled out. Smallest delta: move it from named to spelled out.\n- [unaddressed] \"how many there are, or the population's shape\" has not been addressed on entity-type:order.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:full white-to-tint changeover: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:full white-to-tint changeover: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:full white-to-tint changeover: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:order: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:order: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n\n3 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
           }
         }
       ],
       "signals": [
         {
           "tagName": "affordance-reply-bound",
-          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nTake that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you ha…"
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nOn Meridian being weighted heavier: suppose at end of week you could land on one of two outcomes — (a) three non-Meridian orders a day la…"
         }
       ],
       "toolErrors": [],
-      "pendingQuestion": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines.",
+      "pendingQuestion": "Understood — I'll record that as a hard rule (\"we just don't do that\"), not a weight, and note that a real exchange rate would have to come from commercial. So the model ranks: no Meridian misses first, then late-order count, with changeover and idle hours as your own diagnostics.\n\nNow let me get the edges of the thing. Three related questions, same frame: (1) When you're making that Line 2 call, what's the smallest set of equipment you're really scheduling across — just Line 2, or all the lines plus something shared between them? (2) How far ahead does your schedule actually have to hold to be useful — a shift, a week, a month? (3) Where does an order enter your world and where does it leave it — does it start at \"released from the demand book\" and end at \"off the line\", or does it go further?",
       "completion": {
-        "captures": 43,
+        "captures": 14,
         "complete": false,
-        "unsatisfied": 28,
-        "outsideSlice": 6,
+        "unsatisfied": 8,
+        "outsideSlice": 3,
         "unmapped": 0,
-        "revision": "2b8efdb41c191608",
-        "cue": "The harness folded the model at revision 2b8efdb41c191608 (plugin sdcpn/2026-08-25.2): 15 node(s) from 43 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [below-required-precision] \"how long it takes\" on activity:filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n6 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+        "revision": "3393ca1b0810e08d",
+        "cue": "The harness folded the model at revision 3393ca1b0810e08d (plugin sdcpn/2026-08-26.2): 7 node(s) from 14 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 1 entity-type node(s); the floor needs 2.\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:full white-to-tint changeover.\n- [below-required-precision] \"state that rides along with each instance\" on entity-type:order is known as a named; the model needs spelled out. Smallest delta: move it from named to spelled out.\n- [unaddressed] \"how many there are, or the population's shape\" has not been addressed on entity-type:order.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:full white-to-tint changeover: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:full white-to-tint changeover: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:full white-to-tint changeover: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:order: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:order: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n\n3 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
       },
       "expert": {
-        "content": "Good question, and this is where the sheet lies to me a bit if I'm honest. On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\n\nBut physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between. So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\n\nWhat I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait. I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless."
+        "content": "Fair, let me take those one at a time.\n\n(1) It's never really \"just Line 2\" in my head, even if that's the decision in front of me. The changeover crew is the shared thing — there's one crew, two techs, covering all three lines. So if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\" If they're tied up elsewhere, my \"wash down now\" option isn't even really available — I'd be queuing behind whoever else needs them. So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.\n\n(2) Practically, a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning. Anything past a week is soft; the book itself gets revised. I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially, because you don't want to discover Thursday that you needed to have started Tuesday. But if you ask me to hold a plan that's useful a month out, I'd say no — too much changes.\n\n(3) For me it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date. It ends when it clears QA hold and ships. I know people upstream of me and downstream of me — sales promising dates, warehouse and logistics after QA — but from where I sit, an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line. That QA gap matters more than people think — a batch can be done Tuesday and still ship late if the lab's backed up."
       }
     },
     {
       "turn": 5,
       "text": [
-        "That's a really valuable thing to have said — the sheet says one line, one order; the floor says four bits of kit with small tanks between them. I'll record both rather than pick one.\n\nThat choice matters for what the model can answer, so let me put it to you."
+        "Three lines plus one two-tech changeover crew, a one-week horizon, and the clock stops at \"cleared QA\" — that last one especially; a lot of models would have stopped at the line.",
+        "I'll hold there for your answer."
       ],
       "asks": [
         {
-          "question": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate.",
-          "toolCallId": "toolu_01CfCi6guTLjrxg8Hg8QcC6A"
+          "question": "Two things before I ask you to walk me through an actual order, and then I'll stop asking about the model and start asking about the plant.\n\n(a) Suppose I hand you a finished model and you want to know whether to trust it. What would you check? For instance — if we fed it last month's demand book, what would it have to reproduce before you'd believe its answer on the wash-down-versus-idle call? Late-order count for the month? The changeover hours on Line 2? Something you'd eyeball?\n\n(b) How much of your time have I got, roughly — one sitting, or can I come back? That changes how deep I go versus how much I flag as unknown.",
+          "toolCallId": "toolu_01MVbhFM9C1NH3fzCtTSYana"
+        }
+      ],
+      "sweeps": [
+        {
+          "status": "applied",
+          "appliedCaptureIds": [
+            "capture-37ea41c4-f012-4864-a896-ae745b3ba467",
+            "capture-47724d1f-2419-4d2e-9662-442ea9e7d8e5",
+            "capture-665b5de5-72f5-49c9-938b-55b00afa5252",
+            "capture-ae712ebf-7a14-4cd9-adec-83df50ff2fa2",
+            "capture-e0802c09-2a87-4514-b8a2-51841de54cbc",
+            "capture-01f20a7f-43bf-42f9-a532-f04cf92ad105",
+            "capture-61d5a849-6ada-4278-a08b-86a2f62f2eff",
+            "capture-199dc6be-d352-46eb-a561-b5c6b8b1703e",
+            "capture-a9dd192c-4602-4b65-8896-be0481e9ce8b",
+            "capture-2296040f-dd70-46bf-b603-b128a63be702",
+            "capture-52ae613b-8aaf-4d9f-866d-72f8f37c00e7",
+            "capture-5fc553d4-e294-4ec8-8368-52ffe5044e2f",
+            "capture-8f6e902b-07ed-49ce-aa1b-40d7e46502ce",
+            "capture-7514059e-f02b-4f61-a3a1-11ca6fd01646",
+            "capture-bbeb387d-bf09-4357-b52a-58ad8b679738",
+            "capture-a77d820d-b5ac-45d5-a41b-e94c3bc7973f",
+            "capture-e776f323-41e3-460b-ace7-666b43385453",
+            "capture-c625c3a0-1ce6-4249-b282-309c02e0a0d4",
+            "capture-1842e3f3-9daf-42d7-8803-eafe3b3c5146",
+            "capture-ee33f01c-2e09-4f6b-a34e-6e9c2efb96e3"
+          ],
+          "skippedDedupKeys": [],
+          "advisories": [
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c0aae96c-f4bb-4695-9f86-01228a2b2f87",
+                "capture-e776f323-41e3-460b-ace7-666b43385453"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-6bf8429a-d19a-47bd-8632-6e4e4a018357",
+                "capture-ee33f01c-2e09-4f6b-a34e-6e9c2efb96e3"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-d29040ff-79cb-444b-afba-b81e63886bf4",
+                "capture-ee33f01c-2e09-4f6b-a34e-6e9c2efb96e3"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-01f20a7f-43bf-42f9-a532-f04cf92ad105",
+                "capture-2296040f-dd70-46bf-b603-b128a63be702"
+              ]
+            }
+          ],
+          "completion": {
+            "complete": false,
+            "revision": "2bd46c0f34f76015",
+            "pluginVersion": "sdcpn/2026-08-26.2",
+            "unsatisfied": 24,
+            "unmapped": [],
+            "cue": "The harness folded the model at revision 2bd46c0f34f76015 (plugin sdcpn/2026-08-26.2): 18 node(s) from 34 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:QA hold.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:QA hold.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:QA hold.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:QA hold.\n- … and 12 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n6 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+          }
         }
       ],
-      "sweeps": [],
       "signals": [
         {
           "tagName": "affordance-reply-bound",
-          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can s…"
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nUnderstood — I'll record that as a hard rule (\"we just don't do that\"), not a weight, and note that a real exchange rate would have to co…"
         }
       ],
       "toolErrors": [],
-      "pendingQuestion": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate.",
+      "pendingQuestion": "Two things before I ask you to walk me through an actual order, and then I'll stop asking about the model and start asking about the plant.\n\n(a) Suppose I hand you a finished model and you want to know whether to trust it. What would you check? For instance — if we fed it last month's demand book, what would it have to reproduce before you'd believe its answer on the wash-down-versus-idle call? Late-order count for the month? The changeover hours on Line 2? Something you'd eyeball?\n\n(b) How much of your time have I got, roughly — one sitting, or can I come back? That changes how deep I go versus how much I flag as unknown.",
       "completion": {
-        "captures": 43,
+        "captures": 34,
         "complete": false,
-        "unsatisfied": 28,
+        "unsatisfied": 24,
         "outsideSlice": 6,
         "unmapped": 0,
-        "revision": "2b8efdb41c191608",
-        "cue": "The harness folded the model at revision 2b8efdb41c191608 (plugin sdcpn/2026-08-25.2): 15 node(s) from 43 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [below-required-precision] \"how long it takes\" on activity:filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n6 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+        "revision": "2bd46c0f34f76015",
+        "cue": "The harness folded the model at revision 2bd46c0f34f76015 (plugin sdcpn/2026-08-26.2): 18 node(s) from 34 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:QA hold.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:QA hold.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:QA hold.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:QA hold.\n- … and 12 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n6 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
       },
       "expert": {
-        "content": "No, I do want that in scope — if I'm honest, the disruption question and the tank question are the same underlying thing to me. Half the reason Line 1's options are worse when Line 2 goes down is because it feels sluggish and blocked in ways I can't pin on the published line rate. If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\n\nSo yes — build it as separate stages if that's what it takes. I'll warn you now, though: I don't have clean numbers for tank sizes or stage-by-stage rates. I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head. Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head."
+        "content": "(a) Honestly, the first thing I'd check is the boring one — did it land roughly where we actually landed on late orders that month? If I fed it last month's demand book and it told me we shipped everything on time, I'd stop trusting it immediately, because we didn't — we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones. So: same rough number and same *kind* of misses. If it says we missed distributor orders and we actually missed a Meridian one, that's worse than getting the count wrong.\n\nAfter that I'd want to eyeball changeover hours on Line 2 and 3 specifically, because I know roughly what those looked like — if the model has Line 3 idle half the week waiting on the crew, and that never happens in real life, I'd know it's missing something about how the crew actually gets shared out. And I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1 — because if it only works on the calm weeks, it's not telling me anything I don't already know from the sheet.\n\nI wouldn't trust a single number out of it, put it that way. I'd want to recognize the *shape* of a real month before I'd believe it on something as specific as the wash-versus-idle call.\n\n(b) I've got another half hour or so before I'm back on the floor — go ahead, I can come back another day if we need more."
       }
     },
     {
       "turn": 6,
       "text": [
-        "Understood, and that's an honest and useful boundary: stage-level rates live in the historian, tank sizes on engineering drawings, neither in your head. I'll record those as open with their source rather than let me invent them.\n\nLet me take what you *do* carry.",
-        "The sweep bounced on a misquote of mine: the expert's words were \"I **just** know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\". Retrying with the verbatim text.",
-        "Second bounce, same cause — capitalisation: the expert wrote \"**And** then whatever happens to the bumped tint order…\". Retrying.",
-        "Right — I have your sheet-level knowledge to draw on, so let me take it at that level."
+        "Half an hour is enough for the spine. Let's use it on the walkthrough and the crew, and I'll flag the rest for next time.",
+        "Go ahead when you're ready — I'm listening for the order of things, not polish."
       ],
       "asks": [
         {
-          "question": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white.",
-          "toolCallId": "toolu_0114D18YCRQ5SdR2RDUdY11m"
+          "question": "Take that Meridian white run on Line 2 — the real one from a couple of weeks back. Walk me through it from the moment it landed in the demand book to the moment it cleared QA. Don't generalise, just tell me what happened in order: what had to be true before it could start on Line 2, who did what, roughly how long each part took, and where it sat waiting. Five or six steps is plenty — I'll dig into whichever ones matter.",
+          "toolCallId": "toolu_014sfPH7t4Q7gxcPtfYwxjQt"
         }
       ],
       "sweeps": [
-        {
-          "status": "refused",
-          "refusal": {
-            "code": "evidence-quote-not-found",
-            "excerpt": "I know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit",
-            "message": "No user entry contains the verbatim quote \"I know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\". Repair the quote to match the user's words exactly."
-          }
-        },
-        {
-          "status": "refused",
-          "refusal": {
-            "code": "evidence-quote-not-found",
-            "excerpt": "and then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
-            "message": "No user entry contains the verbatim quote \"and then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\". Repair the quote to match the user's words exactly."
-          }
-        },
         {
           "status": "applied",
           "appliedCaptureIds": [
-            "capture-1cb33f48-6553-4e4f-a8a0-37d7631b08ea",
-            "capture-f073c3ed-2a89-4499-b3b2-fe160e8c1057",
-            "capture-c9864a2c-cbb3-41c9-97a6-e44cc1d7d424",
-            "capture-480c2821-4d80-495b-a652-f5de8b035144",
-            "capture-f3f2c366-eab0-49fa-951c-773f77aa11b2",
-            "capture-3bb35fb7-3954-45d4-839f-20ee46a8c052",
-            "capture-e552ac87-8cfa-4091-a262-6fba33ab9f83",
-            "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-            "capture-dd037a1c-63c0-47b8-8886-81c6d1f70226",
-            "capture-6c46c958-82b9-4ba0-bf0f-363fd70b6dbc",
-            "capture-ee4eb482-b4b3-4392-94d7-ef9dc0a6ca98",
-            "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-            "capture-32521b14-4f1e-41ff-ab95-dfc11d8eee37",
-            "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
-            "capture-c1704cba-8451-47a5-add8-2e388b330a1f",
-            "capture-68ab39e5-8046-4f93-887e-11ed3e3b1da3",
-            "capture-c6d485c6-0e21-4cc0-b626-9091448d6ba1",
-            "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
-            "capture-737200bb-8f75-455f-b90a-3363a30d5fce",
-            "capture-78203b7c-8e00-469c-9d53-01d1a656d5c1",
-            "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3",
-            "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
-            "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
-            "capture-42e0a99d-6cf6-4b30-8199-b430405ba25b",
-            "capture-a27c0fc1-57f3-4eed-bea8-15453c84f2da",
-            "capture-0f6aea65-d3a4-430b-b532-4f1100303f9e",
-            "capture-a3f706dd-453a-4543-9990-26efb1b079dd",
-            "capture-67de2e75-132c-43a7-b64e-412343204931",
-            "capture-bf082835-a2ca-4279-80e5-726f157270bd",
-            "capture-ce28dd53-a53d-4bc9-9956-dc3268c35e3e",
-            "capture-9b28544e-b867-4018-9c35-2691cef17a62",
-            "capture-4c4af9ea-df1a-4449-adb7-d48fce7eae93",
-            "capture-dabdbb5f-9eca-4afb-ad50-5b381d9dfa4f",
-            "capture-292e1165-0990-4d17-b6db-153c675fd66c",
-            "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
-            "capture-54d606d7-8c61-4f0a-bd5f-867bba1af3f7",
-            "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
-            "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
-            "capture-b0908788-ec79-4481-b056-1fa606930f85"
+            "capture-8e963c90-4270-411e-8ec9-9acbb2d2dabc",
+            "capture-65ac2ec5-6286-4058-afdf-08678d733640",
+            "capture-9610d59f-1871-41d2-873c-e80a80daf01a",
+            "capture-cb1567d4-e83b-4ff8-85aa-c917277e92e3",
+            "capture-a64355a7-9a1c-48b4-b1b6-571aa465c457",
+            "capture-ca18e195-3155-4504-b85d-16c7f96d1bdf",
+            "capture-f2135748-e23c-40f8-b30b-54bba48e876e",
+            "capture-8a3b6dae-cba1-4332-a4dc-f98ff6b81bc2",
+            "capture-0f7b50a8-31f5-4025-ac2e-4a65bee0e3af",
+            "capture-1d5aba4c-760f-4e4e-b48f-a3f498a4a75f",
+            "capture-51875f80-77b4-4e1c-b260-ef2cf2d3a47a",
+            "capture-308e3c38-4da1-468b-b8b0-d330d0d3a3de",
+            "capture-db07e2c6-f110-4f71-90a1-aaf5a20fd5ea",
+            "capture-1aba2bfb-ad60-4e76-9a2b-f4ac16294d1d",
+            "capture-25d93015-ae4d-48ce-8708-1d5c257d629a",
+            "capture-d767508b-10f1-41b0-8818-b943bf124b10",
+            "capture-a8c037cd-b9d8-4056-828f-74511da9a726",
+            "capture-ccf25a9c-6c03-47ed-9cd4-e030f3ef1dc9",
+            "capture-760f09f2-bdec-44fe-897d-f81b376a0ad6",
+            "capture-f79e5a2e-1102-4970-a177-0b9c1fab4c03",
+            "capture-03ff88a9-662d-4963-aece-fe45c343df17",
+            "capture-da211e90-dab6-4896-b9f1-9d01a9c55b9e"
           ],
           "skippedDedupKeys": [],
           "advisories": [
@@ -344,161 +331,241 @@
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae"
+                "capture-6bf8429a-d19a-47bd-8632-6e4e4a018357",
+                "capture-03ff88a9-662d-4963-aece-fe45c343df17"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-                "capture-711c9600-2f30-4e86-95a2-cc373696e94c"
+                "capture-d29040ff-79cb-444b-afba-b81e63886bf4",
+                "capture-03ff88a9-662d-4963-aece-fe45c343df17"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
-                "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11"
+                "capture-37ea41c4-f012-4864-a896-ae745b3ba467",
+                "capture-8e963c90-4270-411e-8ec9-9acbb2d2dabc"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
-                "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3"
+                "capture-01f20a7f-43bf-42f9-a532-f04cf92ad105",
+                "capture-a64355a7-9a1c-48b4-b1b6-571aa465c457"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b",
-                "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3"
+                "capture-01f20a7f-43bf-42f9-a532-f04cf92ad105",
+                "capture-db07e2c6-f110-4f71-90a1-aaf5a20fd5ea"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
-                "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53"
+                "capture-2296040f-dd70-46bf-b603-b128a63be702",
+                "capture-a64355a7-9a1c-48b4-b1b6-571aa465c457"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-7df09f81-9c85-43ac-b69e-306d540f8afb",
-                "capture-42e0a99d-6cf6-4b30-8199-b430405ba25b"
+                "capture-2296040f-dd70-46bf-b603-b128a63be702",
+                "capture-db07e2c6-f110-4f71-90a1-aaf5a20fd5ea"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
-                "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a"
+                "capture-1842e3f3-9daf-42d7-8803-eafe3b3c5146",
+                "capture-308e3c38-4da1-468b-b8b0-d330d0d3a3de"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-                "capture-711c9600-2f30-4e86-95a2-cc373696e94c"
+                "capture-ee33f01c-2e09-4f6b-a34e-6e9c2efb96e3",
+                "capture-03ff88a9-662d-4963-aece-fe45c343df17"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
-                "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277"
+                "capture-a64355a7-9a1c-48b4-b1b6-571aa465c457",
+                "capture-db07e2c6-f110-4f71-90a1-aaf5a20fd5ea"
               ]
             }
           ],
           "completion": {
             "complete": false,
-            "revision": "3157c77c0d581ebb",
-            "pluginVersion": "sdcpn/2026-08-25.2",
-            "unsatisfied": 28,
+            "revision": "1c8f78713a851bca",
+            "pluginVersion": "sdcpn/2026-08-26.2",
+            "unsatisfied": 41,
             "unmapped": [],
-            "cue": "The harness folded the model at revision 3157c77c0d581ebb (plugin sdcpn/2026-08-25.2): 28 node(s) from 82 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:tint-to-white washdown.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n19 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+            "cue": "The harness folded the model at revision 1c8f78713a851bca (plugin sdcpn/2026-08-26.2): 29 node(s) from 56 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 29 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n10 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
           }
         }
       ],
       "signals": [
         {
           "tagName": "affordance-reply-bound",
-          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWould you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actuall…"
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nTwo things before I ask you to walk me through an actual order, and then I'll stop asking about the model and start asking about the plan…"
         }
       ],
       "toolErrors": [],
-      "pendingQuestion": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white.",
+      "pendingQuestion": "Take that Meridian white run on Line 2 — the real one from a couple of weeks back. Walk me through it from the moment it landed in the demand book to the moment it cleared QA. Don't generalise, just tell me what happened in order: what had to be true before it could start on Line 2, who did what, roughly how long each part took, and where it sat waiting. Five or six steps is plenty — I'll dig into whichever ones matter.",
       "completion": {
-        "captures": 82,
+        "captures": 56,
         "complete": false,
-        "unsatisfied": 28,
-        "outsideSlice": 19,
+        "unsatisfied": 41,
+        "outsideSlice": 10,
         "unmapped": 0,
-        "revision": "3157c77c0d581ebb",
-        "cue": "The harness folded the model at revision 3157c77c0d581ebb (plugin sdcpn/2026-08-25.2): 28 node(s) from 82 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:tint-to-white washdown.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n19 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+        "revision": "1c8f78713a851bca",
+        "cue": "The harness folded the model at revision 1c8f78713a851bca (plugin sdcpn/2026-08-26.2): 29 node(s) from 56 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 29 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n10 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
       },
       "expert": {
-        "content": "Right, so a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.\n\nBad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more \"the filler hiccupped twice\" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely. Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\n\nOn Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten. That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.\n\nTints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them."
+        "content": "Alright — that one, specifically, as best I remember it.\n\n1. **It landed in the demand book** on the Monday release, part of that week's batch of orders from ERP — a Meridian order, big white SKU, due Friday. No surprise, Meridian white basically always goes to Line 2, so it went into \"my\" Line 2 column on the sheet without much debate.\n\n2. **It had to wait its turn behind whatever was already running on Line 2.** There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run. That's the easy case, no crew involved.\n\n3. **It ran.** Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack. I don't watch this minute by minute, but it's a big volume order, so it was on the line most of the day. I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.\n\n4. **Once fill and pack was done, it went into QA hold.** That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\n\n5. **It sat in QA** — normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold. I don't remember this one having any drama in the lab.\n\n6. **It cleared and shipped Thursday**, ahead of the Friday due date. That's the one that gave me the room to think about the wash-versus-idle call on the *next* job — because Meridian had already cleared, I wasn't worried about that due date anymore, I was worried about the tint order coming up behind it.\n\nThat's the shape of it. The interesting stuff — the crew, the idle decision — happens in the gaps between steps 3 and 4 on the *next* job, not this one."
       }
     },
     {
       "turn": 7,
       "text": [
-        "One thing you said gives me pause, and I'd rather sort it now than bake it in wrong."
+        "That's exactly the shape I needed — and you've told me where the real decision lives. Let's go there."
+      ],
+      "asks": [
+        {
+          "question": "The crew. Two techs, three lines. Tell me about the last time two lines wanted them at the same time — what happened, and who decided? I'm after the practiced rule, not the one on the wall: does the crew go to whoever asked first, to the biggest order, to the tightest due date, to whoever shouts loudest, to Meridian? And has anyone ever overridden that — pulled them off a line mid-job?",
+          "toolCallId": "toolu_0125yowHYNwQisNqZJnRdazC"
+        }
+      ],
+      "sweeps": [],
+      "signals": [
+        {
+          "tagName": "affordance-reply-bound",
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nTake that Meridian white run on Line 2 — the real one from a couple of weeks back. Walk me through it from the moment it landed in the de…"
+        }
+      ],
+      "toolErrors": [],
+      "pendingQuestion": "The crew. Two techs, three lines. Tell me about the last time two lines wanted them at the same time — what happened, and who decided? I'm after the practiced rule, not the one on the wall: does the crew go to whoever asked first, to the biggest order, to the tightest due date, to whoever shouts loudest, to Meridian? And has anyone ever overridden that — pulled them off a line mid-job?",
+      "completion": {
+        "captures": 56,
+        "complete": false,
+        "unsatisfied": 41,
+        "outsideSlice": 10,
+        "unmapped": 0,
+        "revision": "1c8f78713a851bca",
+        "cue": "The harness folded the model at revision 1c8f78713a851bca (plugin sdcpn/2026-08-26.2): 29 node(s) from 56 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 29 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n10 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "Now that's a real story, not a made-up one, thankfully.\n\nIt was maybe three weeks ago — Line 1 had just finished a specialty run and needed the full two-hour changeover before the next job, and around the same time Line 3 finished a tint run and needed a family switch too. Both wanted the crew basically within the same half hour.\n\nPractically, what happens is not some clean rule — it's whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle. That morning I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date, and Line 3's next job had a couple days of slack. Line 3 sat there clean but idle for — I want to say close to two hours — waiting its turn. Nobody died over it, but it's wasted line time that doesn't show up anywhere as a \"problem,\" it's just... the day.\n\nIf it had been Meridian sitting behind either of those changeovers, that decision doesn't even get discussed — the crew goes to whichever line has the Meridian job next, full stop, everyone understands that without me saying it out loud.\n\nHas anyone ever pulled the crew off mid-job? Yes, actually — maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now. That's rare, and it's not my call, that's a maintenance-versus-me argument that goes over my head to the ops director if it's a real fight. But day to day, it's basically me making a judgment call at the huddle about whose due date is tightest, and nobody's written that rule down either."
+      }
+    },
+    {
+      "turn": 8,
+      "text": [
+        "That's the rule in practice: Meridian first without discussion, otherwise your huddle call on tightest due date, otherwise whoever reaches the crew lead first — with maintenance able to pull them for an emergency. I'll record it that way, including the two hours Line 3 sat idle.\n\nNow the number your whole question hangs on."
+      ],
+      "asks": [
+        {
+          "question": "The changeover itself. Thinking of white-to-tint washdowns you've seen on Line 2: what's the *quickest* one you'd realistically see, and what's the *longest* — the bad one where it drags? Then where does it usually land between those. And two follow-ons: does the direction matter — is tint-to-white different from white-to-tint? — and you mentioned \"the full two-hour changeover\" after a specialty run on Line 1, so is specialty a different animal again?",
+          "toolCallId": "toolu_01BL78LJMKt94i4r5FZz9P6v"
+        }
+      ],
+      "sweeps": [],
+      "signals": [
+        {
+          "tagName": "affordance-reply-bound",
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThe crew. Two techs, three lines. Tell me about the last time two lines wanted them at the same time — what happened, and who decided? I'…"
+        }
+      ],
+      "toolErrors": [],
+      "pendingQuestion": "The changeover itself. Thinking of white-to-tint washdowns you've seen on Line 2: what's the *quickest* one you'd realistically see, and what's the *longest* — the bad one where it drags? Then where does it usually land between those. And two follow-ons: does the direction matter — is tint-to-white different from white-to-tint? — and you mentioned \"the full two-hour changeover\" after a specialty run on Line 1, so is specialty a different animal again?",
+      "completion": {
+        "captures": 56,
+        "complete": false,
+        "unsatisfied": 41,
+        "outsideSlice": 10,
+        "unmapped": 0,
+        "revision": "1c8f78713a851bca",
+        "cue": "The harness folded the model at revision 1c8f78713a851bca (plugin sdcpn/2026-08-26.2): 29 node(s) from 56 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 29 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n10 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "Okay, let's separate those because they're genuinely not the same beast.\n\nWhite-to-tint on Line 2 — quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes. Longest, if they're stretched thin or something's stuck, I've seen it drag past an hour, call it an hour twenty on a bad day. Typically though it lands around 45 minutes to an hour. That's the \"cheap\" direction.\n\nTint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric. Any pigment left behind wrecks a white batch, so that's a full washdown. Quickest I've seen that go is maybe two and a half hours if everything's clean and the crew's fresh. On a bad day — dried pigment in a fitting, whatever — it's crept toward four hours. Call it three hours typical, and that's the number I actually use on the sheet.\n\nSpecialty is its own animal again, like you said — going in or coming out of a specialty run, either direction, it's around two hours normally. I've seen it shorter, maybe an hour forty if it's a specialty-to-specialty color change rather than a full family switch. I haven't seen it run much longer than two and a half hours, but I'll be honest, I don't watch specialty changeovers as closely as I watch the white-tint ones because they don't hit my due dates as hard.",
+        "stimulus": "(Sorry — I've just seen the time, I have the floor huddle in ten minutes. How much more do you need?)"
+      }
+    },
+    {
+      "turn": 9,
+      "text": [
+        "That's three separate changeovers with real asymmetry — that alone was worth the session.\n\nTen minutes: I'll name what's still missing and you pick. Open gaps are (1) how orders actually arrive into the demand book — you made that whole call because you *knew* a white order was coming that afternoon; (2) how long a run takes per unit on each line; (3) QA turnaround beyond the four hours for white; (4) breakdowns, which you said I'd need to reproduce the odd weeks. I'd spend the ten minutes on (1), because your decision literally rested on foreknowledge of a release.",
+        "Swept — question above still stands whenever you're ready."
       ],
       "asks": [
         {
-          "question": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?",
-          "toolCallId": "toolu_016Sy8K81vYAJqTRfxPP8zou"
+          "question": "So: that afternoon, how did you know the white order was coming? Was that a scheduled release event — the book updates at fixed times — or did someone tell you, or is it a pattern you've learned? And roughly how many orders land in a typical week's book, and how much do they swing between a quiet week and a busy one?",
+          "toolCallId": "toolu_016xYu97JnWm23xVaBGYSPyz"
         }
       ],
       "sweeps": [
+        {
+          "status": "refused",
+          "refusal": {
+            "code": "evidence-quote-not-found",
+            "excerpt": "an order's mine from release to \"cleared QA\"",
+            "message": "No user entry contains the verbatim quote \"an order's mine from release to \"cleared QA\"\". Repair the quote to match the user's words exactly."
+          }
+        },
         {
           "status": "applied",
           "appliedCaptureIds": [
-            "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057",
-            "capture-9d5063d7-b9fb-400e-8b54-f618c6fde20e",
-            "capture-3245b29a-3687-4313-97c5-e0455e5889ba",
-            "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
-            "capture-770314e5-f47a-463e-908a-1d8c23ee60f5",
-            "capture-6ff1c59a-0664-487b-a946-2680043419a2",
-            "capture-be0c3675-ae93-41c5-9eaa-7d36d84617cb",
-            "capture-3e2a5a8a-bd99-4642-afcf-f9d3dfe2e9f6",
-            "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
-            "capture-27ee0ed5-50d0-47f6-94b8-77e090bca50f",
-            "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
-            "capture-2a491098-b602-4b46-bbaa-439e291027db",
-            "capture-c4aefe40-a022-4990-96a1-b74243850715",
-            "capture-76c7250e-6575-4e31-b667-113f3a497cce",
-            "capture-7da94524-13b5-4c11-a1b4-9cb1b0f07e19",
-            "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
-            "capture-d6985d8d-f85e-4556-a091-df64be080ba6",
-            "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
-            "capture-04a6f876-12f4-4f53-b6f2-f8e5fa9c87bc",
-            "capture-592b83e0-ece3-4e98-aedf-cdf70c202e96",
-            "capture-32fe7be9-75c7-464c-87cb-ca38fef4039b",
-            "capture-31556043-9787-40dc-8c0d-b74a47ed3589",
-            "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
-            "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
-            "capture-d2d6e303-2f63-478a-ace1-0bf61abbfddd",
-            "capture-5548a18b-9f79-4475-a9ab-83a74c750721",
-            "capture-1ee7c206-0c56-4d6b-b091-5861f9c40438",
-            "capture-4b706f60-c02f-4973-aa58-2d3ded113c39",
-            "capture-97ea5a05-d89c-4a7d-a136-f90526beaa27",
-            "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
-            "capture-46d37104-fb87-4105-95d5-4448aade81ac",
-            "capture-0cdda695-1dfa-43ef-971c-b9db09403a07"
+            "capture-da8d88a4-c4e2-499b-b138-3f3df855b108",
+            "capture-d9c81987-582e-43fd-8ebb-a7be078ec2b7",
+            "capture-1e33246c-c307-46c2-b6c2-392fd7d92329",
+            "capture-59c35b27-63c3-4ae7-92d5-5454281a05e0",
+            "capture-7cb7c5b3-1c4e-42b5-8c28-b6b851d7b3c3",
+            "capture-e20e49bb-dbd3-4616-8da4-f14024b09ed0",
+            "capture-41a07d27-a4e5-4f0c-8308-854425894bc5",
+            "capture-858e5f98-ce0c-47ca-9bff-1e41d25523eb",
+            "capture-5ac2a1b3-03ea-4864-a6e6-89ea2a3163d9",
+            "capture-42dc7c2d-13c1-407d-ab6e-8359366321d0",
+            "capture-442393fc-5207-40e8-953f-f32c4077af7b",
+            "capture-9842aaa1-3de6-409e-a76a-4dc761ba75f4",
+            "capture-16bb49bd-8cb1-4840-a016-fb3c2e03ea06",
+            "capture-874499fa-7846-4cc1-b5c3-1a214824b34b",
+            "capture-7b487f70-d5b2-436f-96ca-c18b75d4f706",
+            "capture-1692771b-05c1-41fd-a63b-9b93436ac581",
+            "capture-94cf39d1-87b6-4013-a9cf-06e97177192e",
+            "capture-2e05010d-aa3d-4558-bd3a-91b498169a94",
+            "capture-34154727-71ce-4065-abbf-8be1752385ce",
+            "capture-fc5a25de-846f-488d-9330-4d6b634c33b0",
+            "capture-126e6b44-aa42-452b-9085-7bd038842721",
+            "capture-2b6dc206-914d-4980-b539-3621f9c5a118",
+            "capture-97c6e438-15c4-48f8-84c1-fdb8d5b42e3e",
+            "capture-b1cfeb47-e2b4-4730-9483-1422b8597b5c",
+            "capture-b833dc1b-dd19-4d7d-bc4f-754e5e63bb7b",
+            "capture-6fd52cfc-df4d-4a0b-8381-1a80c29a4d4a",
+            "capture-9da728a5-b72c-4e7a-ba0d-a360ef571059",
+            "capture-4bdfb1af-a858-493c-bf5a-2da4279d18a5",
+            "capture-663314c5-79fe-4e3c-918a-1ac8047113a1",
+            "capture-ccb16fb1-30dc-4a94-8367-fd11a5a97373",
+            "capture-822d9723-b7fa-40c4-8921-2a10de44868f",
+            "capture-03f46087-a1d4-409d-80f3-b7c87e23a1b3",
+            "capture-fac82088-05f2-4519-a697-b149c0798172",
+            "capture-7a236317-f8ea-43e8-b88a-a6c6092fb35f",
+            "capture-60d6dc44-d2ee-456c-ad19-1c54d79f37dd",
+            "capture-16c2b41b-9778-4091-91c3-5f15f72171e9"
           ],
           "skippedDedupKeys": [],
           "advisories": [
@@ -506,188 +573,307 @@
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
-                "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057"
+                "capture-6bf8429a-d19a-47bd-8632-6e4e4a018357",
+                "capture-7a236317-f8ea-43e8-b88a-a6c6092fb35f"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
-                "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057"
+                "capture-d29040ff-79cb-444b-afba-b81e63886bf4",
+                "capture-7a236317-f8ea-43e8-b88a-a6c6092fb35f"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
-                "capture-2a491098-b602-4b46-bbaa-439e291027db"
+                "capture-37ea41c4-f012-4864-a896-ae745b3ba467",
+                "capture-da8d88a4-c4e2-499b-b138-3f3df855b108"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
-                "capture-2afae8eb-1155-4b07-9842-971df47a6a7d"
+                "capture-01f20a7f-43bf-42f9-a532-f04cf92ad105",
+                "capture-41a07d27-a4e5-4f0c-8308-854425894bc5"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-                "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957"
+                "capture-2296040f-dd70-46bf-b603-b128a63be702",
+                "capture-41a07d27-a4e5-4f0c-8308-854425894bc5"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
-                "capture-46d37104-fb87-4105-95d5-4448aade81ac"
+                "capture-1842e3f3-9daf-42d7-8803-eafe3b3c5146",
+                "capture-9da728a5-b72c-4e7a-ba0d-a360ef571059"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
-                "capture-2afae8eb-1155-4b07-9842-971df47a6a7d"
+                "capture-ee33f01c-2e09-4f6b-a34e-6e9c2efb96e3",
+                "capture-7a236317-f8ea-43e8-b88a-a6c6092fb35f"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-0f6aea65-d3a4-430b-b532-4f1100303f9e",
-                "capture-31556043-9787-40dc-8c0d-b74a47ed3589"
+                "capture-8e963c90-4270-411e-8ec9-9acbb2d2dabc",
+                "capture-da8d88a4-c4e2-499b-b138-3f3df855b108"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-67de2e75-132c-43a7-b64e-412343204931",
-                "capture-d2d6e303-2f63-478a-ace1-0bf61abbfddd"
+                "capture-a64355a7-9a1c-48b4-b1b6-571aa465c457",
+                "capture-41a07d27-a4e5-4f0c-8308-854425894bc5"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-54d606d7-8c61-4f0a-bd5f-867bba1af3f7",
-                "capture-4b706f60-c02f-4973-aa58-2d3ded113c39"
+                "capture-1d5aba4c-760f-4e4e-b48f-a3f498a4a75f",
+                "capture-e20e49bb-dbd3-4616-8da4-f14024b09ed0"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
-                "capture-46d37104-fb87-4105-95d5-4448aade81ac"
+                "capture-308e3c38-4da1-468b-b8b0-d330d0d3a3de",
+                "capture-9da728a5-b72c-4e7a-ba0d-a360ef571059"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-b0908788-ec79-4481-b056-1fa606930f85",
-                "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb"
+                "capture-db07e2c6-f110-4f71-90a1-aaf5a20fd5ea",
+                "capture-41a07d27-a4e5-4f0c-8308-854425894bc5"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-6ff1c59a-0664-487b-a946-2680043419a2",
-                "capture-76c7250e-6575-4e31-b667-113f3a497cce"
+                "capture-03ff88a9-662d-4963-aece-fe45c343df17",
+                "capture-7a236317-f8ea-43e8-b88a-a6c6092fb35f"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-da211e90-dab6-4896-b9f1-9d01a9c55b9e",
+                "capture-16c2b41b-9778-4091-91c3-5f15f72171e9"
               ]
             }
           ],
           "completion": {
             "complete": false,
-            "revision": "2e4f73ea071077f9",
-            "pluginVersion": "sdcpn/2026-08-25.2",
-            "unsatisfied": 9,
+            "revision": "0ca4cb771fd758bf",
+            "pluginVersion": "sdcpn/2026-08-26.2",
+            "unsatisfied": 65,
             "unmapped": [],
-            "cue": "The harness folded the model at revision 2e4f73ea071077f9 (plugin sdcpn/2026-08-25.2): 36 node(s) from 114 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"the question, in the expert's words\" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what \"better\" means, and trade-off weights\" has not been addressed on objective:where Line 1 loses its time.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n\nPatterns whose trigger may apply (discretionary):\n- P08 on objective:where Line 1 loses its time: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n\n33 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+            "cue": "The harness folded the model at revision 0ca4cb771fd758bf (plugin sdcpn/2026-08-26.2): 39 node(s) from 92 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 53 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n11 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
           }
         }
       ],
       "signals": [
         {
           "tagName": "affordance-reply-bound",
-          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nTake that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical …"
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThe changeover itself. Thinking of white-to-tint washdowns you've seen on Line 2: what's the *quickest* one you'd realistically see, and …"
         }
       ],
       "toolErrors": [],
-      "pendingQuestion": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?",
+      "pendingQuestion": "So: that afternoon, how did you know the white order was coming? Was that a scheduled release event — the book updates at fixed times — or did someone tell you, or is it a pattern you've learned? And roughly how many orders land in a typical week's book, and how much do they swing between a quiet week and a busy one?",
       "completion": {
-        "captures": 114,
+        "captures": 92,
         "complete": false,
-        "unsatisfied": 9,
-        "outsideSlice": 33,
+        "unsatisfied": 65,
+        "outsideSlice": 11,
         "unmapped": 0,
-        "revision": "2e4f73ea071077f9",
-        "cue": "The harness folded the model at revision 2e4f73ea071077f9 (plugin sdcpn/2026-08-25.2): 36 node(s) from 114 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"the question, in the expert's words\" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what \"better\" means, and trade-off weights\" has not been addressed on objective:where Line 1 loses its time.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n\nPatterns whose trigger may apply (discretionary):\n- P08 on objective:where Line 1 loses its time: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n\n33 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+        "revision": "0ca4cb771fd758bf",
+        "cue": "The harness folded the model at revision 0ca4cb771fd758bf (plugin sdcpn/2026-08-26.2): 39 node(s) from 92 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 53 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n11 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
       },
       "expert": {
-        "content": "That's fair, and yeah, I was sloppy folding them together. If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\n\nThe twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup. So you're right to pull that apart: clean-run variability is small, and the big bad days are really the breakdown showing up inside the run, not the run itself being slow."
+        "content": "Fair question, and it's a bit of both, honestly. The book officially releases Monday morning — that's the big drop, 30-something to 60 orders depending on the week. But it's not the only time things land. Sales and commercial push in additions through the week, sometimes daily, when a customer calls with something last-minute or an order gets confirmed late. That afternoon, specifically, I think our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \"probably coming,\" because it's a repeat account and there's a pattern to when they reorder. So it wasn't a scheduled release, it was more me remembering a conversation and half-expecting it — that's the \"gut\" part, not something the system told me.\n\nAs for volume — quiet week might be 30 orders, a busy one pushes 55–60. It's not wildly seasonal that I've noticed, more just lumpy depending on who's restocking that week. Meridian in particular is fairly regular, close to weekly, but the smaller distributors are the ones that swing.\n\nI really do need to get to the huddle — can we pick this up another time? Happy to keep going on the arrivals side and the breakdowns next round."
       }
     },
     {
-      "turn": 8,
+      "turn": 10,
       "text": [
-        "Two housekeeping things I want to settle, because right now the model has plenty of plant detail but the two questions it's meant to answer aren't yet wired to any of it."
+        "Go to your huddle. Here's what I've got, so you can correct it next time rather than read it now.\n\n## What's captured\n\n**The question the model exists to answer** — \"wash down for the tint right then, or let Line 2 sit idle\" for an expected same-family order; a call you make by gut \"three or four times a month\" and have \"never once been able to prove I got it right.\"\n\n**What \"better\" means** — Meridian misses first: \"we just don't do that\" — recorded as a hard rule, not a weight, because you wouldn't trade even twenty small late orders for one Meridian slip. Then late-order count. Changeover hours and idle time as your own diagnostics, on the same page as late orders for the first time.\n\n**Boundary** — three lines plus one changeover crew of two techs; order starts at demand-book release from ERP (SKU, quantity, due date), ends when it clears QA and ships; due date judged at QA clearance, not off the line.\n\n**Horizon** — one week (demand-book cycle, re-planned at the morning huddle); two weeks soft for specialty minimum runs; a month you'd refuse.\n\n**The flow** — release → wait behind what's on the line → run (mix, mill, tint stage, fill, pack) → QA hold (palletized, off the line, queued for the lab) → clear and ship. Same-family run-into-run needs no crew.\n\n**Crew contention, as practiced** — Meridian next in line wins, no discussion; otherwise your huddle call on tightest due date (Line 1 got them, Line 3 sat \"close to two hours\" clean and idle with slack); otherwise whoever's supervisor reaches the crew lead first. Override: maintenance can pull them for a genuine emergency; a real fight escalates to the ops director. None of it written down.\n\n**Changeovers, asymmetric by direction** — white→tint 40 min best, ~45 min–1 hr typical, ~1 hr 20 bad. Tint→white 2½ hr best, 3 hr typical (\"the number I actually use on the sheet\"), toward 4 hr bad. Specialty either direction ~2 hr, 1 hr 40 for specialty-to-specialty, not much past 2½ — with your own caveat that you don't watch these as closely.\n\n**Arrivals** — Monday drop of 30-something to 60; quiet week 30, busy 55–60; additions pushed in by sales/commercial through the week, sometimes daily; Meridian close to weekly, small distributors are what swing.\n\n**Validation bar** — reproduce last month's late-order count *and the kind* of miss (two Meridian scrapes, a handful of small ones); recognisable changeover hours on Lines 2 and 3; must reproduce the odd weeks, including the breakdown that ate two days on Line 1. Not a single number — \"the shape of a real month.\"\n\n## Open, with where it comes from\n\n1. **Run durations** — no rate for any line. Needs the sheet.\n2. **QA** — four hours for a white is all I have; nothing on specialty holds, lab capacity, or what happens on a fail.\n3. **Breakdowns** — named by you as essential to validation, never elicited: rate and duration per line.\n4. **The Monday-release shape** — I have weekly counts, not the mid-week additions pattern; and the thing your actual decision rested on was a remembered huddle remark, not a system event. That's a gap in the model, not in you.\n5. **What a changeover loses besides time** — scrap, material, first-batch yield: never asked.\n6. **Meridian exchange rate** — deliberately not a number. Your words: it would take \"commercial in a room\" to say it out loud.\n\n## Assumptions I made — none in the model\n\nI've recorded nothing you didn't say. Two things I *would* have assumed and didn't: that changeover time is symmetric (you corrected that before I could), and that the due date is met at end of line (you corrected that too).\n\n## Simplifications to flag next time\n\nQueues aren't modelled as things — the wait behind a running job and the QA queue emerge from the steps either side. And \"Meridian white basically always goes to Line 2\" is captured as your statement; I haven't asked whether that's a hard routing constraint or a habit, and it matters.\n\n**Stopping outcome: expert-stopped, partial-with-open-slots.** The spine is there — objective, boundary, flow, crew rule, changeover times. It can't yet run a week, because it has no run rates and no breakdowns. Next round: arrivals and breakdowns, as you offered, plus run rates off the sheet."
       ],
-      "asks": [
+      "asks": [],
+      "sweeps": [
+        {
+          "status": "applied",
+          "appliedCaptureIds": [
+            "capture-c58069b0-72b7-4ff3-8bb8-16f7861f0212",
+            "capture-727571fe-b1b2-4fb8-9247-5658db4a18f9",
+            "capture-cd397b8a-ae0d-4e4a-887c-46a790d86277",
+            "capture-e0913c34-cd78-40d4-a420-6b28eba826af",
+            "capture-fa08bd90-3a4a-4ce8-880b-8b5ba2b2467f",
+            "capture-62e66b8a-bc31-4ccb-9611-ad1e05dd0aed",
+            "capture-14764933-9818-4f65-b6e2-4623dbbf39b3",
+            "capture-de6129c5-8785-4833-97b5-5767d578660a",
+            "capture-0aec8732-ae48-4d5c-98f1-abedf334e4bf",
+            "capture-46c3af0c-9caa-4e30-ab54-92cc136acac1",
+            "capture-4614313d-ba9f-4286-8cc0-2b2d07978c3e",
+            "capture-aab9beb5-8b53-44ce-a621-4dfd4621d53b",
+            "capture-080fcd60-7191-4d7f-82dd-203e24c66b72",
+            "capture-d93639f5-4867-46ea-9a2f-7a7beedb6b88",
+            "capture-8cee0e81-ca2d-4d87-8400-d68f2a2c73dc",
+            "capture-9866d0f3-f549-4193-8bdb-bf43563f18ee",
+            "capture-151800e3-5e9d-4f3b-aada-02b05532b0cb",
+            "capture-e2e03e25-a4df-4386-955a-56f2634c8bd7",
+            "capture-b458110a-8ab3-4a28-a3b7-52d8a9b6cc8c",
+            "capture-473a9e08-c0d3-4b0c-8e2b-c13b77d9ab95",
+            "capture-2f0e7c48-206b-4d81-8644-c4f649de9a7d",
+            "capture-e47df01b-49ae-4326-a72a-bfb08188d641",
+            "capture-46c666e7-d79c-4187-9eaf-dce49ca64100",
+            "capture-5212259b-d4d4-491b-b122-6af5239030d7",
+            "capture-bff705c5-00cb-426f-9ddd-663d4dbc1e49",
+            "capture-16d70bcc-e61a-4037-bc57-9ac302ff7b25",
+            "capture-d3b4e8c5-eb00-4103-b861-89ac1e3d5c7b",
+            "capture-5f3fa0ff-23ae-4621-9bbe-9778cba7a67d",
+            "capture-34a374d1-d578-4bd6-9842-3db1fe2245f3",
+            "capture-2e7ed53f-9682-4e83-9057-b59be73ca16c",
+            "capture-ea311e48-05a0-4c73-95b3-776de573bde2",
+            "capture-7d5ef992-e1a9-4aed-88ea-30f3bc49da30",
+            "capture-fad3ee18-f276-4db0-b7e2-39bda4fb5066"
+          ],
+          "skippedDedupKeys": [],
+          "advisories": [],
+          "completion": {
+            "complete": false,
+            "revision": "11f0491227a6025f",
+            "pluginVersion": "sdcpn/2026-08-26.2",
+            "unsatisfied": 89,
+            "unmapped": [],
+            "cue": "The harness folded the model at revision 11f0491227a6025f (plugin sdcpn/2026-08-26.2): 44 node(s) from 125 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 77 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n11 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+          }
+        }
+      ],
+      "signals": [
         {
-          "question": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong.",
-          "toolCallId": "toolu_01EHPQiwUUuqA7BA9xjbGyvx"
+          "tagName": "affordance-reply-bound",
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nSo: that afternoon, how did you know the white order was coming? Was that a scheduled release event — the book updates at fixed times — o…"
         }
       ],
+      "toolErrors": [],
+      "completion": {
+        "captures": 125,
+        "complete": false,
+        "unsatisfied": 89,
+        "outsideSlice": 11,
+        "unmapped": 0,
+        "revision": "11f0491227a6025f",
+        "cue": "The harness folded the model at revision 11f0491227a6025f (plugin sdcpn/2026-08-26.2): 44 node(s) from 125 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 77 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n11 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "Looks right to me — and yeah, bring the sheet next time, it'll answer the run-rate question faster than I can talk through it. See you next round."
+      }
+    },
+    {
+      "turn": 11,
+      "text": [
+        "Good — the sheet next time.\n\nOne housekeeping note so nothing goes missing: the final sweep wouldn't apply. The extraction kept trying to anchor quotes to my read-back rather than to your own words, and I'd rather decline it than let a paraphrase of mine enter the model as something you said. Nothing is lost — everything in the summary you just confirmed was already captured from the earlier sweeps, when you said it.\n\nThe only item from this last exchange is the deposit: **run rates per line come from the sheet, which you're bringing.** That's noted against the open gap rather than as a value.\n\nYour confirmation is on record as \"you didn't object to my summary\" — not as your own phrasing. If any line in it is my words standing in for yours, next round is the time to correct it; that's cheaper than finding it in the output later.\n\nNext round, in the order I'd spend your time: breakdowns (rate and duration per line — you've made those a validation requirement), run rates off the sheet, then QA beyond the four-hour white. And one small question I'll open with: whether Meridian white going to Line 2 is a hard routing rule or a habit.",
+        "The mismatch is formatting, not substance — your walkthrough had that first clause in bold, so the run-together quote never existed as a contiguous string. Repairing to the exact contiguous spans:\n\n- \"That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\"\n- \"an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line\"\n- \"That afternoon, specifically, I think our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \"probably coming,\"\" — capital T, as you wrote it.",
+        "I'm declining this sweep rather than repairing it further.\n\nThe reason matters, so I'll state it plainly: the harness now reports that string occurs **only in injected non-user entries**. That means the QA-hold sentence, as the extractor is trying to cite it, is not traceable to something you actually typed in a user turn — it's reachable only through echoed or injected text. Citing it would put a capture in the model whose evidence is my own scaffolding wearing your voice. That is precisely the failure I'd rather take an incomplete model than commit.\n\nWhat this costs: nothing I can identify. Your walkthrough turn — including step 4, the QA hold, palletized and queued for the lab — was already swept successfully at the time you said it. This tail was re-proposing content the model holds on sound evidence. If the extractor's version and the earlier one differ in any way I can't see, the earlier one stands, because it was anchored when you spoke.\n\nSo the position at close is unchanged from the summary you confirmed:\n\n- **Stopping outcome: expert-stopped, partial-with-open-slots.**\n- **One unswept tail, declined on evidence grounds** — not settled-but-skipped, and not a gap in your knowledge. Worth a look by whoever maintains the tooling; a quote that resolves only against injected text is a defect in the harness, not in the interview.\n- **Open next round, in priority order:** breakdowns per line, run rates from the sheet, QA beyond the four-hour white, mid-week additions to the book, changeover losses besides time, and whether Meridian white on Line 2 is a rule or a habit.\n- **Deposit standing:** the Meridian exchange rate needs commercial in a room; run rates need the sheet you're bringing.\n\nI have not built the net, and I'm not claiming this is loadable or runnable — the projection to your Petri-net tooling is a separate step done from the model, and it will report its own losses. What I can say is that the spine it would project from is yours, in your words, with the asymmetric changeover times and the unwritten crew rule intact.\n\nSee you next round.",
+        "It has settled — the session ended, no thread is open, and the only user-authored content in the range is your assent plus one durable fact: the sheet answers the run-rate question. Assent to my phrasing isn't yours to be captured, but the sheet as a named source for an open slot is, and it should live in the model rather than only in my close text. One attempt on that anchor.",
+        "Applied — the tail is swept and the sheet is now recorded in the model as the named source for run rates, anchored to your words rather than sitting only in my summary.\n\nTwo honest notes to carry into next round, neither of which changes what you confirmed:\n\n**The model has duplicate nodes.** There are at least two changeover nodes that are really the same thing under different names, picked up as the conversation circled back — one from when you first mentioned the washdown, one from the detailed timings. That's my bookkeeping, not your inconsistency. First thing next session is merging them, so the 40-minute/3-hour/2-hour figures sit on one node each rather than being split across near-duplicates.\n\n**The Meridian exchange-rate objective is formally unsupported.** The harness flags it as depending on nothing in the model — which is correct and expected, because you deliberately declined to give a number and said it would take commercial in a room. It stays in as a recorded question with its deposit attached, not as something the model pretends to answer. That's the right state for it; I'm noting it so nobody later reads the flag as an oversight.\n\nEverything else stands as read back. **Stopping outcome: expert-stopped, partial-with-open-slots.**\n\nSee you next round — with the sheet."
+      ],
+      "asks": [],
       "sweeps": [
+        {
+          "status": "refused",
+          "refusal": {
+            "code": "evidence-quote-not-found",
+            "excerpt": "that afternoon, specifically, I think our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \"probably coming,\" because it's a repeat account and there's a pattern to when they reorder. So it wasn't a scheduled release, it was more me remembering a conversation and half-expecting it — that's the \"gut\" part, not something the system told me.",
+            "message": "No user entry contains the verbatim quote \"that afternoon, specifically, I think our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \"probably coming,\" because it's a repeat account and there's a pattern to when they reorder. So it wasn't a scheduled release, it was more me remembering a conversation and half-expecting it — that's the \"gut\" part, not something the system told me.\". Repair the quote to match the user's words exactly."
+          }
+        },
+        {
+          "status": "refused",
+          "refusal": {
+            "code": "evidence-quote-not-found",
+            "excerpt": "an order's mine from release to \"cleared QA\"",
+            "message": "No user entry contains the verbatim quote \"an order's mine from release to \"cleared QA\"\". Repair the quote to match the user's words exactly."
+          }
+        },
+        {
+          "status": "refused",
+          "refusal": {
+            "code": "evidence-quote-not-found",
+            "excerpt": "Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.",
+            "message": "No user entry contains the verbatim quote \"Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\". Repair the quote to match the user's words exactly."
+          }
+        },
+        {
+          "status": "refused",
+          "refusal": {
+            "code": "non-user-evidence",
+            "excerpt": "Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.",
+            "message": "The quote \"Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\" occurs only in injected non-user entries and cannot be cited as user evidence."
+          }
+        },
         {
           "status": "applied",
           "appliedCaptureIds": [
-            "capture-a5926e2a-88e8-459e-a296-282b16d499a8",
-            "capture-ea1779b0-9a83-42aa-92d1-746e73de43cc",
-            "capture-1288a3df-c7fd-4319-8d4e-a228572ba0b0",
-            "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6",
-            "capture-bb291ebf-9fe0-4a6e-9840-e7d7fac44033",
-            "capture-edfaf81c-c276-4b57-a88c-914953b1c6be",
-            "capture-13339551-ff3a-414f-8260-e1296530d8ec",
-            "capture-535749ea-ba99-4d11-84c0-8203fd058329",
-            "capture-79eccb7f-a787-40d4-a2fa-e95bfda82d18",
-            "capture-3c6b3e85-7fd3-4831-9201-6e3ef525e7cf",
-            "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
-            "capture-823c9593-db42-45eb-9515-937e6b90bd33",
-            "capture-f7e12936-7567-4b38-be19-a45fb5dc6274",
-            "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
-            "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092",
-            "capture-afd366c9-1ea6-4b73-b2c0-ed97c9af0c79",
-            "capture-86fd1cfb-379b-42f7-bdbb-8586dae7f755",
-            "capture-90d36431-4341-4f9e-8bf6-8b5354b2fedd",
-            "capture-7ef3368b-e678-4c58-b7f9-137d1607d8ec",
-            "capture-10d88b79-af70-4a14-90c1-da56ad526d36",
-            "capture-921611c3-21b5-4ab2-8e56-9b8cdaa2eba2",
-            "capture-6cf8c229-ab84-4448-abc6-3e7f4a76bb4c",
-            "capture-ce789325-dd40-4b21-a936-73485ccb90b9",
-            "capture-1ba32034-be19-432b-a012-326b682fd357",
-            "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7",
-            "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
-            "capture-e28ed067-b6a4-40d8-935a-3598e2401cc1",
-            "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a",
-            "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
-            "capture-cfe5bf57-8879-4592-a938-1527d73c8bac",
-            "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
-            "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
-            "capture-23c5706e-37c1-481e-9438-8fae70973c13",
-            "capture-00863ee1-f99c-48b2-b680-bf4eb71e6a57",
-            "capture-196b8447-3958-444f-9860-8de7330299ec"
+            "capture-df10185e-b1ea-4c96-a225-ba9f1a4870d3",
+            "capture-07d24f63-38a5-4252-9153-f5017bc5eb7c",
+            "capture-fa7c6f67-b993-474b-bcb1-ea2fd55ae510",
+            "capture-354f9e2d-b3c7-4838-8dda-fd4f12d7f2c2",
+            "capture-a6f338a0-c3a7-4427-b125-8ce2759d26e6",
+            "capture-67a39f82-22f8-4b56-825d-03cfacb8a154",
+            "capture-a559675e-115d-4736-85ff-6160abb1a449",
+            "capture-3caeda61-ac3c-4724-905a-3f76e1bfd924",
+            "capture-317a5e27-6e23-4fdb-80c5-2160e7622b9c",
+            "capture-afdf937d-5049-4656-a68a-f0b5c1a15511",
+            "capture-0b6c3aeb-8421-41f3-a77b-0db90e32bc06",
+            "capture-4c36d6d9-17da-4e86-be1a-dc07ef07ff83",
+            "capture-cf61a51f-f803-407f-a6b4-9ffc46972ab0",
+            "capture-0693c605-2dd0-4019-a36a-25c0565e22a4",
+            "capture-83c1866f-aabf-4ce4-8836-7a803a5521cd",
+            "capture-d705d5d1-f8ed-4788-9c21-b426a1edf48f",
+            "capture-61b6af85-58ca-4367-a45a-1f9d20d9a04b",
+            "capture-a584bc16-c132-431c-8c66-64c32cf5715a",
+            "capture-b6778bf0-5fd3-46a9-ac25-be90e5fb6535",
+            "capture-733f30a6-e231-4fd2-a9a1-ef584ad1d139",
+            "capture-a7b79e99-0816-4a9d-b4cb-ce91e9933dd4",
+            "capture-7e1b1ff2-d9f7-4999-b260-ab694dc84fce",
+            "capture-7f1eba90-5fc4-4103-8f8b-fe4400be2ebf",
+            "capture-855f61a1-da7f-4d31-a70e-c72dc905afb3",
+            "capture-e6a85b0b-ac81-4bbd-b62c-40c5d2073bba",
+            "capture-80836a1b-2883-487f-8ca6-451049d38c30",
+            "capture-9e9768db-8715-4ef2-93d5-ebad8b376a90",
+            "capture-a2b17c97-2e39-49b0-b8ff-3c5237927a0d",
+            "capture-d15d35b6-900e-411c-a1cd-46a63c50d4c8",
+            "capture-1ca63cf0-a571-45d3-bf90-d86a3cbfca06",
+            "capture-f2012538-6414-4791-b25b-abdcdb6398c1",
+            "capture-17385ca7-771e-4ab9-a5a6-ac70e9886b75",
+            "capture-c330d313-b17a-496e-bd0d-8f504a444063",
+            "capture-a0b94f9f-7c74-40d1-bfb2-1f7e4d55d152",
+            "capture-60d290d4-26e8-41fc-afc3-208ac1a57b93",
+            "capture-5dde62c7-f641-446a-91e9-27a51f0d33a1",
+            "capture-bd4124dd-9138-4ac2-a781-c67a99a4d1ae",
+            "capture-03de2121-abc0-40dc-8f8a-9e4730fe9e4b",
+            "capture-89bf1a2d-3fcc-4e13-ad48-b874f4221714"
           ],
           "skippedDedupKeys": [],
           "advisories": [
@@ -695,7694 +881,2107 @@
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
-                "capture-a5926e2a-88e8-459e-a296-282b16d499a8"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-3f2444d5-8001-46d9-8a92-c85f8c6f8d6a",
-                "capture-1288a3df-c7fd-4319-8d4e-a228572ba0b0"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
-                "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
-                "capture-a5926e2a-88e8-459e-a296-282b16d499a8"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
-                "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-dba4ec08-0265-420c-95d2-4dce250ae0b6",
-                "capture-f7e12936-7567-4b38-be19-a45fb5dc6274"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
-                "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
-                "capture-b3079749-c23b-4ade-ac51-9bbff19806fb"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-                "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
-                "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a"
+                "capture-1d5aba4c-760f-4e4e-b48f-a3f498a4a75f",
+                "capture-0693c605-2dd0-4019-a36a-25c0565e22a4"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
-                "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d"
+                "capture-e20e49bb-dbd3-4616-8da4-f14024b09ed0",
+                "capture-0693c605-2dd0-4019-a36a-25c0565e22a4"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
-                "capture-b3079749-c23b-4ade-ac51-9bbff19806fb"
+                "capture-62e66b8a-bc31-4ccb-9611-ad1e05dd0aed",
+                "capture-3caeda61-ac3c-4724-905a-3f76e1bfd924"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057",
-                "capture-a5926e2a-88e8-459e-a296-282b16d499a8"
+                "capture-14764933-9818-4f65-b6e2-4623dbbf39b3",
+                "capture-317a5e27-6e23-4fdb-80c5-2160e7622b9c"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
-                "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6"
+                "capture-14764933-9818-4f65-b6e2-4623dbbf39b3",
+                "capture-e6a85b0b-ac81-4bbd-b62c-40c5d2073bba"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
-                "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639"
+                "capture-46c3af0c-9caa-4e30-ab54-92cc136acac1",
+                "capture-4c36d6d9-17da-4e86-be1a-dc07ef07ff83"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-2a491098-b602-4b46-bbaa-439e291027db",
-                "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092"
+                "capture-9866d0f3-f549-4193-8bdb-bf43563f18ee",
+                "capture-d705d5d1-f8ed-4788-9c21-b426a1edf48f"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-c4aefe40-a022-4990-96a1-b74243850715",
-                "capture-823c9593-db42-45eb-9515-937e6b90bd33"
+                "capture-e2e03e25-a4df-4386-955a-56f2634c8bd7",
+                "capture-b6778bf0-5fd3-46a9-ac25-be90e5fb6535"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
-                "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16"
+                "capture-2f0e7c48-206b-4d81-8644-c4f649de9a7d",
+                "capture-7e1b1ff2-d9f7-4999-b260-ab694dc84fce"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
-                "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a"
+                "capture-5f3fa0ff-23ae-4621-9bbe-9778cba7a67d",
+                "capture-80836a1b-2883-487f-8ca6-451049d38c30"
               ]
             },
             {
               "type": "possibly-equivalent",
               "reason": "same-evidence",
               "captureIds": [
-                "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
-                "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2"
+                "capture-317a5e27-6e23-4fdb-80c5-2160e7622b9c",
+                "capture-e6a85b0b-ac81-4bbd-b62c-40c5d2073bba"
               ]
             }
           ],
           "completion": {
             "complete": false,
-            "revision": "36d1240e30d0f4d1",
-            "pluginVersion": "sdcpn/2026-08-25.2",
-            "unsatisfied": 9,
+            "revision": "0be40ea628c71329",
+            "pluginVersion": "sdcpn/2026-08-26.2",
+            "unsatisfied": 93,
             "unmapped": [],
-            "cue": "The harness folded the model at revision 36d1240e30d0f4d1 (plugin sdcpn/2026-08-25.2): 41 node(s) from 149 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"the question, in the expert's words\" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what \"better\" means, and trade-off weights\" has not been addressed on objective:where Line 1 loses its time.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n\nPatterns whose trigger may apply (discretionary):\n- P08 on objective:where Line 1 loses its time: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n\n38 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+            "cue": "The harness folded the model at revision 0be40ea628c71329 (plugin sdcpn/2026-08-26.2): 49 node(s) from 164 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 81 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n14 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
           }
         }
       ],
       "signals": [
         {
-          "tagName": "affordance-reply-bound",
-          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nYou said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you…"
+          "tagName": "sweep-repair",
+          "excerpt": "The sweep was refused: No user entry contains the verbatim quote \"Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\". Repair the quote to…"
+        },
+        {
+          "tagName": "settlement-check",
+          "excerpt": "The harness computed this unswept conversation tail:\n\n[non-user] The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nSo: that afternoon, how did you know the white order was coming? Was tha…"
         }
       ],
       "toolErrors": [],
-      "pendingQuestion": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong.",
       "completion": {
-        "captures": 149,
+        "captures": 164,
         "complete": false,
-        "unsatisfied": 9,
-        "outsideSlice": 38,
+        "unsatisfied": 93,
+        "outsideSlice": 14,
         "unmapped": 0,
-        "revision": "36d1240e30d0f4d1",
-        "cue": "The harness folded the model at revision 36d1240e30d0f4d1 (plugin sdcpn/2026-08-25.2): 41 node(s) from 149 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"the question, in the expert's words\" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what \"better\" means, and trade-off weights\" has not been addressed on objective:where Line 1 loses its time.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n\nPatterns whose trigger may apply (discretionary):\n- P08 on objective:where Line 1 loses its time: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n\n38 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+        "revision": "0be40ea628c71329",
+        "cue": "The harness folded the model at revision 0be40ea628c71329 (plugin sdcpn/2026-08-26.2): 49 node(s) from 164 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 81 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n14 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
       },
       "expert": {
-        "content": "Alright, let me actually try and write these the way I'd type them if I had the box.\n\n**Disruption one:** \"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"\n\nWhat it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of \"could be quick, could be long\" rather than one number. And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours. And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the \"who can absorb it\" judgment call again.\n\nI'd say what's missing from your list, or under-weighted: the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just \"an order got delayed.\" A distributor slipping is fine, so the answer to the question genuinely depends on whose tint was sitting there.\n\n**The Line 1 tank one:** \"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\" That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others. That's not something I'd have said a month ago.",
-        "stimulus": "(Sorry — I've just seen the time, I have the floor huddle in ten minutes. How much more do you need?)"
+        "content": "Sounds good. I'll have the sheet, and I'll poke at whether Meridian-to-Line-2 is written in stone or just habit before you even ask. Talk next round."
       }
     },
     {
-      "turn": 9,
+      "turn": 12,
       "text": [
-        "Honest answer to \"how much more\": we're maybe a third of the way. What's still open, roughly in order of how much it costs you: the filler jam's rate and repair time; what the washdown actually costs including ramp scrap; the \"who can absorb a slip\" rule as you actually apply it; how orders arrive into the demand book; QA hold times; and the stage rates and tank size, which we've already agreed aren't in your head. None of that needs to happen today.\n\nFor the ten minutes, I'd spend them on the jam, because you named it as the thing you never know at the time and nobody else can tell me."
-      ],
-      "asks": [
-        {
-          "question": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?",
-          "toolCallId": "toolu_018NF8gHsprWVmC1fJGrJ3VF"
-        }
+        "Perfect — and that's the better version of the question anyway, since you'll have looked before we talk rather than reconstructing it on the spot.\n\nOne thing worth flagging about what you're going to check: if it turns out to be habit rather than a rule, don't discard the habit. A routing preference that everyone follows without being told is exactly the kind of thing that behaves like a constraint until the week it doesn't — and the week it doesn't is probably one of the odd weeks you said the model has to reproduce. So both answers are useful: \"it's written in the spec\" and \"it's just what we've always done, except that time we ran it on Line 1 because Line 2 was down.\" The second one is worth more.\n\nNothing else needed from you before then. Enjoy the huddle.",
+        "Settled — it's a sign-off, and the one durable item is a deposit in your words: you'll check whether Meridian-to-Line-2 is written in stone or habit. That belongs against the open routing question rather than in my notes.",
+        "Applied — two captures, both deposits rather than values: the sheet as the source for run rates, and your check on Meridian-to-Line-2 as the source for the routing question. No new claims about the plant entered the model from a sign-off, which is as it should be.\n\nThat closes the session. Final state, unchanged from what you signed off on:\n\n**Stopping outcome: expert-stopped, partial-with-open-slots.** 51 nodes, all traceable to your words. The spine runs objective → boundary → flow → crew rule → changeover times. It cannot yet simulate a week: no run rates, no breakdowns.\n\n**Carried to next round, in the order I'd spend your time:** breakdowns per line; run rates off the sheet; QA beyond the four-hour white; mid-week additions to the book; what a changeover loses besides time; and your Meridian-to-Line-2 finding. Plus my own housekeeping — merging the duplicate changeover nodes before anything else, so the timings consolidate.\n\n**Deposits standing:** Meridian exchange rate needs commercial in a room. Run rates need the sheet. Routing question needs your check.\n\nI haven't built the net and I'm not claiming this is loadable — projecting the model to your Petri-net tooling is a separate step, and it will produce its own report of what the net can't carry.\n\nTalk next round."
       ],
+      "asks": [],
       "sweeps": [
         {
           "status": "applied",
           "appliedCaptureIds": [
-            "capture-b58883f3-43e2-4626-bc59-a9c091f1d1b5",
-            "capture-3aa3764b-8dd5-495a-bf3e-b32cbc89ba61",
-            "capture-57ad71c3-f423-4d91-a9f8-d3ce31f1fca1",
-            "capture-1a3325b9-15b6-436a-8e7f-feff95d98036",
-            "capture-0e28490a-6b4b-4996-9b6f-3d9249a7d2dc",
-            "capture-43c5ef42-68ce-478f-89b0-c552111d807a",
-            "capture-ccc2d7eb-8a3f-4684-8f1c-a21a51049550",
-            "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
-            "capture-a158a5da-be3a-461f-87c0-69c38cac1a72",
-            "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23",
-            "capture-4043a577-c1b4-44c3-91f3-2194def82bd9",
-            "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
-            "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
-            "capture-72d414e6-f6a2-420e-8407-667f41535411",
-            "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
-            "capture-53f9387d-f037-4d0f-999b-f89a8f113f46",
-            "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
-            "capture-38e0effa-0fb7-48ff-907c-2fc9f3e64211",
-            "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
-            "capture-314d8187-81ba-478c-8f71-1c9e5826965b",
-            "capture-345fbb5a-c0c1-4e3a-9015-33b3ad727831",
-            "capture-60f6f8c8-f52e-443a-adee-6818339f3b35",
-            "capture-be556841-bf14-4fe0-8c23-ffc773896b2b",
-            "capture-26d3ac6c-4b27-4765-baa3-8437f06fe8ca",
-            "capture-da6d10a4-e0f2-4b1d-8e78-4d58cadeb8f2",
-            "capture-68f9db28-a002-406d-912a-4cc410e5b380",
-            "capture-0a06d184-bf72-42c4-95b3-7ad88ea4e059",
-            "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f",
-            "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b",
-            "capture-7111ab55-5d90-44f6-a1d2-4aa1b48da4bb",
-            "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a",
-            "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993"
+            "capture-1b0da51d-eeab-4750-b872-3cd03e9fb169",
+            "capture-03ef0211-289b-4c3e-a9f1-ff4d4698b625"
           ],
           "skippedDedupKeys": [],
-          "advisories": [
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
-                "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-a2938097-b902-4f24-8e15-70f4b8ce95fb",
-                "capture-be556841-bf14-4fe0-8c23-ffc773896b2b"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
-                "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-                "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
-                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
-                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
-                "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
-                "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
-                "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
-                "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
-                "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-b0908788-ec79-4481-b056-1fa606930f85",
-                "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
-                "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-27ee0ed5-50d0-47f6-94b8-77e090bca50f",
-                "capture-a158a5da-be3a-461f-87c0-69c38cac1a72"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
-                "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-c4aefe40-a022-4990-96a1-b74243850715",
-                "capture-4043a577-c1b4-44c3-91f3-2194def82bd9"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
-                "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
-                "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
-                "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-46d37104-fb87-4105-95d5-4448aade81ac",
-                "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-823c9593-db42-45eb-9515-937e6b90bd33",
-                "capture-4043a577-c1b4-44c3-91f3-2194def82bd9"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
-                "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
-                "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
-                "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
-                "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
-                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
-              ]
-            }
-          ],
+          "advisories": [],
           "completion": {
             "complete": false,
-            "revision": "1dffca1f0e4725ec",
-            "pluginVersion": "sdcpn/2026-08-25.2",
-            "unsatisfied": 42,
+            "revision": "34f9da8a0149564c",
+            "pluginVersion": "sdcpn/2026-08-26.2",
+            "unsatisfied": 93,
             "unmapped": [],
-            "cue": "The harness folded the model at revision 1dffca1f0e4725ec (plugin sdcpn/2026-08-25.2): 47 node(s) from 181 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 30 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n34 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+            "cue": "The harness folded the model at revision 34f9da8a0149564c (plugin sdcpn/2026-08-26.2): 51 node(s) from 166 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 81 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n16 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
           }
         }
       ],
       "signals": [
         {
-          "tagName": "affordance-reply-bound",
-          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nIf the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one …"
+          "tagName": "settlement-check",
+          "excerpt": "The harness computed this unswept conversation tail:\n\n[assistant] Good — the sheet next time.\n\nOne housekeeping note so nothing goes missing: the final sweep wouldn't apply. The extraction kept trying to anchor quotes to my read-back rather…"
         }
       ],
       "toolErrors": [],
-      "pendingQuestion": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?",
       "completion": {
-        "captures": 181,
+        "captures": 166,
         "complete": false,
-        "unsatisfied": 42,
-        "outsideSlice": 34,
+        "unsatisfied": 93,
+        "outsideSlice": 16,
         "unmapped": 0,
-        "revision": "1dffca1f0e4725ec",
-        "cue": "The harness folded the model at revision 1dffca1f0e4725ec (plugin sdcpn/2026-08-25.2): 47 node(s) from 181 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 30 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n34 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-      },
-      "expert": {
-        "content": "Okay, quick version. It's a \"every week or two\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.\n\nWhen it stops: typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift. I don't have a cleaner breakdown than that — maintenance would have the actual work-order times in the CMMS but I've never pulled them.\n\nRight, I need to run — good session though. Same time next week?"
+        "revision": "34f9da8a0149564c",
+        "cue": "The harness folded the model at revision 34f9da8a0149564c (plugin sdcpn/2026-08-26.2): 51 node(s) from 166 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 81 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n16 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
       }
+    }
+  ],
+  "usage": {
+    "interviewer": {
+      "input": 82,
+      "output": 176525,
+      "cacheRead": 1181021,
+      "cacheWrite": 154125,
+      "calls": 41
     },
-    {
-      "turn": 10,
-      "text": [
-        "That bounce was my own phrase, not yours — \"jams badly enough to stop the run\" was my wording. Re-anchoring on what you actually said.",
-        "Go — and yes, same time next week works. Here's where we got to, so you can correct anything when you're back at a desk. **The model is not finished and I'm not going to pretend it is; I wouldn't hand this to your tooling yet.**\n\n## What's on record, in your words\n\n**The two questions the model exists to answer**\n1. \"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"\n2. \"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"\n\n**What \"better\" means** — Meridian-style on-time is a hard line, \"not really a trade-off, that's a line I won't cross.\" Below that line you weigh washdown hours, whether the bumped order slides and by how much, and who the customer is. No formula; judgment on who can absorb the slip.\n\n**The flow** — demand book line item out of ERP → you allocate to a line and a week slot → mix, mill, tint, fill (tint \"barely there\" for a white) → QA hold → release, warehouse, ship against due date.\n\n**The line, both ways** — on the sheet, one row, one order occupies Line 2 mix-to-fill. Physically, separate kit with small holding tanks between, and the crew will start the next mix if there's tank room. Both recorded; neither averaged away.\n\n**Run times, clean of breakdowns** — white on Line 2: typical 8–9 h, bad-but-clean 9–10 h, good day ~6 h. Same order on Line 1: add 50–60%, so typical 13–14 h, best ~10 h. Tints: 8–10 h typical on *either* line, no big gap — which you flagged as unexplained and sheet-derived. The 12–13 h figure has been pulled out as breakdown, not run.\n\n**Filler jam** — every week or two; low once in three weeks, high twice a week. Repair typical 30–45 min, quick one-in-ten 10–15 min, bad one-in-ten 4–5 h, \"occasionally eating the rest of the shift.\"\n\n**Washdown** — tint-to-white, three hours, direction matters, plus ramp scrap you don't have numbers for.\n\n## Gaps, with where they'd come from\n- Stage-level rates per line — historian, never pulled apart.\n- Tank sizes, mill-to-fill on Line 1 — engineering drawings.\n- Jam repair times, properly — maintenance work orders in the CMMS.\n- Ramp scrap after washdown — you said it shouldn't be ignored; no source named yet.\n- Whether the tank matters differently by SKU — your own new thought, unexamined.\n- QA hold: \"a few hours for a white,\" and a longer \"specialty wait\" you mentioned but I never asked about.\n- How orders arrive into the demand book — never asked.\n- The \"who can absorb the slip\" rule — I have distributor-shrugs and prickly-account, not a rule I could apply without you.\n\n## Assumptions ledger\n1. That the four stages are the same four for every product — you said \"same four stages every product goes through,\" so this is yours, not mine, but it's load-bearing enough to re-check.\n2. Nothing else. Where I was tempted to fill in — jam rate before you gave it, washdown scrap, stage rates — it's in the gaps list instead.\n\nBoth objectives are still formally unsupported: I have the plant detail and the questions, but haven't yet wired which pieces each answer depends on tightly enough for the tooling. That plus the ramp scrap and the slip rule are what I'd open with next week."
-      ],
-      "asks": [],
-      "sweeps": [
-        {
-          "status": "refused",
-          "refusal": {
-            "code": "evidence-quote-not-found",
-            "excerpt": "jams badly enough to stop the run",
-            "message": "No user entry contains the verbatim quote \"jams badly enough to stop the run\". Repair the quote to match the user's words exactly."
+    "expert": {
+      "input": 76172,
+      "output": 3833,
+      "cacheRead": 0,
+      "cacheWrite": 0,
+      "calls": 11
+    }
+  },
+  "history": {
+    "v": 1,
+    "conversationId": "conv_01M0Z9CBA9R68H6XYQW930RA82",
+    "offset": "0000000000000000_0000000000000810",
+    "messages": [
+      {
+        "id": "entry_direct_c3ViXzAxTTBaOUNCQTg0UVJZSEdQQUVDUlJOSEQx",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9CBA84QRYHGPAECRRNHD1",
+        "parts": [
+          {
+            "type": "text",
+            "text": "I'm the master scheduler at a coatings plant. My boss wants a simulation model of how we\nschedule production, so we can test scheduling decisions before making them. We have tooling\nthat runs Petri-net-style process models, so the end product should be a model I can hand to\nthat — but I can't tell you much about the format, I'm not the modelling person.\n\nPlease interview me about how our operation works, and then produce the model.",
+            "state": "done"
           }
-        },
-        {
-          "status": "applied",
-          "appliedCaptureIds": [
-            "capture-1a240192-8179-4339-815e-3775a062e986",
-            "capture-85062afa-e82d-46ce-b609-f7ed16f8b093",
-            "capture-2c3fa15f-551b-4380-a3b3-8dbc6334a9bb",
-            "capture-41269bfb-9040-4d54-a113-a94c09f6f2f0",
-            "capture-f7ea7c88-4d40-48e7-84e5-2b12ebc5ea8e",
-            "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26",
-            "capture-0e8d50b2-4222-4129-a619-09c5612c05c5",
-            "capture-117f9832-aaba-473a-9411-6fd4022388f2",
-            "capture-e10d4081-78ed-42da-bb26-857f1118224c",
-            "capture-875ed21b-d257-48fe-867b-6785abf6abb7",
-            "capture-06d48b41-86fb-48c0-b3e0-59012ba81960",
-            "capture-428e3931-676d-4af5-a30c-d7a31ea0d8ad",
-            "capture-ecd3c093-8f6b-4a48-a1fc-d2775d4dbc1f",
-            "capture-c6339dee-036e-47cb-9dcf-42fc22d38aae",
-            "capture-2bc071c4-2919-4ff3-910a-92d872eeaef2",
-            "capture-6ec49aac-c165-4e2b-a937-bed3c8c51c2c",
-            "capture-c3f03d77-6760-4b3b-99e5-b78d119a352f",
-            "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14",
-            "capture-83e1381a-f2df-4713-a2f6-f11d034c2fd4",
-            "capture-95cbfe20-605f-4218-9076-0f4816ebadfa",
-            "capture-1a5a8343-7367-416e-b760-c7e8f587fe25",
-            "capture-bf2e57a3-bda7-4090-92ca-af63e0c7a248",
-            "capture-aec8ff27-3e3f-45d2-9142-b6dc2b5d88a3",
-            "capture-9d59a385-a8ae-410a-a13d-a4bca3dde9a3",
-            "capture-4b22a066-a97c-4329-8513-cbd85edd8d65",
-            "capture-63fabb67-24c4-4bee-926f-17917300c8f4",
-            "capture-b1e5ded4-79d6-4ff4-bd0d-6386509efba9",
-            "capture-147c2765-6bfb-4da0-9df9-b74a1c1049de",
-            "capture-ec5740e7-5068-4222-ad24-8396f5975657",
-            "capture-2884cc84-c616-4227-860a-d6b55a06c13d",
-            "capture-0548a680-8da8-47e9-ad72-fb1e264fac80",
-            "capture-8c6a716b-e09a-4977-94d9-f28ab74be7c4",
-            "capture-a67683fd-0f34-4838-b48e-aa01f657a511",
-            "capture-1b632a29-f1de-48e5-8f96-a5ef908c4a56",
-            "capture-9926552e-289f-4b4a-bc99-4cae34f1720a",
-            "capture-06aac0a9-b270-4b13-a54f-37440769d685",
-            "capture-94948329-18e7-42fe-9538-a84fd72c225d",
-            "capture-16b9c643-8b17-490e-bfe0-022a06efd914",
-            "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af",
-            "capture-821e00ef-6923-43b0-955b-3ed7d60ce127",
-            "capture-6da3fa16-460b-4f07-aefc-f941d7118f76",
-            "capture-731a5768-edc7-4858-ad42-50d2faf4b181",
-            "capture-1bebb3ea-7788-477a-8127-593fe3fe6026",
-            "capture-07cb7ca9-27c5-4395-bc9e-aaebc5811382",
-            "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2",
-            "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1",
-            "capture-a0429a34-1145-458d-bada-32d827d68959"
-          ],
-          "skippedDedupKeys": [],
-          "advisories": [
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-                "capture-e10d4081-78ed-42da-bb26-857f1118224c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
-              ]
+        ]
+      },
+      {
+        "id": "entry_01M0Z9CFQYT2E5ZP6NYJHS1QHW",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9CBA84QRYHGPAECRRNHD1",
+        "turnId": "turn_01M0Z9CBAXCKKKJZGK0C6YXA1X",
+        "parts": [
+          {
+            "type": "reasoning",
+            "text": "I should start by focusing on objectives, so I'll ask a single clarifying question to kick things off.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Good — and you don't need to know the format; that's my job. What I need from you is how the plant actually works, in your words.\n\nLet me start with what the model is *for*.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_01Xhtqpw13HgHpe79SBBpYjx",
+            "state": "output-available",
+            "input": {
+              "question": "When your boss says \"test scheduling decisions before making them\" — what's the specific decision or question you'd want to put to this model first? If you can, give me a real one you've faced recently: something where you had two options and weren't sure which was better."
             },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-0b2046b4-55c8-4ce3-abac-296d6abe469d",
-                "capture-95cbfe20-605f-4218-9076-0f4816ebadfa"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-07de77cc-9de8-41e9-92f6-8fe06a6263c9",
-                "capture-16b9c643-8b17-490e-bfe0-022a06efd914"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
-                "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-e0f39723-a7e5-4656-a8fb-0e2b50bb82da",
-                "capture-a67683fd-0f34-4838-b48e-aa01f657a511"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
-                "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-                "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-dd037a1c-63c0-47b8-8886-81c6d1f70226",
-                "capture-ecd3c093-8f6b-4a48-a1fc-d2775d4dbc1f"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-                "capture-e10d4081-78ed-42da-bb26-857f1118224c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
-                "capture-e10d4081-78ed-42da-bb26-857f1118224c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
-                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
-                "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
-                "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-bf082835-a2ca-4279-80e5-726f157270bd",
-                "capture-6ec49aac-c165-4e2b-a937-bed3c8c51c2c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
-                "capture-6da3fa16-460b-4f07-aefc-f941d7118f76"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
-                "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
-                "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-b0908788-ec79-4481-b056-1fa606930f85",
-                "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
-                "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
-                "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
-                "capture-1a5a8343-7367-416e-b760-c7e8f587fe25"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
-                "capture-4b22a066-a97c-4329-8513-cbd85edd8d65"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
-                "capture-94948329-18e7-42fe-9538-a84fd72c225d"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-5548a18b-9f79-4475-a9ab-83a74c750721",
-                "capture-147c2765-6bfb-4da0-9df9-b74a1c1049de"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
-                "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-46d37104-fb87-4105-95d5-4448aade81ac",
-                "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6",
-                "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
-                "capture-94948329-18e7-42fe-9538-a84fd72c225d"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
-                "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
-                "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
-                "capture-6da3fa16-460b-4f07-aefc-f941d7118f76"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
-                "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
-                "capture-e10d4081-78ed-42da-bb26-857f1118224c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
-                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
-                "capture-e10d4081-78ed-42da-bb26-857f1118224c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
-                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
-                "capture-4b22a066-a97c-4329-8513-cbd85edd8d65"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
-                "capture-94948329-18e7-42fe-9538-a84fd72c225d"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
-                "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f",
-                "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b",
-                "capture-6da3fa16-460b-4f07-aefc-f941d7118f76"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a",
-                "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993",
-                "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-e10d4081-78ed-42da-bb26-857f1118224c",
-                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
-              ]
-            }
-          ],
-          "completion": {
-            "complete": false,
-            "revision": "0028ff75065b59b1",
-            "pluginVersion": "sdcpn/2026-08-25.2",
-            "unsatisfied": 44,
-            "unmapped": [],
-            "cue": "The harness folded the model at revision 0028ff75065b59b1 (plugin sdcpn/2026-08-25.2): 56 node(s) from 228 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"who or what performs it\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 32 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n41 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-          }
-        }
-      ],
-      "signals": [
-        {
-          "tagName": "affordance-reply-bound",
-          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a c…"
-        }
-      ],
-      "toolErrors": [],
-      "completion": {
-        "captures": 228,
-        "complete": false,
-        "unsatisfied": 44,
-        "outsideSlice": 41,
-        "unmapped": 0,
-        "revision": "0028ff75065b59b1",
-        "cue": "The harness folded the model at revision 0028ff75065b59b1 (plugin sdcpn/2026-08-25.2): 56 node(s) from 228 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"who or what performs it\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 32 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n41 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-      },
-      "expert": {
-        "content": "Looks right — that's a fair record, and yeah, next week let's start with ramp scrap and the slip rule, since those feel like the ones I could actually go dig up or nail down between now and then. I'll ask maintenance for the CMMS numbers on the filler too while I'm at it. Go on, get to your huddle — wait, that's me. See you next week."
-      }
-    },
-    {
-      "turn": 11,
-      "text": [
-        "Enjoy the huddle.\n\nThree things I'll have ready for next week, so you don't have to hold them:\n\n1. **Ramp scrap and the slip rule** first, as you asked — for the slip rule I'll come at it through a case rather than a principle, so have in mind the last time you bumped someone's order and it turned out to be the wrong someone.\n2. **CMMS filler numbers** — when you get them, what I want is the same shape you gave me from memory: typical, bad one-in-ten, quick one-in-ten. If the work orders disagree with your 30–45 minutes, that disagreement is worth more to the model than either figure alone, so don't reconcile it before you bring it.\n3. **The tint parity puzzle** — that Line 1 and Line 2 run tints at nearly the same speed with no explanation. It's the loose thread most likely to be the same thing as your tank hunch, and I'd like to pull on it once the scrap and slip rule are in.\n\nNothing needs doing beyond that. See you next week.",
-        "The tail has settled: the read-back was confirmed, the session closed, and the expert's last message adds content in their own words — what they'll dig up before next time and that they'll pull the CMMS numbers from maintenance. That belongs in the record as deferral deposits, not as agreement to my summary.\n\nOne caution I'll carry into the sweep: \"Looks right\" is assent to my phrasing, not origination. It closes nothing that wasn't already sourced to their words.",
-        "Swept and folded — the session's record is durable. Since you've gone, this is a note-to-self for next week rather than anything you need to read now.\n\n**State of the model:** 69 nodes from 267 captures. Not complete, and two things about *how it's held* need fixing before more content goes in:\n\n1. **Objective duplication.** Your two questions have landed as five objective nodes — successive rephrasings of the same two (\"which option loses less\", \"which option actually loses less\", \"wait or shift when Line 2 goes down\" are one question; \"where Line 1 loses its time\" and \"is the mill-to-fill tank on Line 1 slowing the line down\" are the other). That's an artefact of my asking you to restate them, not a fact about your plant. Consolidating is a review-and-revise job, and it needs your word on which phrasing is yours, not my merge.\n\n2. **Nothing is wired to the objectives.** 53 of the 69 nodes sit outside every objective's dependency slice — recorded, but not demanded by anything. That's why the completion report keeps growing without the model getting more answerable. You *did* tell me what the disruption question hangs on: the run being protected, Line 1's state and family, the jam duration, the ramp scrap, and the bumped order's identity. I have those as prose in your answer; they aren't yet linked as dependencies. Doing that link properly is the first thing that makes any of the plant detail count.\n\n3. **Three open conflicts** on the filler jam node and the production-run node, where later answers superseded earlier ones — the 12–13 h that turned out to be breakdown, and the two jam descriptions. Those need your explicit word to close, not my inference about which you meant.\n\nSo next week's order: ramp scrap and the slip rule as you asked, then the objective wiring, then the conflict closes. The tint parity thread stays third."
-      ],
-      "asks": [],
-      "sweeps": [
-        {
-          "status": "applied",
-          "appliedCaptureIds": [
-            "capture-48033ee8-f7eb-4615-b21f-018837fc9c5e",
-            "capture-88da9925-d922-48c3-8ea0-2c631df3ae3d",
-            "capture-f53d8f62-375e-4af6-9aaa-fb903839993c",
-            "capture-ac435640-eea2-4ad6-9695-8e5408b4d852",
-            "capture-f5a658db-c8ec-4ca0-8a87-3ad252dee56d",
-            "capture-618842bb-d23d-4371-ae57-73e5257ba215",
-            "capture-538fb022-2495-46bb-8661-8e1f38c802bf",
-            "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98",
-            "capture-5d5f862f-c18c-4501-b544-76735d28e004",
-            "capture-7f6b8be1-6336-465f-8e11-36a5277d51bd",
-            "capture-1a83c9c6-a8f8-4ece-a5d4-53b81bf8cc9b",
-            "capture-e6ae51ed-e1f6-45f3-aab1-c4bca2a979e8",
-            "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7",
-            "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01",
-            "capture-7f9ac97e-375b-4de3-bbcd-b65e5c7427a6",
-            "capture-66fbb371-91b7-41db-b437-5bd207d08aed",
-            "capture-8da19d62-c082-41f6-ac55-f28afe266a8c",
-            "capture-995374a1-2d25-4690-8397-b342f46ebf02",
-            "capture-3cc84392-4ed4-4804-8a7c-db07d384a8b2",
-            "capture-289ac648-e939-4e62-ad46-a17b112402d4",
-            "capture-5376c084-3889-476f-adab-b09a038ded28",
-            "capture-b9dfddf9-52d8-433e-81b8-5611e7356c34",
-            "capture-27ae8fdf-c227-4160-a1a5-e85530156938",
-            "capture-7bd393bf-3f05-4aa1-b15a-968c293b076f",
-            "capture-ef41e72f-3126-4003-82b2-686b5f8bfdfb",
-            "capture-4fa34ba3-82e3-4a4a-ad28-362765a40046",
-            "capture-2f670377-be1e-4275-9e46-24dd13316300",
-            "capture-9dc62989-7db7-4e58-baf1-b9ed0400d9a2",
-            "capture-b92eccd9-e2ad-41a9-abce-bb1cf8b3c328",
-            "capture-55e95600-febe-4c98-8859-a56eb23ab156",
-            "capture-29c03a62-4be2-4dc2-852e-bfeab6770f1b",
-            "capture-9f708103-e43a-4766-bca4-cb3b7060fdcd",
-            "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c",
-            "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d",
-            "capture-12e575e7-b7a9-472d-b165-308334ae7513",
-            "capture-bc9d210e-beb9-4f7a-aa5d-243950605a2a",
-            "capture-90a38599-7f1b-46ed-9352-d3dd3566b338",
-            "capture-d889a88e-b7be-4055-9da1-e64f9fc858b0",
-            "capture-173c6d39-090f-49a7-9e38-c8998003718b"
-          ],
-          "skippedDedupKeys": [
-            "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\"\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-          ],
-          "advisories": [
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-76159984-4b11-446f-a707-bc8302ef0b1d",
-                "capture-f53d8f62-375e-4af6-9aaa-fb903839993c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
-                "capture-55e95600-febe-4c98-8859-a56eb23ab156"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-caeeeb12-a91f-46a0-88c2-a622d4d30c55",
-                "capture-90a38599-7f1b-46ed-9352-d3dd3566b338"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
-                "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
-                "capture-12e575e7-b7a9-472d-b165-308334ae7513"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
-                "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-                "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
-                "capture-12e575e7-b7a9-472d-b165-308334ae7513"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
-                "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-3e2a5a8a-bd99-4642-afcf-f9d3dfe2e9f6",
-                "capture-1a83c9c6-a8f8-4ece-a5d4-53b81bf8cc9b"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
-                "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
-                "capture-66fbb371-91b7-41db-b437-5bd207d08aed"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-2a491098-b602-4b46-bbaa-439e291027db",
-                "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-c4aefe40-a022-4990-96a1-b74243850715",
-                "capture-8da19d62-c082-41f6-ac55-f28afe266a8c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
-                "capture-5376c084-3889-476f-adab-b09a038ded28"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
-                "capture-27ae8fdf-c227-4160-a1a5-e85530156938"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
-                "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
-                "capture-12e575e7-b7a9-472d-b165-308334ae7513"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
-                "capture-538fb022-2495-46bb-8661-8e1f38c802bf"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
-                "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-823c9593-db42-45eb-9515-937e6b90bd33",
-                "capture-8da19d62-c082-41f6-ac55-f28afe266a8c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
-                "capture-538fb022-2495-46bb-8661-8e1f38c802bf"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
-                "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092",
-                "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-ce789325-dd40-4b21-a936-73485ccb90b9",
-                "capture-b92eccd9-e2ad-41a9-abce-bb1cf8b3c328"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7",
-                "capture-55e95600-febe-4c98-8859-a56eb23ab156"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
-                "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a",
-                "capture-12e575e7-b7a9-472d-b165-308334ae7513"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
-                "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
-                "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23",
-                "capture-66fbb371-91b7-41db-b437-5bd207d08aed"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-4043a577-c1b4-44c3-91f3-2194def82bd9",
-                "capture-8da19d62-c082-41f6-ac55-f28afe266a8c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
-                "capture-27ae8fdf-c227-4160-a1a5-e85530156938"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
-                "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
-                "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-1a240192-8179-4339-815e-3775a062e986",
-                "capture-48033ee8-f7eb-4615-b21f-018837fc9c5e"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14",
-                "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-83e1381a-f2df-4713-a2f6-f11d034c2fd4",
-                "capture-7f9ac97e-375b-4de3-bbcd-b65e5c7427a6"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-1a5a8343-7367-416e-b760-c7e8f587fe25",
-                "capture-5376c084-3889-476f-adab-b09a038ded28"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-4b22a066-a97c-4329-8513-cbd85edd8d65",
-                "capture-27ae8fdf-c227-4160-a1a5-e85530156938"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-ec5740e7-5068-4222-ad24-8396f5975657",
-                "capture-4fa34ba3-82e3-4a4a-ad28-362765a40046"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-0548a680-8da8-47e9-ad72-fb1e264fac80",
-                "capture-9dc62989-7db7-4e58-baf1-b9ed0400d9a2"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-94948329-18e7-42fe-9538-a84fd72c225d",
-                "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af",
-                "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
-              ]
-            },
-            {
-              "type": "possibly-equivalent",
-              "reason": "same-evidence",
-              "captureIds": [
-                "capture-538fb022-2495-46bb-8661-8e1f38c802bf",
-                "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98"
-              ]
-            }
-          ],
-          "completion": {
-            "complete": false,
-            "revision": "26a8219a17118558",
-            "pluginVersion": "sdcpn/2026-08-25.2",
-            "unsatisfied": 46,
-            "unmapped": [],
-            "cue": "The harness folded the model at revision 26a8219a17118558 (plugin sdcpn/2026-08-25.2): 69 node(s) from 267 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:wait or shift when Line 2 goes down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 34 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n53 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-          }
-        }
-      ],
-      "signals": [
-        {
-          "tagName": "settlement-check",
-          "excerpt": "The harness computed this unswept conversation tail:\n\n[non-user] The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThinking of the Line 2 filler specifically: roughly how often does it ja…"
-        }
-      ],
-      "toolErrors": [],
-      "completion": {
-        "captures": 267,
-        "complete": false,
-        "unsatisfied": 46,
-        "outsideSlice": 53,
-        "unmapped": 0,
-        "revision": "26a8219a17118558",
-        "cue": "The harness folded the model at revision 26a8219a17118558 (plugin sdcpn/2026-08-25.2): 69 node(s) from 267 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:wait or shift when Line 2 goes down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 34 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n53 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-      },
-      "expert": {
-        "content": "*[No response — this final message is addressed to the interviewer's own note-taking process, not to Marta. Staying in character as Marta, there is nothing here that calls for a reply; she has already left for the huddle.]*"
-      }
-    },
-    {
-      "turn": 12,
-      "text": [
-        "Session closed. Nothing further pending on Marta's side.\n\nFinal state for the record: model at revision `26a8219a17118558` — 69 nodes, 267 active captures, not complete. Two objectives (held as five duplicate nodes), both formally unsupported. Deferrals carry deposits: CMMS for jam repair times, historian for stage rates, engineering drawings for tank sizes, Marta herself for ramp scrap and the slip rule. Assumption ledger holds one entry, flagged for re-check.\n\nI make no claim that this projects, compiles, or runs. Next session opens as review-and-revise on the objective nodes before any new elicitation.",
-        "Declining this one.\n\nThe range contains no expert testimony. It is my own closing turn, my own sweep-judgment note, and my own state-of-the-model note, terminated by a stage direction confirming Marta has left and is not replying. The only entry in user position is that stage direction — narration about the interview, not Marta's words about her plant.\n\nSweeping it could only do one of two things: extract nothing, or extract something from a non-expert source. The second is the failure mode I've been guarding against all session — a model element with no expert span behind it. My own summary of the model is not evidence for the model; that would be assent taken as origin, with me on both sides of it.\n\nThe substantive content in that stretch — the CMMS follow-up, the ramp-scrap and slip-rule priority, Marta's confirmation of the read-back — was already swept from her actual message at revision `26a8219a17118558`. Nothing is at risk of being lost by leaving this tail unswept.\n\nThe swept high-water mark stays where it is. The session's durable record is complete as of that revision, and next session opens as review-and-revise on the duplicated objective nodes."
-      ],
-      "asks": [],
-      "sweeps": [],
-      "signals": [
-        {
-          "tagName": "settlement-check",
-          "excerpt": "The harness computed this unswept conversation tail:\n\n[assistant] Enjoy the huddle.\n\nThree things I'll have ready for next week, so you don't have to hold them:\n\n1. **Ramp scrap and the slip rule** first, as you asked — for the slip rule I'…"
-        }
-      ],
-      "toolErrors": [],
-      "completion": {
-        "captures": 267,
-        "complete": false,
-        "unsatisfied": 46,
-        "outsideSlice": 53,
-        "unmapped": 0,
-        "revision": "26a8219a17118558",
-        "cue": "The harness folded the model at revision 26a8219a17118558 (plugin sdcpn/2026-08-25.2): 69 node(s) from 267 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:wait or shift when Line 2 goes down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 34 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n53 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-      }
-    }
-  ],
-  "usage": {
-    "interviewer": {
-      "input": 74,
-      "output": 152204,
-      "cacheRead": 969818,
-      "cacheWrite": 132417,
-      "calls": 37
-    },
-    "expert": {
-      "input": 72716,
-      "output": 3478,
-      "cacheRead": 0,
-      "cacheWrite": 0,
-      "calls": 11
-    }
-  },
-  "history": {
-    "v": 1,
-    "conversationId": "conv_01M0X5XEJZSRCZY37FBYJZXVNB",
-    "offset": "0000000000000000_0000000000000699",
-    "messages": [
-      {
-        "id": "entry_direct_c3ViXzAxTTBYNVhFSllRWjVaQlZXTURQS1kyUTlU",
-        "role": "user",
-        "purpose": "user",
-        "display": "visible",
-        "submissionId": "sub_01M0X5XEJYQZ5ZBVWMDPKY2Q9T",
-        "parts": [
-          {
-            "type": "text",
-            "text": "I'm the master scheduler at a coatings plant. My boss wants a simulation model of how we\nschedule production, so we can test scheduling decisions before making them. We have tooling\nthat runs Petri-net-style process models, so the end product should be a model I can hand to\nthat — but I can't tell you much about the format, I'm not the modelling person.\n\nPlease interview me about how our operation works, and then produce the model.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X5XFMN1ZG4EFY9AVWTHV9H",
-        "role": "assistant",
-        "purpose": "assistant",
-        "display": "visible",
-        "submissionId": "sub_01M0X5XEJYQZ5ZBVWMDPKY2Q9T",
-        "turnId": "turn_01M0X5XEKHVQGJ5X2DCYWB9WD3",
-        "parts": [
-          {
-            "type": "reasoning",
-            "text": "I should start by asking about their objectives, keeping it to one question at a time.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "Good — that's exactly the right split: you know the plant, I'll worry about the format. Before I ask anything about how the plant is built, I want to know what the model has to be able to tell you.\n\nLet me start there.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_ask",
-            "toolCallId": "toolu_01VTR3FzE8Wat7pwjPW7jcyh",
-            "state": "output-available",
-            "input": {
-              "question": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong."
-            },
-            "output": {
-              "id": "affordance_toolu_01VTR3FzE8Wat7pwjPW7jcyh",
-              "form": "free-text",
-              "markdown": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong.",
-              "payload": {
-                "question": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong."
-              }
-            },
-            "durationMs": 6
-          },
-          {
-            "type": "data-affordance",
-            "data": {
-              "id": "affordance_toolu_01VTR3FzE8Wat7pwjPW7jcyh",
-              "form": "free-text",
-              "markdown": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong.",
-              "payload": {
-                "question": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong."
-              }
-            }
-          }
-        ]
-      },
-      {
-        "id": "entry_direct_c3ViXzAxTTBYNVhTWFAwTUs1WUJORzkxMUMzVzFE",
-        "role": "user",
-        "purpose": "user",
-        "display": "visible",
-        "submissionId": "sub_01M0X5XSXP0MK5YBNG911C3W1D",
-        "parts": [
-          {
-            "type": "text",
-            "text": "Okay, good question. Let me think of an actual one rather than a hypothetical.\n\nA few weeks back — Line 2 filler jammed at about nine in the morning, half a shift lost. We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.\n\nI went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky. That's the kind of thing — I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X5XSY3F2HAFQYZSZ41RJB0",
-        "role": "system",
-        "purpose": "dispatch",
-        "display": "diagnostic",
-        "submissionId": "sub_01M0X5XSXP0MK5YBNG911C3W1D",
-        "signal": {
-          "tagName": "affordance-reply-bound",
-          "attributes": {
-            "affordanceId": "affordance_toolu_01VTR3FzE8Wat7pwjPW7jcyh"
-          }
-        },
-        "parts": [
-          {
-            "type": "text",
-            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X5XTSMAZ7JTGYCNBEK2AFS",
-        "role": "assistant",
-        "purpose": "assistant",
-        "display": "visible",
-        "submissionId": "sub_01M0X5XSXP0MK5YBNG911C3W1D",
-        "turnId": "turn_01M0X5XSY9SETVXGSADDHT7KMF",
-        "parts": [
-          {
-            "type": "reasoning",
-            "text": "I need to clarify what \"better\" means here—specifically what \"loses less\" actually refers to before I go further with the comparison.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "That's a very usable one — a real disruption, two options, and no way to tell afterwards whether you chose well. That \"which option loses less\" is the heart of the model.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_ask",
-            "toolCallId": "toolu_01RigdvzDsLRJokW4AqBW7UE",
-            "state": "output-available",
-            "input": {
-              "question": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off."
-            },
-            "output": {
-              "id": "affordance_toolu_01RigdvzDsLRJokW4AqBW7UE",
-              "form": "free-text",
-              "markdown": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off.",
-              "payload": {
-                "question": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off."
-              }
-            },
-            "durationMs": 3
-          },
-          {
-            "type": "data-affordance",
-            "data": {
-              "id": "affordance_toolu_01RigdvzDsLRJokW4AqBW7UE",
-              "form": "free-text",
-              "markdown": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off.",
-              "payload": {
-                "question": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off."
-              }
-            }
-          }
-        ]
-      },
-      {
-        "id": "entry_direct_c3ViXzAxTTBYNVk4N0FTNVJaRTQyOEVWME1XNkQ0",
-        "role": "user",
-        "purpose": "user",
-        "display": "visible",
-        "submissionId": "sub_01M0X5Y87AS5RZE428EV0MW6D4",
-        "parts": [
-          {
-            "type": "text",
-            "text": "Honestly, in the moment it's simple-minded: did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\n\nUnderneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\n\nSo really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X5Y87PB790WYFN9ZTV11Y1",
-        "role": "system",
-        "purpose": "dispatch",
-        "display": "diagnostic",
-        "submissionId": "sub_01M0X5Y87AS5RZE428EV0MW6D4",
-        "signal": {
-          "tagName": "affordance-reply-bound",
-          "attributes": {
-            "affordanceId": "affordance_toolu_01RigdvzDsLRJokW4AqBW7UE"
-          }
-        },
-        "parts": [
-          {
-            "type": "text",
-            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X5Y949HBAC6DHA8WYYRGCX",
-        "role": "assistant",
-        "purpose": "assistant",
-        "display": "visible",
-        "submissionId": "sub_01M0X5Y87AS5RZE428EV0MW6D4",
-        "turnId": "turn_01M0X5Y87SSVSRH7S8TAP58QMJ",
-        "parts": [
-          {
-            "type": "reasoning",
-            "text": "Two turns have settled now, so it's time to sweep before moving on. I'm also noting that \"customer tier\" is an awkward entity-type attribute to revisit later, and my next step is to ask a bounded question walking through one order end to end.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_sweep",
-            "toolCallId": "toolu_011HZMxGrrjkdoPHynQCyKKN",
-            "state": "output-available",
-            "input": {},
-            "output": {
-              "status": "applied",
-              "appliedCaptureIds": [
-                "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
-                "capture-76159984-4b11-446f-a707-bc8302ef0b1d",
-                "capture-3f2444d5-8001-46d9-8a92-c85f8c6f8d6a",
-                "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
-                "capture-053410a5-6574-4355-aabf-dd972f0088e1",
-                "capture-e86ee1d3-dbbd-4e2d-b1c0-a8ac719f0e58",
-                "capture-04d27279-48f8-437e-8688-14c400f3f0f1",
-                "capture-7d1cb932-a1d6-4e1a-86a7-984a9d53af80",
-                "capture-330b99df-25fc-4d38-b1f9-6f8da955b79e",
-                "capture-caeeeb12-a91f-46a0-88c2-a622d4d30c55",
-                "capture-422d7f74-a119-45d6-8261-3c71b50af7f7",
-                "capture-f2a03b6c-0420-48a7-85be-bdcb3536a6f7",
-                "capture-c9ac976a-3eef-4a77-8e29-3598b184b450",
-                "capture-6bc324a5-2e12-4070-8275-fdfe819923e6",
-                "capture-b003fc51-0ade-4721-b400-b7b68edf8c60"
-              ],
-              "skippedDedupKeys": [],
-              "advisories": [],
-              "completion": {
-                "complete": false,
-                "revision": "3a1fa5a01b21595c",
-                "pluginVersion": "sdcpn/2026-08-25.2",
-                "unsatisfied": 20,
-                "unmapped": [],
-                "cue": "The harness folded the model at revision 3a1fa5a01b21595c (plugin sdcpn/2026-08-25.2): 6 node(s) from 15 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- [inadmissible-status] \"what it needs before it can start\" on activity:tint-to-white washdown is held under status inferred; accepted: explicit.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:tint-to-white washdown.\n- [below-required-precision] \"how long it takes\" on activity:tint-to-white washdown is known as a number; the model needs spread. Smallest delta: move it from number to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:tint-to-white washdown.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:tint-to-white washdown is known as a number; the model needs range. Smallest delta: move it from number to range.\n- … and 8 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:Line 2 filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:Line 2 filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:Line 2 filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n\n1 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-              }
-            },
-            "durationMs": 112179
-          },
-          {
-            "type": "reasoning",
-            "text": "I'll trace through a single order from start to finish to understand the ordering, flow, and overall structure.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "I've got the objective on record: which option loses less, with Meridian-style on-time as a hard line and washdown hours plus knock-on lateness as the weighing underneath. I'll come back to how you judge \"who can absorb a slip.\"\n\nNow I need the shape of the work itself.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_ask",
-            "toolCallId": "toolu_01BPxGhtkoW98xCiTTeNLW4a",
-            "state": "output-available",
-            "input": {
-              "question": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after."
-            },
-            "output": {
-              "id": "affordance_toolu_01BPxGhtkoW98xCiTTeNLW4a",
-              "form": "free-text",
-              "markdown": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after.",
-              "payload": {
-                "question": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after."
-              }
-            },
-            "durationMs": 2
-          },
-          {
-            "type": "data-affordance",
-            "data": {
-              "id": "affordance_toolu_01BPxGhtkoW98xCiTTeNLW4a",
-              "form": "free-text",
-              "markdown": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after.",
-              "payload": {
-                "question": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after."
-              }
-            }
-          }
-        ]
-      },
-      {
-        "id": "entry_direct_c3ViXzAxTTBYNjI2N0Q4S1QzTTVBUTlBNTA1WThT",
-        "role": "user",
-        "purpose": "user",
-        "display": "visible",
-        "submissionId": "sub_01M0X6267D8KT3M5AQ9A505Y8S",
-        "parts": [
-          {
-            "type": "text",
-            "text": "Sure. So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.\n\nThen it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\n\nOnce it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\n\nThen it's released, goes to the warehouse, and ships against the due date. So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X6267JX8G55G0DC9PYQ5NX",
-        "role": "system",
-        "purpose": "dispatch",
-        "display": "diagnostic",
-        "submissionId": "sub_01M0X6267D8KT3M5AQ9A505Y8S",
-        "signal": {
-          "tagName": "affordance-reply-bound",
-          "attributes": {
-            "affordanceId": "affordance_toolu_01BPxGhtkoW98xCiTTeNLW4a"
-          }
-        },
-        "parts": [
-          {
-            "type": "text",
-            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nTake that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X627DQ7TGEE9S1TJW3D74H",
-        "role": "assistant",
-        "purpose": "assistant",
-        "display": "visible",
-        "submissionId": "sub_01M0X6267D8KT3M5AQ9A505Y8S",
-        "turnId": "turn_01M0X6267K6HQCJ8QRHQE6AJ66",
-        "parts": [
-          {
-            "type": "reasoning",
-            "text": "I should sweep before going deeper, but there's a more structural question worth asking first: does an order stay on one line through all four production stages, or are mixing and milling handled on separate equipment? That distinction seems load-bearing for how I model the process.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_sweep",
-            "toolCallId": "toolu_01XJmxiS6eof5g1i1oSv8mM5",
-            "state": "output-available",
-            "input": {},
-            "output": {
-              "status": "applied",
-              "appliedCaptureIds": [
-                "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
-                "capture-de512bde-aa52-4147-933f-81439aa5ec6d",
-                "capture-a6e8dc50-fffb-494d-8bd2-59704c0427e4",
-                "capture-3cb49f42-f479-4b67-be4c-22c8f9771f6e",
-                "capture-5628ca29-5985-4005-aa3f-a6885dc38223",
-                "capture-6d4d1074-f6fe-4d4c-95c2-f242a6f98233",
-                "capture-a0b65576-83d8-4134-9fbe-9b059663ae12",
-                "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
-                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-                "capture-fa56fa8b-611a-4a38-9a42-1bd038e52d80",
-                "capture-dba4ec08-0265-420c-95d2-4dce250ae0b6",
-                "capture-0b2046b4-55c8-4ce3-abac-296d6abe469d",
-                "capture-8156b872-b3c2-43db-aa67-56166bebe556",
-                "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
-                "capture-589bc2db-8fc9-4d65-8024-b34ce4cd736a",
-                "capture-07de77cc-9de8-41e9-92f6-8fe06a6263c9",
-                "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
-                "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b",
-                "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
-                "capture-7df09f81-9c85-43ac-b69e-306d540f8afb",
-                "capture-e0f39723-a7e5-4656-a8fb-0e2b50bb82da",
-                "capture-d8dffb0f-f148-4af2-ba7e-478a6a1b38c6",
-                "capture-a2938097-b902-4f24-8e15-70f4b8ce95fb",
-                "capture-896881a6-c9ec-469f-ab03-4a56b59f6cad",
-                "capture-4a3ae53c-2c2f-4664-9499-7e81c254abc5",
-                "capture-d662739b-76f0-429a-829a-ccb79763b6b9",
-                "capture-a9e42aa6-8d30-4ded-a8c4-f24220cfb292",
-                "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e"
-              ],
-              "skippedDedupKeys": [],
-              "advisories": [
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
-                    "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-053410a5-6574-4355-aabf-dd972f0088e1",
-                    "capture-d8dffb0f-f148-4af2-ba7e-478a6a1b38c6"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
-                    "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b"
-                  ]
-                }
-              ],
-              "completion": {
-                "complete": false,
-                "revision": "2b8efdb41c191608",
-                "pluginVersion": "sdcpn/2026-08-25.2",
-                "unsatisfied": 28,
-                "unmapped": [],
-                "cue": "The harness folded the model at revision 2b8efdb41c191608 (plugin sdcpn/2026-08-25.2): 15 node(s) from 43 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [below-required-precision] \"how long it takes\" on activity:filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n6 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-              }
-            },
-            "durationMs": 85838
-          },
-          {
-            "type": "reasoning",
-            "text": "I should ask whether a single line represents one consistent resource across all four stages structurally.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_ask",
-            "toolCallId": "toolu_01VcV1KAvgD2ZWUJnBfGcBuh",
-            "state": "output-available",
-            "input": {
-              "question": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines."
-            },
-            "output": {
-              "id": "affordance_toolu_01VcV1KAvgD2ZWUJnBfGcBuh",
-              "form": "free-text",
-              "markdown": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines.",
-              "payload": {
-                "question": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines."
-              }
-            },
-            "durationMs": 3
-          },
-          {
-            "type": "data-affordance",
-            "data": {
-              "id": "affordance_toolu_01VcV1KAvgD2ZWUJnBfGcBuh",
-              "form": "free-text",
-              "markdown": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines.",
-              "payload": {
-                "question": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines."
-              }
-            }
-          }
-        ]
-      },
-      {
-        "id": "entry_direct_c3ViXzAxTTBYNjVBUkFSUzdOVFBYR0UxR0hRQUtH",
-        "role": "user",
-        "purpose": "user",
-        "display": "visible",
-        "submissionId": "sub_01M0X65ARARS7NTPXGE1GHQAKG",
-        "parts": [
-          {
-            "type": "text",
-            "text": "Good question, and this is where the sheet lies to me a bit if I'm honest. On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\n\nBut physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between. So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\n\nWhat I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait. I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X65ARH0JRQCSWP5RADNMZZ",
-        "role": "system",
-        "purpose": "dispatch",
-        "display": "diagnostic",
-        "submissionId": "sub_01M0X65ARARS7NTPXGE1GHQAKG",
-        "signal": {
-          "tagName": "affordance-reply-bound",
-          "attributes": {
-            "affordanceId": "affordance_toolu_01VcV1KAvgD2ZWUJnBfGcBuh"
-          }
-        },
-        "parts": [
-          {
-            "type": "text",
-            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X65BPF0SEY0PZYS6H0ZMRA",
-        "role": "assistant",
-        "purpose": "assistant",
-        "display": "visible",
-        "submissionId": "sub_01M0X65ARARS7NTPXGE1GHQAKG",
-        "turnId": "turn_01M0X65ARMJAKD92XH4MD19G8V",
-        "parts": [
-          {
-            "type": "reasoning",
-            "text": "I'm noting the tank capacity between mill and fill as a genuine second question worth surfacing—the scheduler's suspicion that it's costing them more than admitted could be its own model output. I'll flag it as an optional add-on but stay focused on keeping the current slice tight.\n\nBefore locking down durations for the four stages, I want to check whether they want the model able to test that buffer question, since that determines if the stages need to be separate nodes rather than collapsed. Worth asking directly.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "That's a really valuable thing to have said — the sheet says one line, one order; the floor says four bits of kit with small tanks between them. I'll record both rather than pick one.\n\nThat choice matters for what the model can answer, so let me put it to you.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_ask",
-            "toolCallId": "toolu_01CfCi6guTLjrxg8Hg8QcC6A",
-            "state": "output-available",
-            "input": {
-              "question": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate."
-            },
-            "output": {
-              "id": "affordance_toolu_01CfCi6guTLjrxg8Hg8QcC6A",
-              "form": "free-text",
-              "markdown": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate.",
-              "payload": {
-                "question": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate."
-              }
-            },
-            "durationMs": 1
-          },
-          {
-            "type": "data-affordance",
-            "data": {
-              "id": "affordance_toolu_01CfCi6guTLjrxg8Hg8QcC6A",
-              "form": "free-text",
-              "markdown": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate.",
-              "payload": {
-                "question": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate."
-              }
-            }
-          }
-        ]
-      },
-      {
-        "id": "entry_direct_c3ViXzAxTTBYNjVWSk1CQlFBRTNHR1I3QVZGMlBN",
-        "role": "user",
-        "purpose": "user",
-        "display": "visible",
-        "submissionId": "sub_01M0X65VJMBBQAE3GGR7AVF2PM",
-        "parts": [
-          {
-            "type": "text",
-            "text": "No, I do want that in scope — if I'm honest, the disruption question and the tank question are the same underlying thing to me. Half the reason Line 1's options are worse when Line 2 goes down is because it feels sluggish and blocked in ways I can't pin on the published line rate. If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\n\nSo yes — build it as separate stages if that's what it takes. I'll warn you now, though: I don't have clean numbers for tank sizes or stage-by-stage rates. I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head. Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X65VJRZ2Z8MPBDYT2JXY2Q",
-        "role": "system",
-        "purpose": "dispatch",
-        "display": "diagnostic",
-        "submissionId": "sub_01M0X65VJMBBQAE3GGR7AVF2PM",
-        "signal": {
-          "tagName": "affordance-reply-bound",
-          "attributes": {
-            "affordanceId": "affordance_toolu_01CfCi6guTLjrxg8Hg8QcC6A"
-          }
-        },
-        "parts": [
-          {
-            "type": "text",
-            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWould you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X661931SMD34V46M0CR2G8",
-        "role": "assistant",
-        "purpose": "assistant",
-        "display": "visible",
-        "submissionId": "sub_01M0X65VJMBBQAE3GGR7AVF2PM",
-        "turnId": "turn_01M0X65VJT1Y8A8EVNR55W2SH9",
-        "parts": [
-          {
-            "type": "reasoning",
-            "text": "Good, that covers the second objective, and I should defer stage rates and tank sizes pending deposit of historian data and engineering drawings. Next I want to ask what he already has on hand — end-to-end batch time per SKU per line as a spread, framed around mean versus tail behavior.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "Understood, and that's an honest and useful boundary: stage-level rates live in the historian, tank sizes on engineering drawings, neither in your head. I'll record those as open with their source rather than let me invent them.\n\nLet me take what you *do* carry.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_sweep",
-            "toolCallId": "toolu_01MhhBwG1zLCo3gsmBmjK8Z9",
-            "state": "output-available",
-            "input": {},
-            "output": {
-              "status": "refused",
-              "refusal": {
-                "code": "evidence-quote-not-found",
-                "excerpt": "I know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit",
-                "message": "No user entry contains the verbatim quote \"I know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\". Repair the quote to match the user's words exactly."
-              }
-            },
-            "durationMs": 97241
-          },
-          {
-            "type": "reasoning",
-            "text": "I noticed a misquote in the captured text — it should read \"I just know the tanks are small\" rather than what was extracted, referring to the one between mill and fill on Line 1. I'll flag this discrepancy and retry the sweep to get the accurate wording.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "The sweep bounced on a misquote of mine: the expert's words were \"I **just** know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\". Retrying with the verbatim text.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_sweep",
-            "toolCallId": "toolu_011T9qYtKQVZmhDSeix2mtTS",
-            "state": "output-available",
-            "input": {},
-            "output": {
-              "status": "refused",
-              "refusal": {
-                "code": "evidence-quote-not-found",
-                "excerpt": "and then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
-                "message": "No user entry contains the verbatim quote \"and then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\". Repair the quote to match the user's words exactly."
-              }
-            },
-            "durationMs": 149597
-          },
-          {
-            "type": "reasoning",
-            "text": "I need to fix the capitalization of \"And\" at the start of that sentence and retry the phrasing about the bumped tint order slipping past its due date.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "Second bounce, same cause — capitalisation: the expert wrote \"**And** then whatever happens to the bumped tint order…\". Retrying.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_sweep",
-            "toolCallId": "toolu_01LVoYY2iWjxVep5RNsBHmyZ",
-            "state": "output-available",
-            "input": {},
-            "output": {
-              "status": "applied",
-              "appliedCaptureIds": [
-                "capture-1cb33f48-6553-4e4f-a8a0-37d7631b08ea",
-                "capture-f073c3ed-2a89-4499-b3b2-fe160e8c1057",
-                "capture-c9864a2c-cbb3-41c9-97a6-e44cc1d7d424",
-                "capture-480c2821-4d80-495b-a652-f5de8b035144",
-                "capture-f3f2c366-eab0-49fa-951c-773f77aa11b2",
-                "capture-3bb35fb7-3954-45d4-839f-20ee46a8c052",
-                "capture-e552ac87-8cfa-4091-a262-6fba33ab9f83",
-                "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-                "capture-dd037a1c-63c0-47b8-8886-81c6d1f70226",
-                "capture-6c46c958-82b9-4ba0-bf0f-363fd70b6dbc",
-                "capture-ee4eb482-b4b3-4392-94d7-ef9dc0a6ca98",
-                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-                "capture-32521b14-4f1e-41ff-ab95-dfc11d8eee37",
-                "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
-                "capture-c1704cba-8451-47a5-add8-2e388b330a1f",
-                "capture-68ab39e5-8046-4f93-887e-11ed3e3b1da3",
-                "capture-c6d485c6-0e21-4cc0-b626-9091448d6ba1",
-                "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
-                "capture-737200bb-8f75-455f-b90a-3363a30d5fce",
-                "capture-78203b7c-8e00-469c-9d53-01d1a656d5c1",
-                "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3",
-                "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
-                "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
-                "capture-42e0a99d-6cf6-4b30-8199-b430405ba25b",
-                "capture-a27c0fc1-57f3-4eed-bea8-15453c84f2da",
-                "capture-0f6aea65-d3a4-430b-b532-4f1100303f9e",
-                "capture-a3f706dd-453a-4543-9990-26efb1b079dd",
-                "capture-67de2e75-132c-43a7-b64e-412343204931",
-                "capture-bf082835-a2ca-4279-80e5-726f157270bd",
-                "capture-ce28dd53-a53d-4bc9-9956-dc3268c35e3e",
-                "capture-9b28544e-b867-4018-9c35-2691cef17a62",
-                "capture-4c4af9ea-df1a-4449-adb7-d48fce7eae93",
-                "capture-dabdbb5f-9eca-4afb-ad50-5b381d9dfa4f",
-                "capture-292e1165-0990-4d17-b6db-153c675fd66c",
-                "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
-                "capture-54d606d7-8c61-4f0a-bd5f-867bba1af3f7",
-                "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
-                "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
-                "capture-b0908788-ec79-4481-b056-1fa606930f85"
-              ],
-              "skippedDedupKeys": [],
-              "advisories": [
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-                    "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-                    "capture-711c9600-2f30-4e86-95a2-cc373696e94c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
-                    "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
-                    "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b",
-                    "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
-                    "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-7df09f81-9c85-43ac-b69e-306d540f8afb",
-                    "capture-42e0a99d-6cf6-4b30-8199-b430405ba25b"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
-                    "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-                    "capture-711c9600-2f30-4e86-95a2-cc373696e94c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
-                    "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277"
-                  ]
-                }
-              ],
-              "completion": {
-                "complete": false,
-                "revision": "3157c77c0d581ebb",
-                "pluginVersion": "sdcpn/2026-08-25.2",
-                "unsatisfied": 28,
-                "unmapped": [],
-                "cue": "The harness folded the model at revision 3157c77c0d581ebb (plugin sdcpn/2026-08-25.2): 28 node(s) from 82 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:tint-to-white washdown.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n19 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-              }
-            },
-            "durationMs": 149366
-          },
-          {
-            "type": "reasoning",
-            "text": "I'm noticing 28 nodes with duplicate names like \"filler jam\" and \"Line 2 filler jam\" that I'll need to consolidate, and objectives lack dependency links, so I should ask the expert what the answer actually hinges on. Next I want to get end-to-end batch times as a distribution rather than a single number, so I'll ask what quantiles or spread data he has on his sheet.\n\nI should also ask about run duration for a white batch on Line 2, and whether that duration varies by line or SKU.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "Right — I have your sheet-level knowledge to draw on, so let me take it at that level.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_ask",
-            "toolCallId": "toolu_0114D18YCRQ5SdR2RDUdY11m",
-            "state": "output-available",
-            "input": {
-              "question": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white."
-            },
-            "output": {
-              "id": "affordance_toolu_0114D18YCRQ5SdR2RDUdY11m",
-              "form": "free-text",
-              "markdown": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white.",
-              "payload": {
-                "question": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white."
-              }
-            },
-            "durationMs": 1
-          },
-          {
-            "type": "data-affordance",
-            "data": {
-              "id": "affordance_toolu_0114D18YCRQ5SdR2RDUdY11m",
-              "form": "free-text",
-              "markdown": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white.",
-              "payload": {
-                "question": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white."
-              }
-            }
-          }
-        ]
-      },
-      {
-        "id": "entry_direct_c3ViXzAxTTBYNksxMlExSzlEM0c2MEZCSlc1R1dS",
-        "role": "user",
-        "purpose": "user",
-        "display": "visible",
-        "submissionId": "sub_01M0X6K12Q1K9D3G60FBJW5GWR",
-        "parts": [
-          {
-            "type": "text",
-            "text": "Right, so a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.\n\nBad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more \"the filler hiccupped twice\" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely. Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\n\nOn Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten. That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.\n\nTints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X6K13KW39FXRCVX7KNZJ51",
-        "role": "system",
-        "purpose": "dispatch",
-        "display": "diagnostic",
-        "submissionId": "sub_01M0X6K12Q1K9D3G60FBJW5GWR",
-        "signal": {
-          "tagName": "affordance-reply-bound",
-          "attributes": {
-            "affordanceId": "affordance_toolu_0114D18YCRQ5SdR2RDUdY11m"
-          }
-        },
-        "parts": [
-          {
-            "type": "text",
-            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nTake that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X6K24RQ3TM35JGS0PY0833",
-        "role": "assistant",
-        "purpose": "assistant",
-        "display": "visible",
-        "submissionId": "sub_01M0X6K12Q1K9D3G60FBJW5GWR",
-        "turnId": "turn_01M0X6K13XV6RS6DM925SKCCD5",
-        "parts": [
-          {
-            "type": "reasoning",
-            "text": "I notice a small inconsistency around his tint speed comment, though it's minor. More importantly, I should flag a real modeling hazard: his bad-day figure of 12-13h might already include filler hiccups, which would double-count with jam events I'm planning to model separately — worth asking him directly whether that estimate includes jams.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_sweep",
-            "toolCallId": "toolu_01XE9cAp9zgnYi27UvGN6n6f",
-            "state": "output-available",
-            "input": {},
-            "output": {
-              "status": "applied",
-              "appliedCaptureIds": [
-                "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057",
-                "capture-9d5063d7-b9fb-400e-8b54-f618c6fde20e",
-                "capture-3245b29a-3687-4313-97c5-e0455e5889ba",
-                "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
-                "capture-770314e5-f47a-463e-908a-1d8c23ee60f5",
-                "capture-6ff1c59a-0664-487b-a946-2680043419a2",
-                "capture-be0c3675-ae93-41c5-9eaa-7d36d84617cb",
-                "capture-3e2a5a8a-bd99-4642-afcf-f9d3dfe2e9f6",
-                "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
-                "capture-27ee0ed5-50d0-47f6-94b8-77e090bca50f",
-                "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
-                "capture-2a491098-b602-4b46-bbaa-439e291027db",
-                "capture-c4aefe40-a022-4990-96a1-b74243850715",
-                "capture-76c7250e-6575-4e31-b667-113f3a497cce",
-                "capture-7da94524-13b5-4c11-a1b4-9cb1b0f07e19",
-                "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
-                "capture-d6985d8d-f85e-4556-a091-df64be080ba6",
-                "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
-                "capture-04a6f876-12f4-4f53-b6f2-f8e5fa9c87bc",
-                "capture-592b83e0-ece3-4e98-aedf-cdf70c202e96",
-                "capture-32fe7be9-75c7-464c-87cb-ca38fef4039b",
-                "capture-31556043-9787-40dc-8c0d-b74a47ed3589",
-                "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
-                "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
-                "capture-d2d6e303-2f63-478a-ace1-0bf61abbfddd",
-                "capture-5548a18b-9f79-4475-a9ab-83a74c750721",
-                "capture-1ee7c206-0c56-4d6b-b091-5861f9c40438",
-                "capture-4b706f60-c02f-4973-aa58-2d3ded113c39",
-                "capture-97ea5a05-d89c-4a7d-a136-f90526beaa27",
-                "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
-                "capture-46d37104-fb87-4105-95d5-4448aade81ac",
-                "capture-0cdda695-1dfa-43ef-971c-b9db09403a07"
-              ],
-              "skippedDedupKeys": [],
-              "advisories": [
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
-                    "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
-                    "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
-                    "capture-2a491098-b602-4b46-bbaa-439e291027db"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
-                    "capture-2afae8eb-1155-4b07-9842-971df47a6a7d"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-                    "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
-                    "capture-46d37104-fb87-4105-95d5-4448aade81ac"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
-                    "capture-2afae8eb-1155-4b07-9842-971df47a6a7d"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-0f6aea65-d3a4-430b-b532-4f1100303f9e",
-                    "capture-31556043-9787-40dc-8c0d-b74a47ed3589"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-67de2e75-132c-43a7-b64e-412343204931",
-                    "capture-d2d6e303-2f63-478a-ace1-0bf61abbfddd"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-54d606d7-8c61-4f0a-bd5f-867bba1af3f7",
-                    "capture-4b706f60-c02f-4973-aa58-2d3ded113c39"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
-                    "capture-46d37104-fb87-4105-95d5-4448aade81ac"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b0908788-ec79-4481-b056-1fa606930f85",
-                    "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-6ff1c59a-0664-487b-a946-2680043419a2",
-                    "capture-76c7250e-6575-4e31-b667-113f3a497cce"
-                  ]
-                }
-              ],
-              "completion": {
-                "complete": false,
-                "revision": "2e4f73ea071077f9",
-                "pluginVersion": "sdcpn/2026-08-25.2",
-                "unsatisfied": 9,
-                "unmapped": [],
-                "cue": "The harness folded the model at revision 2e4f73ea071077f9 (plugin sdcpn/2026-08-25.2): 36 node(s) from 114 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"the question, in the expert's words\" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what \"better\" means, and trade-off weights\" has not been addressed on objective:where Line 1 loses its time.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n\nPatterns whose trigger may apply (discretionary):\n- P08 on objective:where Line 1 loses its time: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n\n33 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-              }
-            },
-            "durationMs": 122266
-          },
-          {
-            "type": "reasoning",
-            "text": "The remaining gaps are objective-level: duplicate objective nodes and dependencies lacking support. I should ask the expert to clarify what the answer depends on in their own words and resolve the duplicate phrasing, but first the double-counting issue matters since it affects the spread I just recorded — I'll raise that question now.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "One thing you said gives me pause, and I'd rather sort it now than bake it in wrong.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_ask",
-            "toolCallId": "toolu_016Sy8K81vYAJqTRfxPP8zou",
-            "state": "output-available",
-            "input": {
-              "question": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?"
-            },
-            "output": {
-              "id": "affordance_toolu_016Sy8K81vYAJqTRfxPP8zou",
-              "form": "free-text",
-              "markdown": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?",
-              "payload": {
-                "question": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?"
-              }
-            },
-            "durationMs": 0
-          },
-          {
-            "type": "data-affordance",
-            "data": {
-              "id": "affordance_toolu_016Sy8K81vYAJqTRfxPP8zou",
-              "form": "free-text",
-              "markdown": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?",
-              "payload": {
-                "question": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?"
-              }
-            }
-          }
-        ]
-      },
-      {
-        "id": "entry_direct_c3ViXzAxTTBYNlFDUzk5UVFZMEUyQ0FFMzkxVFgy",
-        "role": "user",
-        "purpose": "user",
-        "display": "visible",
-        "submissionId": "sub_01M0X6QCS99QQY0E2CAE391TX2",
-        "parts": [
-          {
-            "type": "text",
-            "text": "That's fair, and yeah, I was sloppy folding them together. If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\n\nThe twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup. So you're right to pull that apart: clean-run variability is small, and the big bad days are really the breakdown showing up inside the run, not the run itself being slow.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X6QCSWHK8MFRPQXXX1TMSB",
-        "role": "system",
-        "purpose": "dispatch",
-        "display": "diagnostic",
-        "submissionId": "sub_01M0X6QCS99QQY0E2CAE391TX2",
-        "signal": {
-          "tagName": "affordance-reply-bound",
-          "attributes": {
-            "affordanceId": "affordance_toolu_016Sy8K81vYAJqTRfxPP8zou"
-          }
-        },
-        "parts": [
-          {
-            "type": "text",
-            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nYou said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X6QDQH7WRW1YXB1K9S7AVR",
-        "role": "assistant",
-        "purpose": "assistant",
-        "display": "visible",
-        "submissionId": "sub_01M0X6QCS99QQY0E2CAE391TX2",
-        "turnId": "turn_01M0X6QCT6K0JJCHHCXATKD0B7",
-        "parts": [
-          {
-            "type": "reasoning",
-            "text": "I'll supersede and sweep, then focus on the filler jam rate (P01), which is the key unknown for the main objective. I'm also noting that objective dependencies remain unspecified, but I'll set that aside and ask about jam rate first.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_sweep",
-            "toolCallId": "toolu_01VSwNLQXxdV94UeX8FEfjsW",
-            "state": "output-available",
-            "input": {},
-            "output": {
-              "status": "applied",
-              "appliedCaptureIds": [
-                "capture-a5926e2a-88e8-459e-a296-282b16d499a8",
-                "capture-ea1779b0-9a83-42aa-92d1-746e73de43cc",
-                "capture-1288a3df-c7fd-4319-8d4e-a228572ba0b0",
-                "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6",
-                "capture-bb291ebf-9fe0-4a6e-9840-e7d7fac44033",
-                "capture-edfaf81c-c276-4b57-a88c-914953b1c6be",
-                "capture-13339551-ff3a-414f-8260-e1296530d8ec",
-                "capture-535749ea-ba99-4d11-84c0-8203fd058329",
-                "capture-79eccb7f-a787-40d4-a2fa-e95bfda82d18",
-                "capture-3c6b3e85-7fd3-4831-9201-6e3ef525e7cf",
-                "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
-                "capture-823c9593-db42-45eb-9515-937e6b90bd33",
-                "capture-f7e12936-7567-4b38-be19-a45fb5dc6274",
-                "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
-                "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092",
-                "capture-afd366c9-1ea6-4b73-b2c0-ed97c9af0c79",
-                "capture-86fd1cfb-379b-42f7-bdbb-8586dae7f755",
-                "capture-90d36431-4341-4f9e-8bf6-8b5354b2fedd",
-                "capture-7ef3368b-e678-4c58-b7f9-137d1607d8ec",
-                "capture-10d88b79-af70-4a14-90c1-da56ad526d36",
-                "capture-921611c3-21b5-4ab2-8e56-9b8cdaa2eba2",
-                "capture-6cf8c229-ab84-4448-abc6-3e7f4a76bb4c",
-                "capture-ce789325-dd40-4b21-a936-73485ccb90b9",
-                "capture-1ba32034-be19-432b-a012-326b682fd357",
-                "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7",
-                "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
-                "capture-e28ed067-b6a4-40d8-935a-3598e2401cc1",
-                "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a",
-                "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
-                "capture-cfe5bf57-8879-4592-a938-1527d73c8bac",
-                "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
-                "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
-                "capture-23c5706e-37c1-481e-9438-8fae70973c13",
-                "capture-00863ee1-f99c-48b2-b680-bf4eb71e6a57",
-                "capture-196b8447-3958-444f-9860-8de7330299ec"
-              ],
-              "skippedDedupKeys": [],
-              "advisories": [
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
-                    "capture-a5926e2a-88e8-459e-a296-282b16d499a8"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-3f2444d5-8001-46d9-8a92-c85f8c6f8d6a",
-                    "capture-1288a3df-c7fd-4319-8d4e-a228572ba0b0"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
-                    "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
-                    "capture-a5926e2a-88e8-459e-a296-282b16d499a8"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
-                    "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-dba4ec08-0265-420c-95d2-4dce250ae0b6",
-                    "capture-f7e12936-7567-4b38-be19-a45fb5dc6274"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
-                    "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
-                    "capture-b3079749-c23b-4ade-ac51-9bbff19806fb"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-                    "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
-                    "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
-                    "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
-                    "capture-b3079749-c23b-4ade-ac51-9bbff19806fb"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057",
-                    "capture-a5926e2a-88e8-459e-a296-282b16d499a8"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
-                    "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
-                    "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-2a491098-b602-4b46-bbaa-439e291027db",
-                    "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-c4aefe40-a022-4990-96a1-b74243850715",
-                    "capture-823c9593-db42-45eb-9515-937e6b90bd33"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
-                    "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
-                    "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
-                    "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2"
-                  ]
-                }
-              ],
-              "completion": {
-                "complete": false,
-                "revision": "36d1240e30d0f4d1",
-                "pluginVersion": "sdcpn/2026-08-25.2",
-                "unsatisfied": 9,
-                "unmapped": [],
-                "cue": "The harness folded the model at revision 36d1240e30d0f4d1 (plugin sdcpn/2026-08-25.2): 41 node(s) from 149 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"the question, in the expert's words\" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what \"better\" means, and trade-off weights\" has not been addressed on objective:where Line 1 loses its time.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n\nPatterns whose trigger may apply (discretionary):\n- P08 on objective:where Line 1 loses its time: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n\n38 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-              }
-            },
-            "durationMs": 155454
-          },
-          {
-            "type": "reasoning",
-            "text": "38 of 41 nodes fall outside any objective's slice since objectives currently have no dependencies — that's the real structural gap I need to fix by getting the expert to state their questions crisply and what they hinge on. The filler jam rate is also worth asking about, but fixing objectives first is what makes everything else actually count, so I'll craft a question that addresses both.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "Two housekeeping things I want to settle, because right now the model has plenty of plant detail but the two questions it's meant to answer aren't yet wired to any of it.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_ask",
-            "toolCallId": "toolu_01EHPQiwUUuqA7BA9xjbGyvx",
-            "state": "output-available",
-            "input": {
-              "question": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong."
-            },
-            "output": {
-              "id": "affordance_toolu_01EHPQiwUUuqA7BA9xjbGyvx",
-              "form": "free-text",
-              "markdown": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong.",
-              "payload": {
-                "question": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong."
-              }
-            },
-            "durationMs": 3
-          },
-          {
-            "type": "data-affordance",
-            "data": {
-              "id": "affordance_toolu_01EHPQiwUUuqA7BA9xjbGyvx",
-              "form": "free-text",
-              "markdown": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong.",
-              "payload": {
-                "question": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong."
-              }
-            }
-          }
-        ]
-      },
-      {
-        "id": "entry_direct_c3ViXzAxTTBYNldaMzBYQTM1WVI2SjVUNkhGTUJO",
-        "role": "user",
-        "purpose": "user",
-        "display": "visible",
-        "submissionId": "sub_01M0X6WZ30XA35YR6J5T6HFMBN",
-        "parts": [
-          {
-            "type": "text",
-            "text": "Alright, let me actually try and write these the way I'd type them if I had the box.\n\n**Disruption one:** \"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"\n\nWhat it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of \"could be quick, could be long\" rather than one number. And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours. And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the \"who can absorb it\" judgment call again.\n\nI'd say what's missing from your list, or under-weighted: the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just \"an order got delayed.\" A distributor slipping is fine, so the answer to the question genuinely depends on whose tint was sitting there.\n\n**The Line 1 tank one:** \"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\" That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others. That's not something I'd have said a month ago.\n\n(Sorry — I've just seen the time, I have the floor huddle in ten minutes. How much more do you need?)",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X6WZ3K2HCKP0WXTWTDDYPS",
-        "role": "system",
-        "purpose": "dispatch",
-        "display": "diagnostic",
-        "submissionId": "sub_01M0X6WZ30XA35YR6J5T6HFMBN",
-        "signal": {
-          "tagName": "affordance-reply-bound",
-          "attributes": {
-            "affordanceId": "affordance_toolu_01EHPQiwUUuqA7BA9xjbGyvx"
-          }
-        },
-        "parts": [
-          {
-            "type": "text",
-            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nIf the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X6X098KASDR8CJZZTQ1D0A",
-        "role": "assistant",
-        "purpose": "assistant",
-        "display": "visible",
-        "submissionId": "sub_01M0X6WZ30XA35YR6J5T6HFMBN",
-        "turnId": "turn_01M0X6WZ3Y82683W9EYJ7RNYMC",
-        "parts": [
-          {
-            "type": "reasoning",
-            "text": "With ten minutes, I shouldn't rush to close things out — instead I should name what's missing honestly and let them decide where to spend the time. The highest-value gaps are jam rate, repair spread, and washdown/scrap, since those tie directly to the disruption objective and only they have that data, so I'll surface the list and ask them to choose.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_sweep",
-            "toolCallId": "toolu_014CbqDgUVDxZ1c6STNR2cSC",
-            "state": "output-available",
-            "input": {},
-            "output": {
-              "status": "applied",
-              "appliedCaptureIds": [
-                "capture-b58883f3-43e2-4626-bc59-a9c091f1d1b5",
-                "capture-3aa3764b-8dd5-495a-bf3e-b32cbc89ba61",
-                "capture-57ad71c3-f423-4d91-a9f8-d3ce31f1fca1",
-                "capture-1a3325b9-15b6-436a-8e7f-feff95d98036",
-                "capture-0e28490a-6b4b-4996-9b6f-3d9249a7d2dc",
-                "capture-43c5ef42-68ce-478f-89b0-c552111d807a",
-                "capture-ccc2d7eb-8a3f-4684-8f1c-a21a51049550",
-                "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
-                "capture-a158a5da-be3a-461f-87c0-69c38cac1a72",
-                "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23",
-                "capture-4043a577-c1b4-44c3-91f3-2194def82bd9",
-                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
-                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
-                "capture-72d414e6-f6a2-420e-8407-667f41535411",
-                "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
-                "capture-53f9387d-f037-4d0f-999b-f89a8f113f46",
-                "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
-                "capture-38e0effa-0fb7-48ff-907c-2fc9f3e64211",
-                "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
-                "capture-314d8187-81ba-478c-8f71-1c9e5826965b",
-                "capture-345fbb5a-c0c1-4e3a-9015-33b3ad727831",
-                "capture-60f6f8c8-f52e-443a-adee-6818339f3b35",
-                "capture-be556841-bf14-4fe0-8c23-ffc773896b2b",
-                "capture-26d3ac6c-4b27-4765-baa3-8437f06fe8ca",
-                "capture-da6d10a4-e0f2-4b1d-8e78-4d58cadeb8f2",
-                "capture-68f9db28-a002-406d-912a-4cc410e5b380",
-                "capture-0a06d184-bf72-42c4-95b3-7ad88ea4e059",
-                "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f",
-                "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b",
-                "capture-7111ab55-5d90-44f6-a1d2-4aa1b48da4bb",
-                "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a",
-                "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993"
-              ],
-              "skippedDedupKeys": [],
-              "advisories": [
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-                    "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-                    "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
-                    "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-a2938097-b902-4f24-8e15-70f4b8ce95fb",
-                    "capture-be556841-bf14-4fe0-8c23-ffc773896b2b"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
-                    "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-                    "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-                    "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-                    "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
-                    "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
-                    "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
-                    "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
-                    "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
-                    "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
-                    "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
-                    "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b0908788-ec79-4481-b056-1fa606930f85",
-                    "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
-                    "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-27ee0ed5-50d0-47f6-94b8-77e090bca50f",
-                    "capture-a158a5da-be3a-461f-87c0-69c38cac1a72"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
-                    "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-c4aefe40-a022-4990-96a1-b74243850715",
-                    "capture-4043a577-c1b4-44c3-91f3-2194def82bd9"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
-                    "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
-                    "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
-                    "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-46d37104-fb87-4105-95d5-4448aade81ac",
-                    "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-823c9593-db42-45eb-9515-937e6b90bd33",
-                    "capture-4043a577-c1b4-44c3-91f3-2194def82bd9"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
-                    "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
-                    "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
-                    "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
-                    "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
-                    "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
-                  ]
-                }
-              ],
-              "completion": {
-                "complete": false,
-                "revision": "1dffca1f0e4725ec",
-                "pluginVersion": "sdcpn/2026-08-25.2",
-                "unsatisfied": 42,
-                "unmapped": [],
-                "cue": "The harness folded the model at revision 1dffca1f0e4725ec (plugin sdcpn/2026-08-25.2): 47 node(s) from 181 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 30 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n34 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-              }
-            },
-            "durationMs": 138047
-          },
-          {
-            "type": "reasoning",
-            "text": "With ten minutes left, I should give an honest answer on \"how much more\" and then ask the single highest-value question I still need clarity on—the filler jam rate and repair duration spread—since that's central and only they can supply it. I'll also briefly flag what else remains unknown.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "Honest answer to \"how much more\": we're maybe a third of the way. What's still open, roughly in order of how much it costs you: the filler jam's rate and repair time; what the washdown actually costs including ramp scrap; the \"who can absorb a slip\" rule as you actually apply it; how orders arrive into the demand book; QA hold times; and the stage rates and tank size, which we've already agreed aren't in your head. None of that needs to happen today.\n\nFor the ten minutes, I'd spend them on the jam, because you named it as the thing you never know at the time and nobody else can tell me.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_ask",
-            "toolCallId": "toolu_018NF8gHsprWVmC1fJGrJ3VF",
-            "state": "output-available",
-            "input": {
-              "question": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?"
-            },
-            "output": {
-              "id": "affordance_toolu_018NF8gHsprWVmC1fJGrJ3VF",
-              "form": "free-text",
-              "markdown": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?",
-              "payload": {
-                "question": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?"
-              }
-            },
-            "durationMs": 5
-          },
-          {
-            "type": "data-affordance",
-            "data": {
-              "id": "affordance_toolu_018NF8gHsprWVmC1fJGrJ3VF",
-              "form": "free-text",
-              "markdown": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?",
-              "payload": {
-                "question": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?"
-              }
-            }
-          }
-        ]
-      },
-      {
-        "id": "entry_direct_c3ViXzAxTTBYNzFZSzUyUTFFN1I2WVhWNFJGWktT",
-        "role": "user",
-        "purpose": "user",
-        "display": "visible",
-        "submissionId": "sub_01M0X71YK52Q1E7R6YXV4RFZKS",
-        "parts": [
-          {
-            "type": "text",
-            "text": "Okay, quick version. It's a \"every week or two\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.\n\nWhen it stops: typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift. I don't have a cleaner breakdown than that — maintenance would have the actual work-order times in the CMMS but I've never pulled them.\n\nRight, I need to run — good session though. Same time next week?",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X71YKMVR1H78GP6AX8D16B",
-        "role": "system",
-        "purpose": "dispatch",
-        "display": "diagnostic",
-        "submissionId": "sub_01M0X71YK52Q1E7R6YXV4RFZKS",
-        "signal": {
-          "tagName": "affordance-reply-bound",
-          "attributes": {
-            "affordanceId": "affordance_toolu_018NF8gHsprWVmC1fJGrJ3VF"
-          }
-        },
-        "parts": [
-          {
-            "type": "text",
-            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X725HFECA7NBAA6QPFPNQZ",
-        "role": "assistant",
-        "purpose": "assistant",
-        "display": "visible",
-        "submissionId": "sub_01M0X71YK52Q1E7R6YXV4RFZKS",
-        "turnId": "turn_01M0X71YKXS1YG2BC2F4ZP8DE1",
-        "parts": [
-          {
-            "type": "reasoning",
-            "text": "They've stopped, so I should respect that and not introduce anything new. I'll do a final sweep and wrap up with a summary, note any gaps or assumptions, and confirm we're on for next week.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_sweep",
-            "toolCallId": "toolu_013gVphA3fva6xuP624tUbGD",
-            "state": "output-available",
-            "input": {},
-            "output": {
-              "status": "refused",
-              "refusal": {
-                "code": "evidence-quote-not-found",
-                "excerpt": "jams badly enough to stop the run",
-                "message": "No user entry contains the verbatim quote \"jams badly enough to stop the run\". Repair the quote to match the user's words exactly."
-              }
-            },
-            "durationMs": 142365
-          },
-          {
-            "type": "reasoning",
-            "text": "I should use their actual words instead — they described it as \"every week or two,\" ranging from once every three weeks at the low end to twice a week at the high end.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "That bounce was my own phrase, not yours — \"jams badly enough to stop the run\" was my wording. Re-anchoring on what you actually said.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_sweep",
-            "toolCallId": "toolu_01AhAypUknSd3LHrMi8wTivx",
-            "state": "output-available",
-            "input": {},
-            "output": {
-              "status": "applied",
-              "appliedCaptureIds": [
-                "capture-1a240192-8179-4339-815e-3775a062e986",
-                "capture-85062afa-e82d-46ce-b609-f7ed16f8b093",
-                "capture-2c3fa15f-551b-4380-a3b3-8dbc6334a9bb",
-                "capture-41269bfb-9040-4d54-a113-a94c09f6f2f0",
-                "capture-f7ea7c88-4d40-48e7-84e5-2b12ebc5ea8e",
-                "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26",
-                "capture-0e8d50b2-4222-4129-a619-09c5612c05c5",
-                "capture-117f9832-aaba-473a-9411-6fd4022388f2",
-                "capture-e10d4081-78ed-42da-bb26-857f1118224c",
-                "capture-875ed21b-d257-48fe-867b-6785abf6abb7",
-                "capture-06d48b41-86fb-48c0-b3e0-59012ba81960",
-                "capture-428e3931-676d-4af5-a30c-d7a31ea0d8ad",
-                "capture-ecd3c093-8f6b-4a48-a1fc-d2775d4dbc1f",
-                "capture-c6339dee-036e-47cb-9dcf-42fc22d38aae",
-                "capture-2bc071c4-2919-4ff3-910a-92d872eeaef2",
-                "capture-6ec49aac-c165-4e2b-a937-bed3c8c51c2c",
-                "capture-c3f03d77-6760-4b3b-99e5-b78d119a352f",
-                "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14",
-                "capture-83e1381a-f2df-4713-a2f6-f11d034c2fd4",
-                "capture-95cbfe20-605f-4218-9076-0f4816ebadfa",
-                "capture-1a5a8343-7367-416e-b760-c7e8f587fe25",
-                "capture-bf2e57a3-bda7-4090-92ca-af63e0c7a248",
-                "capture-aec8ff27-3e3f-45d2-9142-b6dc2b5d88a3",
-                "capture-9d59a385-a8ae-410a-a13d-a4bca3dde9a3",
-                "capture-4b22a066-a97c-4329-8513-cbd85edd8d65",
-                "capture-63fabb67-24c4-4bee-926f-17917300c8f4",
-                "capture-b1e5ded4-79d6-4ff4-bd0d-6386509efba9",
-                "capture-147c2765-6bfb-4da0-9df9-b74a1c1049de",
-                "capture-ec5740e7-5068-4222-ad24-8396f5975657",
-                "capture-2884cc84-c616-4227-860a-d6b55a06c13d",
-                "capture-0548a680-8da8-47e9-ad72-fb1e264fac80",
-                "capture-8c6a716b-e09a-4977-94d9-f28ab74be7c4",
-                "capture-a67683fd-0f34-4838-b48e-aa01f657a511",
-                "capture-1b632a29-f1de-48e5-8f96-a5ef908c4a56",
-                "capture-9926552e-289f-4b4a-bc99-4cae34f1720a",
-                "capture-06aac0a9-b270-4b13-a54f-37440769d685",
-                "capture-94948329-18e7-42fe-9538-a84fd72c225d",
-                "capture-16b9c643-8b17-490e-bfe0-022a06efd914",
-                "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af",
-                "capture-821e00ef-6923-43b0-955b-3ed7d60ce127",
-                "capture-6da3fa16-460b-4f07-aefc-f941d7118f76",
-                "capture-731a5768-edc7-4858-ad42-50d2faf4b181",
-                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026",
-                "capture-07cb7ca9-27c5-4395-bc9e-aaebc5811382",
-                "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2",
-                "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1",
-                "capture-a0429a34-1145-458d-bada-32d827d68959"
-              ],
-              "skippedDedupKeys": [],
-              "advisories": [
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-                    "capture-e10d4081-78ed-42da-bb26-857f1118224c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-                    "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-0b2046b4-55c8-4ce3-abac-296d6abe469d",
-                    "capture-95cbfe20-605f-4218-9076-0f4816ebadfa"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-07de77cc-9de8-41e9-92f6-8fe06a6263c9",
-                    "capture-16b9c643-8b17-490e-bfe0-022a06efd914"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
-                    "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-e0f39723-a7e5-4656-a8fb-0e2b50bb82da",
-                    "capture-a67683fd-0f34-4838-b48e-aa01f657a511"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
-                    "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-                    "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-dd037a1c-63c0-47b8-8886-81c6d1f70226",
-                    "capture-ecd3c093-8f6b-4a48-a1fc-d2775d4dbc1f"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-                    "capture-e10d4081-78ed-42da-bb26-857f1118224c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-                    "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
-                    "capture-e10d4081-78ed-42da-bb26-857f1118224c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
-                    "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
-                    "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
-                    "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-bf082835-a2ca-4279-80e5-726f157270bd",
-                    "capture-6ec49aac-c165-4e2b-a937-bed3c8c51c2c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
-                    "capture-6da3fa16-460b-4f07-aefc-f941d7118f76"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
-                    "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
-                    "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b0908788-ec79-4481-b056-1fa606930f85",
-                    "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
-                    "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
-                    "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
-                    "capture-1a5a8343-7367-416e-b760-c7e8f587fe25"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
-                    "capture-4b22a066-a97c-4329-8513-cbd85edd8d65"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
-                    "capture-94948329-18e7-42fe-9538-a84fd72c225d"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-5548a18b-9f79-4475-a9ab-83a74c750721",
-                    "capture-147c2765-6bfb-4da0-9df9-b74a1c1049de"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
-                    "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-46d37104-fb87-4105-95d5-4448aade81ac",
-                    "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6",
-                    "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
-                    "capture-94948329-18e7-42fe-9538-a84fd72c225d"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
-                    "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
-                    "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
-                    "capture-6da3fa16-460b-4f07-aefc-f941d7118f76"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
-                    "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
-                    "capture-e10d4081-78ed-42da-bb26-857f1118224c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
-                    "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
-                    "capture-e10d4081-78ed-42da-bb26-857f1118224c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
-                    "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
-                    "capture-4b22a066-a97c-4329-8513-cbd85edd8d65"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
-                    "capture-94948329-18e7-42fe-9538-a84fd72c225d"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
-                    "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f",
-                    "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b",
-                    "capture-6da3fa16-460b-4f07-aefc-f941d7118f76"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a",
-                    "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993",
-                    "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-e10d4081-78ed-42da-bb26-857f1118224c",
-                    "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
-                  ]
-                }
-              ],
-              "completion": {
-                "complete": false,
-                "revision": "0028ff75065b59b1",
-                "pluginVersion": "sdcpn/2026-08-25.2",
-                "unsatisfied": 44,
-                "unmapped": [],
-                "cue": "The harness folded the model at revision 0028ff75065b59b1 (plugin sdcpn/2026-08-25.2): 56 node(s) from 228 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"who or what performs it\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 32 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n41 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-              }
-            },
-            "durationMs": 154331
-          },
-          {
-            "type": "reasoning",
-            "text": "I should wrap up honestly here—confirming next week works, avoiding new topics, and clearly laying out what we have, the gaps, and the assumptions I'm making, while being upfront that I can't hand over a runnable model yet.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "Go — and yes, same time next week works. Here's where we got to, so you can correct anything when you're back at a desk. **The model is not finished and I'm not going to pretend it is; I wouldn't hand this to your tooling yet.**\n\n## What's on record, in your words\n\n**The two questions the model exists to answer**\n1. \"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"\n2. \"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"\n\n**What \"better\" means** — Meridian-style on-time is a hard line, \"not really a trade-off, that's a line I won't cross.\" Below that line you weigh washdown hours, whether the bumped order slides and by how much, and who the customer is. No formula; judgment on who can absorb the slip.\n\n**The flow** — demand book line item out of ERP → you allocate to a line and a week slot → mix, mill, tint, fill (tint \"barely there\" for a white) → QA hold → release, warehouse, ship against due date.\n\n**The line, both ways** — on the sheet, one row, one order occupies Line 2 mix-to-fill. Physically, separate kit with small holding tanks between, and the crew will start the next mix if there's tank room. Both recorded; neither averaged away.\n\n**Run times, clean of breakdowns** — white on Line 2: typical 8–9 h, bad-but-clean 9–10 h, good day ~6 h. Same order on Line 1: add 50–60%, so typical 13–14 h, best ~10 h. Tints: 8–10 h typical on *either* line, no big gap — which you flagged as unexplained and sheet-derived. The 12–13 h figure has been pulled out as breakdown, not run.\n\n**Filler jam** — every week or two; low once in three weeks, high twice a week. Repair typical 30–45 min, quick one-in-ten 10–15 min, bad one-in-ten 4–5 h, \"occasionally eating the rest of the shift.\"\n\n**Washdown** — tint-to-white, three hours, direction matters, plus ramp scrap you don't have numbers for.\n\n## Gaps, with where they'd come from\n- Stage-level rates per line — historian, never pulled apart.\n- Tank sizes, mill-to-fill on Line 1 — engineering drawings.\n- Jam repair times, properly — maintenance work orders in the CMMS.\n- Ramp scrap after washdown — you said it shouldn't be ignored; no source named yet.\n- Whether the tank matters differently by SKU — your own new thought, unexamined.\n- QA hold: \"a few hours for a white,\" and a longer \"specialty wait\" you mentioned but I never asked about.\n- How orders arrive into the demand book — never asked.\n- The \"who can absorb the slip\" rule — I have distributor-shrugs and prickly-account, not a rule I could apply without you.\n\n## Assumptions ledger\n1. That the four stages are the same four for every product — you said \"same four stages every product goes through,\" so this is yours, not mine, but it's load-bearing enough to re-check.\n2. Nothing else. Where I was tempted to fill in — jam rate before you gave it, washdown scrap, stage rates — it's in the gaps list instead.\n\nBoth objectives are still formally unsupported: I have the plant detail and the questions, but haven't yet wired which pieces each answer depends on tightly enough for the tooling. That plus the ramp scrap and the slip rule are what I'd open with next week.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_direct_c3ViXzAxTTBYN0NFRENNUUtEWkozMzIxM1hTMUUw",
-        "role": "user",
-        "purpose": "user",
-        "display": "visible",
-        "submissionId": "sub_01M0X7CEDCMQKDZJ33213XS1E0",
-        "parts": [
-          {
-            "type": "text",
-            "text": "Looks right — that's a fair record, and yeah, next week let's start with ramp scrap and the slip rule, since those feel like the ones I could actually go dig up or nail down between now and then. I'll ask maintenance for the CMMS numbers on the filler too while I'm at it. Go on, get to your huddle — wait, that's me. See you next week.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X7CN402JVB8ATB7XBRY0PM",
-        "role": "assistant",
-        "purpose": "assistant",
-        "display": "visible",
-        "submissionId": "sub_01M0X7CEDCMQKDZJ33213XS1E0",
-        "turnId": "turn_01M0X7CEEJGA9FA73FAKXB1SDQ",
-        "parts": [
-          {
-            "type": "text",
-            "text": "Enjoy the huddle.\n\nThree things I'll have ready for next week, so you don't have to hold them:\n\n1. **Ramp scrap and the slip rule** first, as you asked — for the slip rule I'll come at it through a case rather than a principle, so have in mind the last time you bumped someone's order and it turned out to be the wrong someone.\n2. **CMMS filler numbers** — when you get them, what I want is the same shape you gave me from memory: typical, bad one-in-ten, quick one-in-ten. If the work orders disagree with your 30–45 minutes, that disagreement is worth more to the model than either figure alone, so don't reconcile it before you bring it.\n3. **The tint parity puzzle** — that Line 1 and Line 2 run tints at nearly the same speed with no explanation. It's the loose thread most likely to be the same thing as your tank hunch, and I'd like to pull on it once the scrap and slip rule are in.\n\nNothing needs doing beyond that. See you next week.",
-            "state": "done"
-          },
-          {
-            "type": "reasoning",
-            "text": "The session has closed with the user's confirmation of the read-back — their \"looks right\" is agreement, not new capture, but their own commitments in the tail (digging up ramp scrap and the slip rule, asking maintenance for CMMS numbers) are genuine deferral deposits worth capturing. This is settled — time to sweep.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "The tail has settled: the read-back was confirmed, the session closed, and the expert's last message adds content in their own words — what they'll dig up before next time and that they'll pull the CMMS numbers from maintenance. That belongs in the record as deferral deposits, not as agreement to my summary.\n\nOne caution I'll carry into the sweep: \"Looks right\" is assent to my phrasing, not origination. It closes nothing that wasn't already sourced to their words.",
-            "state": "done"
-          },
-          {
-            "type": "dynamic-tool",
-            "toolName": "brunch_sweep",
-            "toolCallId": "toolu_01TCGhYry4UzwpGQKMAGwEWr",
-            "state": "output-available",
-            "input": {},
-            "output": {
-              "status": "applied",
-              "appliedCaptureIds": [
-                "capture-48033ee8-f7eb-4615-b21f-018837fc9c5e",
-                "capture-88da9925-d922-48c3-8ea0-2c631df3ae3d",
-                "capture-f53d8f62-375e-4af6-9aaa-fb903839993c",
-                "capture-ac435640-eea2-4ad6-9695-8e5408b4d852",
-                "capture-f5a658db-c8ec-4ca0-8a87-3ad252dee56d",
-                "capture-618842bb-d23d-4371-ae57-73e5257ba215",
-                "capture-538fb022-2495-46bb-8661-8e1f38c802bf",
-                "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98",
-                "capture-5d5f862f-c18c-4501-b544-76735d28e004",
-                "capture-7f6b8be1-6336-465f-8e11-36a5277d51bd",
-                "capture-1a83c9c6-a8f8-4ece-a5d4-53b81bf8cc9b",
-                "capture-e6ae51ed-e1f6-45f3-aab1-c4bca2a979e8",
-                "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7",
-                "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01",
-                "capture-7f9ac97e-375b-4de3-bbcd-b65e5c7427a6",
-                "capture-66fbb371-91b7-41db-b437-5bd207d08aed",
-                "capture-8da19d62-c082-41f6-ac55-f28afe266a8c",
-                "capture-995374a1-2d25-4690-8397-b342f46ebf02",
-                "capture-3cc84392-4ed4-4804-8a7c-db07d384a8b2",
-                "capture-289ac648-e939-4e62-ad46-a17b112402d4",
-                "capture-5376c084-3889-476f-adab-b09a038ded28",
-                "capture-b9dfddf9-52d8-433e-81b8-5611e7356c34",
-                "capture-27ae8fdf-c227-4160-a1a5-e85530156938",
-                "capture-7bd393bf-3f05-4aa1-b15a-968c293b076f",
-                "capture-ef41e72f-3126-4003-82b2-686b5f8bfdfb",
-                "capture-4fa34ba3-82e3-4a4a-ad28-362765a40046",
-                "capture-2f670377-be1e-4275-9e46-24dd13316300",
-                "capture-9dc62989-7db7-4e58-baf1-b9ed0400d9a2",
-                "capture-b92eccd9-e2ad-41a9-abce-bb1cf8b3c328",
-                "capture-55e95600-febe-4c98-8859-a56eb23ab156",
-                "capture-29c03a62-4be2-4dc2-852e-bfeab6770f1b",
-                "capture-9f708103-e43a-4766-bca4-cb3b7060fdcd",
-                "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c",
-                "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d",
-                "capture-12e575e7-b7a9-472d-b165-308334ae7513",
-                "capture-bc9d210e-beb9-4f7a-aa5d-243950605a2a",
-                "capture-90a38599-7f1b-46ed-9352-d3dd3566b338",
-                "capture-d889a88e-b7be-4055-9da1-e64f9fc858b0",
-                "capture-173c6d39-090f-49a7-9e38-c8998003718b"
-              ],
-              "skippedDedupKeys": [
-                "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\"\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-              ],
-              "advisories": [
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-76159984-4b11-446f-a707-bc8302ef0b1d",
-                    "capture-f53d8f62-375e-4af6-9aaa-fb903839993c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
-                    "capture-55e95600-febe-4c98-8859-a56eb23ab156"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-caeeeb12-a91f-46a0-88c2-a622d4d30c55",
-                    "capture-90a38599-7f1b-46ed-9352-d3dd3566b338"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
-                    "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
-                    "capture-12e575e7-b7a9-472d-b165-308334ae7513"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
-                    "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-                    "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
-                    "capture-12e575e7-b7a9-472d-b165-308334ae7513"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
-                    "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-3e2a5a8a-bd99-4642-afcf-f9d3dfe2e9f6",
-                    "capture-1a83c9c6-a8f8-4ece-a5d4-53b81bf8cc9b"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
-                    "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
-                    "capture-66fbb371-91b7-41db-b437-5bd207d08aed"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-2a491098-b602-4b46-bbaa-439e291027db",
-                    "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-c4aefe40-a022-4990-96a1-b74243850715",
-                    "capture-8da19d62-c082-41f6-ac55-f28afe266a8c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
-                    "capture-5376c084-3889-476f-adab-b09a038ded28"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
-                    "capture-27ae8fdf-c227-4160-a1a5-e85530156938"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
-                    "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
-                    "capture-12e575e7-b7a9-472d-b165-308334ae7513"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
-                    "capture-538fb022-2495-46bb-8661-8e1f38c802bf"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
-                    "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-823c9593-db42-45eb-9515-937e6b90bd33",
-                    "capture-8da19d62-c082-41f6-ac55-f28afe266a8c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
-                    "capture-538fb022-2495-46bb-8661-8e1f38c802bf"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
-                    "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092",
-                    "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-ce789325-dd40-4b21-a936-73485ccb90b9",
-                    "capture-b92eccd9-e2ad-41a9-abce-bb1cf8b3c328"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7",
-                    "capture-55e95600-febe-4c98-8859-a56eb23ab156"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
-                    "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a",
-                    "capture-12e575e7-b7a9-472d-b165-308334ae7513"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
-                    "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
-                    "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23",
-                    "capture-66fbb371-91b7-41db-b437-5bd207d08aed"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-4043a577-c1b4-44c3-91f3-2194def82bd9",
-                    "capture-8da19d62-c082-41f6-ac55-f28afe266a8c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
-                    "capture-27ae8fdf-c227-4160-a1a5-e85530156938"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
-                    "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
-                    "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-1a240192-8179-4339-815e-3775a062e986",
-                    "capture-48033ee8-f7eb-4615-b21f-018837fc9c5e"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14",
-                    "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-83e1381a-f2df-4713-a2f6-f11d034c2fd4",
-                    "capture-7f9ac97e-375b-4de3-bbcd-b65e5c7427a6"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-1a5a8343-7367-416e-b760-c7e8f587fe25",
-                    "capture-5376c084-3889-476f-adab-b09a038ded28"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-4b22a066-a97c-4329-8513-cbd85edd8d65",
-                    "capture-27ae8fdf-c227-4160-a1a5-e85530156938"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-ec5740e7-5068-4222-ad24-8396f5975657",
-                    "capture-4fa34ba3-82e3-4a4a-ad28-362765a40046"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-0548a680-8da8-47e9-ad72-fb1e264fac80",
-                    "capture-9dc62989-7db7-4e58-baf1-b9ed0400d9a2"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-94948329-18e7-42fe-9538-a84fd72c225d",
-                    "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af",
-                    "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
-                  ]
-                },
-                {
-                  "type": "possibly-equivalent",
-                  "reason": "same-evidence",
-                  "captureIds": [
-                    "capture-538fb022-2495-46bb-8661-8e1f38c802bf",
-                    "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98"
-                  ]
-                }
-              ],
-              "completion": {
-                "complete": false,
-                "revision": "26a8219a17118558",
-                "pluginVersion": "sdcpn/2026-08-25.2",
-                "unsatisfied": 46,
-                "unmapped": [],
-                "cue": "The harness folded the model at revision 26a8219a17118558 (plugin sdcpn/2026-08-25.2): 69 node(s) from 267 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:wait or shift when Line 2 goes down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 34 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n53 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
-              }
-            },
-            "durationMs": 128526
-          },
-          {
-            "type": "reasoning",
-            "text": "The session's over now, so I'll note this for next time: those five objective nodes really boil down to just two distinct questions, duplicated through repeated rephrasing, and none of them carry real dependencies. That's something worth reviewing and cleaning up going forward.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "Swept and folded — the session's record is durable. Since you've gone, this is a note-to-self for next week rather than anything you need to read now.\n\n**State of the model:** 69 nodes from 267 captures. Not complete, and two things about *how it's held* need fixing before more content goes in:\n\n1. **Objective duplication.** Your two questions have landed as five objective nodes — successive rephrasings of the same two (\"which option loses less\", \"which option actually loses less\", \"wait or shift when Line 2 goes down\" are one question; \"where Line 1 loses its time\" and \"is the mill-to-fill tank on Line 1 slowing the line down\" are the other). That's an artefact of my asking you to restate them, not a fact about your plant. Consolidating is a review-and-revise job, and it needs your word on which phrasing is yours, not my merge.\n\n2. **Nothing is wired to the objectives.** 53 of the 69 nodes sit outside every objective's dependency slice — recorded, but not demanded by anything. That's why the completion report keeps growing without the model getting more answerable. You *did* tell me what the disruption question hangs on: the run being protected, Line 1's state and family, the jam duration, the ramp scrap, and the bumped order's identity. I have those as prose in your answer; they aren't yet linked as dependencies. Doing that link properly is the first thing that makes any of the plant detail count.\n\n3. **Three open conflicts** on the filler jam node and the production-run node, where later answers superseded earlier ones — the 12–13 h that turned out to be breakdown, and the two jam descriptions. Those need your explicit word to close, not my inference about which you meant.\n\nSo next week's order: ramp scrap and the slip rule as you asked, then the objective wiring, then the conflict closes. The tint parity thread stays third.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X7CTET9RVN9FFHJH8C93AE",
-        "role": "system",
-        "purpose": "dispatch",
-        "display": "diagnostic",
-        "submissionId": "sub_01M0X7CEDCMQKDZJ33213XS1E0",
-        "signal": {
-          "tagName": "settlement-check"
-        },
-        "parts": [
-          {
-            "type": "text",
-            "text": "The harness computed this unswept conversation tail:\n\n[non-user] The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?\n[assistant] That bounce was my own phrase, not yours — \"jams badly enough to stop the run\" was my wording. Re-anchoring on what you actually said.Go — and yes, same time next week works. Here's where we got to, so you can correct anything when you're back at a desk. **The model is not finished and I'm not going to pretend it is; I wouldn't hand this to your tooling yet.**\n\n## What's on record, in your words\n\n**The two questions the model exists to answer**\n1. \"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"\n2. \"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"\n\n**What \"better\" means** — Meridian-style on-time is a hard line, \"not really a trade-off, that's a line I won't cross.\" Below that line you weigh washdown hours, whether the bumped order slides and by how much, and who the customer is. No formula; judgment on who can absorb the slip.\n\n**The flow** — demand book line item out of ERP → you allocate to a line and a week slot → mix, mill, tint, fill (tint \"barely there\" for a white) → QA hold → release, warehouse, ship against due date.\n\n**The line, both ways** — on the sheet, one row, one order occupies Line 2 mix-to-fill. Physically, separate kit with small holding tanks between, and the crew will start the next mix if there's tank room. Both recorded; neither averaged away.\n\n**Run times, clean of breakdowns** — white on Line 2: typical 8–9 h, bad-but-clean 9–10 h, good day ~6 h. Same order on Line 1: add 50–60%, so typical 13–14 h, best ~10 h. Tints: 8–10 h typical on *either* line, no big gap — which you flagged as unexplained and sheet-derived. The 12–13 h figure has been pulled out as breakdown, not run.\n\n**Filler jam** — every week or two; low once in three weeks, high twice a week. Repair typical 30–45 min, quick one-in-ten 10–15 min, bad one-in-ten 4–5 h, \"occasionally eating the rest of the shift.\"\n\n**Washdown** — tint-to-white, three hours, direction matters, plus ramp scrap you don't have numbers for.\n\n## Gaps, with where they'd come from\n- Stage-level rates per line — historian, never pulled apart.\n- Tank sizes, mill-to-fill on Line 1 — engineering drawings.\n- Jam repair times, properly — maintenance work orders in the CMMS.\n- Ramp scrap after washdown — you said it shouldn't be ignored; no source named yet.\n- Whether the tank matters differently by SKU — your own new thought, unexamined.\n- QA hold: \"a few hours for a white,\" and a longer \"specialty wait\" you mentioned but I never asked about.\n- How orders arrive into the demand book — never asked.\n- The \"who can absorb the slip\" rule — I have distributor-shrugs and prickly-account, not a rule I could apply without you.\n\n## Assumptions ledger\n1. That the four stages are the same four for every product — you said \"same four stages every product goes through,\" so this is yours, not mine, but it's load-bearing enough to re-check.\n2. Nothing else. Where I was tempted to fill in — jam rate before you gave it, washdown scrap, stage rates — it's in the gaps list instead.\n\nBoth objectives are still formally unsupported: I have the plant detail and the questions, but haven't yet wired which pieces each answer depends on tightly enough for the tooling. That plus the ramp scrap and the slip rule are what I'd open with next week.\n[user] Looks right — that's a fair record, and yeah, next week let's start with ramp scrap and the slip rule, since those feel like the ones I could actually go dig up or nail down between now and then. I'll ask maintenance for the CMMS numbers on the filler too while I'm at it. Go on, get to your huddle — wait, that's me. See you next week.\n\nJudge whether this range has settled. If it has, call brunch_sweep. Declining is legal; continue the interview when the topic is still open.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_direct_c3ViXzAxTTBYN0hSRzVCTlhCOERQMThGQlZaUFdR",
-        "role": "user",
-        "purpose": "user",
-        "display": "visible",
-        "submissionId": "sub_01M0X7HRG5BNXB8DP18FBVZPWQ",
-        "parts": [
-          {
-            "type": "text",
-            "text": "*[No response — this final message is addressed to the interviewer's own note-taking process, not to Marta. Staying in character as Marta, there is nothing here that calls for a reply; she has already left for the huddle.]*",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X7HYVCKNG7WPQ3SQTCKRNN",
-        "role": "assistant",
-        "purpose": "assistant",
-        "display": "visible",
-        "submissionId": "sub_01M0X7HRG5BNXB8DP18FBVZPWQ",
-        "turnId": "turn_01M0X7HRHNXMKH4B8VC1PGQNTZ",
-        "parts": [
-          {
-            "type": "reasoning",
-            "text": "No reply is needed here, so I'll just close things out simply without opening a new topic or asking anything.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "Session closed. Nothing further pending on Marta's side.\n\nFinal state for the record: model at revision `26a8219a17118558` — 69 nodes, 267 active captures, not complete. Two objectives (held as five duplicate nodes), both formally unsupported. Deferrals carry deposits: CMMS for jam repair times, historian for stage rates, engineering drawings for tank sizes, Marta herself for ramp scrap and the slip rule. Assumption ledger holds one entry, flagged for re-check.\n\nI make no claim that this projects, compiles, or runs. Next session opens as review-and-revise on the objective nodes before any new elicitation.",
-            "state": "done"
-          },
-          {
-            "type": "reasoning",
-            "text": "This tail has no actual expert content to sweep — just a stage direction, not Marta's words about the plant. Declining seems right here; there's nothing capturable in this range anyway, so leaving it unswept is harmless.",
-            "state": "done"
-          },
-          {
-            "type": "text",
-            "text": "Declining this one.\n\nThe range contains no expert testimony. It is my own closing turn, my own sweep-judgment note, and my own state-of-the-model note, terminated by a stage direction confirming Marta has left and is not replying. The only entry in user position is that stage direction — narration about the interview, not Marta's words about her plant.\n\nSweeping it could only do one of two things: extract nothing, or extract something from a non-expert source. The second is the failure mode I've been guarding against all session — a model element with no expert span behind it. My own summary of the model is not evidence for the model; that would be assent taken as origin, with me on both sides of it.\n\nThe substantive content in that stretch — the CMMS follow-up, the ramp-scrap and slip-rule priority, Marta's confirmation of the read-back — was already swept from her actual message at revision `26a8219a17118558`. Nothing is at risk of being lost by leaving this tail unswept.\n\nThe swept high-water mark stays where it is. The session's durable record is complete as of that revision, and next session opens as review-and-revise on the duplicated objective nodes.",
-            "state": "done"
-          }
-        ]
-      },
-      {
-        "id": "entry_01M0X7J3K3R09V3EER3R7MQC0V",
-        "role": "system",
-        "purpose": "dispatch",
-        "display": "diagnostic",
-        "submissionId": "sub_01M0X7HRG5BNXB8DP18FBVZPWQ",
-        "signal": {
-          "tagName": "settlement-check"
-        },
-        "parts": [
-          {
-            "type": "text",
-            "text": "The harness computed this unswept conversation tail:\n\n[assistant] Enjoy the huddle.\n\nThree things I'll have ready for next week, so you don't have to hold them:\n\n1. **Ramp scrap and the slip rule** first, as you asked — for the slip rule I'll come at it through a case rather than a principle, so have in mind the last time you bumped someone's order and it turned out to be the wrong someone.\n2. **CMMS filler numbers** — when you get them, what I want is the same shape you gave me from memory: typical, bad one-in-ten, quick one-in-ten. If the work orders disagree with your 30–45 minutes, that disagreement is worth more to the model than either figure alone, so don't reconcile it before you bring it.\n3. **The tint parity puzzle** — that Line 1 and Line 2 run tints at nearly the same speed with no explanation. It's the loose thread most likely to be the same thing as your tank hunch, and I'd like to pull on it once the scrap and slip rule are in.\n\nNothing needs doing beyond that. See you next week.The tail has settled: the read-back was confirmed, the session closed, and the expert's last message adds content in their own words — what they'll dig up before next time and that they'll pull the CMMS numbers from maintenance. That belongs in the record as deferral deposits, not as agreement to my summary.\n\nOne caution I'll carry into the sweep: \"Looks right\" is assent to my phrasing, not origination. It closes nothing that wasn't already sourced to their words.Swept and folded — the session's record is durable. Since you've gone, this is a note-to-self for next week rather than anything you need to read now.\n\n**State of the model:** 69 nodes from 267 captures. Not complete, and two things about *how it's held* need fixing before more content goes in:\n\n1. **Objective duplication.** Your two questions have landed as five objective nodes — successive rephrasings of the same two (\"which option loses less\", \"which option actually loses less\", \"wait or shift when Line 2 goes down\" are one question; \"where Line 1 loses its time\" and \"is the mill-to-fill tank on Line 1 slowing the line down\" are the other). That's an artefact of my asking you to restate them, not a fact about your plant. Consolidating is a review-and-revise job, and it needs your word on which phrasing is yours, not my merge.\n\n2. **Nothing is wired to the objectives.** 53 of the 69 nodes sit outside every objective's dependency slice — recorded, but not demanded by anything. That's why the completion report keeps growing without the model getting more answerable. You *did* tell me what the disruption question hangs on: the run being protected, Line 1's state and family, the jam duration, the ramp scrap, and the bumped order's identity. I have those as prose in your answer; they aren't yet linked as dependencies. Doing that link properly is the first thing that makes any of the plant detail count.\n\n3. **Three open conflicts** on the filler jam node and the production-run node, where later answers superseded earlier ones — the 12–13 h that turned out to be breakdown, and the two jam descriptions. Those need your explicit word to close, not my inference about which you meant.\n\nSo next week's order: ramp scrap and the slip rule as you asked, then the objective wiring, then the conflict closes. The tint parity thread stays third.\n[non-user] The harness computed this unswept conversation tail:\n\n[non-user] The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?\n[assistant] That bounce was my own phrase, not yours — \"jams badly enough to stop the run\" was my wording. Re-anchoring on what you actually said.Go — and yes, same time next week works. Here's where we got to, so you can correct anything when you're back at a desk. **The model is not finished and I'm not going to pretend it is; I wouldn't hand this to your tooling yet.**\n\n## What's on record, in your words\n\n**The two questions the model exists to answer**\n1. \"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"\n2. \"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"\n\n**What \"better\" means** — Meridian-style on-time is a hard line, \"not really a trade-off, that's a line I won't cross.\" Below that line you weigh washdown hours, whether the bumped order slides and by how much, and who the customer is. No formula; judgment on who can absorb the slip.\n\n**The flow** — demand book line item out of ERP → you allocate to a line and a week slot → mix, mill, tint, fill (tint \"barely there\" for a white) → QA hold → release, warehouse, ship against due date.\n\n**The line, both ways** — on the sheet, one row, one order occupies Line 2 mix-to-fill. Physically, separate kit with small holding tanks between, and the crew will start the next mix if there's tank room. Both recorded; neither averaged away.\n\n**Run times, clean of breakdowns** — white on Line 2: typical 8–9 h, bad-but-clean 9–10 h, good day ~6 h. Same order on Line 1: add 50–60%, so typical 13–14 h, best ~10 h. Tints: 8–10 h typical on *either* line, no big gap — which you flagged as unexplained and sheet-derived. The 12–13 h figure has been pulled out as breakdown, not run.\n\n**Filler jam** — every week or two; low once in three weeks, high twice a week. Repair typical 30–45 min, quick one-in-ten 10–15 min, bad one-in-ten 4–5 h, \"occasionally eating the rest of the shift.\"\n\n**Washdown** — tint-to-white, three hours, direction matters, plus ramp scrap you don't have numbers for.\n\n## Gaps, with where they'd come from\n- Stage-level rates per line — historian, never pulled apart.\n- Tank sizes, mill-to-fill on Line 1 — engineering drawings.\n- Jam repair times, properly — maintenance work orders in the CMMS.\n- Ramp scrap after washdown — you said it shouldn't be ignored; no source named yet.\n- Whether the tank matters differently by SKU — your own new thought, unexamined.\n- QA hold: \"a few hours for a white,\" and a longer \"specialty wait\" you mentioned but I never asked about.\n- How orders arrive into the demand book — never asked.\n- The \"who can absorb the slip\" rule — I have distributor-shrugs and prickly-account, not a rule I could apply without you.\n\n## Assumptions ledger\n1. That the four stages are the same four for every product — you said \"same four stages every product goes through,\" so this is yours, not mine, but it's load-bearing enough to re-check.\n2. Nothing else. Where I was tempted to fill in — jam rate before you gave it, washdown scrap, stage rates — it's in the gaps list instead.\n\nBoth objectives are still formally unsupported: I have the plant detail and the questions, but haven't yet wired which pieces each answer depends on tightly enough for the tooling. That plus the ramp scrap and the slip rule are what I'd open with next week.\n[user] Looks right — that's a fair record, and yeah, next week let's start with ramp scrap and the slip rule, since those feel like the ones I could actually go dig up or nail down between now and then. I'll ask maintenance for the CMMS numbers on the filler too while I'm at it. Go on, get to your huddle — wait, that's me. See you next week.\n\nJudge whether this range has settled. If it has, call brunch_sweep. Declining is legal; continue the interview when the topic is still open.\n[user] *[No response — this final message is addressed to the interviewer's own note-taking process, not to Marta. Staying in character as Marta, there is nothing here that calls for a reply; she has already left for the huddle.]*\n\nJudge whether this range has settled. If it has, call brunch_sweep. Declining is legal; continue the interview when the topic is still open.",
-            "state": "done"
-          }
-        ]
-      }
-    ],
-    "settlements": [
-      {
-        "submissionId": "sub_01M0X5XEJYQZ5ZBVWMDPKY2Q9T",
-        "outcome": "completed",
-        "answeredBySubmissionId": "sub_01M0X5XEJYQZ5ZBVWMDPKY2Q9T"
-      },
-      {
-        "submissionId": "sub_01M0X5XSXP0MK5YBNG911C3W1D",
-        "outcome": "completed",
-        "answeredBySubmissionId": "sub_01M0X5XSXP0MK5YBNG911C3W1D"
-      },
-      {
-        "submissionId": "sub_01M0X5Y87AS5RZE428EV0MW6D4",
-        "outcome": "completed",
-        "answeredBySubmissionId": "sub_01M0X5Y87AS5RZE428EV0MW6D4"
-      },
-      {
-        "submissionId": "sub_01M0X6267D8KT3M5AQ9A505Y8S",
-        "outcome": "completed",
-        "answeredBySubmissionId": "sub_01M0X6267D8KT3M5AQ9A505Y8S"
-      },
-      {
-        "submissionId": "sub_01M0X65ARARS7NTPXGE1GHQAKG",
-        "outcome": "completed",
-        "answeredBySubmissionId": "sub_01M0X65ARARS7NTPXGE1GHQAKG"
-      },
-      {
-        "submissionId": "sub_01M0X65VJMBBQAE3GGR7AVF2PM",
-        "outcome": "completed",
-        "answeredBySubmissionId": "sub_01M0X65VJMBBQAE3GGR7AVF2PM"
-      },
-      {
-        "submissionId": "sub_01M0X6K12Q1K9D3G60FBJW5GWR",
-        "outcome": "completed",
-        "answeredBySubmissionId": "sub_01M0X6K12Q1K9D3G60FBJW5GWR"
-      },
-      {
-        "submissionId": "sub_01M0X6QCS99QQY0E2CAE391TX2",
-        "outcome": "completed",
-        "answeredBySubmissionId": "sub_01M0X6QCS99QQY0E2CAE391TX2"
-      },
-      {
-        "submissionId": "sub_01M0X6WZ30XA35YR6J5T6HFMBN",
-        "outcome": "completed",
-        "answeredBySubmissionId": "sub_01M0X6WZ30XA35YR6J5T6HFMBN"
-      },
-      {
-        "submissionId": "sub_01M0X71YK52Q1E7R6YXV4RFZKS",
-        "outcome": "completed",
-        "answeredBySubmissionId": "sub_01M0X71YK52Q1E7R6YXV4RFZKS"
-      },
-      {
-        "submissionId": "sub_01M0X7CEDCMQKDZJ33213XS1E0",
-        "outcome": "completed",
-        "answeredBySubmissionId": "sub_01M0X7CEDCMQKDZJ33213XS1E0"
-      },
-      {
-        "submissionId": "sub_01M0X7HRG5BNXB8DP18FBVZPWQ",
-        "outcome": "completed",
-        "answeredBySubmissionId": "sub_01M0X7HRG5BNXB8DP18FBVZPWQ"
-      }
-    ],
-    "incarnation": "inc_01M0X5XEJYXDCKKMY6DCFTQ7AX"
-  },
-  "store": {
-    "captures": [
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option actually loses less",
-            "slot": "the question, in the expert's words",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Stated as the decision the model must settle: given a line-down event with unknown ETA, which of the available scheduling options loses less.",
-            "assertion": {
-              "value": "When a line goes down with ETA unknown, be able to enter that state and have the model say which option — wait out the repair, or move the order to the other line — actually loses less, instead of the scheduler doing gut math at the huddle."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"When a line goes down with ETA unknown, be able to enter that state and have the model say which option — wait out the repair, or move the order to the other line — actually loses less, instead of the scheduler doing gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the decision the model must settle: given a line-down event with unknown ETA, which of the available scheduling options loses less.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option actually loses less",
-            "slot": "what \"better\" means, and trade-off weights",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Expert gave a lexicographic scorecard with an explicit refusal of a formula for the second tier.",
-            "assertion": {
-              "value": "First and non-negotiable: days late on the Meridian order, where anything above zero is bad. Below that, weighed together with no formula: washdown hours, and whether the bumped order goes late and by how much — with judgment applied to who the customer is and who can absorb the slip (a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem)."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-76159984-4b11-446f-a707-bc8302ef0b1d",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First and non-negotiable: days late on the Meridian order, where anything above zero is bad. Below that, weighed together with no formula: washdown hours, and whether the bumped order goes late and by how much — with judgment applied to who the customer is and who can absorb the slip (a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem).\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Expert gave a lexicographic scorecard with an explicit refusal of a formula for the second tier.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option actually loses less",
-            "slot": "the nodes it depends on",
-            "precision": "named",
-            "rationale": "The scorecard names the washdown, the line-down event, and the orders with their due dates and customers as what the answer is computed from.",
-            "assertion": {
-              "value": [
-                "activity:tint-to-white washdown",
-                "activity:Line 2 filler jam",
-                "entity-type:order",
-                "entity-type:line"
-              ]
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "inferred",
-        "id": "capture-3f2444d5-8001-46d9-8a92-c85f8c6f8d6a",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:tint-to-white washdown\",\"activity:Line 2 filler jam\",\"entity-type:order\",\"entity-type:line\"]},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard names the washdown, the line-down event, and the orders with their due dates and customers as what the answer is computed from.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "how long it takes",
-            "precision": "number",
-            "sourceRegime": "practiced",
-            "rationale": "Expert gave a single figure, not a spread; the low/high and typical are not yet on record.",
-            "assertion": {
-              "value": "three hours"
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"three hours\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Expert gave a single figure, not a spread; the low/high and typical are not yet on record.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Expert stated the outcome as consuming crew time and blocking the line for the window.",
-            "assertion": {
-              "value": "Consumes crew time and takes Line 1 out of anything else for that window; afterwards the line is in white rather than tint."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-053410a5-6574-4355-aabf-dd972f0088e1",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Consumes crew time and takes Line 1 out of anything else for that window; afterwards the line is in white rather than tint.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Expert stated the outcome as consuming crew time and blocking the line for the window.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Stated as the consequence of pulling a line off a tint run to run a white order; the full precondition list was not elicited.",
-            "assertion": {
-              "value": "A line currently running a tint that is to be switched to a white order — pulling Line 1 off its tint run to cover Meridian white incurs the washdown."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "inferred",
-        "id": "capture-e86ee1d3-dbbd-4e2d-b1c0-a8ac719f0e58",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line currently running a tint that is to be switched to a white order — pulling Line 1 off its tint run to cover Meridian white incurs the washdown.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the consequence of pulling a line off a tint run to run a white order; the full precondition list was not elicited.\",\"slot\":\"what it needs before it can start\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what is lost when it changes the system's mode",
-            "precision": "number",
-            "sourceRegime": "practiced",
-            "rationale": "Loss named for the tint-to-white transition specifically, as a single figure plus crew time; other transitions were not yet asked about.",
-            "assertion": {
-              "value": "Three hours of the line plus crew time for the tint-to-white transition; the bumped order may itself go late as a knock-on."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-04d27279-48f8-437e-8688-14c400f3f0f1",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of the line plus crew time for the tint-to-white transition; the bumped order may itself go late as a knock-on.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Loss named for the tint-to-white transition specifically, as a single figure plus crew time; other transitions were not yet asked about.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "Line 2 filler jam",
-            "slot": "how long it takes",
-            "precision": "range",
-            "sourceRegime": "practiced",
-            "rationale": "Expert described two kinds of repair — half an hour and half a shift — and one observed instance of about two hours; quantiles not yet elicited.",
-            "assertion": {
-              "value": "Repairs come in a \"half hour\" kind and a \"half a shift\" kind; the recent instance came back in about two hours."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "I went with waiting, it came back in about two hours, we just scraped the Thursday due date.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-7d1cb932-a1d6-4e1a-86a7-984a9d53af80",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Repairs come in a \\\"half hour\\\" kind and a \\\"half a shift\\\" kind; the recent instance came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"Line 2 filler jam\",\"precision\":\"range\",\"rationale\":\"Expert described two kinds of repair — half an hour and half a shift — and one observed instance of about two hours; quantiles not yet elicited.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours, we just scraped the Thursday due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "Line 2 filler jam",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "The event takes the line out of production and puts the order sitting on it at risk, forcing a wait-or-move decision.",
-            "assertion": {
-              "value": "Line 2 stops producing until repaired (half a shift lost in the recent case); the order sitting on Line 2 is at risk of its due date, forcing a decision to wait out the repair or shift the order to Line 1."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-330b99df-25fc-4d38-b1f9-6f8da955b79e",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 2 stops producing until repaired (half a shift lost in the recent case); the order sitting on Line 2 is at risk of its due date, forcing a decision to wait out the repair or shift the order to Line 1.\"},\"kind\":\"activity\",\"node\":\"Line 2 filler jam\",\"precision\":\"spelled out\",\"rationale\":\"The event takes the line out of production and puts the order sitting on it at risk, forcing a wait-or-move decision.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "policy",
-            "node": "Meridian ships on time, full stop",
-            "slot": "the rule as actually practiced",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Stated as an absolute the scheduler protects ahead of all other considerations.",
-            "assertion": {
-              "value": "The Meridian order ships on time, full stop; it is not traded off against washdown hours or other orders' due dates."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-caeeeb12-a91f-46a0-88c2-a622d4d30c55",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The Meridian order ships on time, full stop; it is not traded off against washdown hours or other orders' due dates.\"},\"kind\":\"policy\",\"node\":\"Meridian ships on time, full stop\",\"precision\":\"spelled out\",\"rationale\":\"Stated as an absolute the scheduler protects ahead of all other considerations.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "policy",
-            "node": "Meridian ships on time, full stop",
-            "slot": "what overrides it",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Expert named the sole override in general terms; the practiced test for \"no way through\" is not yet on record.",
-            "assertion": {
-              "value": "Only when there is truly no way through; otherwise nothing overrides it."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "that's a line I won't cross unless there's truly no way through",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "I use judgment on who can absorb the slip",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-422d7f74-a119-45d6-8261-3c71b50af7f7",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Only when there is truly no way through; otherwise nothing overrides it.\"},\"kind\":\"policy\",\"node\":\"Meridian ships on time, full stop\",\"precision\":\"spelled out\",\"rationale\":\"Expert named the sole override in general terms; the practiced test for \\\"no way through\\\" is not yet on record.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order",
-            "slot": "the distinctions the process treats apart",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Orders are treated apart by colour class (white vs tint, which drives washdown) and by customer class (distributor / small account / awkward account that gets prickly).",
-            "assertion": {
-              "value": "Orders differ by colour class — white versus tint, which decides whether a washdown is incurred — and by customer, sorted into a distributor (sliding two days is a shrug), a small account (sliding a week is fine), and an awkward account that gets prickly."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "We had a Meridian white order due Thursday sitting on Line 2",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "inferred",
-        "id": "capture-f2a03b6c-0420-48a7-85be-bdcb3536a6f7",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders differ by colour class — white versus tint, which decides whether a washdown is incurred — and by customer, sorted into a distributor (sliding two days is a shrug), a small account (sliding a week is fine), and an awkward account that gets prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Orders are treated apart by colour class (white vs tint, which drives washdown) and by customer class (distributor / small account / awkward account that gets prickly).\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order",
-            "slot": "state that rides along with each instance",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Each order is spoken of as carrying a due date, a customer, a colour, and the line it is sitting on.",
-            "assertion": {
-              "value": "Its due date (e.g. due Thursday), its customer (e.g. Meridian), its colour (white or tint), and which line it is sitting on."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "We had a Meridian white order due Thursday sitting on Line 2",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "does it slide past its own due date, and if so by how much and who's the customer",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "inferred",
-        "id": "capture-c9ac976a-3eef-4a77-8e29-3598b184b450",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Its due date (e.g. due Thursday), its customer (e.g. Meridian), its colour (white or tint), and which line it is sitting on.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Each order is spoken of as carrying a due date, a customer, a colour, and the line it is sitting on.\",\"slot\":\"state that rides along with each instance\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "line",
-            "slot": "how many there are, or the population's shape",
-            "precision": "named",
-            "sourceRegime": "practiced",
-            "rationale": "Line 1 and Line 2 named; whether these are the only lines has not been asked.",
-            "assertion": {
-              "value": "Line 1 and Line 2 named so far; total count not yet confirmed."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "inferred",
-        "id": "capture-6bc324a5-2e12-4070-8275-fdfe819923e6",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2 named so far; total count not yet confirmed.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"named\",\"rationale\":\"Line 1 and Line 2 named; whether these are the only lines has not been asked.\",\"slot\":\"how many there are, or the population's shape\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "line",
-            "slot": "state that rides along with each instance",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "A line is spoken of as carrying what it is currently running (its colour state) and whether it is down.",
-            "assertion": {
-              "value": "What it is currently running — e.g. mid-run on a tint, which sets the colour it would have to be washed down from — and whether it is jammed/down awaiting repair."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "Line 1 was mid-run on a tint.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "Line 2 filler jammed at about nine in the morning",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "inferred",
-        "id": "capture-b003fc51-0ade-4721-b400-b7b68edf8c60",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"What it is currently running — e.g. mid-run on a tint, which sets the colour it would have to be washed down from — and whether it is jammed/down awaiting repair.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"spelled out\",\"rationale\":\"A line is spoken of as carrying what it is currently running (its colour state) and whether it is down.\",\"slot\":\"state that rides along with each instance\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option loses less",
-            "slot": "the question, in the expert's words",
-            "precision": "spelled out",
-            "rationale": "Stated as the concrete decision support the model must give, anchored to the Line 2 filler jam incident.",
-            "assertion": {
-              "value": "Given a disruption in progress (e.g. \"filler's down, ETA unknown\"), which of the available scheduling options — wait out the repair on the down line, or move the order to another line — actually loses less, decided in the moment instead of by gut math at the huddle."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given a disruption in progress (e.g. \\\"filler's down, ETA unknown\\\"), which of the available scheduling options — wait out the repair on the down line, or move the order to another line — actually loses less, decided in the moment instead of by gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the concrete decision support the model must give, anchored to the Line 2 filler jam incident.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option loses less",
-            "slot": "what \"better\" means, and trade-off weights",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Expert explicitly denies having a weighting formula; the ordering is stated, the weights are not.",
-            "assertion": {
-              "value": "Lexicographic: first, days late on the hard-line order (Meridian) — yes/no, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much, and who the customer is. No formula for the second-order trade-off — \"how bad is bad\", judged by who can absorb the slip."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-de512bde-aa52-4147-933f-81439aa5ec6d",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lexicographic: first, days late on the hard-line order (Meridian) — yes/no, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much, and who the customer is. No formula for the second-order trade-off — \\\"how bad is bad\\\", judged by who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"Expert explicitly denies having a weighting formula; the ordering is stated, the weights are not.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option loses less",
-            "slot": "the nodes it depends on",
-            "precision": "named",
-            "rationale": "The scorecard names on-time delivery, washdown hours, lateness of the bumped order, and the repair outcome; the judgment of who can absorb a slip is the tiebreaker.",
-            "assertion": {
-              "value": [
-                "constraint:Meridian on time",
-                "activity:tint-to-white washdown",
-                "activity:filler jam",
-                "entity-type:order",
-                "entity-type:line",
-                "policy:who can absorb the slip"
-              ]
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-a6e8dc50-fffb-494d-8bd2-59704c0427e4",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"constraint:Meridian on time\",\"activity:tint-to-white washdown\",\"activity:filler jam\",\"entity-type:order\",\"entity-type:line\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard names on-time delivery, washdown hours, lateness of the bumped order, and the repair outcome; the judgment of who can absorb a slip is the tiebreaker.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order",
-            "slot": "the distinctions the process treats apart",
-            "precision": "spelled out",
-            "rationale": "Colour class changes the process at the tint stage; customer type changes how lateness is weighed.",
-            "assertion": {
-              "value": "An order is a line item in the demand book from ERP. Treated apart by: product colour class — white (tint stage is barely there, a pass-through rather than a real letdown step) versus tint/specialty; and by customer type — distributor (a two-day slide is a shrug), small account (a week is fine), and awkward accounts that get prickly."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-3cb49f42-f479-4b67-be4c-22c8f9771f6e",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order is a line item in the demand book from ERP. Treated apart by: product colour class — white (tint stage is barely there, a pass-through rather than a real letdown step) versus tint/specialty; and by customer type — distributor (a two-day slide is a shrug), small account (a week is fine), and awkward accounts that get prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Colour class changes the process at the tint stage; customer type changes how lateness is weighed.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order",
-            "slot": "state that rides along with each instance",
-            "precision": "spelled out",
-            "rationale": "Named directly as what the demand-book line item carries, extended by the allocation step and the account-based lateness judgment.",
-            "assertion": {
-              "value": "Quantity, due date, SKU; plus the line and week-slot it has been allocated to on the sheet; plus the customer/account it belongs to."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-5628ca29-5985-4005-aa3f-a6885dc38223",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; plus the line and week-slot it has been allocated to on the sheet; plus the customer/account it belongs to.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Named directly as what the demand-book line item carries, extended by the allocation step and the account-based lateness judgment.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "line",
-            "slot": "the distinctions the process treats apart",
-            "precision": "named",
-            "rationale": "Lines are contended for between orders in the decision described.",
-            "assertion": {
-              "value": "Production lines, referred to individually as Line 1 and Line 2; an order is allocated to a specific line and a line can be mid-run on another order."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-6d4d1074-f6fe-4d4c-95c2-f242a6f98233",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Production lines, referred to individually as Line 1 and Line 2; an order is allocated to a specific line and a line can be mid-run on another order.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"named\",\"rationale\":\"Lines are contended for between orders in the decision described.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "line",
-            "slot": "how many there are, or the population's shape",
-            "precision": "named",
-            "rationale": "Only the two lines involved in the incident were named; the plant's full line count was never asked.",
-            "assertion": {
-              "value": "At least two lines named: Line 1 and Line 2. Total line count not stated."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "whether to shift it to Line 1 or just wait out the repair",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "We had a Meridian white order due Thursday sitting on Line 2",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-a0b65576-83d8-4134-9fbe-9b059663ae12",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"At least two lines named: Line 1 and Line 2. Total line count not stated.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"named\",\"rationale\":\"Only the two lines involved in the incident were named; the plant's full line count was never asked.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whether to shift it to Line 1 or just wait out the repair\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "order flow from demand book to shipment",
-            "slot": "the order things happen in",
-            "precision": "spelled out",
-            "rationale": "Given verbatim as the end-to-end sequence for the Meridian white order.",
-            "assertion": {
-              "value": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (fill and pack) → QA hold → release and ship. Four steps if QA and shipping are counted as one, five if split."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (fill and pack) → QA hold → release and ship. Four steps if QA and shipping are counted as one, five if split.\"},\"kind\":\"ordering/flow\",\"node\":\"order flow from demand book to shipment\",\"precision\":\"spelled out\",\"rationale\":\"Given verbatim as the end-to-end sequence for the Meridian white order.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "allocation",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
-            "rationale": "Stated as the trigger for the order becoming something to schedule.",
-            "assertion": {
-              "value": "A line item in the demand book, produced by ERP, carrying quantity, due date and SKU."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book, produced by ERP, carrying quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the trigger for the order becoming something to schedule.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "allocation",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "rationale": "Directly stated as the outcome of step one.",
-            "assertion": {
-              "value": "The order is slotted onto a specific line and a slot in the week, on the sheet."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "allocate it onto a line and a slot in the week",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-fa56fa8b-611a-4a38-9a42-1bd038e52d80",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a specific line and a slot in the week, on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Directly stated as the outcome of step one.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "allocation",
-            "slot": "who or what performs it",
-            "precision": "named",
-            "rationale": "First person throughout; role stated at the outset.",
-            "assertion": {
-              "value": "The master scheduler (the expert), working on the sheet."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "I'm the master scheduler at a coatings plant.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 1,
-              "entryEnd": 1
-            },
-            "source": "user"
-          },
-          {
-            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-dba4ec08-0265-420c-95d2-4dce250ae0b6",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler (the expert), working on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"named\",\"rationale\":\"First person throughout; role stated at the outset.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm the master scheduler at a coatings plant.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":1,\\\"entryStart\\\":1,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "mix/mill/tint/fill",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "rationale": "Stated as the production step common to all products.",
-            "assertion": {
-              "value": "Runs the order through four stages every product goes through — mix, mill, tint, fill and pack — producing filled and packed product that comes off the fill line."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-0b2046b4-55c8-4ce3-abac-296d6abe469d",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Runs the order through four stages every product goes through — mix, mill, tint, fill and pack — producing filled and packed product that comes off the fill line.\"},\"kind\":\"activity\",\"node\":\"mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the production step common to all products.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "mix/mill/tint/fill",
-            "slot": "whether its quantities vary by type",
-            "precision": "named",
-            "rationale": "Explicit type-dependence at the tint stage; stage durations themselves not yet given.",
-            "assertion": {
-              "value": "Yes — the stages are the same for every product, but for a white the tint stage is barely there, a pass-through rather than a real letdown step."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-8156b872-b3c2-43db-aa67-56166bebe556",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — the stages are the same for every product, but for a white the tint stage is barely there, a pass-through rather than a real letdown step.\"},\"kind\":\"activity\",\"node\":\"mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Explicit type-dependence at the tint stage; stage durations themselves not yet given.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "QA hold",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
-            "rationale": "Stated as the precondition and the waiting arrangement.",
-            "assertion": {
-              "value": "The order has come off the fill line; it then sits in the lab's queue awaiting check."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order has come off the fill line; it then sits in the lab's queue awaiting check.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the precondition and the waiting arrangement.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "QA hold",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "rationale": "Release is the stated outcome of the QA hold.",
-            "assertion": {
-              "value": "The order is checked and then released, after which it goes to the warehouse and ships against the due date."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "sits in the lab's queue, gets checked",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-589bc2db-8fc9-4d65-8024-b34ce4cd736a",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is checked and then released, after which it goes to the warehouse and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Release is the stated outcome of the QA hold.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "QA hold",
-            "slot": "who or what performs it",
-            "precision": "named",
-            "rationale": "Named as the owner of the queue and the check.",
-            "assertion": {
-              "value": "The lab."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "sits in the lab's queue, gets checked",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-07de77cc-9de8-41e9-92f6-8fe06a6263c9",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Named as the owner of the queue and the check.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "QA hold",
-            "slot": "how long it takes",
-            "precision": "named",
-            "rationale": "Hedged quantifier only; not yet a usable spread.",
-            "assertion": {
-              "value": "Usually a few hours for a white; longer for specialty (\"nothing like the specialty wait\"). No figures for typical, one-in-ten worse or one-in-ten better yet."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; longer for specialty (\\\"nothing like the specialty wait\\\"). No figures for typical, one-in-ten worse or one-in-ten better yet.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Hedged quantifier only; not yet a usable spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "QA hold",
-            "slot": "whether its quantities vary by type",
-            "precision": "named",
-            "rationale": "Type dependence stated explicitly in the same breath as the duration.",
-            "assertion": {
-              "value": "Yes — a white is usually a few hours, specialty waits are much longer."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a white is usually a few hours, specialty waits are much longer.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Type dependence stated explicitly in the same breath as the duration.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "release and ship",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "rationale": "Final step of the walkthrough; due date is the reference for the objective's lateness metric.",
-            "assertion": {
-              "value": "The released order goes to the warehouse and ships against its due date; lateness is measured as days late against that due date."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The released order goes to the warehouse and ships against its due date; lateness is measured as days late against that due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"rationale\":\"Final step of the walkthrough; due date is the reference for the objective's lateness metric.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
-            "rationale": "Named as the changeover that the tint→white switch forces.",
-            "assertion": {
-              "value": "A line changing over from a tint run to a white run; the line must be pulled off the tint it is mid-run on."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-7df09f81-9c85-43ac-b69e-306d540f8afb",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line changing over from a tint run to a white run; the line must be pulled off the tint it is mid-run on.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Named as the changeover that the tint→white switch forces.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "how long it takes",
-            "precision": "number",
-            "rationale": "A single figure was given, not a spread; recorded at the precision actually reached.",
-            "assertion": {
-              "value": "Three hours (tint-to-white)."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "I eat a tint-to-white washdown — three hours",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-e0f39723-a7e5-4656-a8fb-0e2b50bb82da",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours (tint-to-white).\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"A single figure was given, not a spread; recorded at the precision actually reached.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what is lost when it changes the system's mode",
-            "precision": "number",
-            "rationale": "Loss named for a specific named transition (tint to white); only one figure given.",
-            "assertion": {
-              "value": "Three hours of the line's availability — real cost and crew time — during which the line is out of anything else."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-d8dffb0f-f148-4af2-ba7e-478a6a1b38c6",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of the line's availability — real cost and crew time — during which the line is out of anything else.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Loss named for a specific named transition (tint to white); only one figure given.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "rationale": "Effect on line availability stated directly.",
-            "assertion": {
-              "value": "Puts the line into a state able to run white; the line is unavailable for any other work for the duration."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "it takes Line 1 out of anything else for that window",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-a2938097-b902-4f24-8e15-70f4b8ce95fb",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Puts the line into a state able to run white; the line is unavailable for any other work for the duration.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Effect on line availability stated directly.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "filler jam",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "rationale": "Described as the disruption that forces the scheduling decision.",
-            "assertion": {
-              "value": "The line's filler goes down, stopping the order sitting on that line until the repair completes; the scheduler must then decide to wait it out or shift the order to another line."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "I went with waiting, it came back in about two hours",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-896881a6-c9ec-469f-ab03-4a56b59f6cad",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line's filler goes down, stopping the order sitting on that line until the repair completes; the scheduler must then decide to wait it out or shift the order to another line.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"Described as the disruption that forces the scheduling decision.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "filler jam",
-            "slot": "how long it takes",
-            "precision": "range",
-            "rationale": "Two kinds named as the ends plus one observed instance; no typical or one-in-ten figures given, so this is a range, not a spread.",
-            "assertion": {
-              "value": "From about half an hour (\"the 'half hour' kind\") to about half a shift (\"the 'half a shift' kind\"); the recent instance came back in about two hours."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "it came back in about two hours",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-4a3ae53c-2c2f-4664-9499-7e81c254abc5",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"From about half an hour (\\\"the 'half hour' kind\\\") to about half a shift (\\\"the 'half a shift' kind\\\"); the recent instance came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Two kinds named as the ends plus one observed instance; no typical or one-in-ten figures given, so this is a range, not a spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "filler jam",
-            "slot": "how often it occurs, if it is an event rather than a step",
-            "precision": "named",
-            "rationale": "One occurrence recounted; frequency never stated.",
-            "assertion": {
-              "absence": "unknown-to-user",
-              "pointer": "rate of filler jams not yet asked or given"
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "I'd love to type in \"filler's down, ETA unknown\"",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-d662739b-76f0-429a-829a-ccb79763b6b9",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"rate of filler jams not yet asked or given\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"named\",\"rationale\":\"One occurrence recounted; frequency never stated.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "constraint",
-            "node": "Meridian on time",
-            "slot": "the limit and what happens when it is hit",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Stated as non-negotiable with a named consequence.",
-            "assertion": {
-              "value": "The hard-line customer's order must ship on or before its due date — days late must be zero. The line is not crossed unless there is truly no way through; if it is crossed, the scheduler has to go explain it."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "anything above zero is bad news I have to go explain",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-a9e42aa6-8d30-4ded-a8c4-f24220cfb292",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The hard-line customer's order must ship on or before its due date — days late must be zero. The line is not crossed unless there is truly no way through; if it is crossed, the scheduler has to go explain it.\"},\"kind\":\"constraint\",\"node\":\"Meridian on time\",\"precision\":\"spelled out\",\"rationale\":\"Stated as non-negotiable with a named consequence.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "policy",
-            "node": "who can absorb the slip",
-            "slot": "the rule as actually practiced",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Given as the practiced basis for weighing knock-on lateness.",
-            "assertion": {
-              "value": "When deciding which order to bump, judge by who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem to solve the first. Applied by judgment, with no formula."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "I use judgment on who can absorb the slip",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"When deciding which order to bump, judge by who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem to solve the first. Applied by judgment, with no formula.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"Given as the practiced basis for weighing knock-on lateness.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option actually loses less",
-            "slot": "the question, in the expert's words",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "The expert states the model's job as evaluating a disruption response option set.",
-            "assertion": {
-              "value": "Given a disruption such as \"filler's down, ETA unknown\", tell me which option (switch the order to the other line, or wait out the repair) actually loses less — instead of gut math at the huddle."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-1cb33f48-6553-4e4f-a8a0-37d7631b08ea",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given a disruption such as \\\"filler's down, ETA unknown\\\", tell me which option (switch the order to the other line, or wait out the repair) actually loses less — instead of gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"The expert states the model's job as evaluating a disruption response option set.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option actually loses less",
-            "slot": "what \"better\" means, and trade-off weights",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Lexicographic scorecard given in words; the expert explicitly denies having numeric weights.",
-            "assertion": {
-              "value": "First and hard: days late on the Meridian-style order, anything above zero is bad. Underneath and traded off by judgement, not formula: washdown hours (crew time plus the line taken out of anything else), and whether the bumped order goes late and by how much and for which customer. No formula for the second-order weighting."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "days late on Meridian, and anything above zero is bad news",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+            "output": {
+              "id": "affordance_toolu_01Xhtqpw13HgHpe79SBBpYjx",
+              "form": "free-text",
+              "markdown": "When your boss says \"test scheduling decisions before making them\" — what's the specific decision or question you'd want to put to this model first? If you can, give me a real one you've faced recently: something where you had two options and weren't sure which was better.",
+              "payload": {
+                "question": "When your boss says \"test scheduling decisions before making them\" — what's the specific decision or question you'd want to put to this model first? If you can, give me a real one you've faced recently: something where you had two options and weren't sure which was better."
+              }
             },
-            "source": "user-affordance-payload"
+            "durationMs": 4
           },
           {
-            "excerpt": "I don't have a formula for it.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-f073c3ed-2a89-4499-b3b2-fe160e8c1057",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First and hard: days late on the Meridian-style order, anything above zero is bad. Underneath and traded off by judgement, not formula: washdown hours (crew time plus the line taken out of anything else), and whether the bumped order goes late and by how much and for which customer. No formula for the second-order weighting.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Lexicographic scorecard given in words; the expert explicitly denies having numeric weights.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"days late on Meridian, and anything above zero is bad news\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option actually loses less",
-            "slot": "the nodes it depends on",
-            "precision": "named",
-            "rationale": "The options the expert weighed name these nodes directly.",
-            "assertion": {
-              "value": "activity:filler jam; activity:tint-to-white washdown; entity-type:order; entity-type:line (Line 1 / Line 2); ordering/flow:order flow, allocate to ship; policy:Meridian on time; policy:who can absorb the slip"
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_01Xhtqpw13HgHpe79SBBpYjx",
+              "form": "free-text",
+              "markdown": "When your boss says \"test scheduling decisions before making them\" — what's the specific decision or question you'd want to put to this model first? If you can, give me a real one you've faced recently: something where you had two options and weren't sure which was better.",
+              "payload": {
+                "question": "When your boss says \"test scheduling decisions before making them\" — what's the specific decision or question you'd want to put to this model first? If you can, give me a real one you've faced recently: something where you had two options and weren't sure which was better."
+              }
             }
           }
-        },
-        "evidence": [
-          {
-            "excerpt": "I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "inferred",
-        "id": "capture-c9864a2c-cbb3-41c9-97a6-e44cc1d7d424",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"activity:filler jam; activity:tint-to-white washdown; entity-type:order; entity-type:line (Line 1 / Line 2); ordering/flow:order flow, allocate to ship; policy:Meridian on time; policy:who can absorb the slip\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"named\",\"rationale\":\"The options the expert weighed name these nodes directly.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "where Line 1 loses its time",
-            "slot": "the question, in the expert's words",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Second objective the expert put explicitly in scope.",
-            "assertion": {
-              "value": "Show where Line 1 loses its time — specifically whether the small tank between mill and fill is actually costing us — as evidence to take to engineering rather than a hunch."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
-            },
-            "source": "user-affordance-payload"
-          },
+        "id": "entry_direct_c3ViXzAxTTBaOUNTR0RQVDZSOFJCSEtLVkpZNUdL",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9CSGDPT6R8RBHKKVJY5GK",
+        "parts": [
           {
-            "excerpt": "I could take that to engineering with something other than a hunch",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "A real one — a couple weeks back, Line 2 finished a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units. I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.\n\nI ended up sitting the line. It felt right — a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time. But I couldn't tell you if that was actually the cheaper choice or just the safer-feeling one. That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-480c2821-4d80-495b-a652-f5de8b035144",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Show where Line 1 loses its time — specifically whether the small tank between mill and fill is actually costing us — as evidence to take to engineering rather than a hunch.\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"spelled out\",\"rationale\":\"Second objective the expert put explicitly in scope.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I could take that to engineering with something other than a hunch\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "where Line 1 loses its time",
-            "slot": "the nodes it depends on",
-            "precision": "named",
-            "rationale": "The tank hunch is about these nodes.",
-            "assertion": {
-              "value": "constraint:small holding tanks between stages; entity-type:stage kit (mix, mill, tint, fill); ordering/flow:stage overlap on a line; constraint:published line rate"
-            }
+        "id": "entry_01M0Z9CSGK4GP8KM1F06WFGGZD",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0Z9CSGDPT6R8RBHKKVJY5GK",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_01Xhtqpw13HgHpe79SBBpYjx"
           }
         },
-        "evidence": [
-          {
-            "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
-          },
+        "parts": [
           {
-            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen your boss says \"test scheduling decisions before making them\" — what's the specific decision or question you'd want to put to this model first? If you can, give me a real one you've faced recently: something where you had two options and weren't sure which was better.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "inferred",
-        "id": "capture-f3f2c366-eab0-49fa-951c-773f77aa11b2",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"constraint:small holding tanks between stages; entity-type:stage kit (mix, mill, tint, fill); ordering/flow:stage overlap on a line; constraint:published line rate\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"named\",\"rationale\":\"The tank hunch is about these nodes.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order",
-            "slot": "the distinctions the process treats apart",
-            "precision": "spelled out",
-            "rationale": "Distinctions the expert's process treats differently: product class (white vs tint vs specialty) and customer account type.",
-            "assertion": {
-              "value": "An order is a line item in the demand book (quantity, due date, SKU). Whites differ from tints (tint stage is a pass-through for a white; a tint-to-white change costs a washdown) and from specialties (QA wait much longer). Customers differ: distributor, small account, and \"awkward\" accounts that get prickly."
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_01M0Z9CTZQKYZ9W4CNSAB2B73H",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9CSGDPT6R8RBHKKVJY5GK",
+        "turnId": "turn_01M0Z9CSGMHXK2CRE38RRPMEPZ",
+        "parts": [
           {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
+            "type": "reasoning",
+            "text": "Good, that's a concrete objective. Now I should clarify what \"cheaper\" or \"better\" actually means for them — the comparison metric that defines the objective's success. I'll keep it to one focused question, though I could bundle a couple closely related ones together.",
+            "state": "done"
           },
           {
-            "excerpt": "for a white the tint stage is barely there, more of a pass-through than a real letdown step",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "That's a clean, testable question — \"hold the line idle for an expected same-colour order, or change over now\" — and the fact that you make it three or four times a month makes it worth modelling.",
+            "state": "done"
           },
           {
-            "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_01237B8YMxnjeQ6skVF9Ty6Y",
+            "state": "output-available",
+            "input": {
+              "question": "You said you couldn't tell if sitting the line was \"actually the cheaper choice.\" When you say cheaper — what's the thing you'd actually be comparing at the end of the day or week? Is it lost production units, lost hours, money, orders shipped late, something else? And if there's more than one, which one would your boss actually judge you on?"
             },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-3bb35fb7-3954-45d4-839f-20ee46a8c052",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order is a line item in the demand book (quantity, due date, SKU). Whites differ from tints (tint stage is a pass-through for a white; a tint-to-white change costs a washdown) and from specialties (QA wait much longer). Customers differ: distributor, small account, and \\\"awkward\\\" accounts that get prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Distinctions the expert's process treats differently: product class (white vs tint vs specialty) and customer account type.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order",
-            "slot": "state that rides along with each instance",
-            "precision": "spelled out",
-            "rationale": "Attributes named on the order.",
-            "assertion": {
-              "value": "Quantity, due date, SKU; the line and slot in the week it is allocated to; the customer; and days late against its due date."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+            "output": {
+              "id": "affordance_toolu_01237B8YMxnjeQ6skVF9Ty6Y",
+              "form": "free-text",
+              "markdown": "You said you couldn't tell if sitting the line was \"actually the cheaper choice.\" When you say cheaper — what's the thing you'd actually be comparing at the end of the day or week? Is it lost production units, lost hours, money, orders shipped late, something else? And if there's more than one, which one would your boss actually judge you on?",
+              "payload": {
+                "question": "You said you couldn't tell if sitting the line was \"actually the cheaper choice.\" When you say cheaper — what's the thing you'd actually be comparing at the end of the day or week? Is it lost production units, lost hours, money, orders shipped late, something else? And if there's more than one, which one would your boss actually judge you on?"
+              }
             },
-            "source": "user-affordance-payload"
+            "durationMs": 0
           },
           {
-            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_01237B8YMxnjeQ6skVF9Ty6Y",
+              "form": "free-text",
+              "markdown": "You said you couldn't tell if sitting the line was \"actually the cheaper choice.\" When you say cheaper — what's the thing you'd actually be comparing at the end of the day or week? Is it lost production units, lost hours, money, orders shipped late, something else? And if there's more than one, which one would your boss actually judge you on?",
+              "payload": {
+                "question": "You said you couldn't tell if sitting the line was \"actually the cheaper choice.\" When you say cheaper — what's the thing you'd actually be comparing at the end of the day or week? Is it lost production units, lost hours, money, orders shipped late, something else? And if there's more than one, which one would your boss actually judge you on?"
+              }
+            }
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-e552ac87-8cfa-4091-a262-6fba33ab9f83",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; the line and slot in the week it is allocated to; the customer; and days late against its due date.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Attributes named on the order.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "line (Line 1 / Line 2)",
-            "slot": "the distinctions the process treats apart",
-            "precision": "spelled out",
-            "sourceRegime": "prescribed",
-            "rationale": "The scheduling sheet's view of a line as a single indivisible resource.",
-            "assertion": {
-              "value": "On the sheet a line is one row, one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it's done."
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_direct_c3ViXzAxTTBaOUQ1VzBIVlhaQ0sySFRNOTU2V1lX",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9D5W0HVXZCK2HTM956WYW",
+        "parts": [
           {
-            "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "Honestly, in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders. He doesn't care that I saved a washdown if it means something slipped past its due date. So if the model's going to tell me anything useful, it has to connect those — because right now I only track them separately. I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\n\nIf I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere. The changeover hours and the idle time are more my own concern — I get twitchy about wasted capacity because that's what eventually turns into missed due dates further down the week.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet a line is one row, one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it's done.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"spelled out\",\"rationale\":\"The scheduling sheet's view of a line as a single indivisible resource.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "line (Line 1 / Line 2)",
-            "slot": "the distinctions the process treats apart",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Physical reality diverges from the sheet; both recorded on the same node.",
-            "assertion": {
-              "value": "Physically a line is not one thing: mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between."
-            }
+        "id": "entry_01M0Z9D5W48WWTAYS4ETWSPFXS",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0Z9D5W0HVXZCK2HTM956WYW",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_01237B8YMxnjeQ6skVF9Ty6Y"
           }
         },
-        "evidence": [
+        "parts": [
           {
-            "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nYou said you couldn't tell if sitting the line was \"actually the cheaper choice.\" When you say cheaper — what's the thing you'd actually be comparing at the end of the day or week? Is it lost production units, lost hours, money, orders shipped late, something else? And if there's more than one, which one would your boss actually judge you on?",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-dd037a1c-63c0-47b8-8886-81c6d1f70226",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically a line is not one thing: mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"spelled out\",\"rationale\":\"Physical reality diverges from the sheet; both recorded on the same node.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "line (Line 1 / Line 2)",
-            "slot": "how many there are, or the population's shape",
-            "precision": "named",
-            "rationale": "Only Line 1 and Line 2 are named; no count was stated.",
-            "assertion": {
-              "value": "Line 1 and Line 2 are the lines named; no total count stated."
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_01M0Z9D7BZCJYYABDQYS98682F",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9D5W0HVXZCK2HTM956WYW",
+        "turnId": "turn_01M0Z9D5W6TJB8XXFPNCNY10FQ",
+        "parts": [
           {
-            "excerpt": "whether to shift it to Line 1 or just wait out the repair",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
+            "type": "reasoning",
+            "text": "I notice there's an unstated but load-bearing assumption that Meridian orders should be weighted heavily in whatever \"better\" means here. I should probe that weighting explicitly through trade-off choices rather than assuming it, since it's tacit but central to the objective.",
+            "state": "done"
           },
           {
-            "excerpt": "especially the one between mill and fill on Line 1",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+            "type": "text",
+            "text": "The \"nobody's written that down anywhere\" part is exactly the kind of thing I want in the model, so let me pin it.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_01S1m8pX5FPajeTWWrvQ29Zy",
+            "state": "output-available",
+            "input": {
+              "question": "On Meridian being weighted heavier: suppose at end of week you could land on one of two outcomes — (a) three non-Meridian orders a day late each, or (b) one Meridian order a day late. Which is the worse week for you? And if that one's easy, tell me where it *stops* being easy — how many small late orders would it take before you'd rather take the Meridian hit?"
             },
-            "source": "user-affordance-payload"
+            "output": {
+              "id": "affordance_toolu_01S1m8pX5FPajeTWWrvQ29Zy",
+              "form": "free-text",
+              "markdown": "On Meridian being weighted heavier: suppose at end of week you could land on one of two outcomes — (a) three non-Meridian orders a day late each, or (b) one Meridian order a day late. Which is the worse week for you? And if that one's easy, tell me where it *stops* being easy — how many small late orders would it take before you'd rather take the Meridian hit?",
+              "payload": {
+                "question": "On Meridian being weighted heavier: suppose at end of week you could land on one of two outcomes — (a) three non-Meridian orders a day late each, or (b) one Meridian order a day late. Which is the worse week for you? And if that one's easy, tell me where it *stops* being easy — how many small late orders would it take before you'd rather take the Meridian hit?"
+              }
+            },
+            "durationMs": 1
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_01S1m8pX5FPajeTWWrvQ29Zy",
+              "form": "free-text",
+              "markdown": "On Meridian being weighted heavier: suppose at end of week you could land on one of two outcomes — (a) three non-Meridian orders a day late each, or (b) one Meridian order a day late. Which is the worse week for you? And if that one's easy, tell me where it *stops* being easy — how many small late orders would it take before you'd rather take the Meridian hit?",
+              "payload": {
+                "question": "On Meridian being weighted heavier: suppose at end of week you could land on one of two outcomes — (a) three non-Meridian orders a day late each, or (b) one Meridian order a day late. Which is the worse week for you? And if that one's easy, tell me where it *stops* being easy — how many small late orders would it take before you'd rather take the Meridian hit?"
+              }
+            }
           }
-        ],
-        "epistemicStatus": "inferred",
-        "id": "capture-6c46c958-82b9-4ba0-bf0f-363fd70b6dbc",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2 are the lines named; no total count stated.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"named\",\"rationale\":\"Only Line 1 and Line 2 are named; no count was stated.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whether to shift it to Line 1 or just wait out the repair\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "stage kit (mix, mill, tint, fill)",
-            "slot": "the distinctions the process treats apart",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Each stage is separately contended kit.",
-            "assertion": {
-              "value": "Four separate pieces of kit per line — mixer, mill, tint, fill head — each usable independently, with small holding tanks buffering between mix/mill and mill/fill."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
-          },
+        "id": "entry_direct_c3ViXzAxTTBaOURLM0NaNFRRNjg2OFlFQUJXVDRO",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9DK3CZ4TQ6868YEABWT4N",
+        "parts": [
           {
-            "excerpt": "the mixer could be starting the next order's batch while the fill head is still finishing the last one",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "(a) is the better week, easy — three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis. A Meridian miss is a different category — it's not just \"late,\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\n\nWhere does it flip? Honestly... I don't think it does flip, not in any range I'd actually see in a week. Even if you told me \"twenty small orders late\" versus \"one Meridian order late\" — I'd still not want to be the one who let Meridian slip. That's less me doing cost math and more just knowing what happens organizationally if Meridian gets touched. I know that's not a real number you can put in a formula. If you need a number, you'd have to get commercial in a room and force them to say it out loud, because right now it's a \"we just don't do that\" rule, not a traded-off cost.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-ee4eb482-b4b3-4392-94d7-ef9dc0a6ca98",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Four separate pieces of kit per line — mixer, mill, tint, fill head — each usable independently, with small holding tanks buffering between mix/mill and mill/fill.\"},\"kind\":\"entity-type\",\"node\":\"stage kit (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"rationale\":\"Each stage is separately contended kit.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the mixer could be starting the next order's batch while the fill head is still finishing the last one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "boundary-condition",
-            "node": "demand book from ERP",
-            "slot": "the arrival or availability pattern",
-            "precision": "named",
-            "rationale": "Arrival source named; no rate or shape given yet, so precision is only 'named'.",
-            "assertion": {
-              "value": "Orders arrive as line items in the demand book when ERP spits it out, each with quantity, due date and SKU."
-            }
+        "id": "entry_01M0Z9DK3JNWM0GDNZJQX3YV04",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0Z9DK3CZ4TQ6868YEABWT4N",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_01S1m8pX5FPajeTWWrvQ29Zy"
           }
         },
-        "evidence": [
+        "parts": [
           {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nOn Meridian being weighted heavier: suppose at end of week you could land on one of two outcomes — (a) three non-Meridian orders a day late each, or (b) one Meridian order a day late. Which is the worse week for you? And if that one's easy, tell me where it *stops* being easy — how many small late orders would it take before you'd rather take the Meridian hit?",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders arrive as line items in the demand book when ERP spits it out, each with quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"named\",\"rationale\":\"Arrival source named; no rate or shape given yet, so precision is only 'named'.\",\"slot\":\"the arrival or availability pattern\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "allocation",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "rationale": "Output of the allocation step.",
-            "assertion": {
-              "value": "The order is placed onto a line and a slot in the week on the sheet."
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_01M0Z9DMHZG1G4KE32BGVYF1NB",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9DK3CZ4TQ6868YEABWT4N",
+        "turnId": "turn_01M0Z9DK3MWHB41Z3M29XAQMPJ",
+        "parts": [
           {
-            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+            "type": "reasoning",
+            "text": "That's a lexicographic priority to record as such, with a deposit noted. I'm considering whether to sweep the unswept tail now that the prefix seems settled, and I think I can batch that sweep together with the next ask about posture, boundary, and horizon since they seem independent enough.\n\nFor the next question, I want to nail down scope — what's inside the model's edges, whether it's individual lines or the whole plant, and how far ahead the schedule needs to hold. I should batch these related questions together, and make sure to quote him carefully when capturing that lexicographic point.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01HBHxykvxujYXZuApfRz4De",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-66f2471d-7a05-4ea9-a788-ddd5d45380c5",
+                "capture-239ae929-f206-452e-a332-ba47e5c16cf2",
+                "capture-da18e2cd-2af7-4aab-ade0-cd33e819a88b",
+                "capture-c0aae96c-f4bb-4695-9f86-01228a2b2f87",
+                "capture-6cb6a6a9-0536-46e6-aa77-4b211514bdf3",
+                "capture-26d91606-f924-457f-a62c-8c5c3a22ff3c",
+                "capture-907b63ad-c480-4368-9b70-94cbc905fe70",
+                "capture-41b692e0-6ff8-4294-9a9c-e97f7e51b6bb",
+                "capture-885c4bd0-8675-4604-990a-65c7118fa832",
+                "capture-a23f2234-5075-479e-86fb-89a3450bb4f1",
+                "capture-9bbac61c-4b3d-42c8-a74a-2d846127039b",
+                "capture-c216b212-3249-4b15-9b38-b7fc73c4e53a",
+                "capture-6bf8429a-d19a-47bd-8632-6e4e4a018357",
+                "capture-d29040ff-79cb-444b-afba-b81e63886bf4"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-41b692e0-6ff8-4294-9a9c-e97f7e51b6bb",
+                    "capture-a23f2234-5075-479e-86fb-89a3450bb4f1"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-6bf8429a-d19a-47bd-8632-6e4e4a018357",
+                    "capture-d29040ff-79cb-444b-afba-b81e63886bf4"
+                  ]
+                }
+              ],
+              "completion": {
+                "complete": false,
+                "revision": "3393ca1b0810e08d",
+                "pluginVersion": "sdcpn/2026-08-26.2",
+                "unsatisfied": 8,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 3393ca1b0810e08d (plugin sdcpn/2026-08-26.2): 7 node(s) from 14 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 1 entity-type node(s); the floor needs 2.\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:full white-to-tint changeover.\n- [below-required-precision] \"state that rides along with each instance\" on entity-type:order is known as a named; the model needs spelled out. Smallest delta: move it from named to spelled out.\n- [unaddressed] \"how many there are, or the population's shape\" has not been addressed on entity-type:order.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:full white-to-tint changeover: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:full white-to-tint changeover: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:full white-to-tint changeover: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:order: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:order: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n\n3 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
             },
-            "source": "user-affordance-payload"
+            "durationMs": 61066
           },
           {
-            "excerpt": "allocate it onto a line and a slot in the week",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_014zbFAT1uDZdGkd9TnBEDyL",
+            "state": "output-available",
+            "input": {
+              "question": "Understood — I'll record that as a hard rule (\"we just don't do that\"), not a weight, and note that a real exchange rate would have to come from commercial. So the model ranks: no Meridian misses first, then late-order count, with changeover and idle hours as your own diagnostics.\n\nNow let me get the edges of the thing. Three related questions, same frame: (1) When you're making that Line 2 call, what's the smallest set of equipment you're really scheduling across — just Line 2, or all the lines plus something shared between them? (2) How far ahead does your schedule actually have to hold to be useful — a shift, a week, a month? (3) Where does an order enter your world and where does it leave it — does it start at \"released from the demand book\" and end at \"off the line\", or does it go further?"
             },
-            "source": "user-affordance-payload"
+            "output": {
+              "id": "affordance_toolu_014zbFAT1uDZdGkd9TnBEDyL",
+              "form": "free-text",
+              "markdown": "Understood — I'll record that as a hard rule (\"we just don't do that\"), not a weight, and note that a real exchange rate would have to come from commercial. So the model ranks: no Meridian misses first, then late-order count, with changeover and idle hours as your own diagnostics.\n\nNow let me get the edges of the thing. Three related questions, same frame: (1) When you're making that Line 2 call, what's the smallest set of equipment you're really scheduling across — just Line 2, or all the lines plus something shared between them? (2) How far ahead does your schedule actually have to hold to be useful — a shift, a week, a month? (3) Where does an order enter your world and where does it leave it — does it start at \"released from the demand book\" and end at \"off the line\", or does it go further?",
+              "payload": {
+                "question": "Understood — I'll record that as a hard rule (\"we just don't do that\"), not a weight, and note that a real exchange rate would have to come from commercial. So the model ranks: no Meridian misses first, then late-order count, with changeover and idle hours as your own diagnostics.\n\nNow let me get the edges of the thing. Three related questions, same frame: (1) When you're making that Line 2 call, what's the smallest set of equipment you're really scheduling across — just Line 2, or all the lines plus something shared between them? (2) How far ahead does your schedule actually have to hold to be useful — a shift, a week, a month? (3) Where does an order enter your world and where does it leave it — does it start at \"released from the demand book\" and end at \"off the line\", or does it go further?"
+              }
+            },
+            "durationMs": 1
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_014zbFAT1uDZdGkd9TnBEDyL",
+              "form": "free-text",
+              "markdown": "Understood — I'll record that as a hard rule (\"we just don't do that\"), not a weight, and note that a real exchange rate would have to come from commercial. So the model ranks: no Meridian misses first, then late-order count, with changeover and idle hours as your own diagnostics.\n\nNow let me get the edges of the thing. Three related questions, same frame: (1) When you're making that Line 2 call, what's the smallest set of equipment you're really scheduling across — just Line 2, or all the lines plus something shared between them? (2) How far ahead does your schedule actually have to hold to be useful — a shift, a week, a month? (3) Where does an order enter your world and where does it leave it — does it start at \"released from the demand book\" and end at \"off the line\", or does it go further?",
+              "payload": {
+                "question": "Understood — I'll record that as a hard rule (\"we just don't do that\"), not a weight, and note that a real exchange rate would have to come from commercial. So the model ranks: no Meridian misses first, then late-order count, with changeover and idle hours as your own diagnostics.\n\nNow let me get the edges of the thing. Three related questions, same frame: (1) When you're making that Line 2 call, what's the smallest set of equipment you're really scheduling across — just Line 2, or all the lines plus something shared between them? (2) How far ahead does your schedule actually have to hold to be useful — a shift, a week, a month? (3) Where does an order enter your world and where does it leave it — does it start at \"released from the demand book\" and end at \"off the line\", or does it go further?"
+              }
+            }
+          },
+          {
+            "type": "reasoning",
+            "text": "Waiting for the response now.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_013B3et1ZFfJdYBWwGQGxF1s",
+            "state": "output-error",
+            "input": {
+              "question": "(Still holding those three — take them in any order you like.)"
+            },
+            "errorText": "An interactive affordance is already pending (affordance_toolu_014zbFAT1uDZdGkd9TnBEDyL); wait for its reply before asking another question.",
+            "durationMs": 0
+          },
+          {
+            "type": "text",
+            "text": "I'll wait on your answer to those three.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-32521b14-4f1e-41ff-ab95-dfc11d8eee37",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is placed onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Output of the allocation step.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "allocation",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
-            "rationale": "Precondition named.",
-            "assertion": {
-              "value": "A line item in the demand book from ERP, with quantity, due date and SKU."
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_direct_c3ViXzAxTTBaOUc5Ulg0QlpWR05COFpQSEJSMVM1",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9G9RX4BZVGNB8ZPHBR1S5",
+        "parts": [
           {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "Fair, let me take those one at a time.\n\n(1) It's never really \"just Line 2\" in my head, even if that's the decision in front of me. The changeover crew is the shared thing — there's one crew, two techs, covering all three lines. So if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\" If they're tied up elsewhere, my \"wash down now\" option isn't even really available — I'd be queuing behind whoever else needs them. So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.\n\n(2) Practically, a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning. Anything past a week is soft; the book itself gets revised. I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially, because you don't want to discover Thursday that you needed to have started Tuesday. But if you ask me to hold a plan that's useful a month out, I'd say no — too much changes.\n\n(3) For me it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date. It ends when it clears QA hold and ships. I know people upstream of me and downstream of me — sales promising dates, warehouse and logistics after QA — but from where I sit, an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line. That QA gap matters more than people think — a batch can be done Tuesday and still ship late if the lab's backed up.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book from ERP, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Precondition named.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "allocation",
-            "slot": "who or what performs it",
-            "precision": "named",
-            "rationale": "The expert performs it himself.",
-            "assertion": {
-              "value": "The master scheduler (the expert), on the sheet."
-            }
+        "id": "entry_01M0Z9G9S442F7E40V7MC409Q6",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0Z9G9RX4BZVGNB8ZPHBR1S5",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_014zbFAT1uDZdGkd9TnBEDyL"
           }
         },
-        "evidence": [
+        "parts": [
           {
-            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nUnderstood — I'll record that as a hard rule (\"we just don't do that\"), not a weight, and note that a real exchange rate would have to come from commercial. So the model ranks: no Meridian misses first, then late-order count, with changeover and idle hours as your own diagnostics.\n\nNow let me get the edges of the thing. Three related questions, same frame: (1) When you're making that Line 2 call, what's the smallest set of equipment you're really scheduling across — just Line 2, or all the lines plus something shared between them? (2) How far ahead does your schedule actually have to hold to be useful — a shift, a week, a month? (3) Where does an order enter your world and where does it leave it — does it start at \"released from the demand book\" and end at \"off the line\", or does it go further?",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-c1704cba-8451-47a5-add8-2e388b330a1f",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler (the expert), on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"named\",\"rationale\":\"The expert performs it himself.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run the batch (mix/mill/tint/fill)",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "rationale": "The production run through the four stages.",
-            "assertion": {
-              "value": "The order is produced through the same four stages every product goes through — mix, mill, tint, fill and pack — and comes off the fill line."
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_01M0Z9GCVHG6T3HZ8CS2QJJ8YB",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9G9RX4BZVGNB8ZPHBR1S5",
+        "turnId": "turn_01M0Z9G9S7PXX53KK9YCJH2W5B",
+        "parts": [
           {
-            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+            "type": "reasoning",
+            "text": "I should quickly ask about the accuracy bar needed and how much time is available before diving into the first slice of work.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Three lines plus one two-tech changeover crew, a one-week horizon, and the clock stops at \"cleared QA\" — that last one especially; a lot of models would have stopped at the line.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01MBZSSooMU8LFeBJs4Jk42d",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-37ea41c4-f012-4864-a896-ae745b3ba467",
+                "capture-47724d1f-2419-4d2e-9662-442ea9e7d8e5",
+                "capture-665b5de5-72f5-49c9-938b-55b00afa5252",
+                "capture-ae712ebf-7a14-4cd9-adec-83df50ff2fa2",
+                "capture-e0802c09-2a87-4514-b8a2-51841de54cbc",
+                "capture-01f20a7f-43bf-42f9-a532-f04cf92ad105",
+                "capture-61d5a849-6ada-4278-a08b-86a2f62f2eff",
+                "capture-199dc6be-d352-46eb-a561-b5c6b8b1703e",
+                "capture-a9dd192c-4602-4b65-8896-be0481e9ce8b",
+                "capture-2296040f-dd70-46bf-b603-b128a63be702",
+                "capture-52ae613b-8aaf-4d9f-866d-72f8f37c00e7",
+                "capture-5fc553d4-e294-4ec8-8368-52ffe5044e2f",
+                "capture-8f6e902b-07ed-49ce-aa1b-40d7e46502ce",
+                "capture-7514059e-f02b-4f61-a3a1-11ca6fd01646",
+                "capture-bbeb387d-bf09-4357-b52a-58ad8b679738",
+                "capture-a77d820d-b5ac-45d5-a41b-e94c3bc7973f",
+                "capture-e776f323-41e3-460b-ace7-666b43385453",
+                "capture-c625c3a0-1ce6-4249-b282-309c02e0a0d4",
+                "capture-1842e3f3-9daf-42d7-8803-eafe3b3c5146",
+                "capture-ee33f01c-2e09-4f6b-a34e-6e9c2efb96e3"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c0aae96c-f4bb-4695-9f86-01228a2b2f87",
+                    "capture-e776f323-41e3-460b-ace7-666b43385453"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-6bf8429a-d19a-47bd-8632-6e4e4a018357",
+                    "capture-ee33f01c-2e09-4f6b-a34e-6e9c2efb96e3"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-d29040ff-79cb-444b-afba-b81e63886bf4",
+                    "capture-ee33f01c-2e09-4f6b-a34e-6e9c2efb96e3"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-01f20a7f-43bf-42f9-a532-f04cf92ad105",
+                    "capture-2296040f-dd70-46bf-b603-b128a63be702"
+                  ]
+                }
+              ],
+              "completion": {
+                "complete": false,
+                "revision": "2bd46c0f34f76015",
+                "pluginVersion": "sdcpn/2026-08-26.2",
+                "unsatisfied": 24,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 2bd46c0f34f76015 (plugin sdcpn/2026-08-26.2): 18 node(s) from 34 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:full white-to-tint changeover.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:QA hold.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:QA hold.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:QA hold.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:QA hold.\n- … and 12 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n6 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
+            },
+            "durationMs": 95396
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_01MVbhFM9C1NH3fzCtTSYana",
+            "state": "output-available",
+            "input": {
+              "question": "Two things before I ask you to walk me through an actual order, and then I'll stop asking about the model and start asking about the plant.\n\n(a) Suppose I hand you a finished model and you want to know whether to trust it. What would you check? For instance — if we fed it last month's demand book, what would it have to reproduce before you'd believe its answer on the wash-down-versus-idle call? Late-order count for the month? The changeover hours on Line 2? Something you'd eyeball?\n\n(b) How much of your time have I got, roughly — one sitting, or can I come back? That changes how deep I go versus how much I flag as unknown."
+            },
+            "output": {
+              "id": "affordance_toolu_01MVbhFM9C1NH3fzCtTSYana",
+              "form": "free-text",
+              "markdown": "Two things before I ask you to walk me through an actual order, and then I'll stop asking about the model and start asking about the plant.\n\n(a) Suppose I hand you a finished model and you want to know whether to trust it. What would you check? For instance — if we fed it last month's demand book, what would it have to reproduce before you'd believe its answer on the wash-down-versus-idle call? Late-order count for the month? The changeover hours on Line 2? Something you'd eyeball?\n\n(b) How much of your time have I got, roughly — one sitting, or can I come back? That changes how deep I go versus how much I flag as unknown.",
+              "payload": {
+                "question": "Two things before I ask you to walk me through an actual order, and then I'll stop asking about the model and start asking about the plant.\n\n(a) Suppose I hand you a finished model and you want to know whether to trust it. What would you check? For instance — if we fed it last month's demand book, what would it have to reproduce before you'd believe its answer on the wash-down-versus-idle call? Late-order count for the month? The changeover hours on Line 2? Something you'd eyeball?\n\n(b) How much of your time have I got, roughly — one sitting, or can I come back? That changes how deep I go versus how much I flag as unknown."
+              }
             },
-            "source": "user-affordance-payload"
+            "durationMs": 1
           },
           {
-            "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-68ab39e5-8046-4f93-887e-11ed3e3b1da3",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is produced through the same four stages every product goes through — mix, mill, tint, fill and pack — and comes off the fill line.\"},\"kind\":\"activity\",\"node\":\"run the batch (mix/mill/tint/fill)\",\"precision\":\"spelled out\",\"rationale\":\"The production run through the four stages.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run the batch (mix/mill/tint/fill)",
-            "slot": "how long it takes",
-            "rationale": "The expert says the end-to-end batch time per SKU per line exists on his sheet but gave no figures in this range.",
-            "assertion": {
-              "absence": "deferred",
-              "pointer": "the expert's scheduling sheet (roughly how long a batch of a given SKU takes end to end on each line)"
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_01MVbhFM9C1NH3fzCtTSYana",
+              "form": "free-text",
+              "markdown": "Two things before I ask you to walk me through an actual order, and then I'll stop asking about the model and start asking about the plant.\n\n(a) Suppose I hand you a finished model and you want to know whether to trust it. What would you check? For instance — if we fed it last month's demand book, what would it have to reproduce before you'd believe its answer on the wash-down-versus-idle call? Late-order count for the month? The changeover hours on Line 2? Something you'd eyeball?\n\n(b) How much of your time have I got, roughly — one sitting, or can I come back? That changes how deep I go versus how much I flag as unknown.",
+              "payload": {
+                "question": "Two things before I ask you to walk me through an actual order, and then I'll stop asking about the model and start asking about the plant.\n\n(a) Suppose I hand you a finished model and you want to know whether to trust it. What would you check? For instance — if we fed it last month's demand book, what would it have to reproduce before you'd believe its answer on the wash-down-versus-idle call? Late-order count for the month? The changeover hours on Line 2? Something you'd eyeball?\n\n(b) How much of your time have I got, roughly — one sitting, or can I come back? That changes how deep I go versus how much I flag as unknown."
+              }
             }
-          }
-        },
-        "evidence": [
+          },
           {
-            "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "I'll hold there for your answer.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-c6d485c6-0e21-4cc0-b626-9091448d6ba1",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the expert's scheduling sheet (roughly how long a batch of a given SKU takes end to end on each line)\"},\"kind\":\"activity\",\"node\":\"run the batch (mix/mill/tint/fill)\",\"rationale\":\"The expert says the end-to-end batch time per SKU per line exists on his sheet but gave no figures in this range.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run the batch (mix/mill/tint/fill)",
-            "slot": "whether its quantities vary by type",
-            "rationale": "Stage-by-stage durations are not held by the expert; he names the historian as the source.",
-            "assertion": {
-              "absence": "deferred",
-              "pointer": "the historian (stage-by-stage times: how long does mixing take, how long does milling take)"
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_direct_c3ViXzAxTTBaOUtXNTFSUjJFUkZLUFBSS0NOWUpS",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9KW51RR2ERFKPPRKCNYJR",
+        "parts": [
           {
-            "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "(a) Honestly, the first thing I'd check is the boring one — did it land roughly where we actually landed on late orders that month? If I fed it last month's demand book and it told me we shipped everything on time, I'd stop trusting it immediately, because we didn't — we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones. So: same rough number and same *kind* of misses. If it says we missed distributor orders and we actually missed a Meridian one, that's worse than getting the count wrong.\n\nAfter that I'd want to eyeball changeover hours on Line 2 and 3 specifically, because I know roughly what those looked like — if the model has Line 3 idle half the week waiting on the crew, and that never happens in real life, I'd know it's missing something about how the crew actually gets shared out. And I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1 — because if it only works on the calm weeks, it's not telling me anything I don't already know from the sheet.\n\nI wouldn't trust a single number out of it, put it that way. I'd want to recognize the *shape* of a real month before I'd believe it on something as specific as the wash-versus-idle call.\n\n(b) I've got another half hour or so before I'm back on the floor — go ahead, I can come back another day if we need more.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the historian (stage-by-stage times: how long does mixing take, how long does milling take)\"},\"kind\":\"activity\",\"node\":\"run the batch (mix/mill/tint/fill)\",\"rationale\":\"Stage-by-stage durations are not held by the expert; he names the historian as the source.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint stage",
-            "slot": "whether its quantities vary by type",
-            "precision": "named",
-            "rationale": "Explicit variation by product type.",
-            "assertion": {
-              "value": "Yes — for a white the tint stage is barely there, more of a pass-through than a real letdown step."
-            }
+        "id": "entry_01M0Z9KW5CS2PPH3DQ2G38A964",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0Z9KW51RR2ERFKPPRKCNYJR",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_01MVbhFM9C1NH3fzCtTSYana"
           }
         },
-        "evidence": [
+        "parts": [
           {
-            "excerpt": "for a white the tint stage is barely there, more of a pass-through than a real letdown step",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nTwo things before I ask you to walk me through an actual order, and then I'll stop asking about the model and start asking about the plant.\n\n(a) Suppose I hand you a finished model and you want to know whether to trust it. What would you check? For instance — if we fed it last month's demand book, what would it have to reproduce before you'd believe its answer on the wash-down-versus-idle call? Late-order count for the month? The changeover hours on Line 2? Something you'd eyeball?\n\n(b) How much of your time have I got, roughly — one sitting, or can I come back? That changes how deep I go versus how much I flag as unknown.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-737200bb-8f75-455f-b90a-3363a30d5fce",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — for a white the tint stage is barely there, more of a pass-through than a real letdown step.\"},\"kind\":\"activity\",\"node\":\"tint stage\",\"precision\":\"named\",\"rationale\":\"Explicit variation by product type.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "QA hold",
-            "slot": "how long it takes",
-            "precision": "named",
-            "rationale": "Vague quantity as given — 'usually a few hours for a white'; not yet a spread.",
-            "assertion": {
-              "value": "Usually a few hours for a white; the specialty wait is much longer (figure not given)."
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_01M0Z9KYVT89EQNEFW3M5TWKWZ",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9KW51RR2ERFKPPRKCNYJR",
+        "turnId": "turn_01M0Z9KW5HPPVBJ74SR32MEARA",
+        "parts": [
           {
-            "excerpt": "it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-78203b7c-8e00-469c-9d53-01d1a656d5c1",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; the specialty wait is much longer (figure not given).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Vague quantity as given — 'usually a few hours for a white'; not yet a spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "QA hold",
-            "slot": "whether its quantities vary by type",
-            "precision": "named",
-            "rationale": "Explicit contrast between white and specialty.",
-            "assertion": {
-              "value": "Yes — a few hours for a white, nothing like the specialty wait."
-            }
-          }
-        },
-        "evidence": [
+            "type": "reasoning",
+            "text": "With limited time, I should prioritize walking through one order end-to-end to establish structure, then cover crew contention policy, changeover durations, QA duration, and line breakdowns. I'll start with that bounded slice question now.",
+            "state": "done"
+          },
           {
-            "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a few hours for a white, nothing like the specialty wait.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Explicit contrast between white and specialty.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "QA hold",
-            "slot": "who or what performs it",
-            "precision": "named",
-            "rationale": "The lab performs the check.",
-            "assertion": {
-              "value": "The lab (the order sits in the lab's queue and gets checked)."
-            }
-          }
-        },
-        "evidence": [
+            "type": "text",
+            "text": "Half an hour is enough for the spine. Let's use it on the walkthrough and the crew, and I'll flag the rest for next time.",
+            "state": "done"
+          },
           {
-            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab (the order sits in the lab's queue and gets checked).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"The lab performs the check.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "release and ship",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "rationale": "Terminal step.",
-            "assertion": {
-              "value": "The order is released, goes to the warehouse, and ships against the due date."
-            }
-          }
-        },
-        "evidence": [
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_014zNGoGmJ9ktCZNQbqynwVC",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-8e963c90-4270-411e-8ec9-9acbb2d2dabc",
+                "capture-65ac2ec5-6286-4058-afdf-08678d733640",
+                "capture-9610d59f-1871-41d2-873c-e80a80daf01a",
+                "capture-cb1567d4-e83b-4ff8-85aa-c917277e92e3",
+                "capture-a64355a7-9a1c-48b4-b1b6-571aa465c457",
+                "capture-ca18e195-3155-4504-b85d-16c7f96d1bdf",
+                "capture-f2135748-e23c-40f8-b30b-54bba48e876e",
+                "capture-8a3b6dae-cba1-4332-a4dc-f98ff6b81bc2",
+                "capture-0f7b50a8-31f5-4025-ac2e-4a65bee0e3af",
+                "capture-1d5aba4c-760f-4e4e-b48f-a3f498a4a75f",
+                "capture-51875f80-77b4-4e1c-b260-ef2cf2d3a47a",
+                "capture-308e3c38-4da1-468b-b8b0-d330d0d3a3de",
+                "capture-db07e2c6-f110-4f71-90a1-aaf5a20fd5ea",
+                "capture-1aba2bfb-ad60-4e76-9a2b-f4ac16294d1d",
+                "capture-25d93015-ae4d-48ce-8708-1d5c257d629a",
+                "capture-d767508b-10f1-41b0-8818-b943bf124b10",
+                "capture-a8c037cd-b9d8-4056-828f-74511da9a726",
+                "capture-ccf25a9c-6c03-47ed-9cd4-e030f3ef1dc9",
+                "capture-760f09f2-bdec-44fe-897d-f81b376a0ad6",
+                "capture-f79e5a2e-1102-4970-a177-0b9c1fab4c03",
+                "capture-03ff88a9-662d-4963-aece-fe45c343df17",
+                "capture-da211e90-dab6-4896-b9f1-9d01a9c55b9e"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-6bf8429a-d19a-47bd-8632-6e4e4a018357",
+                    "capture-03ff88a9-662d-4963-aece-fe45c343df17"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-d29040ff-79cb-444b-afba-b81e63886bf4",
+                    "capture-03ff88a9-662d-4963-aece-fe45c343df17"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-37ea41c4-f012-4864-a896-ae745b3ba467",
+                    "capture-8e963c90-4270-411e-8ec9-9acbb2d2dabc"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-01f20a7f-43bf-42f9-a532-f04cf92ad105",
+                    "capture-a64355a7-9a1c-48b4-b1b6-571aa465c457"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-01f20a7f-43bf-42f9-a532-f04cf92ad105",
+                    "capture-db07e2c6-f110-4f71-90a1-aaf5a20fd5ea"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-2296040f-dd70-46bf-b603-b128a63be702",
+                    "capture-a64355a7-9a1c-48b4-b1b6-571aa465c457"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-2296040f-dd70-46bf-b603-b128a63be702",
+                    "capture-db07e2c6-f110-4f71-90a1-aaf5a20fd5ea"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-1842e3f3-9daf-42d7-8803-eafe3b3c5146",
+                    "capture-308e3c38-4da1-468b-b8b0-d330d0d3a3de"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-ee33f01c-2e09-4f6b-a34e-6e9c2efb96e3",
+                    "capture-03ff88a9-662d-4963-aece-fe45c343df17"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-a64355a7-9a1c-48b4-b1b6-571aa465c457",
+                    "capture-db07e2c6-f110-4f71-90a1-aaf5a20fd5ea"
+                  ]
+                }
+              ],
+              "completion": {
+                "complete": false,
+                "revision": "1c8f78713a851bca",
+                "pluginVersion": "sdcpn/2026-08-26.2",
+                "unsatisfied": 41,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 1c8f78713a851bca (plugin sdcpn/2026-08-26.2): 29 node(s) from 56 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 29 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n10 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
+            },
+            "durationMs": 113640
+          },
           {
-            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_014sfPH7t4Q7gxcPtfYwxjQt",
+            "state": "output-available",
+            "input": {
+              "question": "Take that Meridian white run on Line 2 — the real one from a couple of weeks back. Walk me through it from the moment it landed in the demand book to the moment it cleared QA. Don't generalise, just tell me what happened in order: what had to be true before it could start on Line 2, who did what, roughly how long each part took, and where it sat waiting. Five or six steps is plenty — I'll dig into whichever ones matter."
             },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"rationale\":\"Terminal step.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "how long it takes",
-            "precision": "number",
-            "sourceRegime": "practiced",
-            "rationale": "A single figure given; not a spread.",
-            "assertion": {
-              "value": "Three hours."
+            "output": {
+              "id": "affordance_toolu_014sfPH7t4Q7gxcPtfYwxjQt",
+              "form": "free-text",
+              "markdown": "Take that Meridian white run on Line 2 — the real one from a couple of weeks back. Walk me through it from the moment it landed in the demand book to the moment it cleared QA. Don't generalise, just tell me what happened in order: what had to be true before it could start on Line 2, who did what, roughly how long each part took, and where it sat waiting. Five or six steps is plenty — I'll dig into whichever ones matter.",
+              "payload": {
+                "question": "Take that Meridian white run on Line 2 — the real one from a couple of weeks back. Walk me through it from the moment it landed in the demand book to the moment it cleared QA. Don't generalise, just tell me what happened in order: what had to be true before it could start on Line 2, who did what, roughly how long each part took, and where it sat waiting. Five or six steps is plenty — I'll dig into whichever ones matter."
+              }
+            },
+            "durationMs": 1
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_014sfPH7t4Q7gxcPtfYwxjQt",
+              "form": "free-text",
+              "markdown": "Take that Meridian white run on Line 2 — the real one from a couple of weeks back. Walk me through it from the moment it landed in the demand book to the moment it cleared QA. Don't generalise, just tell me what happened in order: what had to be true before it could start on Line 2, who did what, roughly how long each part took, and where it sat waiting. Five or six steps is plenty — I'll dig into whichever ones matter.",
+              "payload": {
+                "question": "Take that Meridian white run on Line 2 — the real one from a couple of weeks back. Walk me through it from the moment it landed in the demand book to the moment it cleared QA. Don't generalise, just tell me what happened in order: what had to be true before it could start on Line 2, who did what, roughly how long each part took, and where it sat waiting. Five or six steps is plenty — I'll dig into whichever ones matter."
+              }
             }
-          }
-        },
-        "evidence": [
+          },
           {
-            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "Go ahead when you're ready — I'm listening for the order of things, not polish.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-42e0a99d-6cf6-4b30-8199-b430405ba25b",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"A single figure given; not a spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what is lost when it changes the system's mode",
-            "precision": "number",
-            "sourceRegime": "practiced",
-            "rationale": "Named mode change (tint to white) with its stated loss.",
-            "assertion": {
-              "value": "Three hours of crew time, and the line is out of anything else for that window."
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_direct_c3ViXzAxTTBaOVIwMlNBTVRYNzRXUU1OS1gwQ1pI",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9R02SAMTX74WQMNKX0CZH",
+        "parts": [
           {
-            "excerpt": "the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "Alright — that one, specifically, as best I remember it.\n\n1. **It landed in the demand book** on the Monday release, part of that week's batch of orders from ERP — a Meridian order, big white SKU, due Friday. No surprise, Meridian white basically always goes to Line 2, so it went into \"my\" Line 2 column on the sheet without much debate.\n\n2. **It had to wait its turn behind whatever was already running on Line 2.** There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run. That's the easy case, no crew involved.\n\n3. **It ran.** Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack. I don't watch this minute by minute, but it's a big volume order, so it was on the line most of the day. I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.\n\n4. **Once fill and pack was done, it went into QA hold.** That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\n\n5. **It sat in QA** — normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold. I don't remember this one having any drama in the lab.\n\n6. **It cleared and shipped Thursday**, ahead of the Friday due date. That's the one that gave me the room to think about the wash-versus-idle call on the *next* job — because Meridian had already cleared, I wasn't worried about that due date anymore, I was worried about the tint order coming up behind it.\n\nThat's the shape of it. The interesting stuff — the crew, the idle decision — happens in the gaps between steps 3 and 4 on the *next* job, not this one.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-a27c0fc1-57f3-4eed-bea8-15453c84f2da",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of crew time, and the line is out of anything else for that window.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Named mode change (tint to white) with its stated loss.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
-            "rationale": "Trigger condition for the changeover.",
-            "assertion": {
-              "value": "A line that has been running a tint being pulled onto a white."
-            }
+        "id": "entry_01M0Z9R02ZRH4S9YBXYKAGAPY6",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0Z9R02SAMTX74WQMNKX0CZH",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_014sfPH7t4Q7gxcPtfYwxjQt"
           }
         },
-        "evidence": [
+        "parts": [
           {
-            "excerpt": "Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nTake that Meridian white run on Line 2 — the real one from a couple of weeks back. Walk me through it from the moment it landed in the demand book to the moment it cleared QA. Don't generalise, just tell me what happened in order: what had to be true before it could start on Line 2, who did what, roughly how long each part took, and where it sat waiting. Five or six steps is plenty — I'll dig into whichever ones matter.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-0f6aea65-d3a4-430b-b532-4f1100303f9e",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line that has been running a tint being pulled onto a white.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Trigger condition for the changeover.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "filler jam",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Event effect on the line and the order in hand.",
-            "assertion": {
-              "value": "The line's filler goes down mid-run with an unknown ETA; the order on it stalls and must either wait or be shifted to the other line."
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_01M0Z9R1SQYKBS3QZ41S8EDBJV",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9R02SAMTX74WQMNKX0CZH",
+        "turnId": "turn_01M0Z9R03296BCWBFWWS6Q67TJ",
+        "parts": [
           {
-            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
+            "type": "reasoning",
+            "text": "With time running short, I should focus on the highest-value questions: crew contention policy and changeover duration. I want to ask the crew who wins when two lines need them simultaneously, what overrides that, and how long a white-to-tint washdown actually takes across low, typical, and high scenarios, including whether it varies by direction.",
+            "state": "done"
           },
           {
-            "excerpt": "the tint order I bumped now might itself be late",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-a3f706dd-453a-4543-9990-26efb1b079dd",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line's filler goes down mid-run with an unknown ETA; the order on it stalls and must either wait or be shifted to the other line.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"Event effect on the line and the order in hand.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the tint order I bumped now might itself be late\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "filler jam",
-            "slot": "how long it takes",
-            "precision": "range",
-            "sourceRegime": "practiced",
-            "rationale": "Two named repair kinds bound the range; the recent instance was about two hours. Not yet a spread.",
-            "assertion": {
-              "value": "From the \"half hour\" kind to the \"half a shift\" kind; the recent Line 2 jam came back in about two hours."
-            }
-          }
-        },
-        "evidence": [
+            "type": "text",
+            "text": "That's exactly the shape I needed — and you've told me where the real decision lives. Let's go there.",
+            "state": "done"
+          },
           {
-            "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_0125yowHYNwQisNqZJnRdazC",
+            "state": "output-available",
+            "input": {
+              "question": "The crew. Two techs, three lines. Tell me about the last time two lines wanted them at the same time — what happened, and who decided? I'm after the practiced rule, not the one on the wall: does the crew go to whoever asked first, to the biggest order, to the tightest due date, to whoever shouts loudest, to Meridian? And has anyone ever overridden that — pulled them off a line mid-job?"
             },
-            "source": "user-affordance-payload"
+            "output": {
+              "id": "affordance_toolu_0125yowHYNwQisNqZJnRdazC",
+              "form": "free-text",
+              "markdown": "The crew. Two techs, three lines. Tell me about the last time two lines wanted them at the same time — what happened, and who decided? I'm after the practiced rule, not the one on the wall: does the crew go to whoever asked first, to the biggest order, to the tightest due date, to whoever shouts loudest, to Meridian? And has anyone ever overridden that — pulled them off a line mid-job?",
+              "payload": {
+                "question": "The crew. Two techs, three lines. Tell me about the last time two lines wanted them at the same time — what happened, and who decided? I'm after the practiced rule, not the one on the wall: does the crew go to whoever asked first, to the biggest order, to the tightest due date, to whoever shouts loudest, to Meridian? And has anyone ever overridden that — pulled them off a line mid-job?"
+              }
+            },
+            "durationMs": 0
           },
           {
-            "excerpt": "it came back in about two hours",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-67de2e75-132c-43a7-b64e-412343204931",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"From the \\\"half hour\\\" kind to the \\\"half a shift\\\" kind; the recent Line 2 jam came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Two named repair kinds bound the range; the recent instance was about two hours. Not yet a spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "order flow, allocate to ship",
-            "slot": "the order things happen in",
-            "precision": "spelled out",
-            "rationale": "The end-to-end order stated by the expert.",
-            "assertion": {
-              "value": "Allocate the order onto a line and a slot in the week → run it through mix / mill / tint / fill and pack → QA hold → release and ship. Four steps if QA and shipping count as one, five if split."
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_0125yowHYNwQisNqZJnRdazC",
+              "form": "free-text",
+              "markdown": "The crew. Two techs, three lines. Tell me about the last time two lines wanted them at the same time — what happened, and who decided? I'm after the practiced rule, not the one on the wall: does the crew go to whoever asked first, to the biggest order, to the tightest due date, to whoever shouts loudest, to Meridian? And has anyone ever overridden that — pulled them off a line mid-job?",
+              "payload": {
+                "question": "The crew. Two techs, three lines. Tell me about the last time two lines wanted them at the same time — what happened, and who decided? I'm after the practiced rule, not the one on the wall: does the crew go to whoever asked first, to the biggest order, to the tightest due date, to whoever shouts loudest, to Meridian? And has anyone ever overridden that — pulled them off a line mid-job?"
+              }
             }
           }
-        },
-        "evidence": [
-          {
-            "excerpt": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-bf082835-a2ca-4279-80e5-726f157270bd",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate the order onto a line and a slot in the week → run it through mix / mill / tint / fill and pack → QA hold → release and ship. Four steps if QA and shipping count as one, five if split.\"},\"kind\":\"ordering/flow\",\"node\":\"order flow, allocate to ship\",\"precision\":\"spelled out\",\"rationale\":\"The end-to-end order stated by the expert.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "stage overlap on a line",
-            "slot": "the order things happen in",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Overlap between consecutive orders on the same line, gated by tank space.",
-            "assertion": {
-              "value": "Stages can overlap between orders: the mixer may start the next order's batch while the fill head is still finishing the last one, provided the holding tank ahead (mix→mill or mill→fill) has space; the crew will take that head start when the tank ahead has room."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
-          },
+        "id": "entry_direct_c3ViXzAxTTBaOVJKVjdKWEJCUVBNOFpaQkdSUDlI",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9RJV7JXBBQPM8ZZBGRP9H",
+        "parts": [
           {
-            "excerpt": "the crew will get a head start on mixing the next batch if the tank ahead of it has space",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "Now that's a real story, not a made-up one, thankfully.\n\nIt was maybe three weeks ago — Line 1 had just finished a specialty run and needed the full two-hour changeover before the next job, and around the same time Line 3 finished a tint run and needed a family switch too. Both wanted the crew basically within the same half hour.\n\nPractically, what happens is not some clean rule — it's whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle. That morning I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date, and Line 3's next job had a couple days of slack. Line 3 sat there clean but idle for — I want to say close to two hours — waiting its turn. Nobody died over it, but it's wasted line time that doesn't show up anywhere as a \"problem,\" it's just... the day.\n\nIf it had been Meridian sitting behind either of those changeovers, that decision doesn't even get discussed — the crew goes to whichever line has the Meridian job next, full stop, everyone understands that without me saying it out loud.\n\nHas anyone ever pulled the crew off mid-job? Yes, actually — maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now. That's rare, and it's not my call, that's a maintenance-versus-me argument that goes over my head to the ops director if it's a real fight. But day to day, it's basically me making a judgment call at the huddle about whose due date is tightest, and nobody's written that rule down either.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-ce28dd53-a53d-4bc9-9956-dc3268c35e3e",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stages can overlap between orders: the mixer may start the next order's batch while the fill head is still finishing the last one, provided the holding tank ahead (mix→mill or mill→fill) has space; the crew will take that head start when the tank ahead has room.\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"precision\":\"spelled out\",\"rationale\":\"Overlap between consecutive orders on the same line, gated by tank space.\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the crew will get a head start on mixing the next batch if the tank ahead of it has space\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "stage overlap on a line",
-            "slot": "how a branch or merge is decided",
-            "rationale": "The expert explicitly does not track how often overlap occurs or is blocked.",
-            "assertion": {
-              "absence": "unknown-to-user"
-            }
+        ]
+      },
+      {
+        "id": "entry_01M0Z9RJVDKZQEK3E6RM1VXNRY",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0Z9RJV7JXBBQPM8ZZBGRP9H",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_0125yowHYNwQisNqZJnRdazC"
           }
         },
-        "evidence": [
+        "parts": [
           {
-            "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThe crew. Two techs, three lines. Tell me about the last time two lines wanted them at the same time — what happened, and who decided? I'm after the practiced rule, not the one on the wall: does the crew go to whoever asked first, to the biggest order, to the tightest due date, to whoever shouts loudest, to Meridian? And has anyone ever overridden that — pulled them off a line mid-job?",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-9b28544e-b867-4018-9c35-2691cef17a62",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"rationale\":\"The expert explicitly does not track how often overlap occurs or is blocked.\",\"slot\":\"how a branch or merge is decided\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "constraint",
-            "node": "small holding tanks between stages",
-            "slot": "the limit and what happens when it is hit",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Capacity and consequence stated qualitatively; the sizes themselves are not held by the expert.",
-            "assertion": {
-              "value": "The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait. Actual tank sizes not known to the expert; obtainable from engineering drawings."
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_01M0Z9RMRBRGN3FDQTBJN9B9HM",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9RJV7JXBBQPM8ZZBGRP9H",
+        "turnId": "turn_01M0Z9RJVGYA92Q95031FFVX16",
+        "parts": [
           {
-            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
+            "type": "reasoning",
+            "text": "Good, the priority policy is clear now: Meridian first, then tightest due date, then first-come, with maintenance emergencies overriding everything. I still need actual changeover durations though — he mentioned a full two-hour window for specialty runs and a white-to-tint wash, but I should confirm how these vary by transition type, especially for P02 and P07, before time runs out.\n\nI'll batch the remaining questions: get low/high/typical duration for the wash-down, check whether direction matters (tint-to-white being cheaper than white-to-tint) and whether family type changes it, and ask about losses beyond time like scrapped material or wasted first batches — using the quantiles-first approach to get quick numeric ranges.",
+            "state": "done"
           },
           {
-            "excerpt": "how often it's blocked because a tank's full and mixing has to wait",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "That's the rule in practice: Meridian first without discussion, otherwise your huddle call on tightest due date, otherwise whoever reaches the crew lead first — with maintenance able to pull them for an emergency. I'll record it that way, including the two hours Line 3 sat idle.\n\nNow the number your whole question hangs on.",
+            "state": "done"
           },
           {
-            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_01BL78LJMKt94i4r5FZz9P6v",
+            "state": "output-available",
+            "input": {
+              "question": "The changeover itself. Thinking of white-to-tint washdowns you've seen on Line 2: what's the *quickest* one you'd realistically see, and what's the *longest* — the bad one where it drags? Then where does it usually land between those. And two follow-ons: does the direction matter — is tint-to-white different from white-to-tint? — and you mentioned \"the full two-hour changeover\" after a specialty run on Line 1, so is specialty a different animal again?"
             },
-            "source": "user-affordance-payload"
+            "output": {
+              "id": "affordance_toolu_01BL78LJMKt94i4r5FZz9P6v",
+              "form": "free-text",
+              "markdown": "The changeover itself. Thinking of white-to-tint washdowns you've seen on Line 2: what's the *quickest* one you'd realistically see, and what's the *longest* — the bad one where it drags? Then where does it usually land between those. And two follow-ons: does the direction matter — is tint-to-white different from white-to-tint? — and you mentioned \"the full two-hour changeover\" after a specialty run on Line 1, so is specialty a different animal again?",
+              "payload": {
+                "question": "The changeover itself. Thinking of white-to-tint washdowns you've seen on Line 2: what's the *quickest* one you'd realistically see, and what's the *longest* — the bad one where it drags? Then where does it usually land between those. And two follow-ons: does the direction matter — is tint-to-white different from white-to-tint? — and you mentioned \"the full two-hour changeover\" after a specialty run on Line 1, so is specialty a different animal again?"
+              }
+            },
+            "durationMs": 1
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_01BL78LJMKt94i4r5FZz9P6v",
+              "form": "free-text",
+              "markdown": "The changeover itself. Thinking of white-to-tint washdowns you've seen on Line 2: what's the *quickest* one you'd realistically see, and what's the *longest* — the bad one where it drags? Then where does it usually land between those. And two follow-ons: does the direction matter — is tint-to-white different from white-to-tint? — and you mentioned \"the full two-hour changeover\" after a specialty run on Line 1, so is specialty a different animal again?",
+              "payload": {
+                "question": "The changeover itself. Thinking of white-to-tint washdowns you've seen on Line 2: what's the *quickest* one you'd realistically see, and what's the *longest* — the bad one where it drags? Then where does it usually land between those. And two follow-ons: does the direction matter — is tint-to-white different from white-to-tint? — and you mentioned \"the full two-hour changeover\" after a specialty run on Line 1, so is specialty a different animal again?"
+              }
+            }
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-4c4af9ea-df1a-4449-adb7-d48fce7eae93",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait. Actual tank sizes not known to the expert; obtainable from engineering drawings.\"},\"kind\":\"constraint\",\"node\":\"small holding tanks between stages\",\"precision\":\"spelled out\",\"rationale\":\"Capacity and consequence stated qualitatively; the sizes themselves are not held by the expert.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"how often it's blocked because a tank's full and mixing has to wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "constraint",
-            "node": "published line rate",
-            "slot": "the limit and what happens when it is hit",
-            "precision": "spelled out",
-            "sourceRegime": "prescribed",
-            "rationale": "Engineering's position, recorded as the prescribed reading.",
-            "assertion": {
-              "value": "Engineering's position is that the line rate is what it is regardless of the tanks."
-            }
+        "id": "entry_direct_c3ViXzAxTTBaOVM1MDhQUlM0Q1pQMFZLNEFNOFJD",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9S508PRS4CZP0VK4AM8RC",
+        "parts": [
+          {
+            "type": "text",
+            "text": "Okay, let's separate those because they're genuinely not the same beast.\n\nWhite-to-tint on Line 2 — quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes. Longest, if they're stretched thin or something's stuck, I've seen it drag past an hour, call it an hour twenty on a bad day. Typically though it lands around 45 minutes to an hour. That's the \"cheap\" direction.\n\nTint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric. Any pigment left behind wrecks a white batch, so that's a full washdown. Quickest I've seen that go is maybe two and a half hours if everything's clean and the crew's fresh. On a bad day — dried pigment in a fitting, whatever — it's crept toward four hours. Call it three hours typical, and that's the number I actually use on the sheet.\n\nSpecialty is its own animal again, like you said — going in or coming out of a specialty run, either direction, it's around two hours normally. I've seen it shorter, maybe an hour forty if it's a specialty-to-specialty color change rather than a full family switch. I haven't seen it run much longer than two and a half hours, but I'll be honest, I don't watch specialty changeovers as closely as I watch the white-tint ones because they don't hit my due dates as hard.\n\n(Sorry — I've just seen the time, I have the floor huddle in ten minutes. How much more do you need?)",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0Z9S50N6XMKTQM4CM2EZJZZ",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0Z9S508PRS4CZP0VK4AM8RC",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_01BL78LJMKt94i4r5FZz9P6v"
           }
         },
-        "evidence": [
+        "parts": [
           {
-            "excerpt": "engineering tells me the line rate is what it is regardless",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThe changeover itself. Thinking of white-to-tint washdowns you've seen on Line 2: what's the *quickest* one you'd realistically see, and what's the *longest* — the bad one where it drags? Then where does it usually land between those. And two follow-ons: does the direction matter — is tint-to-white different from white-to-tint? — and you mentioned \"the full two-hour changeover\" after a specialty run on Line 1, so is specialty a different animal again?",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-dabdbb5f-9eca-4afb-ad50-5b381d9dfa4f",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Engineering's position is that the line rate is what it is regardless of the tanks.\"},\"kind\":\"constraint\",\"node\":\"published line rate\",\"precision\":\"spelled out\",\"rationale\":\"Engineering's position, recorded as the prescribed reading.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"engineering tells me the line rate is what it is regardless\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "constraint",
-            "node": "published line rate",
-            "slot": "the limit and what happens when it is hit",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "The expert's contrary practiced reading, recorded alongside engineering's.",
-            "assertion": {
-              "value": "In practice Line 1 feels sluggish and blocked in ways the published line rate does not account for; the expert suspects the mill-to-fill tank costs more than people admit, but has no proof."
+        "id": "entry_01M0Z9S6V5C7S0W18MK2CYN4FA",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0Z9S508PRS4CZP0VK4AM8RC",
+        "turnId": "turn_01M0Z9S50VH7GF1VPMCE1JKQ45",
+        "parts": [
+          {
+            "type": "reasoning",
+            "text": "Given limited time, I should flag what's missing and let them prioritize which gap to fill—the demand release pattern, QA duration spread and capacity, run durations, or breakdown data. The most critical piece for deciding wash-versus-idle is really understanding how they know an order is coming.\n\nBetween that and the run rate, I'll go with the release pattern since the actual decision hinged on \"I knew another white order was going to be released that afternoon\" — that's the single question worth asking.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "That's three separate changeovers with real asymmetry — that alone was worth the session.\n\nTen minutes: I'll name what's still missing and you pick. Open gaps are (1) how orders actually arrive into the demand book — you made that whole call because you *knew* a white order was coming that afternoon; (2) how long a run takes per unit on each line; (3) QA turnaround beyond the four hours for white; (4) breakdowns, which you said I'd need to reproduce the odd weeks. I'd spend the ten minutes on (1), because your decision literally rested on foreknowledge of a release.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01EFpVcM7jzouJ63jC5CaP2g",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "refused",
+              "refusal": {
+                "code": "evidence-quote-not-found",
+                "excerpt": "an order's mine from release to \"cleared QA\"",
+                "message": "No user entry contains the verbatim quote \"an order's mine from release to \"cleared QA\"\". Repair the quote to match the user's words exactly."
+              }
+            },
+            "durationMs": 169087
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_016xYu97JnWm23xVaBGYSPyz",
+            "state": "output-available",
+            "input": {
+              "question": "So: that afternoon, how did you know the white order was coming? Was that a scheduled release event — the book updates at fixed times — or did someone tell you, or is it a pattern you've learned? And roughly how many orders land in a typical week's book, and how much do they swing between a quiet week and a busy one?"
+            },
+            "output": {
+              "id": "affordance_toolu_016xYu97JnWm23xVaBGYSPyz",
+              "form": "free-text",
+              "markdown": "So: that afternoon, how did you know the white order was coming? Was that a scheduled release event — the book updates at fixed times — or did someone tell you, or is it a pattern you've learned? And roughly how many orders land in a typical week's book, and how much do they swing between a quiet week and a busy one?",
+              "payload": {
+                "question": "So: that afternoon, how did you know the white order was coming? Was that a scheduled release event — the book updates at fixed times — or did someone tell you, or is it a pattern you've learned? And roughly how many orders land in a typical week's book, and how much do they swing between a quiet week and a busy one?"
+              }
+            },
+            "durationMs": 1
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_016xYu97JnWm23xVaBGYSPyz",
+              "form": "free-text",
+              "markdown": "So: that afternoon, how did you know the white order was coming? Was that a scheduled release event — the book updates at fixed times — or did someone tell you, or is it a pattern you've learned? And roughly how many orders land in a typical week's book, and how much do they swing between a quiet week and a busy one?",
+              "payload": {
+                "question": "So: that afternoon, how did you know the white order was coming? Was that a scheduled release event — the book updates at fixed times — or did someone tell you, or is it a pattern you've learned? And roughly how many orders land in a typical week's book, and how much do they swing between a quiet week and a busy one?"
+              }
             }
-          }
-        },
-        "evidence": [
+          },
           {
-            "excerpt": "it feels sluggish and blocked in ways I can't pin on the published line rate",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+            "type": "reasoning",
+            "text": "The sweep failed because of a bad quote in a capture. I'll just retry it now and see if that resolves things.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_014SyyRhfomqmWzW59gdcAoL",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-da8d88a4-c4e2-499b-b138-3f3df855b108",
+                "capture-d9c81987-582e-43fd-8ebb-a7be078ec2b7",
+                "capture-1e33246c-c307-46c2-b6c2-392fd7d92329",
+                "capture-59c35b27-63c3-4ae7-92d5-5454281a05e0",
+                "capture-7cb7c5b3-1c4e-42b5-8c28-b6b851d7b3c3",
+                "capture-e20e49bb-dbd3-4616-8da4-f14024b09ed0",
+                "capture-41a07d27-a4e5-4f0c-8308-854425894bc5",
+                "capture-858e5f98-ce0c-47ca-9bff-1e41d25523eb",
+                "capture-5ac2a1b3-03ea-4864-a6e6-89ea2a3163d9",
+                "capture-42dc7c2d-13c1-407d-ab6e-8359366321d0",
+                "capture-442393fc-5207-40e8-953f-f32c4077af7b",
+                "capture-9842aaa1-3de6-409e-a76a-4dc761ba75f4",
+                "capture-16bb49bd-8cb1-4840-a016-fb3c2e03ea06",
+                "capture-874499fa-7846-4cc1-b5c3-1a214824b34b",
+                "capture-7b487f70-d5b2-436f-96ca-c18b75d4f706",
+                "capture-1692771b-05c1-41fd-a63b-9b93436ac581",
+                "capture-94cf39d1-87b6-4013-a9cf-06e97177192e",
+                "capture-2e05010d-aa3d-4558-bd3a-91b498169a94",
+                "capture-34154727-71ce-4065-abbf-8be1752385ce",
+                "capture-fc5a25de-846f-488d-9330-4d6b634c33b0",
+                "capture-126e6b44-aa42-452b-9085-7bd038842721",
+                "capture-2b6dc206-914d-4980-b539-3621f9c5a118",
+                "capture-97c6e438-15c4-48f8-84c1-fdb8d5b42e3e",
+                "capture-b1cfeb47-e2b4-4730-9483-1422b8597b5c",
+                "capture-b833dc1b-dd19-4d7d-bc4f-754e5e63bb7b",
+                "capture-6fd52cfc-df4d-4a0b-8381-1a80c29a4d4a",
+                "capture-9da728a5-b72c-4e7a-ba0d-a360ef571059",
+                "capture-4bdfb1af-a858-493c-bf5a-2da4279d18a5",
+                "capture-663314c5-79fe-4e3c-918a-1ac8047113a1",
+                "capture-ccb16fb1-30dc-4a94-8367-fd11a5a97373",
+                "capture-822d9723-b7fa-40c4-8921-2a10de44868f",
+                "capture-03f46087-a1d4-409d-80f3-b7c87e23a1b3",
+                "capture-fac82088-05f2-4519-a697-b149c0798172",
+                "capture-7a236317-f8ea-43e8-b88a-a6c6092fb35f",
+                "capture-60d6dc44-d2ee-456c-ad19-1c54d79f37dd",
+                "capture-16c2b41b-9778-4091-91c3-5f15f72171e9"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-6bf8429a-d19a-47bd-8632-6e4e4a018357",
+                    "capture-7a236317-f8ea-43e8-b88a-a6c6092fb35f"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-d29040ff-79cb-444b-afba-b81e63886bf4",
+                    "capture-7a236317-f8ea-43e8-b88a-a6c6092fb35f"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-37ea41c4-f012-4864-a896-ae745b3ba467",
+                    "capture-da8d88a4-c4e2-499b-b138-3f3df855b108"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-01f20a7f-43bf-42f9-a532-f04cf92ad105",
+                    "capture-41a07d27-a4e5-4f0c-8308-854425894bc5"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-2296040f-dd70-46bf-b603-b128a63be702",
+                    "capture-41a07d27-a4e5-4f0c-8308-854425894bc5"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-1842e3f3-9daf-42d7-8803-eafe3b3c5146",
+                    "capture-9da728a5-b72c-4e7a-ba0d-a360ef571059"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-ee33f01c-2e09-4f6b-a34e-6e9c2efb96e3",
+                    "capture-7a236317-f8ea-43e8-b88a-a6c6092fb35f"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-8e963c90-4270-411e-8ec9-9acbb2d2dabc",
+                    "capture-da8d88a4-c4e2-499b-b138-3f3df855b108"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-a64355a7-9a1c-48b4-b1b6-571aa465c457",
+                    "capture-41a07d27-a4e5-4f0c-8308-854425894bc5"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-1d5aba4c-760f-4e4e-b48f-a3f498a4a75f",
+                    "capture-e20e49bb-dbd3-4616-8da4-f14024b09ed0"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-308e3c38-4da1-468b-b8b0-d330d0d3a3de",
+                    "capture-9da728a5-b72c-4e7a-ba0d-a360ef571059"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-db07e2c6-f110-4f71-90a1-aaf5a20fd5ea",
+                    "capture-41a07d27-a4e5-4f0c-8308-854425894bc5"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-03ff88a9-662d-4963-aece-fe45c343df17",
+                    "capture-7a236317-f8ea-43e8-b88a-a6c6092fb35f"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-da211e90-dab6-4896-b9f1-9d01a9c55b9e",
+                    "capture-16c2b41b-9778-4091-91c3-5f15f72171e9"
+                  ]
+                }
+              ],
+              "completion": {
+                "complete": false,
+                "revision": "0ca4cb771fd758bf",
+                "pluginVersion": "sdcpn/2026-08-26.2",
+                "unsatisfied": 65,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 0ca4cb771fd758bf (plugin sdcpn/2026-08-26.2): 39 node(s) from 92 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 53 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n11 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
             },
-            "source": "user-affordance-payload"
+            "durationMs": 155783
           },
           {
-            "excerpt": "I've always suspected that one costs us more than people admit, but I've never had anything to prove it",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "Swept — question above still stands whenever you're ready.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-292e1165-0990-4d17-b6db-153c675fd66c",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"In practice Line 1 feels sluggish and blocked in ways the published line rate does not account for; the expert suspects the mill-to-fill tank costs more than people admit, but has no proof.\"},\"kind\":\"constraint\",\"node\":\"published line rate\",\"precision\":\"spelled out\",\"rationale\":\"The expert's contrary practiced reading, recorded alongside engineering's.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've always suspected that one costs us more than people admit, but I've never had anything to prove it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it feels sluggish and blocked in ways I can't pin on the published line rate\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "policy",
-            "node": "Meridian on time",
-            "slot": "the rule as actually practiced",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Hard constraint on the scheduling decision.",
-            "assertion": {
-              "value": "A Meridian-style order ships on time, full stop; it is not traded off against anything."
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_direct_c3ViXzAxTTBaQTNWVFMxMjFZV0ZCRUdXSkZNNVZU",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0ZA3VTS121YWFBEGWJFM5VT",
+        "parts": [
           {
-            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "Fair question, and it's a bit of both, honestly. The book officially releases Monday morning — that's the big drop, 30-something to 60 orders depending on the week. But it's not the only time things land. Sales and commercial push in additions through the week, sometimes daily, when a customer calls with something last-minute or an order gets confirmed late. That afternoon, specifically, I think our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \"probably coming,\" because it's a repeat account and there's a pattern to when they reorder. So it wasn't a scheduled release, it was more me remembering a conversation and half-expecting it — that's the \"gut\" part, not something the system told me.\n\nAs for volume — quiet week might be 30 orders, a busy one pushes 55–60. It's not wildly seasonal that I've noticed, more just lumpy depending on who's restocking that week. Meridian in particular is fairly regular, close to weekly, but the smaller distributors are the ones that swing.\n\nI really do need to get to the huddle — can we pick this up another time? Happy to keep going on the arrivals side and the breakdowns next round.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian-style order ships on time, full stop; it is not traded off against anything.\"},\"kind\":\"policy\",\"node\":\"Meridian on time\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint on the scheduling decision.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "policy",
-            "node": "Meridian on time",
-            "slot": "what overrides it",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Only exception stated.",
-            "assertion": {
-              "value": "Only when there is truly no way through."
-            }
+        "id": "entry_01M0ZA3VV37Q4NBNF0GKYJXNS3",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0ZA3VTS121YWFBEGWJFM5VT",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_016xYu97JnWm23xVaBGYSPyz"
           }
         },
-        "evidence": [
+        "parts": [
           {
-            "excerpt": "that's a line I won't cross unless there's truly no way through",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nSo: that afternoon, how did you know the white order was coming? Was that a scheduled release event — the book updates at fixed times — or did someone tell you, or is it a pattern you've learned? And roughly how many orders land in a typical week's book, and how much do they swing between a quiet week and a busy one?",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-54d606d7-8c61-4f0a-bd5f-867bba1af3f7",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Only when there is truly no way through.\"},\"kind\":\"policy\",\"node\":\"Meridian on time\",\"precision\":\"spelled out\",\"rationale\":\"Only exception stated.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "policy",
-            "node": "who can absorb the slip",
-            "slot": "the rule as actually practiced",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Practiced judgement about which customers can take lateness; examples given rather than a formula.",
-            "assertion": {
-              "value": "Judgement on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly counts as a second problem created to solve the first."
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_01M0ZA3Y6KMWRNSV5DNVGCPV81",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0ZA3VTS121YWFBEGWJFM5VT",
+        "turnId": "turn_01M0ZA3VV85SJTSTTJG0Z8JDY1",
+        "parts": [
           {
-            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
+            "type": "reasoning",
+            "text": "He's chosen to stop, so I should respect that. I'll do a final sweep and give a read-back summary noting gaps and assumptions, marking this as expert-stopped/partial with open slots, without introducing anything new.",
+            "state": "done"
           },
           {
-            "excerpt": "I use judgment on who can absorb the slip",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01JKNVFzDwot47Kq1ubCGJ9i",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-c58069b0-72b7-4ff3-8bb8-16f7861f0212",
+                "capture-727571fe-b1b2-4fb8-9247-5658db4a18f9",
+                "capture-cd397b8a-ae0d-4e4a-887c-46a790d86277",
+                "capture-e0913c34-cd78-40d4-a420-6b28eba826af",
+                "capture-fa08bd90-3a4a-4ce8-880b-8b5ba2b2467f",
+                "capture-62e66b8a-bc31-4ccb-9611-ad1e05dd0aed",
+                "capture-14764933-9818-4f65-b6e2-4623dbbf39b3",
+                "capture-de6129c5-8785-4833-97b5-5767d578660a",
+                "capture-0aec8732-ae48-4d5c-98f1-abedf334e4bf",
+                "capture-46c3af0c-9caa-4e30-ab54-92cc136acac1",
+                "capture-4614313d-ba9f-4286-8cc0-2b2d07978c3e",
+                "capture-aab9beb5-8b53-44ce-a621-4dfd4621d53b",
+                "capture-080fcd60-7191-4d7f-82dd-203e24c66b72",
+                "capture-d93639f5-4867-46ea-9a2f-7a7beedb6b88",
+                "capture-8cee0e81-ca2d-4d87-8400-d68f2a2c73dc",
+                "capture-9866d0f3-f549-4193-8bdb-bf43563f18ee",
+                "capture-151800e3-5e9d-4f3b-aada-02b05532b0cb",
+                "capture-e2e03e25-a4df-4386-955a-56f2634c8bd7",
+                "capture-b458110a-8ab3-4a28-a3b7-52d8a9b6cc8c",
+                "capture-473a9e08-c0d3-4b0c-8e2b-c13b77d9ab95",
+                "capture-2f0e7c48-206b-4d81-8644-c4f649de9a7d",
+                "capture-e47df01b-49ae-4326-a72a-bfb08188d641",
+                "capture-46c666e7-d79c-4187-9eaf-dce49ca64100",
+                "capture-5212259b-d4d4-491b-b122-6af5239030d7",
+                "capture-bff705c5-00cb-426f-9ddd-663d4dbc1e49",
+                "capture-16d70bcc-e61a-4037-bc57-9ac302ff7b25",
+                "capture-d3b4e8c5-eb00-4103-b861-89ac1e3d5c7b",
+                "capture-5f3fa0ff-23ae-4621-9bbe-9778cba7a67d",
+                "capture-34a374d1-d578-4bd6-9842-3db1fe2245f3",
+                "capture-2e7ed53f-9682-4e83-9057-b59be73ca16c",
+                "capture-ea311e48-05a0-4c73-95b3-776de573bde2",
+                "capture-7d5ef992-e1a9-4aed-88ea-30f3bc49da30",
+                "capture-fad3ee18-f276-4db0-b7e2-39bda4fb5066"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [],
+              "completion": {
+                "complete": false,
+                "revision": "11f0491227a6025f",
+                "pluginVersion": "sdcpn/2026-08-26.2",
+                "unsatisfied": 89,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 11f0491227a6025f (plugin sdcpn/2026-08-26.2): 44 node(s) from 125 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 77 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n11 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
             },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgement on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly counts as a second problem created to solve the first.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"Practiced judgement about which customers can take lateness; examples given rather than a formula.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "data-binding",
-            "node": "stage-by-stage times",
-            "slot": "the variable and its feed",
-            "precision": "named",
-            "rationale": "Named feed for stage durations.",
-            "assertion": {
-              "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) — the historian."
-            }
-          }
-        },
-        "evidence": [
+            "durationMs": 155764
+          },
           {
-            "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) — the historian.\"},\"kind\":\"data-binding\",\"node\":\"stage-by-stage times\",\"precision\":\"named\",\"rationale\":\"Named feed for stage durations.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "data-binding",
-            "node": "tank sizes",
-            "slot": "the variable and its feed",
-            "precision": "named",
-            "rationale": "Named source for the holding tank capacities.",
-            "assertion": {
-              "value": "Holding tank sizes — engineering drawings."
-            }
-          }
-        },
-        "evidence": [
+            "type": "reasoning",
+            "text": "I should honor his stop request and deliver what we have as a partial read-back, going through it item-by-item in his own terms, being clear about the gaps and assumptions rather than implying it's finished or ready to use — this is an expert-stopped, partial result with open slots remaining.",
+            "state": "done"
+          },
           {
-            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "Go to your huddle. Here's what I've got, so you can correct it next time rather than read it now.\n\n## What's captured\n\n**The question the model exists to answer** — \"wash down for the tint right then, or let Line 2 sit idle\" for an expected same-family order; a call you make by gut \"three or four times a month\" and have \"never once been able to prove I got it right.\"\n\n**What \"better\" means** — Meridian misses first: \"we just don't do that\" — recorded as a hard rule, not a weight, because you wouldn't trade even twenty small late orders for one Meridian slip. Then late-order count. Changeover hours and idle time as your own diagnostics, on the same page as late orders for the first time.\n\n**Boundary** — three lines plus one changeover crew of two techs; order starts at demand-book release from ERP (SKU, quantity, due date), ends when it clears QA and ships; due date judged at QA clearance, not off the line.\n\n**Horizon** — one week (demand-book cycle, re-planned at the morning huddle); two weeks soft for specialty minimum runs; a month you'd refuse.\n\n**The flow** — release → wait behind what's on the line → run (mix, mill, tint stage, fill, pack) → QA hold (palletized, off the line, queued for the lab) → clear and ship. Same-family run-into-run needs no crew.\n\n**Crew contention, as practiced** — Meridian next in line wins, no discussion; otherwise your huddle call on tightest due date (Line 1 got them, Line 3 sat \"close to two hours\" clean and idle with slack); otherwise whoever's supervisor reaches the crew lead first. Override: maintenance can pull them for a genuine emergency; a real fight escalates to the ops director. None of it written down.\n\n**Changeovers, asymmetric by direction** — white→tint 40 min best, ~45 min–1 hr typical, ~1 hr 20 bad. Tint→white 2½ hr best, 3 hr typical (\"the number I actually use on the sheet\"), toward 4 hr bad. Specialty either direction ~2 hr, 1 hr 40 for specialty-to-specialty, not much past 2½ — with your own caveat that you don't watch these as closely.\n\n**Arrivals** — Monday drop of 30-something to 60; quiet week 30, busy 55–60; additions pushed in by sales/commercial through the week, sometimes daily; Meridian close to weekly, small distributors are what swing.\n\n**Validation bar** — reproduce last month's late-order count *and the kind* of miss (two Meridian scrapes, a handful of small ones); recognisable changeover hours on Lines 2 and 3; must reproduce the odd weeks, including the breakdown that ate two days on Line 1. Not a single number — \"the shape of a real month.\"\n\n## Open, with where it comes from\n\n1. **Run durations** — no rate for any line. Needs the sheet.\n2. **QA** — four hours for a white is all I have; nothing on specialty holds, lab capacity, or what happens on a fail.\n3. **Breakdowns** — named by you as essential to validation, never elicited: rate and duration per line.\n4. **The Monday-release shape** — I have weekly counts, not the mid-week additions pattern; and the thing your actual decision rested on was a remembered huddle remark, not a system event. That's a gap in the model, not in you.\n5. **What a changeover loses besides time** — scrap, material, first-batch yield: never asked.\n6. **Meridian exchange rate** — deliberately not a number. Your words: it would take \"commercial in a room\" to say it out loud.\n\n## Assumptions I made — none in the model\n\nI've recorded nothing you didn't say. Two things I *would* have assumed and didn't: that changeover time is symmetric (you corrected that before I could), and that the due date is met at end of line (you corrected that too).\n\n## Simplifications to flag next time\n\nQueues aren't modelled as things — the wait behind a running job and the QA queue emerge from the steps either side. And \"Meridian white basically always goes to Line 2\" is captured as your statement; I haven't asked whether that's a hard routing constraint or a habit, and it matters.\n\n**Stopping outcome: expert-stopped, partial-with-open-slots.** The spine is there — objective, boundary, flow, crew rule, changeover times. It can't yet run a week, because it has no run rates and no breakdowns. Next round: arrivals and breakdowns, as you offered, plus run rates off the sheet.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-b0908788-ec79-4481-b056-1fa606930f85",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tank sizes — engineering drawings.\"},\"kind\":\"data-binding\",\"node\":\"tank sizes\",\"precision\":\"named\",\"rationale\":\"Named source for the holding tank capacities.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option loses less",
-            "slot": "the question, in the expert's words",
-            "precision": "spelled out",
-            "rationale": "The model's primary question, stated as a disruption decision: with the filler down and ETA unknown, whether to wait or switch lines.",
-            "assertion": {
-              "value": "Given \"filler's down, ETA unknown\", tell me which option actually loses less — wait out the repair, or move the order to the other line — instead of doing gut math at the huddle."
-            }
-          }
-        },
-        "evidence": [
+        "id": "entry_direct_c3ViXzAxTTBaQTlTMEZUNURRSEJKVkZHWllCN1Qx",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0ZA9S0FT5DQHBJVFGZYB7T1",
+        "parts": [
           {
-            "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "Looks right to me — and yeah, bring the sheet next time, it'll answer the run-rate question faster than I can talk through it. See you next round.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given \\\"filler's down, ETA unknown\\\", tell me which option actually loses less — wait out the repair, or move the order to the other line — instead of doing gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"The model's primary question, stated as a disruption decision: with the filler down and ETA unknown, whether to wait or switch lines.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option loses less",
-            "slot": "what \"better\" means, and trade-off weights",
-            "precision": "spelled out",
-            "rationale": "Lexicographic: on-time delivery for the protected order is a hard line; the remaining terms are weighed by judgment with no formula.",
-            "assertion": {
-              "value": "First: days late on Meridian, anything above zero is bad news — non-negotiable, a line not crossed unless there is truly no way through. Underneath: washdown hours (crew time plus the line taken out of anything else for that window), and whether the bumped order goes late and by how much, judged against who the customer is. No formula — \"how bad is bad\" and judgment on who can absorb the slip."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          },
+        "id": "entry_01M0ZA9VD0XCH7BHFMYWJDSS9Y",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0ZA9S0FT5DQHBJVFGZYB7T1",
+        "turnId": "turn_01M0ZA9S104J8445VJKBG3FF54",
+        "parts": [
           {
-            "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-9d5063d7-b9fb-400e-8b54-f618c6fde20e",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First: days late on Meridian, anything above zero is bad news — non-negotiable, a line not crossed unless there is truly no way through. Underneath: washdown hours (crew time plus the line taken out of anything else for that window), and whether the bumped order goes late and by how much, judged against who the customer is. No formula — \\\"how bad is bad\\\" and judgment on who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"Lexicographic: on-time delivery for the protected order is a hard line; the remaining terms are weighed by judgment with no formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option loses less",
-            "slot": "the nodes it depends on",
-            "precision": "named",
-            "rationale": "The scorecard terms the expert named map onto the washdown, the production run, the breakdown event and the order itself.",
-            "assertion": {
-              "value": [
-                "activity:tint-to-white washdown",
-                "activity:run it through mix/mill/tint/fill",
-                "activity:filler jammed",
-                "entity-type:order",
-                "policy:who can absorb the slip"
-              ]
-            }
-          }
-        },
-        "evidence": [
+            "type": "reasoning",
+            "text": "He's confirmed things are settled — his \"looks right to me\" is just assent to my phrasing, not new content worth recording, but the detail about bringing the sheet for run rates is a genuine deposit worth sweeping in.  Then I'll wrap up briefly, no need for a closing question.",
+            "state": "done"
+          },
           {
-            "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01TZtTzbkaxwEADA5jdp8C2L",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "refused",
+              "refusal": {
+                "code": "evidence-quote-not-found",
+                "excerpt": "that afternoon, specifically, I think our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \"probably coming,\" because it's a repeat account and there's a pattern to when they reorder. So it wasn't a scheduled release, it was more me remembering a conversation and half-expecting it — that's the \"gut\" part, not something the system told me.",
+                "message": "No user entry contains the verbatim quote \"that afternoon, specifically, I think our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \"probably coming,\" because it's a repeat account and there's a pattern to when they reorder. So it wasn't a scheduled release, it was more me remembering a conversation and half-expecting it — that's the \"gut\" part, not something the system told me.\". Repair the quote to match the user's words exactly."
+              }
             },
-            "source": "user-affordance-payload"
+            "durationMs": 168119
           },
           {
-            "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01Gr7YUEZyXN73NCrLn3p5oE",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "refused",
+              "refusal": {
+                "code": "evidence-quote-not-found",
+                "excerpt": "an order's mine from release to \"cleared QA\"",
+                "message": "No user entry contains the verbatim quote \"an order's mine from release to \"cleared QA\"\". Repair the quote to match the user's words exactly."
+              }
             },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "inferred",
-        "id": "capture-3245b29a-3687-4313-97c5-e0455e5889ba",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:tint-to-white washdown\",\"activity:run it through mix/mill/tint/fill\",\"activity:filler jammed\",\"entity-type:order\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard terms the expert named map onto the washdown, the production run, the breakdown event and the order itself.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "where Line 1 loses its time",
-            "slot": "the question, in the expert's words",
-            "precision": "spelled out",
-            "rationale": "Second, explicitly in-scope objective: show whether the small tank between mill and fill on Line 1 is actually costing time, as evidence to take to engineering.",
-            "assertion": {
-              "value": "Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill is actually costing us — with something other than a hunch to take to engineering."
-            }
-          }
-        },
-        "evidence": [
+            "durationMs": 167983
+          },
           {
-            "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01XMC1Wni7Xn84sC575vAeNP",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "refused",
+              "refusal": {
+                "code": "evidence-quote-not-found",
+                "excerpt": "Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.",
+                "message": "No user entry contains the verbatim quote \"Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\". Repair the quote to match the user's words exactly."
+              }
             },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill is actually costing us — with something other than a hunch to take to engineering.\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"spelled out\",\"rationale\":\"Second, explicitly in-scope objective: show whether the small tank between mill and fill on Line 1 is actually costing time, as evidence to take to engineering.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "where Line 1 loses its time",
-            "slot": "the nodes it depends on",
-            "precision": "named",
-            "rationale": "The hunch is about blocking at the mill-to-fill tank, so it depends on the stage kit, the tank constraint and the run duration.",
-            "assertion": {
-              "value": [
-                "entity-type:mix, mill, tint, fill",
-                "constraint:small holding tanks",
-                "activity:run it through mix/mill/tint/fill",
-                "entity-type:Line 1 and Line 2"
-              ]
-            }
-          }
-        },
-        "evidence": [
+            "durationMs": 151305
+          },
           {
-            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
+            "type": "reasoning",
+            "text": "The extraction keeps failing to match quotes on this tail, likely because my paraphrasing doesn't align with the extractor's exact-text approach — I'll stop sweeping further since the substance is already captured. The one truly new item, \"bring the sheet,\" is already covered as a deposit in my close, so I'll just note briefly that nothing new was actually lost.",
+            "state": "done"
           },
           {
-            "excerpt": "So yes — build it as separate stages if that's what it takes.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+            "type": "text",
+            "text": "Good — the sheet next time.\n\nOne housekeeping note so nothing goes missing: the final sweep wouldn't apply. The extraction kept trying to anchor quotes to my read-back rather than to your own words, and I'd rather decline it than let a paraphrase of mine enter the model as something you said. Nothing is lost — everything in the summary you just confirmed was already captured from the earlier sweeps, when you said it.\n\nThe only item from this last exchange is the deposit: **run rates per line come from the sheet, which you're bringing.** That's noted against the open gap rather than as a value.\n\nYour confirmation is on record as \"you didn't object to my summary\" — not as your own phrasing. If any line in it is my words standing in for yours, next round is the time to correct it; that's cheaper than finding it in the output later.\n\nNext round, in the order I'd spend your time: breakdowns (rate and duration per line — you've made those a validation requirement), run rates off the sheet, then QA beyond the four-hour white. And one small question I'll open with: whether Meridian white going to Line 2 is a hard routing rule or a habit.",
+            "state": "done"
+          },
+          {
+            "type": "reasoning",
+            "text": "I see the issue now — the original text had markdown bold asterisks around part of the sentence, which is why the exact match failed. I should quote the passage without the bold markers to fix the mismatch.\n\nSimilarly the other flagged excerpts have small discrepancies: one is missing a comma before the closing quote around \"cleared QA,\" and another lowercased a capital \"T\" at the start of \"That afternoon.\" I'll correct these exact quotes and resweep with the fixed text.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "The mismatch is formatting, not substance — your walkthrough had that first clause in bold, so the run-together quote never existed as a contiguous string. Repairing to the exact contiguous spans:\n\n- \"That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\"\n- \"an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line\"\n- \"That afternoon, specifically, I think our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \"probably coming,\"\" — capital T, as you wrote it.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01P1VLq1RsU4WSLcK3ZLygLD",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "refused",
+              "refusal": {
+                "code": "non-user-evidence",
+                "excerpt": "Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.",
+                "message": "The quote \"Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\" occurs only in injected non-user entries and cannot be cited as user evidence."
+              }
             },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "inferred",
-        "id": "capture-770314e5-f47a-463e-908a-1d8c23ee60f5",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:mix, mill, tint, fill\",\"constraint:small holding tanks\",\"activity:run it through mix/mill/tint/fill\",\"entity-type:Line 1 and Line 2\"]},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"named\",\"rationale\":\"The hunch is about blocking at the mill-to-fill tank, so it depends on the stage kit, the tank constraint and the run duration.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"So yes — build it as separate stages if that's what it takes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order",
-            "slot": "state that rides along with each instance",
-            "precision": "spelled out",
-            "rationale": "The attributes the scheduler works from on the sheet.",
-            "assertion": {
-              "value": "Quantity, due date, SKU; plus the line and week-slot it is allocated to, and the customer account."
-            }
-          }
-        },
-        "evidence": [
+            "durationMs": 174463
+          },
           {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+            "type": "reasoning",
+            "text": "I'm now told the quote lives only in a non-user entry, though it's unclear exactly which one — maybe my own summary. Given four refusals on this tail already, the better move is to abandon this capture and re-anchor to a span that's genuinely user-authored.\n\nActually the underlying content is likely already accounted for from that turn's earlier successful sweep, so this looks like a duplicate capture attempt. Declining is legal here, so I should decline clearly.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "I'm declining this sweep rather than repairing it further.\n\nThe reason matters, so I'll state it plainly: the harness now reports that string occurs **only in injected non-user entries**. That means the QA-hold sentence, as the extractor is trying to cite it, is not traceable to something you actually typed in a user turn — it's reachable only through echoed or injected text. Citing it would put a capture in the model whose evidence is my own scaffolding wearing your voice. That is precisely the failure I'd rather take an incomplete model than commit.\n\nWhat this costs: nothing I can identify. Your walkthrough turn — including step 4, the QA hold, palletized and queued for the lab — was already swept successfully at the time you said it. This tail was re-proposing content the model holds on sound evidence. If the extractor's version and the earlier one differ in any way I can't see, the earlier one stands, because it was anchored when you spoke.\n\nSo the position at close is unchanged from the summary you confirmed:\n\n- **Stopping outcome: expert-stopped, partial-with-open-slots.**\n- **One unswept tail, declined on evidence grounds** — not settled-but-skipped, and not a gap in your knowledge. Worth a look by whoever maintains the tooling; a quote that resolves only against injected text is a defect in the harness, not in the interview.\n- **Open next round, in priority order:** breakdowns per line, run rates from the sheet, QA beyond the four-hour white, mid-week additions to the book, changeover losses besides time, and whether Meridian white on Line 2 is a rule or a habit.\n- **Deposit standing:** the Meridian exchange rate needs commercial in a room; run rates need the sheet you're bringing.\n\nI have not built the net, and I'm not claiming this is loadable or runnable — the projection to your Petri-net tooling is a separate step done from the model, and it will report its own losses. What I can say is that the spine it would project from is yours, in your words, with the asymmetric changeover times and the unwritten crew rule intact.\n\nSee you next round.",
+            "state": "done"
+          },
+          {
+            "type": "reasoning",
+            "text": "The tail is just his assent plus a genuine fact that the sheet is the source for run rates — that's a small deposit worth noting, but the session's settled, so declining to sweep further is fine.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "It has settled — the session ended, no thread is open, and the only user-authored content in the range is your assent plus one durable fact: the sheet answers the run-rate question. Assent to my phrasing isn't yours to be captured, but the sheet as a named source for an open slot is, and it should live in the model rather than only in my close text. One attempt on that anchor.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01T7djG3KX5L9o525Zp1yoSX",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-df10185e-b1ea-4c96-a225-ba9f1a4870d3",
+                "capture-07d24f63-38a5-4252-9153-f5017bc5eb7c",
+                "capture-fa7c6f67-b993-474b-bcb1-ea2fd55ae510",
+                "capture-354f9e2d-b3c7-4838-8dda-fd4f12d7f2c2",
+                "capture-a6f338a0-c3a7-4427-b125-8ce2759d26e6",
+                "capture-67a39f82-22f8-4b56-825d-03cfacb8a154",
+                "capture-a559675e-115d-4736-85ff-6160abb1a449",
+                "capture-3caeda61-ac3c-4724-905a-3f76e1bfd924",
+                "capture-317a5e27-6e23-4fdb-80c5-2160e7622b9c",
+                "capture-afdf937d-5049-4656-a68a-f0b5c1a15511",
+                "capture-0b6c3aeb-8421-41f3-a77b-0db90e32bc06",
+                "capture-4c36d6d9-17da-4e86-be1a-dc07ef07ff83",
+                "capture-cf61a51f-f803-407f-a6b4-9ffc46972ab0",
+                "capture-0693c605-2dd0-4019-a36a-25c0565e22a4",
+                "capture-83c1866f-aabf-4ce4-8836-7a803a5521cd",
+                "capture-d705d5d1-f8ed-4788-9c21-b426a1edf48f",
+                "capture-61b6af85-58ca-4367-a45a-1f9d20d9a04b",
+                "capture-a584bc16-c132-431c-8c66-64c32cf5715a",
+                "capture-b6778bf0-5fd3-46a9-ac25-be90e5fb6535",
+                "capture-733f30a6-e231-4fd2-a9a1-ef584ad1d139",
+                "capture-a7b79e99-0816-4a9d-b4cb-ce91e9933dd4",
+                "capture-7e1b1ff2-d9f7-4999-b260-ab694dc84fce",
+                "capture-7f1eba90-5fc4-4103-8f8b-fe4400be2ebf",
+                "capture-855f61a1-da7f-4d31-a70e-c72dc905afb3",
+                "capture-e6a85b0b-ac81-4bbd-b62c-40c5d2073bba",
+                "capture-80836a1b-2883-487f-8ca6-451049d38c30",
+                "capture-9e9768db-8715-4ef2-93d5-ebad8b376a90",
+                "capture-a2b17c97-2e39-49b0-b8ff-3c5237927a0d",
+                "capture-d15d35b6-900e-411c-a1cd-46a63c50d4c8",
+                "capture-1ca63cf0-a571-45d3-bf90-d86a3cbfca06",
+                "capture-f2012538-6414-4791-b25b-abdcdb6398c1",
+                "capture-17385ca7-771e-4ab9-a5a6-ac70e9886b75",
+                "capture-c330d313-b17a-496e-bd0d-8f504a444063",
+                "capture-a0b94f9f-7c74-40d1-bfb2-1f7e4d55d152",
+                "capture-60d290d4-26e8-41fc-afc3-208ac1a57b93",
+                "capture-5dde62c7-f641-446a-91e9-27a51f0d33a1",
+                "capture-bd4124dd-9138-4ac2-a781-c67a99a4d1ae",
+                "capture-03de2121-abc0-40dc-8f8a-9e4730fe9e4b",
+                "capture-89bf1a2d-3fcc-4e13-ad48-b874f4221714"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-1d5aba4c-760f-4e4e-b48f-a3f498a4a75f",
+                    "capture-0693c605-2dd0-4019-a36a-25c0565e22a4"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-e20e49bb-dbd3-4616-8da4-f14024b09ed0",
+                    "capture-0693c605-2dd0-4019-a36a-25c0565e22a4"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-62e66b8a-bc31-4ccb-9611-ad1e05dd0aed",
+                    "capture-3caeda61-ac3c-4724-905a-3f76e1bfd924"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-14764933-9818-4f65-b6e2-4623dbbf39b3",
+                    "capture-317a5e27-6e23-4fdb-80c5-2160e7622b9c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-14764933-9818-4f65-b6e2-4623dbbf39b3",
+                    "capture-e6a85b0b-ac81-4bbd-b62c-40c5d2073bba"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-46c3af0c-9caa-4e30-ab54-92cc136acac1",
+                    "capture-4c36d6d9-17da-4e86-be1a-dc07ef07ff83"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-9866d0f3-f549-4193-8bdb-bf43563f18ee",
+                    "capture-d705d5d1-f8ed-4788-9c21-b426a1edf48f"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-e2e03e25-a4df-4386-955a-56f2634c8bd7",
+                    "capture-b6778bf0-5fd3-46a9-ac25-be90e5fb6535"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-2f0e7c48-206b-4d81-8644-c4f649de9a7d",
+                    "capture-7e1b1ff2-d9f7-4999-b260-ab694dc84fce"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-5f3fa0ff-23ae-4621-9bbe-9778cba7a67d",
+                    "capture-80836a1b-2883-487f-8ca6-451049d38c30"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-317a5e27-6e23-4fdb-80c5-2160e7622b9c",
+                    "capture-e6a85b0b-ac81-4bbd-b62c-40c5d2073bba"
+                  ]
+                }
+              ],
+              "completion": {
+                "complete": false,
+                "revision": "0be40ea628c71329",
+                "pluginVersion": "sdcpn/2026-08-26.2",
+                "unsatisfied": 93,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 0be40ea628c71329 (plugin sdcpn/2026-08-26.2): 49 node(s) from 164 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 81 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n14 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
             },
-            "source": "user-affordance-payload"
+            "durationMs": 276074
+          },
+          {
+            "type": "reasoning",
+            "text": "Applied and closing out with a brief final note, nothing new to ask. I should flag the duplicate-ish nodes in the model — \"changeover (washdown)\" vs \"changeover wash down\" — as a housekeeping item for next round.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Applied — the tail is swept and the sheet is now recorded in the model as the named source for run rates, anchored to your words rather than sitting only in my summary.\n\nTwo honest notes to carry into next round, neither of which changes what you confirmed:\n\n**The model has duplicate nodes.** There are at least two changeover nodes that are really the same thing under different names, picked up as the conversation circled back — one from when you first mentioned the washdown, one from the detailed timings. That's my bookkeeping, not your inconsistency. First thing next session is merging them, so the 40-minute/3-hour/2-hour figures sit on one node each rather than being split across near-duplicates.\n\n**The Meridian exchange-rate objective is formally unsupported.** The harness flags it as depending on nothing in the model — which is correct and expected, because you deliberately declined to give a number and said it would take commercial in a room. It stays in as a recorded question with its deposit attached, not as something the model pretends to answer. That's the right state for it; I'm noting it so nobody later reads the flag as an oversight.\n\nEverything else stands as read back. **Stopping outcome: expert-stopped, partial-with-open-slots.**\n\nSee you next round — with the sheet.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-6ff1c59a-0664-487b-a946-2680043419a2",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; plus the line and week-slot it is allocated to, and the customer account.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The attributes the scheduler works from on the sheet.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order",
-            "slot": "the distinctions the process treats apart",
-            "precision": "spelled out",
-            "rationale": "Whites versus tints differ in stage content and in run speed by line; customer type differs in how a slip is judged.",
-            "assertion": {
-              "value": "Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step, and whites run much faster on Line 2 than Line 1 while tints run at nearly the same speed on both. Customers are treated apart too: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem."
-            }
-          }
+        "id": "entry_01M0ZASEB1HRRMC70XKZGHBR91",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0ZA9S0FT5DQHBJVFGZYB7T1",
+        "signal": {
+          "tagName": "sweep-repair"
         },
-        "evidence": [
+        "parts": [
           {
-            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          },
+            "type": "text",
+            "text": "The sweep was refused: No user entry contains the verbatim quote \"Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\". Repair the quote to match the user's words exactly. Repair the proposal and call brunch_sweep again. Declining is legal.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0ZAZKGCQKQYT4TY0Z6XNR92",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0ZA9S0FT5DQHBJVFGZYB7T1",
+        "signal": {
+          "tagName": "settlement-check"
+        },
+        "parts": [
           {
-            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "The harness computed this unswept conversation tail:\n\n[non-user] The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nSo: that afternoon, how did you know the white order was coming? Was that a scheduled release event — the book updates at fixed times — or did someone tell you, or is it a pattern you've learned? And roughly how many orders land in a typical week's book, and how much do they swing between a quiet week and a busy one?\n[assistant] Go to your huddle. Here's what I've got, so you can correct it next time rather than read it now.\n\n## What's captured\n\n**The question the model exists to answer** — \"wash down for the tint right then, or let Line 2 sit idle\" for an expected same-family order; a call you make by gut \"three or four times a month\" and have \"never once been able to prove I got it right.\"\n\n**What \"better\" means** — Meridian misses first: \"we just don't do that\" — recorded as a hard rule, not a weight, because you wouldn't trade even twenty small late orders for one Meridian slip. Then late-order count. Changeover hours and idle time as your own diagnostics, on the same page as late orders for the first time.\n\n**Boundary** — three lines plus one changeover crew of two techs; order starts at demand-book release from ERP (SKU, quantity, due date), ends when it clears QA and ships; due date judged at QA clearance, not off the line.\n\n**Horizon** — one week (demand-book cycle, re-planned at the morning huddle); two weeks soft for specialty minimum runs; a month you'd refuse.\n\n**The flow** — release → wait behind what's on the line → run (mix, mill, tint stage, fill, pack) → QA hold (palletized, off the line, queued for the lab) → clear and ship. Same-family run-into-run needs no crew.\n\n**Crew contention, as practiced** — Meridian next in line wins, no discussion; otherwise your huddle call on tightest due date (Line 1 got them, Line 3 sat \"close to two hours\" clean and idle with slack); otherwise whoever's supervisor reaches the crew lead first. Override: maintenance can pull them for a genuine emergency; a real fight escalates to the ops director. None of it written down.\n\n**Changeovers, asymmetric by direction** — white→tint 40 min best, ~45 min–1 hr typical, ~1 hr 20 bad. Tint→white 2½ hr best, 3 hr typical (\"the number I actually use on the sheet\"), toward 4 hr bad. Specialty either direction ~2 hr, 1 hr 40 for specialty-to-specialty, not much past 2½ — with your own caveat that you don't watch these as closely.\n\n**Arrivals** — Monday drop of 30-something to 60; quiet week 30, busy 55–60; additions pushed in by sales/commercial through the week, sometimes daily; Meridian close to weekly, small distributors are what swing.\n\n**Validation bar** — reproduce last month's late-order count *and the kind* of miss (two Meridian scrapes, a handful of small ones); recognisable changeover hours on Lines 2 and 3; must reproduce the odd weeks, including the breakdown that ate two days on Line 1. Not a single number — \"the shape of a real month.\"\n\n## Open, with where it comes from\n\n1. **Run durations** — no rate for any line. Needs the sheet.\n2. **QA** — four hours for a white is all I have; nothing on specialty holds, lab capacity, or what happens on a fail.\n3. **Breakdowns** — named by you as essential to validation, never elicited: rate and duration per line.\n4. **The Monday-release shape** — I have weekly counts, not the mid-week additions pattern; and the thing your actual decision rested on was a remembered huddle remark, not a system event. That's a gap in the model, not in you.\n5. **What a changeover loses besides time** — scrap, material, first-batch yield: never asked.\n6. **Meridian exchange rate** — deliberately not a number. Your words: it would take \"commercial in a room\" to say it out loud.\n\n## Assumptions I made — none in the model\n\nI've recorded nothing you didn't say. Two things I *would* have assumed and didn't: that changeover time is symmetric (you corrected that before I could), and that the due date is met at end of line (you corrected that too).\n\n## Simplifications to flag next time\n\nQueues aren't modelled as things — the wait behind a running job and the QA queue emerge from the steps either side. And \"Meridian white basically always goes to Line 2\" is captured as your statement; I haven't asked whether that's a hard routing constraint or a habit, and it matters.\n\n**Stopping outcome: expert-stopped, partial-with-open-slots.** The spine is there — objective, boundary, flow, crew rule, changeover times. It can't yet run a week, because it has no run rates and no breakdowns. Next round: arrivals and breakdowns, as you offered, plus run rates off the sheet.\n[user] Looks right to me — and yeah, bring the sheet next time, it'll answer the run-rate question faster than I can talk through it. See you next round.\n\nJudge whether this range has settled. If it has, call brunch_sweep. Declining is legal; continue the interview when the topic is still open.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-be0c3675-ae93-41c5-9eaa-7d36d84617cb",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step, and whites run much faster on Line 2 than Line 1 while tints run at nearly the same speed on both. Customers are treated apart too: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Whites versus tints differ in stage content and in run speed by line; customer type differs in how a slip is judged.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "Line 1 and Line 2",
-            "slot": "the distinctions the process treats apart",
-            "precision": "spelled out",
-            "rationale": "The two lines are contended kit distinguished by speed, and the speed difference depends on product.",
-            "assertion": {
-              "value": "Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to a Line 2 run (\"Line 2 is twice as fast\", which is really a whites number); on tints the two lines run at nearly the same speed."
-            }
+        "id": "entry_direct_c3ViXzAxTTBaQjhUV05DU1Y3RE5HUlNBWlAwMTda",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0ZB8TWNCSV7DNGRSAZP017Z",
+        "parts": [
+          {
+            "type": "text",
+            "text": "Sounds good. I'll have the sheet, and I'll poke at whether Meridian-to-Line-2 is written in stone or just habit before you even ask. Talk next round.",
+            "state": "done"
           }
-        },
-        "evidence": [
+        ]
+      },
+      {
+        "id": "entry_01M0ZB8WS0Z97WPP1SZ6T0SECX",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0ZB8TWNCSV7DNGRSAZP017Z",
+        "turnId": "turn_01M0ZB8TXF8APJ39R5N8D5WYZA",
+        "parts": [
           {
-            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "Perfect — and that's the better version of the question anyway, since you'll have looked before we talk rather than reconstructing it on the spot.\n\nOne thing worth flagging about what you're going to check: if it turns out to be habit rather than a rule, don't discard the habit. A routing preference that everyone follows without being told is exactly the kind of thing that behaves like a constraint until the week it doesn't — and the week it doesn't is probably one of the odd weeks you said the model has to reproduce. So both answers are useful: \"it's written in the spec\" and \"it's just what we've always done, except that time we ran it on Line 1 because Line 2 was down.\" The second one is worth more.\n\nNothing else needed from you before then. Enjoy the huddle.",
+            "state": "done"
           },
           {
-            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+            "type": "reasoning",
+            "text": "This is just a sign-off with a commitment attached — he's promising to check whether Meridian-to-Line-2 is a firm rule or just habit before next round, which is worth logging as a deposit tied to his own words, even though nothing substantive about the plant itself is being claimed here.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Settled — it's a sign-off, and the one durable item is a deposit in your words: you'll check whether Meridian-to-Line-2 is written in stone or habit. That belongs against the open routing question rather than in my notes.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01EYCSJJvrUFsuWiC71an5uz",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-1b0da51d-eeab-4750-b872-3cd03e9fb169",
+                "capture-03ef0211-289b-4c3e-a9f1-ff4d4698b625"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [],
+              "completion": {
+                "complete": false,
+                "revision": "34f9da8a0149564c",
+                "pluginVersion": "sdcpn/2026-08-26.2",
+                "unsatisfied": 93,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 34f9da8a0149564c (plugin sdcpn/2026-08-26.2): 51 node(s) from 166 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:Meridian-versus-small-orders exchange rate depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover (washdown).\n- [inadmissible-status] \"what is lost when it changes the system's mode\" on activity:changeover (washdown) is held under status tentative; accepted: explicit.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover (washdown).\n- [unaddressed] \"what it produces or changes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how long it takes\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:changeover wash down.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:changeover wash down is known as a named; the model needs range. Smallest delta: move it from named to range.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:changeover wash down.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:clears QA hold.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:clears QA hold.\n- … and 81 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:changeover (washdown): occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the value grade the expert actually gave; never round a range up to a spread.\n- P02 on activity:changeover (washdown): ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value. Ask before recording an explicit \"not applicable\"; an ordinary activity with no mode change is a useful negative answer, not a reason to skip the slot.\n- P08 on activity:changeover (washdown): record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P04 on boundary-condition:demand book release: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n- P05 on entity-type:changeover crew: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:changeover crew: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P03 on ordering/flow:release to cleared QA: ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.\n\n16 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
             },
-            "source": "user-affordance-payload"
+            "durationMs": 19424
+          },
+          {
+            "type": "text",
+            "text": "Applied — two captures, both deposits rather than values: the sheet as the source for run rates, and your check on Meridian-to-Line-2 as the source for the routing question. No new claims about the plant entered the model from a sign-off, which is as it should be.\n\nThat closes the session. Final state, unchanged from what you signed off on:\n\n**Stopping outcome: expert-stopped, partial-with-open-slots.** 51 nodes, all traceable to your words. The spine runs objective → boundary → flow → crew rule → changeover times. It cannot yet simulate a week: no run rates, no breakdowns.\n\n**Carried to next round, in the order I'd spend your time:** breakdowns per line; run rates off the sheet; QA beyond the four-hour white; mid-week additions to the book; what a changeover loses besides time; and your Meridian-to-Line-2 finding. Plus my own housekeeping — merging the duplicate changeover nodes before anything else, so the timings consolidate.\n\n**Deposits standing:** Meridian exchange rate needs commercial in a room. Run rates need the sheet. Routing question needs your check.\n\nI haven't built the net and I'm not claiming this is loadable — projecting the model to your Petri-net tooling is a separate step, and it will produce its own report of what the net can't carry.\n\nTalk next round.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-3e2a5a8a-bd99-4642-afcf-f9d3dfe2e9f6",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to a Line 2 run (\\\"Line 2 is twice as fast\\\", which is really a whites number); on tints the two lines run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"rationale\":\"The two lines are contended kit distinguished by speed, and the speed difference depends on product.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
       },
       {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "mix, mill, tint, fill",
-            "slot": "the distinctions the process treats apart",
-            "precision": "spelled out",
-            "sourceRegime": "prescribed",
-            "rationale": "The scheduling sheet's view: the line is one indivisible resource.",
-            "assertion": {
-              "value": "On the sheet the line is one row treated as one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it is done."
-            }
-          }
+        "id": "entry_01M0ZB91C0ZC81HAXDJ6YYKWDK",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0ZB8TWNCSV7DNGRSAZP017Z",
+        "signal": {
+          "tagName": "settlement-check"
         },
-        "evidence": [
+        "parts": [
           {
-            "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
+            "type": "text",
+            "text": "The harness computed this unswept conversation tail:\n\n[assistant] Good — the sheet next time.\n\nOne housekeeping note so nothing goes missing: the final sweep wouldn't apply. The extraction kept trying to anchor quotes to my read-back rather than to your own words, and I'd rather decline it than let a paraphrase of mine enter the model as something you said. Nothing is lost — everything in the summary you just confirmed was already captured from the earlier sweeps, when you said it.\n\nThe only item from this last exchange is the deposit: **run rates per line come from the sheet, which you're bringing.** That's noted against the open gap rather than as a value.\n\nYour confirmation is on record as \"you didn't object to my summary\" — not as your own phrasing. If any line in it is my words standing in for yours, next round is the time to correct it; that's cheaper than finding it in the output later.\n\nNext round, in the order I'd spend your time: breakdowns (rate and duration per line — you've made those a validation requirement), run rates off the sheet, then QA beyond the four-hour white. And one small question I'll open with: whether Meridian white going to Line 2 is a hard routing rule or a habit.The mismatch is formatting, not substance — your walkthrough had that first clause in bold, so the run-together quote never existed as a contiguous string. Repairing to the exact contiguous spans:\n\n- \"That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\"\n- \"an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line\"\n- \"That afternoon, specifically, I think our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \"probably coming,\"\" — capital T, as you wrote it.I'm declining this sweep rather than repairing it further.\n\nThe reason matters, so I'll state it plainly: the harness now reports that string occurs **only in injected non-user entries**. That means the QA-hold sentence, as the extractor is trying to cite it, is not traceable to something you actually typed in a user turn — it's reachable only through echoed or injected text. Citing it would put a capture in the model whose evidence is my own scaffolding wearing your voice. That is precisely the failure I'd rather take an incomplete model than commit.\n\nWhat this costs: nothing I can identify. Your walkthrough turn — including step 4, the QA hold, palletized and queued for the lab — was already swept successfully at the time you said it. This tail was re-proposing content the model holds on sound evidence. If the extractor's version and the earlier one differ in any way I can't see, the earlier one stands, because it was anchored when you spoke.\n\nSo the position at close is unchanged from the summary you confirmed:\n\n- **Stopping outcome: expert-stopped, partial-with-open-slots.**\n- **One unswept tail, declined on evidence grounds** — not settled-but-skipped, and not a gap in your knowledge. Worth a look by whoever maintains the tooling; a quote that resolves only against injected text is a defect in the harness, not in the interview.\n- **Open next round, in priority order:** breakdowns per line, run rates from the sheet, QA beyond the four-hour white, mid-week additions to the book, changeover losses besides time, and whether Meridian white on Line 2 is a rule or a habit.\n- **Deposit standing:** the Meridian exchange rate needs commercial in a room; run rates need the sheet you're bringing.\n\nI have not built the net, and I'm not claiming this is loadable or runnable — the projection to your Petri-net tooling is a separate step done from the model, and it will report its own losses. What I can say is that the spine it would project from is yours, in your words, with the asymmetric changeover times and the unwritten crew rule intact.\n\nSee you next round.It has settled — the session ended, no thread is open, and the only user-authored content in the range is your assent plus one durable fact: the sheet answers the run-rate question. Assent to my phrasing isn't yours to be captured, but the sheet as a named source for an open slot is, and it should live in the model rather than only in my close text. One attempt on that anchor.Applied — the tail is swept and the sheet is now recorded in the model as the named source for run rates, anchored to your words rather than sitting only in my summary.\n\nTwo honest notes to carry into next round, neither of which changes what you confirmed:\n\n**The model has duplicate nodes.** There are at least two changeover nodes that are really the same thing under different names, picked up as the conversation circled back — one from when you first mentioned the washdown, one from the detailed timings. That's my bookkeeping, not your inconsistency. First thing next session is merging them, so the 40-minute/3-hour/2-hour figures sit on one node each rather than being split across near-duplicates.\n\n**The Meridian exchange-rate objective is formally unsupported.** The harness flags it as depending on nothing in the model — which is correct and expected, because you deliberately declined to give a number and said it would take commercial in a room. It stays in as a recorded question with its deposit attached, not as something the model pretends to answer. That's the right state for it; I'm noting it so nobody later reads the flag as an oversight.\n\nEverything else stands as read back. **Stopping outcome: expert-stopped, partial-with-open-slots.**\n\nSee you next round — with the sheet.\n[non-user] The sweep was refused: No user entry contains the verbatim quote \"Once fill and pack was done, it went into QA hold. That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\". Repair the quote to match the user's words exactly. Repair the proposal and call brunch_sweep again. Declining is legal.\n[non-user] The harness computed this unswept conversation tail:\n\n[non-user] The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nSo: that afternoon, how did you know the white order was coming? Was that a scheduled release event — the book updates at fixed times — or did someone tell you, or is it a pattern you've learned? And roughly how many orders land in a typical week's book, and how much do they swing between a quiet week and a busy one?\n[assistant] Go to your huddle. Here's what I've got, so you can correct it next time rather than read it now.\n\n## What's captured\n\n**The question the model exists to answer** — \"wash down for the tint right then, or let Line 2 sit idle\" for an expected same-family order; a call you make by gut \"three or four times a month\" and have \"never once been able to prove I got it right.\"\n\n**What \"better\" means** — Meridian misses first: \"we just don't do that\" — recorded as a hard rule, not a weight, because you wouldn't trade even twenty small late orders for one Meridian slip. Then late-order count. Changeover hours and idle time as your own diagnostics, on the same page as late orders for the first time.\n\n**Boundary** — three lines plus one changeover crew of two techs; order starts at demand-book release from ERP (SKU, quantity, due date), ends when it clears QA and ships; due date judged at QA clearance, not off the line.\n\n**Horizon** — one week (demand-book cycle, re-planned at the morning huddle); two weeks soft for specialty minimum runs; a month you'd refuse.\n\n**The flow** — release → wait behind what's on the line → run (mix, mill, tint stage, fill, pack) → QA hold (palletized, off the line, queued for the lab) → clear and ship. Same-family run-into-run needs no crew.\n\n**Crew contention, as practiced** — Meridian next in line wins, no discussion; otherwise your huddle call on tightest due date (Line 1 got them, Line 3 sat \"close to two hours\" clean and idle with slack); otherwise whoever's supervisor reaches the crew lead first. Override: maintenance can pull them for a genuine emergency; a real fight escalates to the ops director. None of it written down.\n\n**Changeovers, asymmetric by direction** — white→tint 40 min best, ~45 min–1 hr typical, ~1 hr 20 bad. Tint→white 2½ hr best, 3 hr typical (\"the number I actually use on the sheet\"), toward 4 hr bad. Specialty either direction ~2 hr, 1 hr 40 for specialty-to-specialty, not much past 2½ — with your own caveat that you don't watch these as closely.\n\n**Arrivals** — Monday drop of 30-something to 60; quiet week 30, busy 55–60; additions pushed in by sales/commercial through the week, sometimes daily; Meridian close to weekly, small distributors are what swing.\n\n**Validation bar** — reproduce last month's late-order count *and the kind* of miss (two Meridian scrapes, a handful of small ones); recognisable changeover hours on Lines 2 and 3; must reproduce the odd weeks, including the breakdown that ate two days on Line 1. Not a single number — \"the shape of a real month.\"\n\n## Open, with where it comes from\n\n1. **Run durations** — no rate for any line. Needs the sheet.\n2. **QA** — four hours for a white is all I have; nothing on specialty holds, lab capacity, or what happens on a fail.\n3. **Breakdowns** — named by you as essential to validation, never elicited: rate and duration per line.\n4. **The Monday-release shape** — I have weekly counts, not the mid-week additions pattern; and the thing your actual decision rested on was a remembered huddle remark, not a system event. That's a gap in the model, not in you.\n5. **What a changeover loses besides time** — scrap, material, first-batch yield: never asked.\n6. **Meridian exchange rate** — deliberately not a number. Your words: it would take \"commercial in a room\" to say it out loud.\n\n## Assumptions I made — none in the model\n\nI've recorded nothing you didn't say. Two things I *would* have assumed and didn't: that changeover time is symmetric (you corrected that before I could), and that the due date is met at end of line (you corrected that too).\n\n## Simplifications to flag next time\n\nQueues aren't modelled as things — the wait behind a running job and the QA queue emerge from the steps either side. And \"Meridian white basically always goes to Line 2\" is captured as your statement; I haven't asked whether that's a hard routing constraint or a habit, and it matters.\n\n**Stopping outcome: expert-stopped, partial-with-open-slots.** The spine is there — objective, boundary, flow, crew rule, changeover times. It can't yet run a week, because it has no run rates and no breakdowns. Next round: arrivals and breakdowns, as you offered, plus run rates off the sheet.\n[user] Looks right to me — and yeah, bring the sheet next time, it'll answer the run-rate question faster than I can talk through it. See you next round.\n\nJudge whether this range has settled. If it has, call brunch_sweep. Declining is legal; continue the interview when the topic is still open.\n[user] Sounds good. I'll have the sheet, and I'll poke at whether Meridian-to-Line-2 is written in stone or just habit before you even ask. Talk next round.\n\nJudge whether this range has settled. If it has, call brunch_sweep. Declining is legal; continue the interview when the topic is still open.",
+            "state": "done"
           }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet the line is one row treated as one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it is done.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill\",\"precision\":\"spelled out\",\"rationale\":\"The scheduling sheet's view: the line is one indivisible resource.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        ]
+      }
+    ],
+    "settlements": [
+      {
+        "submissionId": "sub_01M0Z9CBA84QRYHGPAECRRNHD1",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0Z9CBA84QRYHGPAECRRNHD1"
+      },
+      {
+        "submissionId": "sub_01M0Z9CSGDPT6R8RBHKKVJY5GK",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0Z9CSGDPT6R8RBHKKVJY5GK"
+      },
+      {
+        "submissionId": "sub_01M0Z9D5W0HVXZCK2HTM956WYW",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0Z9D5W0HVXZCK2HTM956WYW"
+      },
+      {
+        "submissionId": "sub_01M0Z9DK3CZ4TQ6868YEABWT4N",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0Z9DK3CZ4TQ6868YEABWT4N"
+      },
+      {
+        "submissionId": "sub_01M0Z9G9RX4BZVGNB8ZPHBR1S5",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0Z9G9RX4BZVGNB8ZPHBR1S5"
+      },
+      {
+        "submissionId": "sub_01M0Z9KW51RR2ERFKPPRKCNYJR",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0Z9KW51RR2ERFKPPRKCNYJR"
       },
+      {
+        "submissionId": "sub_01M0Z9R02SAMTX74WQMNKX0CZH",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0Z9R02SAMTX74WQMNKX0CZH"
+      },
+      {
+        "submissionId": "sub_01M0Z9RJV7JXBBQPM8ZZBGRP9H",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0Z9RJV7JXBBQPM8ZZBGRP9H"
+      },
+      {
+        "submissionId": "sub_01M0Z9S508PRS4CZP0VK4AM8RC",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0Z9S508PRS4CZP0VK4AM8RC"
+      },
+      {
+        "submissionId": "sub_01M0ZA3VTS121YWFBEGWJFM5VT",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0ZA3VTS121YWFBEGWJFM5VT"
+      },
+      {
+        "submissionId": "sub_01M0ZA9S0FT5DQHBJVFGZYB7T1",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0ZA9S0FT5DQHBJVFGZYB7T1"
+      },
+      {
+        "submissionId": "sub_01M0ZB8TWNCSV7DNGRSAZP017Z",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0ZB8TWNCSV7DNGRSAZP017Z"
+      }
+    ],
+    "incarnation": "inc_01M0Z9CBA8GZS2KSQPKGQ8FHNW"
+  },
+  "store": {
+    "captures": [
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "mix, mill, tint, fill",
-            "slot": "the distinctions the process treats apart",
+            "kind": "objective",
+            "node": "wash down for the tint now, or sit the line for the white order coming later",
+            "slot": "the question, in the expert's words",
             "precision": "spelled out",
             "sourceRegime": "practiced",
-            "rationale": "The floor view: four separately contended pieces of kit with buffering between them, allowing overlap.",
+            "rationale": "The expert's own recent decision, stated as the first question to put to the model.",
             "assertion": {
-              "value": "Physically four separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head is still finishing the last, if there is room in the holding tank — the crew will get a head start on mixing the next batch if the tank ahead of it has space."
+              "value": "Whether to wash down for the tint right then, or let the line sit idle for about an hour waiting for another same-colour (white) order that will be released from the demand book later that day — i.e. whether sitting the line was actually the cheaper choice or just the safer-feeling one."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+            "excerpt": "I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "the crew will get a head start on mixing the next batch if the tank ahead of it has space",
+            "excerpt": "That's exactly the kind of call I'd love to be able to test",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-27ee0ed5-50d0-47f6-94b8-77e090bca50f",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically four separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head is still finishing the last, if there is room in the holding tank — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill\",\"precision\":\"spelled out\",\"rationale\":\"The floor view: four separately contended pieces of kit with buffering between them, allowing overlap.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the crew will get a head start on mixing the next batch if the tank ahead of it has space\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-66f2471d-7a05-4ea9-a788-ddd5d45380c5",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whether to wash down for the tint right then, or let the line sit idle for about an hour waiting for another same-colour (white) order that will be released from the demand book later that day — i.e. whether sitting the line was actually the cheaper choice or just the safer-feeling one.\"},\"kind\":\"objective\",\"node\":\"wash down for the tint now, or sit the line for the white order coming later\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own recent decision, stated as the first question to put to the model.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That's exactly the kind of call I'd love to be able to test\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "mix, mill, tint, fill",
-            "slot": "how many there are, or the population's shape",
+            "kind": "objective",
+            "node": "wash down for the tint now, or sit the line for the white order coming later",
+            "slot": "the nodes it depends on",
             "precision": "named",
+            "rationale": "The expert names changeover hours, idle hours and late orders as the things the model must put on the same page.",
             "assertion": {
-              "absence": "unknown-to-user",
-              "pointer": "how much overlap happens and how often mixing is blocked by a full tank is not tracked by the scheduler"
+              "value": [
+                "activity:full white-to-tint changeover",
+                "entity-type:order",
+                "policy:we just don't do that (Meridian never slips)"
+              ]
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+            "excerpt": "in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
             },
             "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"how much overlap happens and how often mixing is blocked by a full tank is not tracked by the scheduler\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill\",\"precision\":\"named\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "allocate → run → QA hold → release and ship",
-            "slot": "the order things happen in",
-            "precision": "spelled out",
-            "rationale": "The order's life from demand-book line item to shipment, as walked end to end.",
-            "assertion": {
-              "value": "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (and pack) → QA hold in the lab's queue → release, go to the warehouse and ship against the due date."
-            }
-          }
-        },
-        "evidence": [
+          },
           {
-            "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+            "excerpt": "if the model's going to tell me anything useful, it has to connect those — because right now I only track them separately",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "explicit",
-        "id": "capture-2a491098-b602-4b46-bbaa-439e291027db",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (and pack) → QA hold in the lab's queue → release, go to the warehouse and ship against the due date.\"},\"kind\":\"ordering/flow\",\"node\":\"allocate → run → QA hold → release and ship\",\"precision\":\"spelled out\",\"rationale\":\"The order's life from demand-book line item to shipment, as walked end to end.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "inferred",
+        "id": "capture-239ae929-f206-452e-a332-ba47e5c16cf2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:full white-to-tint changeover\",\"entity-type:order\",\"policy:we just don't do that (Meridian never slips)\"]},\"kind\":\"objective\",\"node\":\"wash down for the tint now, or sit the line for the white order coming later\",\"precision\":\"named\",\"rationale\":\"The expert names changeover hours, idle hours and late orders as the things the model must put on the same page.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"if the model's going to tell me anything useful, it has to connect those — because right now I only track them separately\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "allocation",
-            "slot": "what it produces or changes",
+            "kind": "objective",
+            "node": "wash down for the tint now, or sit the line for the white order coming later",
+            "slot": "what \"better\" means, and trade-off weights",
             "precision": "spelled out",
-            "rationale": "Allocation binds the order to a line and a week slot, which is the scheduling decision under test.",
+            "sourceRegime": "practiced",
+            "rationale": "Better = fewer late orders with Meridian dominating; the expert explicitly refuses an exchange rate and names where a number would have to come from.",
             "assertion": {
-              "value": "The order is slotted onto a line and a slot in the week on the sheet."
+              "value": "Graded on the late-order count, with Meridian orders weighted extra heavy in practice though nobody has written that down; three non-Meridian orders a day late each is the better week than one Meridian order a day late, and the trade does not flip even at twenty small orders versus one Meridian — so no exchange rate exists; a real number would require getting commercial in a room and forcing them to say it out loud."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "excerpt": "If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I don't think it does flip, not in any range I'd actually see in a week. Even if you told me \"twenty small orders late\" versus \"one Meridian order late\" — I'd still not want to be the one who let Meridian slip.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 9,
               "entryEnd": 9
             },
@@ -8390,57 +2989,39 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-c4aefe40-a022-4990-96a1-b74243850715",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Allocation binds the order to a line and a week slot, which is the scheduling decision under test.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-da18e2cd-2af7-4aab-ade0-cd33e819a88b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Graded on the late-order count, with Meridian orders weighted extra heavy in practice though nobody has written that down; three non-Meridian orders a day late each is the better week than one Meridian order a day late, and the trade does not flip even at twenty small orders versus one Meridian — so no exchange rate exists; a real number would require getting commercial in a room and forcing them to say it out loud.\"},\"kind\":\"objective\",\"node\":\"wash down for the tint now, or sit the line for the white order coming later\",\"precision\":\"spelled out\",\"rationale\":\"Better = fewer late orders with Meridian dominating; the expert explicitly refuses an exchange rate and names where a number would have to come from.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't think it does flip, not in any range I'd actually see in a week. Even if you told me \\\\\\\"twenty small orders late\\\\\\\" versus \\\\\\\"one Meridian order late\\\\\\\" — I'd still not want to be the one who let Meridian slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "allocation",
-            "slot": "what it needs before it can start",
+            "kind": "policy",
+            "node": "we just don't do that (Meridian never slips)",
+            "slot": "the rule as actually practiced",
             "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "An unwritten rule stated by the expert as absolute, with its organisational consequence.",
             "assertion": {
-              "value": "The order exists as a line item in the demand book once ERP spits it out, with quantity, due date and SKU."
+              "value": "A Meridian order is never allowed to slip its due date — it is a \"we just don't do that\" rule rather than a traded-off cost, because a Meridian miss means a fine plus ammunition for them to delist a line item at next contract review, and commercial and the boss get calls. Non-Meridian distributor orders that slip 2-3 days are handled with a phone call."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+            "excerpt": "right now it's a \"we just don't do that\" rule, not a traded-off cost",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 9,
               "entryEnd": 9
             },
             "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-76c7250e-6575-4e31-b667-113f3a497cce",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order exists as a line item in the demand book once ERP spits it out, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
-            "assertion": {
-              "value": "The order must first be allocated onto a line and a slot in the week."
-            }
-          }
-        },
-        "evidence": [
+          },
           {
-            "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship.",
+            "excerpt": "A Meridian miss is a different category — it's not just \"late,\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 9,
               "entryEnd": 9
             },
@@ -8448,28 +3029,30 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-7da94524-13b5-4c11-a1b4-9cb1b0f07e19",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order must first be allocated onto a line and a slot in the week.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-c0aae96c-f4bb-4695-9f86-01228a2b2f87",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian order is never allowed to slip its due date — it is a \\\"we just don't do that\\\" rule rather than a traded-off cost, because a Meridian miss means a fine plus ammunition for them to delist a line item at next contract review, and commercial and the boss get calls. Non-Meridian distributor orders that slip 2-3 days are handled with a phone call.\"},\"kind\":\"policy\",\"node\":\"we just don't do that (Meridian never slips)\",\"precision\":\"spelled out\",\"rationale\":\"An unwritten rule stated by the expert as absolute, with its organisational consequence.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"A Meridian miss is a different category — it's not just \\\\\\\"late,\\\\\\\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"right now it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "what it produces or changes",
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "we just don't do that (Meridian never slips)",
+            "slot": "what overrides it",
             "precision": "spelled out",
+            "rationale": "The expert says no quantity of small late orders overrides the rule within the range they would see.",
             "assertion": {
-              "value": "Filled and packed product coming off the fill line, which then goes into QA hold."
+              "absence": "explicitly-absent",
+              "pointer": "no number of small late orders flips it in any range seen in a week"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Once it comes off the fill line it goes into QA hold",
+            "excerpt": "Where does it flip? Honestly... I don't think it does flip, not in any range I'd actually see in a week.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 9,
               "entryEnd": 9
             },
@@ -8477,88 +3060,104 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Filled and packed product coming off the fill line, which then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-6cb6a6a9-0536-46e6-aa77-4b211514bdf3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"explicitly-absent\",\"pointer\":\"no number of small late orders flips it in any range seen in a week\"},\"kind\":\"policy\",\"node\":\"we just don't do that (Meridian never slips)\",\"precision\":\"spelled out\",\"rationale\":\"The expert says no quantity of small late orders overrides the rule within the range they would see.\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Where does it flip? Honestly... I don't think it does flip, not in any range I'd actually see in a week.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "how long it takes",
-            "precision": "spread",
-            "sourceRegime": "practiced",
-            "rationale": "Sheet-level, mix-to-last-pack, for a Meridian-sized white on Line 2; includes fill-up time getting the line running plus actual throughput. The bad tail is loosely folded-in filler hiccups and QA-adjacent time.",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "rationale": "The expert distinguishes orders by colour class (white vs tint) and by customer class (Meridian vs distributor).",
             "assertion": {
-              "value": "White, normal/Meridian-sized order, Line 2, mix-to-last-pack: typical 8–9 hours; one run in ten worse than 12–13 hours; one run in ten better than about 6 hours."
+              "value": "Orders differ by colour class — white versus tint, where white-to-white needs no changeover and white-to-tint needs a full washdown — and by customer: Meridian orders (a miss is a fine and delisting risk) versus distributor orders (slip 2-3 days with a phone call)."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
+            "excerpt": "a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours",
+            "excerpt": "another white order — a smaller one, but still white, no changeover needed",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
+            "excerpt": "three little late orders to distributors who slip 2-3 days with a phone call anyway",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "A Meridian miss is a different category",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-d6985d8d-f85e-4556-a091-df64be080ba6",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, normal/Meridian-sized order, Line 2, mix-to-last-pack: typical 8–9 hours; one run in ten worse than 12–13 hours; one run in ten better than about 6 hours.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"Sheet-level, mix-to-last-pack, for a Meridian-sized white on Line 2; includes fill-up time getting the line running plus actual throughput. The bad tail is loosely folded-in filler hiccups and QA-adjacent time.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-26d91606-f924-457f-a62c-8c5c3a22ff3c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders differ by colour class — white versus tint, where white-to-white needs no changeover and white-to-tint needs a full washdown — and by customer: Meridian orders (a miss is a fine and delisting risk) versus distributor orders (slip 2-3 days with a phone call).\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The expert distinguishes orders by colour class (white vs tint) and by customer class (Meridian vs distributor).\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"A Meridian miss is a different category\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"another white order — a smaller one, but still white, no changeover needed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"three little late orders to distributors who slip 2-3 days with a phone call anyway\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "how long it takes",
-            "precision": "spread",
-            "sourceRegime": "practiced",
-            "rationale": "Same white order on the slower line.",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "state that rides along with each instance",
+            "precision": "named",
+            "rationale": "Only colour, customer and a unit size were named for the instance; size given as one example figure.",
             "assertion": {
-              "value": "White, same order, Line 1: typical 13–14 hours; worse days pushing 18-plus hours; best day maybe 10 hours — roughly fifty to sixty percent added to the Line 2 figures."
+              "value": "Colour (white or tint), customer (Meridian or distributor), a due date, and an order size in units — the example tint order was \"maybe 800 units\"."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+            "excerpt": "the next job on the sheet was a tint order, maybe 800 units",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "another white order — a smaller one, but still white",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, same order, Line 1: typical 13–14 hours; worse days pushing 18-plus hours; best day maybe 10 hours — roughly fifty to sixty percent added to the Line 2 figures.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"Same white order on the slower line.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-907b63ad-c480-4368-9b70-94cbc905fe70",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Colour (white or tint), customer (Meridian or distributor), a due date, and an order size in units — the example tint order was \\\"maybe 800 units\\\".\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"named\",\"rationale\":\"Only colour, customer and a unit size were named for the instance; size given as one example figure.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"another white order — a smaller one, but still white\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the next job on the sheet was a tint order, maybe 800 units\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -8566,30 +3165,39 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "how long it takes",
-            "precision": "range",
+            "node": "full white-to-tint changeover",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
             "sourceRegime": "practiced",
-            "rationale": "Only a typical range was given for tints; no one-in-ten tails.",
+            "rationale": "The changeover is triggered by a colour change from white to tint; same-colour succession needs none.",
             "assertion": {
-              "value": "Tint run, either line: 8–10 hours typical. No one-in-ten worse/better figures given."
+              "value": "The next job is a different colour class than the one just run — a white-to-tint switch requires the changeover; a white order following white needs no changeover."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.",
+            "excerpt": "a full white-to-tint changeover is a wash we can't get back",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "still white, no changeover needed",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-04a6f876-12f4-4f53-b6f2-f8e5fa9c87bc",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Tint run, either line: 8–10 hours typical. No one-in-ten worse/better figures given.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"range\",\"rationale\":\"Only a typical range was given for tints; no one-in-ten tails.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-41b692e0-6ff8-4294-9a9c-e97f7e51b6bb",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The next job is a different colour class than the one just run — a white-to-tint switch requires the changeover; a white order following white needs no changeover.\"},\"kind\":\"activity\",\"node\":\"full white-to-tint changeover\",\"precision\":\"spelled out\",\"rationale\":\"The changeover is triggered by a colour change from white to tint; same-colour succession needs none.\",\"slot\":\"what it needs before it can start\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"still white, no changeover needed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -8597,77 +3205,69 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "whether its quantities vary by type",
-            "precision": "named",
-            "rationale": "Duration varies by product type and by line, and the two interact; the expert has no explanation for the tint parity.",
+            "node": "full white-to-tint changeover",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Expert's own characterisation of the outcome of the changeover.",
             "assertion": {
-              "value": "Yes — duration varies both by product (white vs tint) and by line, and the two interact: whites are much slower on Line 1, tints run at nearly the same speed on both. \"I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\""
+              "value": "The line is washed down and set for tint; it is \"a wash we can't get back\" — the changeover hours are consumed capacity."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+            "excerpt": "a full white-to-tint changeover is a wash we can't get back",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-592b83e0-ece3-4e98-aedf-cdf70c202e96",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — duration varies both by product (white vs tint) and by line, and the two interact: whites are much slower on Line 1, tints run at nearly the same speed on both. \\\"I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\\\"\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Duration varies by product type and by line, and the two interact; the expert has no explanation for the tint parity.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-885c4bd0-8675-4604-990a-65c7118fa832",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line is washed down and set for tint; it is \\\"a wash we can't get back\\\" — the changeover hours are consumed capacity.\"},\"kind\":\"activity\",\"node\":\"full white-to-tint changeover\",\"precision\":\"spelled out\",\"rationale\":\"Expert's own characterisation of the outcome of the changeover.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what is lost when it changes the system's mode",
-            "precision": "number",
-            "rationale": "Named transition: tint to white on Line 1.",
+            "node": "full white-to-tint changeover",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "rationale": "The expert distinguishes white-to-tint (full wash) from white-to-white (none); other direction/colour pairs not yet stated.",
             "assertion": {
-              "value": "Three hours for a tint-to-white changeover — real cost in crew time, and it takes the line out of anything else for that window."
+              "value": "Yes by colour pair: white-to-tint is a full washdown, white-to-white needs no changeover at all."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
+            "excerpt": "still white, no changeover needed",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 3,
               "entryEnd": 3
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "it takes Line 1 out of anything else for that window",
+            "excerpt": "a full white-to-tint changeover is a wash we can't get back",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-32fe7be9-75c7-464c-87cb-ca38fef4039b",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours for a tint-to-white changeover — real cost in crew time, and it takes the line out of anything else for that window.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Named transition: tint to white on Line 1.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-a23f2234-5075-479e-86fb-89a3450bb4f1",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes by colour pair: white-to-tint is a full washdown, white-to-white needs no changeover at all.\"},\"kind\":\"activity\",\"node\":\"full white-to-tint changeover\",\"precision\":\"named\",\"rationale\":\"The expert distinguishes white-to-tint (full wash) from white-to-white (none); other direction/colour pairs not yet stated.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"still white, no changeover needed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -8675,19 +3275,21 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
+            "node": "the hold-or-change-over call",
+            "slot": "how often it occurs, if it is an event rather than a step",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Frequency of the decision point the model is meant to test.",
             "assertion": {
-              "value": "A line coming off a tint run and being switched to a white — pulling Line 1 off its tint to cover a white order."
+              "value": "three or four times a month"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown",
+            "excerpt": "I make that judgment by gut maybe three or four times a month",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 3,
               "entryEnd": 3
             },
@@ -8695,8 +3297,8 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-31556043-9787-40dc-8c0d-b74a47ed3589",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line coming off a tint run and being switched to a white — pulling Line 1 off its tint to cover a white order.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-9bbac61c-4b3d-42c8-a74a-2d846127039b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"three or four times a month\"},\"kind\":\"activity\",\"node\":\"the hold-or-change-over call\",\"precision\":\"range\",\"rationale\":\"Frequency of the decision point the model is meant to test.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I make that judgment by gut maybe three or four times a month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "hedged",
@@ -8704,119 +3306,129 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "QA hold",
-            "slot": "how long it takes",
+            "node": "the hold-or-change-over call",
+            "slot": "who or what performs it",
             "precision": "named",
-            "rationale": "Only a vague magnitude was given; no typical or tail figures, and the specialty case is named but unquantified.",
+            "rationale": "The expert makes the call themselves, by gut.",
             "assertion": {
-              "value": "Usually a few hours for a white; \"nothing like the specialty wait\". No typical/tail figures given."
+              "value": "The master scheduler, by gut judgment"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+            "excerpt": "I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I'm the master scheduler at a coatings plant.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 1,
+              "entryEnd": 1
+            },
+            "source": "user"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; \\\"nothing like the specialty wait\\\". No typical/tail figures given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Only a vague magnitude was given; no typical or tail figures, and the specialty case is named but unquantified.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-c216b212-3249-4b15-9b38-b7fc73c4e53a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler, by gut judgment\"},\"kind\":\"activity\",\"node\":\"the hold-or-change-over call\",\"precision\":\"named\",\"rationale\":\"The expert makes the call themselves, by gut.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm the master scheduler at a coatings plant.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":1,\\\"entryStart\\\":1,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "QA hold",
-            "slot": "who or what performs it",
+            "kind": "data-binding",
+            "node": "changeover log",
+            "slot": "the variable and its feed",
             "precision": "named",
+            "rationale": "Named existing record of changeover hours.",
             "assertion": {
-              "value": "The lab — the order sits in the lab's queue and gets checked."
+              "value": "Changeover hours, fed by the plant's changeover log (tracked separately from the late-order report)"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+            "excerpt": "I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab — the order sits in the lab's queue and gets checked.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-6bf8429a-d19a-47bd-8632-6e4e4a018357",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Changeover hours, fed by the plant's changeover log (tracked separately from the late-order report)\"},\"kind\":\"data-binding\",\"node\":\"changeover log\",\"precision\":\"named\",\"rationale\":\"Named existing record of changeover hours.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "filler jammed",
-            "slot": "how long it takes",
-            "precision": "range",
-            "sourceRegime": "practiced",
-            "rationale": "Two recognised repair kinds bracket the duration; the recent instance fell between them.",
+            "kind": "data-binding",
+            "node": "late-order report",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "rationale": "Named existing record of late orders, the boss's grading measure.",
             "assertion": {
-              "value": "Two kinds of repair: the \"half hour\" kind and the \"half a shift\" kind. The most recent Line 2 filler jam came back in about two hours."
+              "value": "Late-order count, fed by the late-order report (tracked separately from the changeover log)"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "it came back in about two hours",
+            "excerpt": "I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-d2d6e303-2f63-478a-ace1-0bf61abbfddd",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two kinds of repair: the \\\"half hour\\\" kind and the \\\"half a shift\\\" kind. The most recent Line 2 filler jam came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jammed\",\"precision\":\"range\",\"rationale\":\"Two recognised repair kinds bracket the duration; the recent instance fell between them.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-d29040ff-79cb-444b-afba-b81e63886bf4",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Late-order count, fed by the late-order report (tracked separately from the changeover log)\"},\"kind\":\"data-binding\",\"node\":\"late-order report\",\"precision\":\"named\",\"rationale\":\"Named existing record of late orders, the boss's grading measure.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "filler jammed",
-            "slot": "what it produces or changes",
+            "kind": "objective",
+            "node": "wash down now or sit the line idle",
+            "slot": "the question, in the expert's words",
             "precision": "spelled out",
-            "rationale": "An event that befalls the line mid-run and forces the switch-or-wait decision.",
+            "sourceRegime": "practiced",
+            "rationale": "The expert's own recent decision, stated as the first question for the model.",
             "assertion": {
-              "value": "The line's filler stops mid-run with an unknown ETA, putting the order on it at risk and forcing a decision to wait out the repair or move the order to the other line."
+              "value": "Whether to \"wash down for the tint right then, or let Line 2 sit idle for about an hour\" waiting for another white order that needs no changeover — a call made \"by gut maybe three or four times a month\""
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+            "excerpt": "I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 3,
               "entryEnd": 3
             },
@@ -8824,556 +3436,500 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-5548a18b-9f79-4475-a9ab-83a74c750721",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line's filler stops mid-run with an unknown ETA, putting the order on it at risk and forcing a decision to wait out the repair or move the order to the other line.\"},\"kind\":\"activity\",\"node\":\"filler jammed\",\"precision\":\"spelled out\",\"rationale\":\"An event that befalls the line mid-run and forces the switch-or-wait decision.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-37ea41c4-f012-4864-a896-ae745b3ba467",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whether to \\\"wash down for the tint right then, or let Line 2 sit idle for about an hour\\\" waiting for another white order that needs no changeover — a call made \\\"by gut maybe three or four times a month\\\"\"},\"kind\":\"objective\",\"node\":\"wash down now or sit the line idle\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own recent decision, stated as the first question for the model.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "policy",
-            "node": "who can absorb the slip",
-            "slot": "the rule as actually practiced",
+            "kind": "objective",
+            "node": "wash down now or sit the line idle",
+            "slot": "what \"better\" means, and trade-off weights",
             "precision": "spelled out",
             "sourceRegime": "practiced",
-            "rationale": "The practiced rule for choosing which order gets bumped when two cannot both be on time.",
+            "rationale": "Expert gave a qualitative ranking and explicitly refused a numeric exchange rate.",
             "assertion": {
-              "value": "Protect the non-negotiable order's due date; for anything bumped, judge by how far it slips and who the customer is — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first. No formula; judgment on who can absorb the slip."
+              "value": "Graded on \"the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere\"; a Meridian miss never trades against small late orders — \"I don't think it does flip, not in any range I'd actually see in a week\"; \"changeover hours and the idle time are more my own concern\" as diagnostics. No numeric exchange rate: \"you'd have to get commercial in a room and force them to say it out loud\""
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+            "excerpt": "Honestly, in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 6,
               "entryEnd": 6
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "I use judgment on who can absorb the slip.",
+            "excerpt": "If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere. The changeover hours and the idle time are more my own concern",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 6,
               "entryEnd": 6
             },
             "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-1ee7c206-0c56-4d6b-b091-5861f9c40438",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Protect the non-negotiable order's due date; for anything bumped, judge by how far it slips and who the customer is — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first. No formula; judgment on who can absorb the slip.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The practiced rule for choosing which order gets bumped when two cannot both be on time.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "policy",
-            "node": "who can absorb the slip",
-            "slot": "what overrides it",
-            "precision": "spelled out",
-            "assertion": {
-              "value": "The on-time line is crossed only when there is truly no way through."
-            }
-          }
-        },
-        "evidence": [
+          },
           {
-            "excerpt": "that's a line I won't cross unless there's truly no way through",
+            "excerpt": "Where does it flip? Honestly... I don't think it does flip, not in any range I'd actually see in a week.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-4b706f60-c02f-4973-aa58-2d3ded113c39",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The on-time line is crossed only when there is truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-47724d1f-2419-4d2e-9662-442ea9e7d8e5",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Graded on \\\"the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere\\\"; a Meridian miss never trades against small late orders — \\\"I don't think it does flip, not in any range I'd actually see in a week\\\"; \\\"changeover hours and the idle time are more my own concern\\\" as diagnostics. No numeric exchange rate: \\\"you'd have to get commercial in a room and force them to say it out loud\\\"\"},\"kind\":\"objective\",\"node\":\"wash down now or sit the line idle\",\"precision\":\"spelled out\",\"rationale\":\"Expert gave a qualitative ranking and explicitly refused a numeric exchange rate.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Honestly, in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere. The changeover hours and the idle time are more my own concern\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Where does it flip? Honestly... I don't think it does flip, not in any range I'd actually see in a week.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "constraint",
-            "node": "small holding tanks",
-            "slot": "the limit and what happens when it is hit",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Consequence is stated (upstream stage waits); the numeric capacity is not held by the expert.",
+            "kind": "objective",
+            "node": "wash down now or sit the line idle",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "The expert named the scheduling unit (three lines plus the one crew) and the span release-to-cleared-QA as what the decision turns on.",
             "assertion": {
-              "value": "The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait; overlap is only possible if the tank ahead has space. Suspected to cost more than people admit, never proven."
+              "value": [
+                "entity-type:order",
+                "entity-type:changeover crew",
+                "entity-type:line",
+                "activity:changeover (washdown)",
+                "activity:QA hold",
+                "ordering/flow:release to cleared QA",
+                "boundary-condition:demand book release",
+                "constraint:no Meridian miss"
+              ]
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
+            "excerpt": "So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "how often it's blocked because a tank's full and mixing has to wait",
+            "excerpt": "an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "explicit",
-        "id": "capture-97ea5a05-d89c-4a7d-a136-f90526beaa27",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait; overlap is only possible if the tank ahead has space. Suspected to cost more than people admit, never proven.\"},\"kind\":\"constraint\",\"node\":\"small holding tanks\",\"precision\":\"spelled out\",\"rationale\":\"Consequence is stated (upstream stage waits); the numeric capacity is not held by the expert.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"how often it's blocked because a tank's full and mixing has to wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "inferred",
+        "id": "capture-665b5de5-72f5-49c9-938b-55b00afa5252",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:changeover crew\",\"entity-type:line\",\"activity:changeover (washdown)\",\"activity:QA hold\",\"ordering/flow:release to cleared QA\",\"boundary-condition:demand book release\",\"constraint:no Meridian miss\"]},\"kind\":\"objective\",\"node\":\"wash down now or sit the line idle\",\"precision\":\"named\",\"rationale\":\"The expert named the scheduling unit (three lines plus the one crew) and the span release-to-cleared-QA as what the decision turns on.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"an order's mine from release to \\\\\\\"cleared QA,\\\\\\\" and the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "constraint",
-            "node": "small holding tanks",
-            "slot": "the limit and what happens when it is hit",
-            "precision": "named",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "rationale": "Expert distinguishes Meridian from distributor orders, and white from tint, as treated differently.",
             "assertion": {
-              "absence": "deferred",
-              "pointer": "engineering drawings — tank sizes obtainable from engineering, not carried in the scheduler's head"
+              "value": "Orders differ by customer — Meridian versus distributors (\"A Meridian miss is a different category\"; distributors \"slip 2-3 days with a phone call anyway\") — and by colour class, white versus tint, since white-to-tint requires a changeover and white-to-white does not"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "excerpt": "For me it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings — tank sizes obtainable from engineering, not carried in the scheduler's head\"},\"kind\":\"constraint\",\"node\":\"small holding tanks\",\"precision\":\"named\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "data-binding",
-            "node": "stage-by-stage rates from the historian",
-            "slot": "the variable and its feed",
-            "precision": "named",
-            "rationale": "Stage-level durations are needed for the separate-stage model and exist only in the historian.",
-            "assertion": {
-              "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the plant historian; never pulled apart, not known to the scheduler."
-            }
-          }
-        },
-        "evidence": [
+          },
           {
-            "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+            "excerpt": "Line 2 finished a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis. A Meridian miss is a different category",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-46d37104-fb87-4105-95d5-4448aade81ac",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the plant historian; never pulled apart, not known to the scheduler.\"},\"kind\":\"data-binding\",\"node\":\"stage-by-stage rates from the historian\",\"precision\":\"named\",\"rationale\":\"Stage-level durations are needed for the separate-stage model and exist only in the historian.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-ae712ebf-7a14-4cd9-adec-83df50ff2fa2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders differ by customer — Meridian versus distributors (\\\"A Meridian miss is a different category\\\"; distributors \\\"slip 2-3 days with a phone call anyway\\\") — and by colour class, white versus tint, since white-to-tint requires a changeover and white-to-white does not\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Expert distinguishes Meridian from distributor orders, and white from tint, as treated differently.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"For me it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 finished a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis. A Meridian miss is a different category\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "validation-criterion",
-            "node": "the sheet's end-to-end batch times",
-            "slot": "how the expert would know the model is right",
-            "precision": "named",
-            "rationale": "The only figures the expert holds first-hand are sheet-level end-to-end times per SKU per line; engineering's counter-claim is that the line rate is what it is regardless of the tanks.",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "state that rides along with each instance",
+            "precision": "spelled out",
+            "rationale": "Attributes the expert named on a released order plus the lateness test.",
             "assertion": {
-              "value": "The model's end-to-end batch time for a given SKU on each line should match what the scheduler's sheet shows; and it would have to speak to engineering's claim that \"the line rate is what it is regardless\"."
+              "value": "SKU, quantity, due date; lateness is judged against when the order clears QA, not when it comes off the line"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "engineering tells me the line rate is what it is regardless",
+            "excerpt": "it's got an SKU, quantity, due date",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet",
+            "excerpt": "the due date is judged against when it clears, not when it comes off the line",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-0cdda695-1dfa-43ef-971c-b9db09403a07",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The model's end-to-end batch time for a given SKU on each line should match what the scheduler's sheet shows; and it would have to speak to engineering's claim that \\\"the line rate is what it is regardless\\\".\"},\"kind\":\"validation-criterion\",\"node\":\"the sheet's end-to-end batch times\",\"precision\":\"named\",\"rationale\":\"The only figures the expert holds first-hand are sheet-level end-to-end times per SKU per line; engineering's counter-claim is that the line rate is what it is regardless of the tanks.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"engineering tells me the line rate is what it is regardless\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-e0802c09-2a87-4514-b8a2-51841de54cbc",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"SKU, quantity, due date; lateness is judged against when the order clears QA, not when it comes off the line\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Attributes the expert named on a released order plus the lateness test.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option actually loses less",
-            "slot": "the question, in the expert's words",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "The expert's stated use: type in a disruption state and be told which of switch-or-wait loses less.",
+            "kind": "entity-type",
+            "node": "changeover crew",
+            "slot": "how many there are, or the population's shape",
+            "precision": "number",
+            "rationale": "Expert stated the crew count directly.",
             "assertion": {
-              "value": "Given a disruption like \"filler's down, ETA unknown\", tell me which option actually loses less — shift the order to the other line or wait out the repair — instead of doing gut math at the huddle."
+              "value": "One crew of two techs, covering all three lines"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+            "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-a5926e2a-88e8-459e-a296-282b16d499a8",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given a disruption like \\\"filler's down, ETA unknown\\\", tell me which option actually loses less — shift the order to the other line or wait out the repair — instead of doing gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"The expert's stated use: type in a disruption state and be told which of switch-or-wait loses less.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-01f20a7f-43bf-42f9-a532-f04cf92ad105",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One crew of two techs, covering all three lines\"},\"kind\":\"entity-type\",\"node\":\"changeover crew\",\"precision\":\"number\",\"rationale\":\"Expert stated the crew count directly.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option actually loses less",
-            "slot": "what \"better\" means, and trade-off weights",
+            "kind": "entity-type",
+            "node": "changeover crew",
+            "slot": "the distinctions the process treats apart",
             "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Hard constraint plus unweighted secondary terms; the expert explicitly denies having a formula.",
+            "rationale": "The crew is a single shared contended resource, not differentiated by line.",
             "assertion": {
-              "value": "First number: days late on Meridian, anything above zero is bad — on-time is non-negotiable, a line not crossed unless there's truly no way through. Underneath that: washdown hours (crew time, line taken out of anything else for that window) and whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip."
+              "value": "A single shared changeover crew — \"the shared thing\" — not split by line; it is either free or pulled onto Line 1 or Line 3"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.",
+            "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+            "excerpt": "if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\"",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-ea1779b0-9a83-42aa-92d1-746e73de43cc",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First number: days late on Meridian, anything above zero is bad — on-time is non-negotiable, a line not crossed unless there's truly no way through. Underneath that: washdown hours (crew time, line taken out of anything else for that window) and whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint plus unweighted secondary terms; the expert explicitly denies having a formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-61d5a849-6ada-4278-a08b-86a2f62f2eff",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A single shared changeover crew — \\\"the shared thing\\\" — not split by line; it is either free or pulled onto Line 1 or Line 3\"},\"kind\":\"entity-type\",\"node\":\"changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"The crew is a single shared contended resource, not differentiated by line.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if I wash Line 2 down now, I'm also asking \\\\\\\"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "which option actually loses less",
-            "slot": "the nodes it depends on",
-            "precision": "named",
-            "rationale": "The scorecard terms name the run, the jam, the washdown, the order type and the flow.",
+            "kind": "entity-type",
+            "node": "line",
+            "slot": "how many there are, or the population's shape",
+            "precision": "number",
+            "rationale": "Expert named three lines as the scheduling scope.",
             "assertion": {
-              "value": [
-                "activity:run it through mix/mill/tint/fill",
-                "activity:filler jam",
-                "activity:tint-to-white washdown",
-                "entity-type:order (line item in the demand book)",
-                "entity-type:Line 1 and Line 2",
-                "ordering/flow:allocate → run → QA hold → release and ship",
-                "policy:who can absorb the slip"
-              ]
+              "value": "Three lines — Line 1, Line 2, Line 3"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
+            "excerpt": "So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+            "excerpt": "are they about to be pulled onto Line 1 or Line 3 for something else?",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "inferred",
-        "id": "capture-1288a3df-c7fd-4319-8d4e-a228572ba0b0",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:run it through mix/mill/tint/fill\",\"activity:filler jam\",\"activity:tint-to-white washdown\",\"entity-type:order (line item in the demand book)\",\"entity-type:Line 1 and Line 2\",\"ordering/flow:allocate → run → QA hold → release and ship\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard terms name the run, the jam, the washdown, the order type and the flow.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "explicit",
+        "id": "capture-199dc6be-d352-46eb-a561-b5c6b8b1703e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three lines — Line 1, Line 2, Line 3\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"number\",\"rationale\":\"Expert named three lines as the scheduling scope.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"are they about to be pulled onto Line 1 or Line 3 for something else?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "where Line 1 loses its time",
-            "slot": "the question, in the expert's words",
+            "kind": "activity",
+            "node": "changeover (washdown)",
+            "slot": "what it needs before it can start",
             "precision": "spelled out",
-            "rationale": "Second in-scope question: whether the small tank between mill and fill on Line 1 is actually costing time.",
+            "sourceRegime": "practiced",
+            "rationale": "Crew availability is the stated precondition.",
             "assertion": {
-              "value": "Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill on Line 1 is costing more than the published line rate admits, so it can be taken to engineering as something other than a hunch."
+              "value": "The changeover crew must be free — \"If they're tied up elsewhere, my 'wash down now' option isn't even really available\" — and the line must have finished its current run"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.",
+            "excerpt": "if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\" If they're tied up elsewhere, my \"wash down now\" option isn't even really available",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill on Line 1 is costing more than the published line rate admits, so it can be taken to engineering as something other than a hunch.\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"spelled out\",\"rationale\":\"Second in-scope question: whether the small tank between mill and fill on Line 1 is actually costing time.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-a9dd192c-4602-4b65-8896-be0481e9ce8b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The changeover crew must be free — \\\"If they're tied up elsewhere, my 'wash down now' option isn't even really available\\\" — and the line must have finished its current run\"},\"kind\":\"activity\",\"node\":\"changeover (washdown)\",\"precision\":\"spelled out\",\"rationale\":\"Crew availability is the stated precondition.\",\"slot\":\"what it needs before it can start\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"if I wash Line 2 down now, I'm also asking \\\\\\\"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\\\\\\\" If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "where Line 1 loses its time",
-            "slot": "the nodes it depends on",
+            "kind": "activity",
+            "node": "changeover (washdown)",
+            "slot": "who or what performs it",
             "precision": "named",
-            "rationale": "The tank question depends on the stage kit and the holding-tank constraint.",
+            "rationale": "Directly named performer.",
             "assertion": {
-              "value": [
-                "entity-type:mix, mill, tint, fill stages",
-                "constraint:small holding tanks between stages",
-                "activity:run it through mix/mill/tint/fill",
-                "entity-type:Line 1 and Line 2"
-              ]
+              "value": "entity-type:changeover crew — one crew of two techs"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "So yes — build it as separate stages if that's what it takes.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between",
+            "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "inferred",
-        "id": "capture-bb291ebf-9fe0-4a6e-9840-e7d7fac44033",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:mix, mill, tint, fill stages\",\"constraint:small holding tanks between stages\",\"activity:run it through mix/mill/tint/fill\",\"entity-type:Line 1 and Line 2\"]},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"named\",\"rationale\":\"The tank question depends on the stage kit and the holding-tank constraint.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So yes — build it as separate stages if that's what it takes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "explicit",
+        "id": "capture-2296040f-dd70-46bf-b603-b128a63be702",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:changeover crew — one crew of two techs\"},\"kind\":\"activity\",\"node\":\"changeover (washdown)\",\"precision\":\"named\",\"rationale\":\"Directly named performer.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order (line item in the demand book)",
-            "slot": "the distinctions the process treats apart",
+            "kind": "activity",
+            "node": "changeover (washdown)",
+            "slot": "what it produces or changes",
             "precision": "spelled out",
-            "rationale": "Whites vs tints differ in the tint stage and in run time by line; customer identity differs in slip tolerance.",
+            "rationale": "The changeover converts the line's colour state; same-colour succession needs none.",
             "assertion": {
-              "value": "Orders are line items with quantity, due date and SKU. Treated apart: whites (tint stage barely there, more of a pass-through than a real letdown step) vs tints (real letdown); and by customer — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem."
+              "value": "Converts the line from the previous colour to the next — \"a full white-to-tint changeover is a wash we can't get back\"; a white-to-white succession needs \"no changeover\""
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+            "excerpt": "a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+            "excerpt": "still white, no changeover needed",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-edfaf81c-c276-4b57-a88c-914953b1c6be",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders are line items with quantity, due date and SKU. Treated apart: whites (tint stage barely there, more of a pass-through than a real letdown step) vs tints (real letdown); and by customer — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem.\"},\"kind\":\"entity-type\",\"node\":\"order (line item in the demand book)\",\"precision\":\"spelled out\",\"rationale\":\"Whites vs tints differ in the tint stage and in run time by line; customer identity differs in slip tolerance.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-52ae613b-8aaf-4d9f-866d-72f8f37c00e7",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Converts the line from the previous colour to the next — \\\"a full white-to-tint changeover is a wash we can't get back\\\"; a white-to-white succession needs \\\"no changeover\\\"\"},\"kind\":\"activity\",\"node\":\"changeover (washdown)\",\"precision\":\"spelled out\",\"rationale\":\"The changeover converts the line's colour state; same-colour succession needs none.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"still white, no changeover needed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order (line item in the demand book)",
-            "slot": "state that rides along with each instance",
-            "precision": "spelled out",
-            "rationale": "Quantity, due date, SKU come from ERP; customer type is used in the slip judgement; line allocation is set at step one.",
+            "kind": "activity",
+            "node": "changeover (washdown)",
+            "slot": "what is lost when it changes the system's mode",
+            "precision": "named",
+            "sourceRegime": "practiced",
+            "rationale": "Expert named the loss qualitatively (a wash, changeover hours) but gave no figure in this range.",
             "assertion": {
-              "value": "Quantity, due date, SKU; the customer (distributor / small account / awkward account); which line and week-slot it has been allocated to; whether it has gone late and by how many days."
+              "value": "A wash that \"we can't get back\", counted by the expert as changeover hours; no quantity given yet"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "excerpt": "a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+            "excerpt": "in the moment I'm weighing changeover hours against idle hours — that's the gut math",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 6,
               "entryEnd": 6
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "explicit",
-        "id": "capture-13339551-ff3a-414f-8260-e1296530d8ec",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; the customer (distributor / small account / awkward account); which line and week-slot it has been allocated to; whether it has gone late and by how many days.\"},\"kind\":\"entity-type\",\"node\":\"order (line item in the demand book)\",\"precision\":\"spelled out\",\"rationale\":\"Quantity, due date, SKU come from ERP; customer type is used in the slip judgement; line allocation is set at step one.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "tentative",
+        "id": "capture-5fc553d4-e294-4ec8-8368-52ffe5044e2f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A wash that \\\"we can't get back\\\", counted by the expert as changeover hours; no quantity given yet\"},\"kind\":\"activity\",\"node\":\"changeover (washdown)\",\"precision\":\"named\",\"rationale\":\"Expert named the loss qualitatively (a wash, changeover hours) but gave no figure in this range.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in the moment I'm weighing changeover hours against idle hours — that's the gut math\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "Line 1 and Line 2",
-            "slot": "the distinctions the process treats apart",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "what it produces or changes",
             "precision": "spelled out",
-            "rationale": "The two lines differ on whites but not on tints — load-bearing for switch-or-wait.",
+            "rationale": "QA clearance is the event the due date is judged against.",
             "assertion": {
-              "value": "Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to Line 2's figures (\"Line 2 is twice as fast\", though that's really a whites number). On tints they run at nearly the same speed."
+              "value": "Clears the batch out of QA hold so it can ship; until then \"a batch can be done Tuesday and still ship late if the lab's backed up\", and the due date is judged against clearance"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
+            "excerpt": "It ends when it clears QA hold and ships.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.",
+            "excerpt": "a batch can be done Tuesday and still ship late if the lab's backed up",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-535749ea-ba99-4d11-84c0-8203fd058329",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to Line 2's figures (\\\"Line 2 is twice as fast\\\", though that's really a whites number). On tints they run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"rationale\":\"The two lines differ on whites but not on tints — load-bearing for switch-or-wait.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-8f6e902b-07ed-49ce-aa1b-40d7e46502ce",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Clears the batch out of QA hold so it can ship; until then \\\"a batch can be done Tuesday and still ship late if the lab's backed up\\\", and the due date is judged against clearance\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"QA clearance is the event the due date is judged against.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It ends when it clears QA hold and ships.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a batch can be done Tuesday and still ship late if the lab's backed up\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "mix, mill, tint, fill stages",
-            "slot": "the distinctions the process treats apart",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "The floor's account: four separately contended pieces of kit per line, buffered by small holding tanks.",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "Expert names the lab as the constrained performer.",
             "assertion": {
-              "value": "Mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can be starting the next order's batch while the fill head is still finishing the last one, if the holding tank between mix and mill, or mill and fill, has room."
+              "value": "the lab"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.",
+            "excerpt": "a batch can be done Tuesday and still ship late if the lab's backed up",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
@@ -9381,99 +3937,127 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-79eccb7f-a787-40d4-a2fa-e95bfda82d18",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can be starting the next order's batch while the fill head is still finishing the last one, if the holding tank between mix and mill, or mill and fill, has room.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill stages\",\"precision\":\"spelled out\",\"rationale\":\"The floor's account: four separately contended pieces of kit per line, buffered by small holding tanks.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-7514059e-f02b-4f61-a3a1-11ca6fd01646",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"the lab\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Expert names the lab as the constrained performer.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a batch can be done Tuesday and still ship late if the lab's backed up\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "mix, mill, tint, fill stages",
-            "slot": "how many there are, or the population's shape",
-            "precision": "named",
-            "rationale": "Stage counts per line and tank sizes not carried by the expert; source named.",
+            "kind": "ordering/flow",
+            "node": "release to cleared QA",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "rationale": "The expert stated the in-scope span end to end.",
             "assertion": {
-              "absence": "deferred",
-              "pointer": "engineering drawings (tank sizes) — expert does not carry them in his head"
+              "value": "Order lands in the demand book from ERP (\"released\") → scheduled onto a line, with a changeover first if the colour differs from the previous run → run on the line → QA hold → clears QA and ships. Upstream sales promising dates and downstream warehouse/logistics are outside the expert's scope"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I don't have clean numbers for tank sizes or stage-by-stage rates.",
+            "excerpt": "For me it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date. It ends when it clears QA hold and ships.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "excerpt": "an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-3c6b3e85-7fd3-4831-9201-6e3ef525e7cf",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings (tank sizes) — expert does not carry them in his head\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill stages\",\"precision\":\"named\",\"rationale\":\"Stage counts per line and tank sizes not carried by the expert; source named.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have clean numbers for tank sizes or stage-by-stage rates.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-bbeb387d-bf09-4357-b52a-58ad8b679738",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Order lands in the demand book from ERP (\\\"released\\\") → scheduled onto a line, with a changeover first if the colour differs from the previous run → run on the line → QA hold → clears QA and ships. Upstream sales promising dates and downstream warehouse/logistics are outside the expert's scope\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"The expert stated the in-scope span end to end.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"For me it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date. It ends when it clears QA hold and ships.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"an order's mine from release to \\\\\\\"cleared QA,\\\\\\\" and the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "boundary-condition",
-            "node": "demand book from ERP",
-            "slot": "the starting state",
-            "precision": "spelled out",
-            "rationale": "Orders enter the scheduler's world as ERP-generated demand-book line items.",
+            "node": "demand book release",
+            "slot": "the arrival or availability pattern",
+            "precision": "named",
+            "sourceRegime": "practiced",
+            "rationale": "Expert described the cycle and replan rhythm but gave no rate or shape.",
             "assertion": {
-              "value": "Orders arrive as line items in the demand book once ERP spits that out, carrying quantity, due date and SKU."
+              "value": "Orders arrive by release into the demand book from ERP on a weekly book cycle, re-planned by the morning huddle; releases occur within the day (e.g. an order \"was going to be released from the demand book that afternoon\"). No rate or shape given"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+            "excerpt": "For me it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders arrive as line items in the demand book once ERP spits that out, carrying quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"spelled out\",\"rationale\":\"Orders enter the scheduler's world as ERP-generated demand-book line items.\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-a77d820d-b5ac-45d5-a41b-e94c3bc7973f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders arrive by release into the demand book from ERP on a weekly book cycle, re-planned by the morning huddle; releases occur within the day (e.g. an order \\\"was going to be released from the demand book that afternoon\\\"). No rate or shape given\"},\"kind\":\"boundary-condition\",\"node\":\"demand book release\",\"precision\":\"named\",\"rationale\":\"Expert described the cycle and replan rhythm but gave no rate or shape.\",\"slot\":\"the arrival or availability pattern\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"For me it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "allocation",
-            "slot": "what it produces or changes",
+            "kind": "constraint",
+            "node": "no Meridian miss",
+            "slot": "the limit and what happens when it is hit",
             "precision": "spelled out",
-            "rationale": "Allocation fixes line and week-slot on the sheet.",
+            "sourceRegime": "practiced",
+            "rationale": "Stated as an unwritten absolute rule with named consequences.",
             "assertion": {
-              "value": "The order is slotted onto a line and a slot in the week on the sheet."
+              "value": "A Meridian order must not miss its due date — a \"we just don't do that\" rule, written nowhere; if hit: \"it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\""
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "excerpt": "A Meridian miss is a different category — it's not just \"late,\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "right now it's a \"we just don't do that\" rule, not a traded-off cost",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 9,
               "entryEnd": 9
             },
@@ -9481,167 +4065,207 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-823c9593-db42-45eb-9515-937e6b90bd33",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Allocation fixes line and week-slot on the sheet.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-e776f323-41e3-460b-ace7-666b43385453",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian order must not miss its due date — a \\\"we just don't do that\\\" rule, written nowhere; if hit: \\\"it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\\\"\"},\"kind\":\"constraint\",\"node\":\"no Meridian miss\",\"precision\":\"spelled out\",\"rationale\":\"Stated as an unwritten absolute rule with named consequences.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"A Meridian miss is a different category — it's not just \\\\\\\"late,\\\\\\\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"right now it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "allocation",
-            "slot": "who or what performs it",
-            "precision": "named",
-            "rationale": "The expert himself, as master scheduler, does the slotting on the sheet.",
+            "kind": "constraint",
+            "node": "planning horizon",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Horizon over which the plan must remain useful, with the expert's stated failure beyond it.",
             "assertion": {
-              "value": "The master scheduler, on the sheet"
+              "value": "One week is the horizon that must hold; two weeks is watched only for \"the big minimum-run stuff, specialty especially\"; beyond a month the plan is refused — \"too much changes\" and the book itself gets revised"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "excerpt": "if you ask me to hold a plan that's useful a month out, I'd say no — too much changes",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "I'm the master scheduler at a coatings plant.",
+            "excerpt": "a week is the horizon that matters — that's the cycle of the demand book",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 1,
-              "entryEnd": 1
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
-            "source": "user"
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially, because you don't want to discover Thursday that you needed to have started Tuesday.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-f7e12936-7567-4b38-be19-a45fb5dc6274",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler, on the sheet\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"named\",\"rationale\":\"The expert himself, as master scheduler, does the slotting on the sheet.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm the master scheduler at a coatings plant.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":1,\\\"entryStart\\\":1,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
+        "id": "capture-c625c3a0-1ce6-4249-b282-309c02e0a0d4",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One week is the horizon that must hold; two weeks is watched only for \\\"the big minimum-run stuff, specialty especially\\\"; beyond a month the plan is refused — \\\"too much changes\\\" and the book itself gets revised\"},\"kind\":\"constraint\",\"node\":\"planning horizon\",\"precision\":\"spelled out\",\"rationale\":\"Horizon over which the plan must remain useful, with the expert's stated failure beyond it.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially, because you don't want to discover Thursday that you needed to have started Tuesday.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a week is the horizon that matters — that's the cycle of the demand book\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if you ask me to hold a plan that's useful a month out, I'd say no — too much changes\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "allocation",
-            "slot": "what it needs before it can start",
+            "kind": "policy",
+            "node": "who gets the changeover crew",
+            "slot": "the rule as actually practiced",
             "precision": "spelled out",
-            "rationale": "Allocation follows the ERP demand-book line item existing.",
+            "sourceRegime": "practiced",
+            "rationale": "Expert described crew contention as first-come queueing; the tie-break and override are not yet stated.",
             "assertion": {
-              "value": "A line item in the demand book from ERP, with quantity, due date and SKU."
+              "value": "If the crew is already committed to another line, the requesting line waits — \"I'd be queuing behind whoever else needs them\""
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+            "excerpt": "If they're tied up elsewhere, my \"wash down now\" option isn't even really available — I'd be queuing behind whoever else needs them.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "inferred",
-        "id": "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book from ERP, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Allocation follows the ERP demand-book line item existing.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "explicit",
+        "id": "capture-1842e3f3-9daf-42d7-8803-eafe3b3c5146",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"If the crew is already committed to another line, the requesting line waits — \\\"I'd be queuing behind whoever else needs them\\\"\"},\"kind\":\"policy\",\"node\":\"who gets the changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"Expert described crew contention as first-come queueing; the tie-break and override are not yet stated.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available — I'd be queuing behind whoever else needs them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "allocate → run → QA hold → release and ship",
-            "slot": "the order things happen in",
-            "precision": "spelled out",
-            "rationale": "The expert's own end-to-end sequence for one order.",
+            "kind": "data-binding",
+            "node": "changeover log and late-order report",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "rationale": "Two existing feeds named by the expert, currently unlinked.",
             "assertion": {
-              "value": "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (mix, mill, tint, fill and pack) → QA hold in the lab's queue → release, warehouse, and ship against the due date."
+              "value": "Changeover hours from the changeover log; late orders from the late-order report — \"nobody's ever put them on the same page\""
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+            "excerpt": "I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (mix, mill, tint, fill and pack) → QA hold in the lab's queue → release, warehouse, and ship against the due date.\"},\"kind\":\"ordering/flow\",\"node\":\"allocate → run → QA hold → release and ship\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own end-to-end sequence for one order.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-ee33f01c-2e09-4f6b-a34e-6e9c2efb96e3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Changeover hours from the changeover log; late orders from the late-order report — \\\"nobody's ever put them on the same page\\\"\"},\"kind\":\"data-binding\",\"node\":\"changeover log and late-order report\",\"precision\":\"named\",\"rationale\":\"Two existing feeds named by the expert, currently unlinked.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "what it needs before it can start",
+            "kind": "objective",
+            "node": "wash down now or sit Line 2 idle",
+            "slot": "the question, in the expert's words",
             "precision": "spelled out",
-            "rationale": "A run needs the order allocated to a line and that line's kit available.",
+            "sourceRegime": "practiced",
+            "rationale": "The expert's own statement of the decision the model must inform, given as a recent real case.",
             "assertion": {
-              "value": "The order must have been allocated onto a line and a slot in the week, and the line's kit (mix, mill, tint, fill) available."
+              "value": "Whether to wash down for the tint right then, or let Line 2 sit idle for about an hour waiting for another white order (smaller, still white, no changeover needed) to be released from the demand book that afternoon — a call made by gut three or four times a month, never provably right."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "excerpt": "I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
+            "excerpt": "That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "inferred",
-        "id": "capture-afd366c9-1ea6-4b73-b2c0-ed97c9af0c79",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order must have been allocated onto a line and a slot in the week, and the line's kit (mix, mill, tint, fill) available.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"A run needs the order allocated to a line and that line's kit available.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "explicit",
+        "id": "capture-8e963c90-4270-411e-8ec9-9acbb2d2dabc",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whether to wash down for the tint right then, or let Line 2 sit idle for about an hour waiting for another white order (smaller, still white, no changeover needed) to be released from the demand book that afternoon — a call made by gut three or four times a month, never provably right.\"},\"kind\":\"objective\",\"node\":\"wash down now or sit Line 2 idle\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own statement of the decision the model must inform, given as a recent real case.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "what it produces or changes",
+            "kind": "objective",
+            "node": "wash down now or sit Line 2 idle",
+            "slot": "what \"better\" means, and trade-off weights",
             "precision": "spelled out",
-            "rationale": "Output is finished, packed product that comes off the fill line into QA hold.",
+            "sourceRegime": "practiced",
+            "rationale": "Better is judged on late orders, with Meridian misses as an unwritten hard rule rather than a weight; changeover and idle hours are the expert's own diagnostics.",
             "assertion": {
-              "value": "The order is produced through mix, mill, tint, fill and pack; it comes off the fill line as packed product ready for QA hold."
+              "value": "Graded on late-order count, with Meridian orders weighted extra heavy in practice though nobody has written that down; a Meridian miss is a \"we just don't do that\" rule, not a traded-off cost; changeover hours and idle hours are the expert's own concern because wasted capacity turns into missed due dates later in the week."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+            "excerpt": "in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "The changeover hours and the idle time are more my own concern — I get twitchy about wasted capacity because that's what eventually turns into missed due dates further down the week.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "right now it's a \"we just don't do that\" rule, not a traded-off cost",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 9,
               "entryEnd": 9
             },
@@ -9649,366 +4273,353 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-86fd1cfb-379b-42f7-bdbb-8586dae7f755",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is produced through mix, mill, tint, fill and pack; it comes off the fill line as packed product ready for QA hold.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"Output is finished, packed product that comes off the fill line into QA hold.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-65ac2ec5-6286-4058-afdf-08678d733640",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Graded on late-order count, with Meridian orders weighted extra heavy in practice though nobody has written that down; a Meridian miss is a \\\"we just don't do that\\\" rule, not a traded-off cost; changeover hours and idle hours are the expert's own concern because wasted capacity turns into missed due dates later in the week.\"},\"kind\":\"objective\",\"node\":\"wash down now or sit Line 2 idle\",\"precision\":\"spelled out\",\"rationale\":\"Better is judged on late orders, with Meridian misses as an unwritten hard rule rather than a weight; changeover and idle hours are the expert's own diagnostics.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The changeover hours and the idle time are more my own concern — I get twitchy about wasted capacity because that's what eventually turns into missed due dates further down the week.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"right now it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "who or what performs it",
-            "precision": "named",
-            "rationale": "The run is performed by whichever line the order is allocated to, with its crew.",
+            "kind": "objective",
+            "node": "Meridian-versus-small-orders exchange rate",
+            "slot": "what \"better\" means, and trade-off weights",
+            "precision": "spelled out",
+            "rationale": "The expert explicitly cannot supply an exchange rate and names commercial as the source that would have to state it.",
             "assertion": {
-              "value": "entity-type:Line 1 and Line 2 — the line the order is slotted onto, plus its crew"
+              "absence": "deferred",
+              "pointer": "commercial — would have to be got in a room and forced to say it out loud"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I slot it onto Line 2 on the sheet",
+            "excerpt": "I know that's not a real number you can put in a formula. If you need a number, you'd have to get commercial in a room and force them to say it out loud",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 9,
               "entryEnd": 9
             },
             "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "On Line 1, same order — slower machine",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
-            },
-            "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "inferred",
-        "id": "capture-90d36431-4341-4f9e-8bf6-8b5354b2fedd",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:Line 1 and Line 2 — the line the order is slotted onto, plus its crew\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"The run is performed by whichever line the order is allocated to, with its crew.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "explicit",
+        "id": "capture-9610d59f-1871-41d2-873c-e80a80daf01a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"commercial — would have to be got in a room and forced to say it out loud\"},\"kind\":\"objective\",\"node\":\"Meridian-versus-small-orders exchange rate\",\"precision\":\"spelled out\",\"rationale\":\"The expert explicitly cannot supply an exchange rate and names commercial as the source that would have to state it.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know that's not a real number you can put in a formula. If you need a number, you'd have to get commercial in a room and force them to say it out loud\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "how long it takes",
-            "precision": "spread",
-            "sourceRegime": "practiced",
-            "rationale": "First-pass spread for a Meridian-sized white on Line 2, mix-to-last-pack, with breakdowns folded in loosely; superseded by the clean-run capture.",
+            "kind": "objective",
+            "node": "wash down now or sit Line 2 idle",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "The expert names the scheduling unit (three lines plus the one crew) and the span of an order (release to cleared QA) as what the decision turns on.",
             "assertion": {
-              "value": "White, Meridian-sized order, Line 2, mix-to-last-pack (includes fill-up time plus throughput): typical eight to nine hours; one in ten worse than twelve to thirteen hours (breakdowns folded in loosely); one in ten better than about six hours."
+              "value": [
+                "entity-type:lines",
+                "entity-type:changeover crew",
+                "entity-type:order",
+                "boundary-condition:release from the demand book",
+                "activity:changeover wash down",
+                "activity:clears QA hold",
+                "ordering/flow:release to cleared QA",
+                "constraint:no Meridian misses"
+              ]
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more \"the filler hiccupped twice\" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely.",
+            "excerpt": "the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
+            "excerpt": "an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-7ef3368b-e678-4c58-b7f9-137d1607d8ec",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, Meridian-sized order, Line 2, mix-to-last-pack (includes fill-up time plus throughput): typical eight to nine hours; one in ten worse than twelve to thirteen hours (breakdowns folded in loosely); one in ten better than about six hours.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"First-pass spread for a Meridian-sized white on Line 2, mix-to-last-pack, with breakdowns folded in loosely; superseded by the clean-run capture.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more \\\\\\\"the filler hiccupped twice\\\\\\\" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-cb1567d4-e83b-4ff8-85aa-c917277e92e3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:lines\",\"entity-type:changeover crew\",\"entity-type:order\",\"boundary-condition:release from the demand book\",\"activity:changeover wash down\",\"activity:clears QA hold\",\"ordering/flow:release to cleared QA\",\"constraint:no Meridian misses\"]},\"kind\":\"objective\",\"node\":\"wash down now or sit Line 2 idle\",\"precision\":\"named\",\"rationale\":\"The expert names the scheduling unit (three lines plus the one crew) and the span of an order (release to cleared QA) as what the decision turns on.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"an order's mine from release to \\\\\\\"cleared QA,\\\\\\\" and the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "how long it takes",
-            "precision": "spread",
-            "sourceRegime": "practiced",
-            "rationale": "Superseding capture: breakdown time stripped out so filler jams are not double-counted; clean-run variability is small.",
+            "kind": "entity-type",
+            "node": "changeover crew",
+            "slot": "how many there are, or the population's shape",
+            "precision": "number",
+            "rationale": "Expert states one crew of two techs shared across all three lines.",
             "assertion": {
-              "value": "Clean run (nothing breaks — no jam, no QA holdup), white on Line 2: typical eight or nine hours; one in ten worse than nine to ten hours (normal slack, someone slow changing a roll of packaging film); one in ten better than about six hours. The twelve-to-thirteen-hour days are breakdowns showing up inside the run, not the run being slow."
+              "value": "one crew, two techs, covering all three lines"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 21,
-              "entryEnd": 21
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
+            "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 21,
-              "entryEnd": 21
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-10d88b79-af70-4a14-90c1-da56ad526d36",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Clean run (nothing breaks — no jam, no QA holdup), white on Line 2: typical eight or nine hours; one in ten worse than nine to ten hours (normal slack, someone slow changing a roll of packaging film); one in ten better than about six hours. The twelve-to-thirteen-hour days are breakdowns showing up inside the run, not the run being slow.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"Superseding capture: breakdown time stripped out so filler jams are not double-counted; clean-run variability is small.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-a64355a7-9a1c-48b4-b1b6-571aa465c457",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"one crew, two techs, covering all three lines\"},\"kind\":\"entity-type\",\"node\":\"changeover crew\",\"precision\":\"number\",\"rationale\":\"Expert states one crew of two techs shared across all three lines.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "whether its quantities vary by type",
+            "kind": "entity-type",
+            "node": "changeover crew",
+            "slot": "state that rides along with each instance",
             "precision": "spelled out",
             "sourceRegime": "practiced",
-            "rationale": "P07: run duration varies both by product type and by line, and the two interact.",
+            "rationale": "The crew is either free or tied up on another line; that state gates whether a changeover can start.",
             "assertion": {
-              "value": "Yes. White on Line 1: add maybe fifty, sixty percent to the Line 2 figures — typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten (this is where \"Line 2 is twice as fast\" comes from, and that's really a whites number). Tints: Line 1 and Line 2 run them at nearly the same speed — eight to ten hours typical on either line. No good reason known for why; it's what the sheet has always shown."
+              "value": "free, or tied up / about to be pulled onto Line 1 or Line 3 for something else — if tied up, the wash-down option isn't available and the job queues behind whoever else needs them"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+            "excerpt": "if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\"",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.",
+            "excerpt": "If they're tied up elsewhere, my \"wash down now\" option isn't even really available — I'd be queuing behind whoever else needs them.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-921611c3-21b5-4ab2-8e56-9b8cdaa2eba2",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes. White on Line 1: add maybe fifty, sixty percent to the Line 2 figures — typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten (this is where \\\"Line 2 is twice as fast\\\" comes from, and that's really a whites number). Tints: Line 1 and Line 2 run them at nearly the same speed — eight to ten hours typical on either line. No good reason known for why; it's what the sheet has always shown.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"P07: run duration varies both by product type and by line, and the two interact.\",\"slot\":\"whether its quantities vary by type\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-ca18e195-3155-4504-b85d-16c7f96d1bdf",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"free, or tied up / about to be pulled onto Line 1 or Line 3 for something else — if tied up, the wash-down option isn't available and the job queues behind whoever else needs them\"},\"kind\":\"entity-type\",\"node\":\"changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"The crew is either free or tied up on another line; that state gates whether a changeover can start.\",\"slot\":\"state that rides along with each instance\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available — I'd be queuing behind whoever else needs them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if I wash Line 2 down now, I'm also asking \\\\\\\"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "filler jam",
-            "slot": "how long it takes",
-            "precision": "range",
-            "sourceRegime": "practiced",
-            "rationale": "Expert gave two named repair kinds and one recent instance; no quantiles yet, so range not spread.",
+            "kind": "entity-type",
+            "node": "lines",
+            "slot": "how many there are, or the population's shape",
+            "precision": "number",
+            "rationale": "Three lines, named Line 1, Line 2, Line 3.",
             "assertion": {
-              "value": "Either the \"half hour\" kind or the \"half a shift\" kind of repair; the recent Line 2 instance came back in about two hours."
+              "value": "three lines — Line 1, Line 2, Line 3"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+            "excerpt": "there's one crew, two techs, covering all three lines",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "I went with waiting, it came back in about two hours, we just scraped the Thursday due date.",
+            "excerpt": "pulled onto Line 1 or Line 3 for something else",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-6cf8c229-ab84-4448-abc6-3e7f4a76bb4c",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Either the \\\"half hour\\\" kind or the \\\"half a shift\\\" kind of repair; the recent Line 2 instance came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Expert gave two named repair kinds and one recent instance; no quantiles yet, so range not spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours, we just scraped the Thursday due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-f2135748-e23c-40f8-b30b-54bba48e876e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"three lines — Line 1, Line 2, Line 3\"},\"kind\":\"entity-type\",\"node\":\"lines\",\"precision\":\"number\",\"rationale\":\"Three lines, named Line 1, Line 2, Line 3.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"pulled onto Line 1 or Line 3 for something else\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "filler jam",
-            "slot": "what it produces or changes",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "state that rides along with each instance",
             "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "The jam halts the line's fill stage and forces the switch-or-wait decision.",
+            "rationale": "The expert lists what an order carries when released.",
             "assertion": {
-              "value": "The filler stops and the run stalls — the line loses time (half a shift lost in the recent case), the in-progress order's finish is pushed out, and the scheduler must decide whether to shift the order to the other line or wait out the repair."
+              "value": "SKU, quantity, due date"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
+            "excerpt": "it's got an SKU, quantity, due date",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
+            "excerpt": "Line 2 finished a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 21,
-              "entryEnd": 21
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-ce789325-dd40-4b21-a936-73485ccb90b9",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The filler stops and the run stalls — the line loses time (half a shift lost in the recent case), the in-progress order's finish is pushed out, and the scheduler must decide whether to shift the order to the other line or wait out the repair.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"The jam halts the line's fill stage and forces the switch-or-wait decision.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-8a3b6dae-cba1-4332-a4dc-f98ff6b81bc2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"SKU, quantity, due date\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The expert lists what an order carries when released.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 finished a big Meridian white run around 10am and the next job on the sheet was a tint order, maybe 800 units\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what is lost when it changes the system's mode",
-            "precision": "number",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
             "sourceRegime": "practiced",
-            "rationale": "P02: named transition (tint to white) with a stated loss; a single figure, not a spread.",
+            "rationale": "Two distinctions the process treats differently: colour (white vs tint — whether a changeover is needed) and customer category (Meridian vs distributor).",
             "assertion": {
-              "value": "Three hours of washdown — crew time, and it takes the line out of anything else for that window."
+              "value": "colour — white versus tint, where a same-colour order needs no changeover; and customer — Meridian orders versus small distributor orders, which are a different category when late"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+            "excerpt": "another white order — a smaller one, but still white, no changeover needed",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 3,
               "entryEnd": 3
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
+            "excerpt": "three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "A Meridian miss is a different category",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-1ba32034-be19-432b-a012-326b682fd357",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of washdown — crew time, and it takes the line out of anything else for that window.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"P02: named transition (tint to white) with a stated loss; a single figure, not a spread.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-0f7b50a8-31f5-4025-ac2e-4a65bee0e3af",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"colour — white versus tint, where a same-colour order needs no changeover; and customer — Meridian orders versus small distributor orders, which are a different category when late\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Two distinctions the process treats differently: colour (white vs tint — whether a changeover is needed) and customer category (Meridian vs distributor).\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"A Meridian miss is a different category\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"another white order — a smaller one, but still white, no changeover needed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what it needs before it can start",
+            "kind": "boundary-condition",
+            "node": "release from the demand book",
+            "slot": "the starting state",
             "precision": "spelled out",
-            "rationale": "Triggered by pulling a line off a tint run to run a white.",
+            "rationale": "Orders enter the expert's world on release into the demand book from ERP, carrying SKU, quantity and due date.",
             "assertion": {
-              "value": "A line that is mid-run or last-run on a tint being pulled onto a white — the changeover from tint to white."
+              "value": "An order lands in the demand book from ERP — that is \"released\" — with an SKU, quantity and due date."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+            "excerpt": "it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line that is mid-run or last-run on a tint being pulled onto a white — the changeover from tint to white.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Triggered by pulling a line off a tint run to run a white.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-1d5aba4c-760f-4e4e-b48f-a3f498a4a75f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order lands in the demand book from ERP — that is \\\"released\\\" — with an SKU, quantity and due date.\"},\"kind\":\"boundary-condition\",\"node\":\"release from the demand book\",\"precision\":\"spelled out\",\"rationale\":\"Orders enter the expert's world on release into the demand book from ERP, carrying SKU, quantity and due date.\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "QA hold",
-            "slot": "how long it takes",
-            "precision": "named",
-            "sourceRegime": "practiced",
-            "rationale": "Vague quantifier — \"usually a few hours\" for a white — not yet quantiles; specialty products wait longer.",
+            "kind": "boundary-condition",
+            "node": "release from the demand book",
+            "slot": "the arrival or availability pattern",
+            "precision": "spelled out",
+            "rationale": "The expert gives the release cycle (weekly demand book, re-planned each morning at the huddle) but no rate or shape of arrivals.",
             "assertion": {
-              "value": "Usually a few hours for a white; \"nothing like the specialty wait\" — specialty products wait longer (amount not given)."
+              "value": "Releases follow the demand book's weekly cycle, re-planned every morning at the huddle; past a week the book is soft and gets revised. Rate and shape of arrivals not yet given."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+            "excerpt": "a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Anything past a week is soft; the book itself gets revised.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; \\\"nothing like the specialty wait\\\" — specialty products wait longer (amount not given).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Vague quantifier — \\\"usually a few hours\\\" for a white — not yet quantiles; specialty products wait longer.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-51875f80-77b4-4e1c-b260-ef2cf2d3a47a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Releases follow the demand book's weekly cycle, re-planned every morning at the huddle; past a week the book is soft and gets revised. Rate and shape of arrivals not yet given.\"},\"kind\":\"boundary-condition\",\"node\":\"release from the demand book\",\"precision\":\"spelled out\",\"rationale\":\"The expert gives the release cycle (weekly demand book, re-planned each morning at the huddle) but no rate or shape of arrivals.\",\"slot\":\"the arrival or availability pattern\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Anything past a week is soft; the book itself gets revised.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -10016,38 +4627,30 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "QA hold",
-            "slot": "what it produces or changes",
+            "node": "changeover wash down",
+            "slot": "what it needs before it can start",
             "precision": "spelled out",
-            "rationale": "QA check gates release to warehouse and shipping.",
+            "sourceRegime": "practiced",
+            "rationale": "Availability of the shared changeover crew gates the start of a wash down.",
             "assertion": {
-              "value": "The batch is checked and then released, goes to the warehouse, and ships against the due date."
+              "value": "The changeover crew must be free; if they are tied up on another line the wash-down option isn't available and the job queues behind whoever else needs them."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+            "excerpt": "If they're tied up elsewhere, my \"wash down now\" option isn't even really available — I'd be queuing behind whoever else needs them.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-e28ed067-b6a4-40d8-935a-3598e2401cc1",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The batch is checked and then released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"QA check gates release to warehouse and shipping.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-308e3c38-4da1-468b-b8b0-d330d0d3a3de",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The changeover crew must be free; if they are tied up on another line the wash-down option isn't available and the job queues behind whoever else needs them.\"},\"kind\":\"activity\",\"node\":\"changeover wash down\",\"precision\":\"spelled out\",\"rationale\":\"Availability of the shared changeover crew gates the start of a wash down.\",\"slot\":\"what it needs before it can start\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available — I'd be queuing behind whoever else needs them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -10055,91 +4658,99 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "QA hold",
+            "node": "changeover wash down",
             "slot": "who or what performs it",
             "precision": "named",
-            "rationale": "The lab holds the queue and does the check.",
+            "rationale": "The changeover crew performs the wash down.",
             "assertion": {
-              "value": "The lab"
+              "value": "the changeover crew — one crew, two techs, shared across all three lines"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+            "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"The lab holds the queue and does the check.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-db07e2c6-f110-4f71-90a1-aaf5a20fd5ea",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"the changeover crew — one crew, two techs, shared across all three lines\"},\"kind\":\"activity\",\"node\":\"changeover wash down\",\"precision\":\"named\",\"rationale\":\"The changeover crew performs the wash down.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "policy",
-            "node": "a line is occupied for the whole run",
-            "slot": "the rule as actually practiced",
-            "precision": "spelled out",
-            "sourceRegime": "prescribed",
-            "rationale": "P08: the scheduling sheet's rule, which the expert says lies to him a bit.",
+            "kind": "activity",
+            "node": "changeover wash down",
+            "slot": "what is lost when it changes the system's mode",
+            "precision": "named",
+            "rationale": "The expert names the loss qualitatively — a full white-to-tint changeover is a wash that cannot be recovered — without giving hours.",
             "assertion": {
-              "value": "On the sheet, a line is one row: the order occupies that line for its whole run, mix through fill, and nothing else is scheduled on it till it's done."
+              "value": "a full white-to-tint changeover is \"a wash we can't get back\"; the amount of time or capacity lost was not quantified"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+            "excerpt": "a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet, a line is one row: the order occupies that line for its whole run, mix through fill, and nothing else is scheduled on it till it's done.\"},\"kind\":\"policy\",\"node\":\"a line is occupied for the whole run\",\"precision\":\"spelled out\",\"rationale\":\"P08: the scheduling sheet's rule, which the expert says lies to him a bit.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-1aba2bfb-ad60-4e76-9a2b-f4ac16294d1d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"a full white-to-tint changeover is \\\"a wash we can't get back\\\"; the amount of time or capacity lost was not quantified\"},\"kind\":\"activity\",\"node\":\"changeover wash down\",\"precision\":\"named\",\"rationale\":\"The expert names the loss qualitatively — a full white-to-tint changeover is a wash that cannot be recovered — without giving hours.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "policy",
-            "node": "a line is occupied for the whole run",
-            "slot": "what overrides it",
+            "kind": "activity",
+            "node": "clears QA hold",
+            "slot": "what it produces or changes",
             "precision": "spelled out",
             "sourceRegime": "practiced",
-            "rationale": "P08 divergence: floor practice overlaps stages when buffer space allows.",
+            "rationale": "Clearing QA is the event against which lateness is judged and the point the order leaves the expert's scope.",
             "assertion": {
-              "value": "On the floor the crew will get a head start on mixing the next batch if the tank ahead of it has space — the mixer can start the next order while the fill head finishes the last one. How much overlap happens, and how often it is blocked because a tank is full, is not tracked."
+              "value": "The order clears QA hold and ships; the due date is judged against when it clears, not when it comes off the line — a batch can be done Tuesday and still ship late if the lab's backed up."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.",
+            "excerpt": "It ends when it clears QA hold and ships.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.",
+            "excerpt": "the due date is judged against when it clears, not when it comes off the line",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "a batch can be done Tuesday and still ship late if the lab's backed up",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
@@ -10147,150 +4758,194 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-cfe5bf57-8879-4592-a938-1527d73c8bac",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the floor the crew will get a head start on mixing the next batch if the tank ahead of it has space — the mixer can start the next order while the fill head finishes the last one. How much overlap happens, and how often it is blocked because a tank is full, is not tracked.\"},\"kind\":\"policy\",\"node\":\"a line is occupied for the whole run\",\"precision\":\"spelled out\",\"rationale\":\"P08 divergence: floor practice overlaps stages when buffer space allows.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-25d93015-ae4d-48ce-8708-1d5c257d629a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order clears QA hold and ships; the due date is judged against when it clears, not when it comes off the line — a batch can be done Tuesday and still ship late if the lab's backed up.\"},\"kind\":\"activity\",\"node\":\"clears QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Clearing QA is the event against which lateness is judged and the point the order leaves the expert's scope.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It ends when it clears QA hold and ships.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a batch can be done Tuesday and still ship late if the lab's backed up\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "policy",
-            "node": "who can absorb the slip",
-            "slot": "the rule as actually practiced",
+            "kind": "ordering/flow",
+            "node": "release to cleared QA",
+            "slot": "the order things happen in",
             "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "The practiced rule for choosing which order to bump; explicitly judgement, not formula.",
+            "rationale": "The end-to-end span the expert owns; intermediate line steps not yet detailed.",
             "assertion": {
-              "value": "Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem. No formula — \"how bad is bad\" for the second-order stuff."
+              "value": "Order is released into the demand book from ERP → run on a line (with a changeover before it if the colour differs) → comes off the line → clears QA hold → ships. Steps within the line run not yet detailed."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+            "excerpt": "an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "I use judgment on who can absorb the slip",
+            "excerpt": "it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "It ends when it clears QA hold and ships.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem. No formula — \\\"how bad is bad\\\" for the second-order stuff.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The practiced rule for choosing which order to bump; explicitly judgement, not formula.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-d767508b-10f1-41b0-8818-b943bf124b10",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Order is released into the demand book from ERP → run on a line (with a changeover before it if the colour differs) → comes off the line → clears QA hold → ships. Steps within the line run not yet detailed.\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"The end-to-end span the expert owns; intermediate line steps not yet detailed.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It ends when it clears QA hold and ships.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"an order's mine from release to \\\\\\\"cleared QA,\\\\\\\" and the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "policy",
-            "node": "who can absorb the slip",
-            "slot": "what overrides it",
+            "kind": "constraint",
+            "node": "no Meridian misses",
+            "slot": "the limit and what happens when it is hit",
             "precision": "spelled out",
             "sourceRegime": "practiced",
-            "rationale": "The hard on-time line overrides the slip-absorption weighing.",
+            "rationale": "An unwritten hard rule with a named consequence, stated as not tradeable even against twenty small late orders.",
             "assertion": {
-              "value": "The Meridian-style on-time line overrides everything: that order shipping on time is non-negotiable unless there's truly no way through."
+              "value": "A Meridian order must not slip its due date. If it does: a fine, ammunition for Meridian to delist a line item at next contract review, and calls to commercial and to the boss. Not traded off — even twenty small orders late is preferred to one Meridian miss; it is a \"we just don't do that\" rule that nobody has written down."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+            "excerpt": "it's not just \"late,\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Even if you told me \"twenty small orders late\" versus \"one Meridian order late\" — I'd still not want to be the one who let Meridian slip.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "right now it's a \"we just don't do that\" rule, not a traded-off cost",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The Meridian-style on-time line overrides everything: that order shipping on time is non-negotiable unless there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The hard on-time line overrides the slip-absorption weighing.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-a8c037cd-b9d8-4056-828f-74511da9a726",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian order must not slip its due date. If it does: a fine, ammunition for Meridian to delist a line item at next contract review, and calls to commercial and to the boss. Not traded off — even twenty small orders late is preferred to one Meridian miss; it is a \\\"we just don't do that\\\" rule that nobody has written down.\"},\"kind\":\"constraint\",\"node\":\"no Meridian misses\",\"precision\":\"spelled out\",\"rationale\":\"An unwritten hard rule with a named consequence, stated as not tradeable even against twenty small late orders.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Even if you told me \\\\\\\"twenty small orders late\\\\\\\" versus \\\\\\\"one Meridian order late\\\\\\\" — I'd still not want to be the one who let Meridian slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's not just \\\\\\\"late,\\\\\\\" it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"right now it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "constraint",
-            "node": "small holding tanks between stages",
+            "node": "one-week planning horizon",
             "slot": "the limit and what happens when it is hit",
-            "precision": "named",
+            "precision": "spelled out",
             "sourceRegime": "practiced",
-            "rationale": "Consequence named (mixing has to wait when the tank ahead is full) but the capacities themselves are not held by the expert; source named.",
+            "rationale": "The horizon over which the model's answer must hold, with the expert's stated reason it fails beyond it.",
             "assertion": {
-              "absence": "deferred",
-              "pointer": "engineering drawings — tank sizes; consequence as stated: the tanks are small, especially the one between mill and fill on Line 1, and when a tank is full mixing has to wait"
+              "value": "A week is the horizon that matters — the demand book's cycle, re-planned every morning at the huddle; two weeks out is watched only for big minimum-run specialty work; a plan held a month out is refused because too much changes."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.",
+            "excerpt": "Practically, a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially, because you don't want to discover Thursday that you needed to have started Tuesday.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "excerpt": "But if you ask me to hold a plan that's useful a month out, I'd say no — too much changes.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-23c5706e-37c1-481e-9438-8fae70973c13",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings — tank sizes; consequence as stated: the tanks are small, especially the one between mill and fill on Line 1, and when a tank is full mixing has to wait\"},\"kind\":\"constraint\",\"node\":\"small holding tanks between stages\",\"precision\":\"named\",\"rationale\":\"Consequence named (mixing has to wait when the tank ahead is full) but the capacities themselves are not held by the expert; source named.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-ccf25a9c-6c03-47ed-9cd4-e030f3ef1dc9",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A week is the horizon that matters — the demand book's cycle, re-planned every morning at the huddle; two weeks out is watched only for big minimum-run specialty work; a plan held a month out is refused because too much changes.\"},\"kind\":\"constraint\",\"node\":\"one-week planning horizon\",\"precision\":\"spelled out\",\"rationale\":\"The horizon over which the model's answer must hold, with the expert's stated reason it fails beyond it.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But if you ask me to hold a plan that's useful a month out, I'd say no — too much changes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially, because you don't want to discover Thursday that you needed to have started Tuesday.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Practically, a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "data-binding",
-            "node": "stage-by-stage durations from the historian",
-            "slot": "the variable and its feed",
-            "precision": "named",
-            "rationale": "Stage-level rates exist as data but not in the expert's head; feed named.",
+            "kind": "policy",
+            "node": "sit the line for an expected same-colour order",
+            "slot": "the rule as actually practiced",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The practiced rule behind the decision, given as gut judgment on a real occasion; not yet elicited as a general rule with conditions.",
             "assertion": {
-              "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) per SKU and line — feed: the historian. Never pulled apart; only end-to-end batch time per SKU per line is on the scheduling sheet."
+              "value": "When a same-colour order is expected to be released later the same day, hold the line idle rather than change over — because a full white-to-tint changeover is a wash that can't be got back, versus an hour of idle time. Judged by gut, three or four times a month."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that.",
+            "excerpt": "I ended up sitting the line. It felt right — a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I make that judgment by gut maybe three or four times a month",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-00863ee1-f99c-48b2-b680-bf4eb71e6a57",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) per SKU and line — feed: the historian. Never pulled apart; only end-to-end batch time per SKU per line is on the scheduling sheet.\"},\"kind\":\"data-binding\",\"node\":\"stage-by-stage durations from the historian\",\"precision\":\"named\",\"rationale\":\"Stage-level rates exist as data but not in the expert's head; feed named.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-760f09f2-bdec-44fe-897d-f81b376a0ad6",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"When a same-colour order is expected to be released later the same day, hold the line idle rather than change over — because a full white-to-tint changeover is a wash that can't be got back, versus an hour of idle time. Judged by gut, three or four times a month.\"},\"kind\":\"policy\",\"node\":\"sit the line for an expected same-colour order\",\"precision\":\"spelled out\",\"rationale\":\"The practiced rule behind the decision, given as gut judgment on a real occasion; not yet elicited as a general rule with conditions.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I ended up sitting the line. It felt right — a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I make that judgment by gut maybe three or four times a month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -10298,136 +4953,104 @@
           "value": {
             "type": "slot-asserted",
             "kind": "validation-criterion",
-            "node": "stage rates must come from data, not gut-feel",
+            "node": "recognize the shape of a real month",
             "slot": "how the expert would know the model is right",
             "precision": "spelled out",
-            "rationale": "Expert explicitly bounds what his own testimony can support.",
+            "rationale": "A replay test on last month's demand book with three named checks and an explicit refusal to trust a single number.",
             "assertion": {
-              "value": "Stage-level rates and tank sizes must not be taken from the expert's gut-feel — he can supply gut-feel and known bottleneck stories, but real numbers must come from the historian and engineering drawings."
+              "value": "Feed it last month's demand book: it must land roughly where we actually landed on late orders — same rough number and same kind of misses (getting the kind wrong, e.g. distributor instead of Meridian, is worse than getting the count wrong); changeover hours on Line 2 and 3 must look about right, and Line 3 must not sit idle half the week waiting on the crew because that never happens; and it must reproduce the odd weeks, e.g. a breakdown chewing up two days on Line 1. No single number would be trusted — the shape of a real month must be recognizable."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head.",
+            "excerpt": "the first thing I'd check is the boring one — did it land roughly where we actually landed on late orders that month?",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 15,
               "entryEnd": 15
             },
             "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-196b8447-3958-444f-9860-8de7330299ec",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-level rates and tank sizes must not be taken from the expert's gut-feel — he can supply gut-feel and known bottleneck stories, but real numbers must come from the historian and engineering drawings.\"},\"kind\":\"validation-criterion\",\"node\":\"stage rates must come from data, not gut-feel\",\"precision\":\"spelled out\",\"rationale\":\"Expert explicitly bounds what his own testimony can support.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "switch or wait when Line 2 goes down",
-            "slot": "the question, in the expert's words",
-            "precision": "spelled out",
-            "rationale": "The expert wrote the question as he would type it into the tool.",
-            "assertion": {
-              "value": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\""
-            }
-          }
-        },
-        "evidence": [
+          },
           {
-            "excerpt": "If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?",
+            "excerpt": "we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones. So: same rough number and same *kind* of misses.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
             },
             "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-b58883f3-43e2-4626-bc59-a9c091f1d1b5",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\"\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down\",\"precision\":\"spelled out\",\"rationale\":\"The expert wrote the question as he would type it into the tool.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "objective",
-            "node": "switch or wait when Line 2 goes down",
-            "slot": "the nodes it depends on",
-            "precision": "named",
-            "rationale": "The expert listed what the answer hangs on: the protected run and its due date, the state of Line 1, the changeover and its direction, the jam duration, and whose order gets bumped.",
-            "assertion": {
-              "value": [
-                "entity-type:order",
-                "entity-type:line",
-                "activity:run it through mix/mill/tint/fill",
-                "activity:tint-to-white washdown",
-                "activity:filler jam",
-                "policy:who can absorb the slip"
-              ]
-            }
-          }
-        },
-        "evidence": [
+          },
           {
-            "excerpt": "the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself",
+            "excerpt": "If it says we missed distributor orders and we actually missed a Meridian one, that's worse than getting the count wrong.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "the bumped order's identity matters, not just \"an order got delayed.\"",
+            "excerpt": "After that I'd want to eyeball changeover hours on Line 2 and 3 specifically",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "if the model has Line 3 idle half the week waiting on the crew, and that never happens in real life, I'd know it's missing something about how the crew actually gets shared out",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "And I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I'd want to recognize the *shape* of a real month before I'd believe it on something as specific as the wash-versus-idle call.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-3aa3764b-8dd5-495a-bf3e-b32cbc89ba61",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:line\",\"activity:run it through mix/mill/tint/fill\",\"activity:tint-to-white washdown\",\"activity:filler jam\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down\",\"precision\":\"named\",\"rationale\":\"The expert listed what the answer hangs on: the protected run and its due date, the state of Line 1, the changeover and its direction, the jam duration, and whose order gets bumped.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the bumped order's identity matters, not just \\\\\\\"an order got delayed.\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-f79e5a2e-1102-4970-a177-0b9c1fab4c03",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Feed it last month's demand book: it must land roughly where we actually landed on late orders — same rough number and same kind of misses (getting the kind wrong, e.g. distributor instead of Meridian, is worse than getting the count wrong); changeover hours on Line 2 and 3 must look about right, and Line 3 must not sit idle half the week waiting on the crew because that never happens; and it must reproduce the odd weeks, e.g. a breakdown chewing up two days on Line 1. No single number would be trusted — the shape of a real month must be recognizable.\"},\"kind\":\"validation-criterion\",\"node\":\"recognize the shape of a real month\",\"precision\":\"spelled out\",\"rationale\":\"A replay test on last month's demand book with three named checks and an explicit refusal to trust a single number.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"After that I'd want to eyeball changeover hours on Line 2 and 3 specifically\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"And I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'd want to recognize the *shape* of a real month before I'd believe it on something as specific as the wash-versus-idle call.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If it says we missed distributor orders and we actually missed a Meridian one, that's worse than getting the count wrong.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if the model has Line 3 idle half the week waiting on the crew, and that never happens in real life, I'd know it's missing something about how the crew actually gets shared out\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first thing I'd check is the boring one — did it land roughly where we actually landed on late orders that month?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones. So: same rough number and same *kind* of misses.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "switch or wait when Line 2 goes down",
-            "slot": "what \"better\" means, and trade-off weights",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "Expert gave a lexicographic hard constraint plus unweighted second-order criteria, explicitly denying a formula.",
+            "kind": "data-binding",
+            "node": "changeover log and late-order report",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "rationale": "Two existing records the expert already keeps, tracked separately today.",
             "assertion": {
-              "value": "Hard line: days late on Meridian, anything above zero is bad news. Underneath that, weighed by judgment with no formula: washdown hours, and whether the bumped order goes late and by how much and for which customer."
+              "value": "changeover hours from the changeover log; late orders from the late-order report — currently tracked separately and never put on the same page"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news",
+            "excerpt": "I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 6,
               "entryEnd": 6
             },
@@ -10435,38 +5058,39 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-57ad71c3-f423-4d91-a9f8-d3ce31f1fca1",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Hard line: days late on Meridian, anything above zero is bad news. Underneath that, weighed by judgment with no formula: washdown hours, and whether the bumped order goes late and by how much and for which customer.\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down\",\"precision\":\"spelled out\",\"rationale\":\"Expert gave a lexicographic hard constraint plus unweighted second-order criteria, explicitly denying a formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-03ff88a9-662d-4963-aece-fe45c343df17",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"changeover hours from the changeover log; late orders from the late-order report — currently tracked separately and never put on the same page\"},\"kind\":\"data-binding\",\"node\":\"changeover log and late-order report\",\"precision\":\"named\",\"rationale\":\"Two existing records the expert already keeps, tracked separately today.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "speculative",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "is the mill-to-fill tank on Line 1 slowing the line down",
-            "slot": "the question, in the expert's words",
-            "precision": "spelled out",
-            "rationale": "Second question the expert wrote out as he would type it.",
+            "kind": "activity",
+            "node": "breakdown on a line",
+            "slot": "how long it takes",
+            "precision": "number",
+            "sourceRegime": "practiced",
+            "rationale": "Mentioned in passing as a validation case — one recalled incident, not a rate or a distribution.",
             "assertion": {
-              "value": "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\""
+              "value": "a breakdown chewed up two days on Line 1 in one recalled odd week"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?",
+            "excerpt": "the ones where a breakdown chewed up two days on Line 1",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "explicit",
-        "id": "capture-1a3325b9-15b6-436a-8e7f-feff95d98036",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\"\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"rationale\":\"Second question the expert wrote out as he would type it.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "tentative",
+        "id": "capture-da211e90-dab6-4896-b9f1-9d01a9c55b9e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"a breakdown chewed up two days on Line 1 in one recalled odd week\"},\"kind\":\"activity\",\"node\":\"breakdown on a line\",\"precision\":\"number\",\"rationale\":\"Mentioned in passing as a validation case — one recalled incident, not a rate or a distribution.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -10474,152 +5098,180 @@
           "value": {
             "type": "slot-asserted",
             "kind": "objective",
-            "node": "is the mill-to-fill tank on Line 1 slowing the line down",
-            "slot": "the nodes it depends on",
-            "precision": "named",
-            "rationale": "Expert named stage-level rates on Line 1, the tank size between mill and fill, and per-SKU stage differences.",
+            "node": "the wash-versus-idle call",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The expert's own framing of the decision the model must inform, given as a real recent case.",
             "assertion": {
-              "value": [
-                "entity-type:the four stages — mix, mill, tint, fill",
-                "constraint:small holding tank between mill and fill on Line 1",
-                "entity-type:order",
-                "entity-type:line"
-              ]
+              "value": "Whether to wash down Line 2 for the tint order right then, or let Line 2 sit idle for about an hour waiting for a smaller white order that needs no changeover — a judgment made by gut maybe three or four times a month, never verified."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.",
+            "excerpt": "I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others",
+            "excerpt": "That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-0e28490a-6b4b-4996-9b6f-3d9249a7d2dc",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:the four stages — mix, mill, tint, fill\",\"constraint:small holding tank between mill and fill on Line 1\",\"entity-type:order\",\"entity-type:line\"]},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"named\",\"rationale\":\"Expert named stage-level rates on Line 1, the tank size between mill and fill, and per-SKU stage differences.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-da8d88a4-c4e2-499b-b138-3f3df855b108",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whether to wash down Line 2 for the tint order right then, or let Line 2 sit idle for about an hour waiting for a smaller white order that needs no changeover — a judgment made by gut maybe three or four times a month, never verified.\"},\"kind\":\"objective\",\"node\":\"the wash-versus-idle call\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own framing of the decision the model must inform, given as a real recent case.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour because I knew another white order — a smaller one, but still white, no changeover needed — was going to be released from the demand book that afternoon.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That's exactly the kind of call I'd love to be able to test — because I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order",
-            "slot": "state that rides along with each instance",
-            "precision": "spelled out",
-            "rationale": "Expert named the fields the order carries from the demand book and the state he consults mid-disruption.",
+            "kind": "objective",
+            "node": "the wash-versus-idle call",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "The expert named the scope of the decision: orders, three lines, the shared crew, the changeovers, the run and the QA hold up to cleared-QA.",
             "assertion": {
-              "value": "Quantity, due date, SKU; remaining quantity as it runs; the customer it belongs to; how far through it is; which line and slot it is allocated to."
+              "value": [
+                "entity-type:order",
+                "entity-type:the three lines",
+                "entity-type:the changeover crew",
+                "boundary-condition:the demand book",
+                "activity:white-to-tint changeover on Line 2",
+                "activity:tint-to-white changeover",
+                "activity:specialty changeover",
+                "activity:the run",
+                "activity:QA hold",
+                "ordering/flow:release to cleared QA",
+                "policy:who gets the crew",
+                "constraint:no Meridian misses"
+              ]
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "excerpt": "in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "whose order was it — that's the \"who can absorb it\" judgment call again",
+            "excerpt": "So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "an order's mine from release to \"cleared QA,\" and the due date is judged against when it clears, not when it comes off the line",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-43c5ef42-68ce-478f-89b0-c552111d807a",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; remaining quantity as it runs; the customer it belongs to; how far through it is; which line and slot it is allocated to.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Expert named the fields the order carries from the demand book and the state he consults mid-disruption.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whose order was it — that's the \\\\\\\"who can absorb it\\\\\\\" judgment call again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-d9c81987-582e-43fd-8ebb-a7be078ec2b7",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:the three lines\",\"entity-type:the changeover crew\",\"boundary-condition:the demand book\",\"activity:white-to-tint changeover on Line 2\",\"activity:tint-to-white changeover\",\"activity:specialty changeover\",\"activity:the run\",\"activity:QA hold\",\"ordering/flow:release to cleared QA\",\"policy:who gets the crew\",\"constraint:no Meridian misses\"]},\"kind\":\"objective\",\"node\":\"the wash-versus-idle call\",\"precision\":\"named\",\"rationale\":\"The expert named the scope of the decision: orders, three lines, the shared crew, the changeovers, the run and the QA hold up to cleared-QA.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So realistically the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"an order's mine from release to \\\\\\\"cleared QA,\\\\\\\" and the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in the moment I'm weighing changeover hours against idle hours — that's the gut math. But what my boss actually looks at is late orders.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order",
-            "slot": "the distinctions the process treats apart",
+            "kind": "objective",
+            "node": "the wash-versus-idle call",
+            "slot": "what \"better\" means, and trade-off weights",
             "precision": "spelled out",
-            "rationale": "The process treats whites and tints differently at the tint stage and in run times; customer type changes how a slip is judged.",
+            "sourceRegime": "practiced",
+            "rationale": "A lexicographic ranking, not a weight: Meridian misses are refused at any exchange rate the expert would see in a week.",
             "assertion": {
-              "value": "Whites versus tints (for a white the tint stage is barely there, a pass-through); and by customer type — distributor, small account, or an awkward account that gets prickly."
+              "value": "Better = no Meridian late orders first (not tradeable — three small late orders beat one Meridian miss, and even twenty small late orders would not flip it), then late-order count, with changeover hours and idle time as the expert's own diagnostics rather than the graded measure."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+            "excerpt": "If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere. The changeover hours and the idle time are more my own concern",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "(a) is the better week, easy — three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 9,
               "entryEnd": 9
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly",
+            "excerpt": "Even if you told me \"twenty small orders late\" versus \"one Meridian order late\" — I'd still not want to be the one who let Meridian slip.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-ccc2d7eb-8a3f-4684-8f1c-a21a51049550",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints (for a white the tint stage is barely there, a pass-through); and by customer type — distributor, small account, or an awkward account that gets prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The process treats whites and tints differently at the tint stage and in run times; customer type changes how a slip is judged.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-1e33246c-c307-46c2-b6c2-392fd7d92329",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Better = no Meridian late orders first (not tradeable — three small late orders beat one Meridian miss, and even twenty small late orders would not flip it), then late-order count, with changeover hours and idle time as the expert's own diagnostics rather than the graded measure.\"},\"kind\":\"objective\",\"node\":\"the wash-versus-idle call\",\"precision\":\"spelled out\",\"rationale\":\"A lexicographic ranking, not a weight: Meridian misses are refused at any exchange rate the expert would see in a week.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"(a) is the better week, easy — three little late orders to distributors who slip 2-3 days with a phone call anyway, that's a Tuesday, not a crisis.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Even if you told me \\\\\\\"twenty small orders late\\\\\\\" versus \\\\\\\"one Meridian order late\\\\\\\" — I'd still not want to be the one who let Meridian slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere. The changeover hours and the idle time are more my own concern\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "line",
-            "slot": "the distinctions the process treats apart",
+            "kind": "constraint",
+            "node": "no Meridian misses",
+            "slot": "the limit and what happens when it is hit",
             "precision": "spelled out",
-            "sourceRegime": "prescribed",
-            "rationale": "The sheet's representation of a line, which the expert says 'lies to me a bit'.",
+            "sourceRegime": "practiced",
+            "rationale": "An unwritten hard rule with a named consequence; the monetary exchange rate is explicitly unavailable and would have to come from commercial.",
             "assertion": {
-              "value": "On the scheduling sheet a line is one row and one resource: an order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done."
+              "value": "Meridian orders must not miss their due date — \"we just don't do that\". If one does: it's a fine, and ammunition for Meridian to delist a line item at next contract review; commercial gets calls and the boss gets calls. No cost exchange rate exists; obtaining one would require getting commercial in a room to state it."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+            "excerpt": "I know that's not a real number you can put in a formula. If you need a number, you'd have to get commercial in a room and force them to say it out loud, because right now it's a \"we just don't do that\" rule, not a traded-off cost.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the scheduling sheet a line is one row and one resource: an order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"spelled out\",\"rationale\":\"The sheet's representation of a line, which the expert says 'lies to me a bit'.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-59c35b27-63c3-4ae7-92d5-5454281a05e0",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian orders must not miss their due date — \\\"we just don't do that\\\". If one does: it's a fine, and ammunition for Meridian to delist a line item at next contract review; commercial gets calls and the boss gets calls. No cost exchange rate exists; obtaining one would require getting commercial in a room to state it.\"},\"kind\":\"constraint\",\"node\":\"no Meridian misses\",\"precision\":\"spelled out\",\"rationale\":\"An unwritten hard rule with a named consequence; the monetary exchange rate is explicitly unavailable and would have to come from commercial.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know that's not a real number you can put in a formula. If you need a number, you'd have to get commercial in a room and force them to say it out loud, because right now it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -10627,60 +5279,59 @@
           "value": {
             "type": "slot-asserted",
             "kind": "entity-type",
-            "node": "the four stages — mix, mill, tint, fill",
+            "node": "order",
             "slot": "the distinctions the process treats apart",
             "precision": "spelled out",
-            "sourceRegime": "practiced",
-            "rationale": "The floor's version of the line: four contended stages with buffers, not one resource.",
+            "rationale": "Customer class (Meridian vs distributor) and colour family (white / tint / specialty) are the distinctions that drive changeovers and lateness consequences.",
             "assertion": {
-              "value": "Physically mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head finishes the last one if the tank ahead has space."
+              "value": "Orders divide by customer — Meridian versus distributors (distributors slip 2-3 days with a phone call; a Meridian miss is a different category) — and by colour family: white, tint, and specialty, which decide whether and what kind of changeover is needed."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+            "excerpt": "it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "the crew will get a head start on mixing the next batch if the tank ahead of it has space",
+            "excerpt": "A Meridian miss is a different category — it's not just \"late,\"",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-a158a5da-be3a-461f-87c0-69c38cac1a72",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head finishes the last one if the tank ahead has space.\"},\"kind\":\"entity-type\",\"node\":\"the four stages — mix, mill, tint, fill\",\"precision\":\"spelled out\",\"rationale\":\"The floor's version of the line: four contended stages with buffers, not one resource.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the crew will get a head start on mixing the next batch if the tank ahead of it has space\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-7cb7c5b3-1c4e-42b5-8c28-b6b851d7b3c3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders divide by customer — Meridian versus distributors (distributors slip 2-3 days with a phone call; a Meridian miss is a different category) — and by colour family: white, tint, and specialty, which decide whether and what kind of changeover is needed.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Customer class (Meridian vs distributor) and colour family (white / tint / specialty) are the distinctions that drive changeovers and lateness consequences.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"A Meridian miss is a different category — it's not just \\\\\\\"late,\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's a fine, and it's ammunition for them to delist a line item next contract review. Commercial gets calls, my boss gets calls.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "entity-type",
-            "node": "the four stages — mix, mill, tint, fill",
-            "slot": "how many there are, or the population's shape",
-            "precision": "named",
-            "rationale": "Count of stages is stated; occupancy/blocking frequency is explicitly untracked.",
+            "node": "order",
+            "slot": "state that rides along with each instance",
+            "precision": "spelled out",
+            "rationale": "The attributes the order carries from release.",
             "assertion": {
-              "value": "Four stages in series per line — mix, mill, tint, fill — with small holding tanks between them; how often blocking occurs is not tracked."
+              "value": "SKU, quantity, and due date, carried from release in the demand book from ERP."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+            "excerpt": "it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
@@ -10688,189 +5339,185 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Four stages in series per line — mix, mill, tint, fill — with small holding tanks between them; how often blocking occurs is not tracked.\"},\"kind\":\"entity-type\",\"node\":\"the four stages — mix, mill, tint, fill\",\"precision\":\"named\",\"rationale\":\"Count of stages is stated; occupancy/blocking frequency is explicitly untracked.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "allocation",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "rationale": "Expert's step one.",
-            "assertion": {
-              "value": "The order is slotted onto a line and a slot in the week on the sheet."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-4043a577-c1b4-44c3-91f3-2194def82bd9",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Expert's step one.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-e20e49bb-dbd3-4616-8da4-f14024b09ed0",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"SKU, quantity, and due date, carried from release in the demand book from ERP.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The attributes the order carries from release.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "allocation",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
-            "rationale": "Precondition named in the walkthrough.",
+            "kind": "entity-type",
+            "node": "the changeover crew",
+            "slot": "how many there are, or the population's shape",
+            "precision": "number",
+            "rationale": "Explicit count of the contended resource.",
             "assertion": {
-              "value": "A line item in the demand book, produced by ERP, carrying quantity, due date and SKU."
+              "value": "One crew of two techs, covering all three lines."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book, produced by ERP, carrying quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Precondition named in the walkthrough.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-41a07d27-a4e5-4f0c-8308-854425894bc5",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One crew of two techs, covering all three lines.\"},\"kind\":\"entity-type\",\"node\":\"the changeover crew\",\"precision\":\"number\",\"rationale\":\"Explicit count of the contended resource.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "boundary-condition",
-            "node": "demand book from ERP",
-            "slot": "the starting state",
+            "kind": "entity-type",
+            "node": "the changeover crew",
+            "slot": "the distinctions the process treats apart",
             "precision": "spelled out",
-            "rationale": "External source of work into the scheduling process.",
+            "rationale": "The crew is treated as one indivisible unit serving one line at a time; other lines queue behind it.",
             "assertion": {
-              "value": "Orders exist as line items in the demand book, each with quantity, due date and SKU, once ERP produces it."
+              "value": "Treated as a single unit — either free or tied up on another line; if tied up, the wash-down option is not available and the line queues behind whoever else needs them."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "excerpt": "if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\" If they're tied up elsewhere, my \"wash down now\" option isn't even really available — I'd be queuing behind whoever else needs them.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders exist as line items in the demand book, each with quantity, due date and SKU, once ERP produces it.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"spelled out\",\"rationale\":\"External source of work into the scheduling process.\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-858e5f98-ce0c-47ca-9bff-1e41d25523eb",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Treated as a single unit — either free or tied up on another line; if tied up, the wash-down option is not available and the line queues behind whoever else needs them.\"},\"kind\":\"entity-type\",\"node\":\"the changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"The crew is treated as one indivisible unit serving one line at a time; other lines queue behind it.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"if I wash Line 2 down now, I'm also asking \\\\\\\"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\\\\\\\" If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available — I'd be queuing behind whoever else needs them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "how long it takes",
-            "precision": "range",
-            "sourceRegime": "practiced",
-            "rationale": "Expert corrected his first spread to strip out jams, so the clean-run figure supersedes; no one-in-ten-better figure was given for the clean run.",
+            "kind": "entity-type",
+            "node": "the three lines",
+            "slot": "how many there are, or the population's shape",
+            "precision": "number",
+            "rationale": "Three production lines, named Line 1, Line 2, Line 3.",
             "assertion": {
-              "value": "Meridian-sized white on Line 2, clean run (nothing breaks): typically eight to nine hours mix-to-last-pack; a bad-but-clean day nine to ten hours. Clean-run variability is small; the twelve-to-thirteen-hour bad days are breakdowns showing up inside the run and are modelled separately."
+              "value": "Three lines — Line 1, Line 2, Line 3."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
+            "excerpt": "there's one crew, two techs, covering all three lines",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.",
+            "excerpt": "Meridian white basically always goes to Line 2",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 21,
-              "entryEnd": 21
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-72d414e6-f6a2-420e-8407-667f41535411",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian-sized white on Line 2, clean run (nothing breaks): typically eight to nine hours mix-to-last-pack; a bad-but-clean day nine to ten hours. Clean-run variability is small; the twelve-to-thirteen-hour bad days are breakdowns showing up inside the run and are modelled separately.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"range\",\"rationale\":\"Expert corrected his first spread to strip out jams, so the clean-run figure supersedes; no one-in-ten-better figure was given for the clean run.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-5ac2a1b3-03ea-4864-a6e6-89ea2a3163d9",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three lines — Line 1, Line 2, Line 3.\"},\"kind\":\"entity-type\",\"node\":\"the three lines\",\"precision\":\"number\",\"rationale\":\"Three production lines, named Line 1, Line 2, Line 3.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "whether its quantities vary by type",
-            "precision": "named",
-            "rationale": "Durations vary by line and by white-versus-tint; the Line 1 figures were given before the clean-run/breakdown split and may still fold in stoppages.",
+            "kind": "entity-type",
+            "node": "the three lines",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "rationale": "Lines are distinguished by what they habitually run; Meridian white is effectively assigned to Line 2.",
             "assertion": {
-              "value": "Yes. Same white order on Line 1 is about fifty to sixty percent longer than Line 2 — typical thirteen to fourteen hours, worse days eighteen-plus, best day about ten. Tints run at nearly the same speed on either line, about eight to ten hours typical, with no big gap; the 'Line 2 is twice as fast' rule is really a whites number."
+              "value": "Lines are treated apart by what they run: Meridian white basically always goes to Line 2; Line 1 was running specialty and Line 3 tint in the recalled case."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+            "excerpt": "Meridian white basically always goes to Line 2, so it went into \"my\" Line 2 column on the sheet without much debate.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 18,
               "entryEnd": 18
             },
             "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Line 1 had just finished a specialty run",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Line 3 finished a tint run",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes. Same white order on Line 1 is about fifty to sixty percent longer than Line 2 — typical thirteen to fourteen hours, worse days eighteen-plus, best day about ten. Tints run at nearly the same speed on either line, about eight to ten hours typical, with no big gap; the 'Line 2 is twice as fast' rule is really a whites number.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Durations vary by line and by white-versus-tint; the Line 1 figures were given before the clean-run/breakdown split and may still fold in stoppages.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-42dc7c2d-13c1-407d-ab6e-8359366321d0",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lines are treated apart by what they run: Meridian white basically always goes to Line 2; Line 1 was running specialty and Line 3 tint in the recalled case.\"},\"kind\":\"entity-type\",\"node\":\"the three lines\",\"precision\":\"spelled out\",\"rationale\":\"Lines are distinguished by what they habitually run; Meridian white is effectively assigned to Line 2.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 had just finished a specialty run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 3 finished a tint run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2, so it went into \\\\\\\"my\\\\\\\" Line 2 column on the sheet without much debate.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "run it through mix/mill/tint/fill",
-            "slot": "who or what performs it",
-            "precision": "named",
-            "rationale": "Runs are performed on a named line; the expert compares Line 1 and Line 2 as the performing kit.",
+            "kind": "boundary-condition",
+            "node": "the demand book",
+            "slot": "the arrival or availability pattern",
+            "precision": "spelled out",
+            "rationale": "Orders arrive in weekly batches released from ERP into the demand book; the book is revised weekly and re-planned each morning at the huddle.",
             "assertion": {
-              "value": "One of the two production lines (Line 1 or Line 2) with its crew."
+              "value": "Orders are released from ERP into the demand book in a weekly batch (the recalled one was the Monday release). A week is the horizon that matters — the cycle of the demand book, re-planned every morning at the huddle. Beyond a week is soft because the book itself gets revised; the expert keeps half an eye two weeks out for big minimum-run specialty work, and would refuse to hold a plan a month out."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.",
+            "excerpt": "Practically, a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "on the Monday release, part of that week's batch of orders from ERP",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 18,
               "entryEnd": 18
             },
@@ -10878,8 +5525,8 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-53f9387d-f037-4d0f-999b-f89a8f113f46",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One of the two production lines (Line 1 or Line 2) with its crew.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Runs are performed on a named line; the expert compares Line 1 and Line 2 as the performing kit.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-442393fc-5207-40e8-953f-f32c4077af7b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders are released from ERP into the demand book in a weekly batch (the recalled one was the Monday release). A week is the horizon that matters — the cycle of the demand book, re-planned every morning at the huddle. Beyond a week is soft because the book itself gets revised; the expert keeps half an eye two weeks out for big minimum-run specialty work, and would refuse to hold a plan a month out.\"},\"kind\":\"boundary-condition\",\"node\":\"the demand book\",\"precision\":\"spelled out\",\"rationale\":\"Orders arrive in weekly batches released from ERP into the demand book; the book is revised weekly and re-planned each morning at the huddle.\",\"slot\":\"the arrival or availability pattern\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Practically, a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"on the Monday release, part of that week's batch of orders from ERP\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -10887,119 +5534,137 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "QA hold",
-            "slot": "who or what performs it",
-            "precision": "named",
-            "rationale": "Named performer in the walkthrough.",
+            "node": "the run",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "Precondition stated in the walkthrough: the line free of the previous job, and either same family (no changeover) or a completed changeover.",
             "assertion": {
-              "value": "The lab."
+              "value": "The order must be in the Line 2 column on the sheet and must wait its turn behind whatever is already running on that line; if the job ahead is the same family, no changeover is needed — a straight run-into-run."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+            "excerpt": "It had to wait its turn behind whatever was already running on Line 2.** There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Named performer in the walkthrough.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-9842aaa1-3de6-409e-a76a-4dc761ba75f4",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order must be in the Line 2 column on the sheet and must wait its turn behind whatever is already running on that line; if the job ahead is the same family, no changeover is needed — a straight run-into-run.\"},\"kind\":\"activity\",\"node\":\"the run\",\"precision\":\"spelled out\",\"rationale\":\"Precondition stated in the walkthrough: the line free of the previous job, and either same family (no changeover) or a completed changeover.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It had to wait its turn behind whatever was already running on Line 2.** There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "QA hold",
-            "slot": "how long it takes",
-            "precision": "named",
-            "rationale": "Only a vague 'few hours' was given; not yet a range or spread.",
+            "node": "the run",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "The run's output as described.",
             "assertion": {
-              "value": "Usually a few hours for a white; explicitly longer for specialty ('nothing like the specialty wait'), figure not given."
+              "value": "Mix, mill, tint stage (skipped for a white), through fill and pack; the finished order is palletized and moved off the line into the queue for the lab."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait",
+            "excerpt": "Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Once fill and pack was done, it went into QA hold.** That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-38e0effa-0fb7-48ff-907c-2fc9f3e64211",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; explicitly longer for specialty ('nothing like the specialty wait'), figure not given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Only a vague 'few hours' was given; not yet a range or spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-16bb49bd-8cb1-4840-a016-fb3c2e03ea06",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Mix, mill, tint stage (skipped for a white), through fill and pack; the finished order is palletized and moved off the line into the queue for the lab.\"},\"kind\":\"activity\",\"node\":\"the run\",\"precision\":\"spelled out\",\"rationale\":\"The run's output as described.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.** That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "release and ship",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "rationale": "Final step of the walkthrough.",
+            "node": "the run",
+            "slot": "how long it takes",
+            "precision": "number",
+            "rationale": "Only a single recalled case at roughly a day; the expert explicitly says exact hours would need the sheet, so no range or spread was reached.",
             "assertion": {
-              "value": "The order is released, goes to the warehouse, and ships against its due date."
+              "value": "For that big-volume Meridian white order: on the line most of the day — started Wednesday morning and wrapped Wednesday evening; exact hours would have to be checked on the sheet."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+            "excerpt": "it's a big volume order, so it was on the line most of the day. I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against its due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"rationale\":\"Final step of the walkthrough.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-874499fa-7846-4cc1-b5c3-1a214824b34b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"For that big-volume Meridian white order: on the line most of the day — started Wednesday morning and wrapped Wednesday evening; exact hours would have to be checked on the sheet.\"},\"kind\":\"activity\",\"node\":\"the run\",\"precision\":\"number\",\"rationale\":\"Only a single recalled case at roughly a day; the expert explicitly says exact hours would need the sheet, so no range or spread was reached.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it's a big volume order, so it was on the line most of the day. I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "order life on the floor",
-            "slot": "the order things happen in",
-            "precision": "spelled out",
-            "rationale": "Expert's own summary of the end-to-end sequence.",
+            "kind": "activity",
+            "node": "the run",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "The expert names the line as what runs the order and says he does not watch the operators minute by minute; no crew is involved in a run-into-run.",
             "assertion": {
-              "value": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship"
+              "value": "The line itself (Line 2 in the recalled case); no changeover crew involved — \"that's the easy case, no crew involved\". The expert does not watch it minute by minute."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+            "excerpt": "It ran.** Mix, mill, tint stage",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I don't watch this minute by minute",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-314d8187-81ba-478c-8f71-1c9e5826965b",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\"},\"kind\":\"ordering/flow\",\"node\":\"order life on the floor\",\"precision\":\"spelled out\",\"rationale\":\"Expert's own summary of the end-to-end sequence.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-7b487f70-d5b2-436f-96ca-c18b75d4f706",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line itself (Line 2 in the recalled case); no changeover crew involved — \\\"that's the easy case, no crew involved\\\". The expert does not watch it minute by minute.\"},\"kind\":\"activity\",\"node\":\"the run\",\"precision\":\"named\",\"rationale\":\"The expert names the line as what runs the order and says he does not watch the operators minute by minute; no crew is involved in a run-into-run.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't watch this minute by minute\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It ran.** Mix, mill, tint stage\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -11007,29 +5672,29 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "tint-to-white washdown",
+            "node": "QA hold",
             "slot": "how long it takes",
             "precision": "number",
-            "rationale": "Single figure given for the tint-to-white washdown; no spread elicited.",
+            "rationale": "A single typical figure for white only; no low/high given.",
             "assertion": {
-              "value": "Three hours"
+              "value": "Normally about four hours for a white."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late",
+            "excerpt": "It sat in QA** — normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-345fbb5a-c0c1-4e3a-9015-33b3ad727831",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Single figure given for the tint-to-white washdown; no spread elicited.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-1692771b-05c1-41fd-a63b-9b93436ac581",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Normally about four hours for a white.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"number\",\"rationale\":\"A single typical figure for white only; no low/high given.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It sat in QA** — normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -11037,38 +5702,38 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
-            "rationale": "Changeover is directional and triggered by the family of what was running versus what is coming.",
+            "node": "QA hold",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "rationale": "The expert distinguishes the white hold from the long specialty hold, and notes lab backlog extends it.",
             "assertion": {
-              "value": "A changeover between product families on the same line; the direction decides the cost — tint-to-white is the expensive one, not the other way."
+              "value": "Yes — a white is about four hours; specialty has a \"long specialty hold\". Duration also stretches when the lab is backed up."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "the direction of the changeover matters as much as the fact of it",
+            "excerpt": "nothing exotic about it chemically, so it's not the long specialty hold",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
+            "excerpt": "That QA gap matters more than people think — a batch can be done Tuesday and still ship late if the lab's backed up.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-60f6f8c8-f52e-443a-adee-6818339f3b35",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A changeover between product families on the same line; the direction decides the cost — tint-to-white is the expensive one, not the other way.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Changeover is directional and triggered by the family of what was running versus what is coming.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the direction of the changeover matters as much as the fact of it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-94cf39d1-87b6-4013-a9cf-06e97177192e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a white is about four hours; specialty has a \\\"long specialty hold\\\". Duration also stretches when the lab is backed up.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"The expert distinguishes the white hold from the long specialty hold, and notes lab backlog extends it.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That QA gap matters more than people think — a batch can be done Tuesday and still ship late if the lab's backed up.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"nothing exotic about it chemically, so it's not the long specialty hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -11076,29 +5741,38 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what it produces or changes",
+            "node": "QA hold",
+            "slot": "what it needs before it can start",
             "precision": "spelled out",
-            "rationale": "Stated consequence of the washdown.",
+            "rationale": "Precondition and completion as narrated.",
             "assertion": {
-              "value": "The line is cleaned from tint to white and is taken out of anything else for that window; it costs crew time."
+              "value": "Fill and pack complete; the order is palletized, moved off the line, and joins the queue for the lab. It ends when it clears QA and ships — lateness is judged against clearing QA."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "it takes Line 1 out of anything else for that window",
+            "excerpt": "Once fill and pack was done, it went into QA hold.** That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "It cleared and shipped Thursday**, ahead of the Friday due date.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-be556841-bf14-4fe0-8c23-ffc773896b2b",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line is cleaned from tint to white and is taken out of anything else for that window; it costs crew time.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Stated consequence of the washdown.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-2e05010d-aa3d-4558-bd3a-91b498169a94",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Fill and pack complete; the order is palletized, moved off the line, and joins the queue for the lab. It ends when it clears QA and ships — lateness is judged against clearing QA.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Precondition and completion as narrated.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It cleared and shipped Thursday**, ahead of the Friday due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.** That's where it sits — physically it's palletized and moved off the line, into the queue for the lab.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -11106,29 +5780,38 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what is lost when it changes the system's mode",
-            "rationale": "Loss is named and affirmed as material but no quantity is held by the expert.",
+            "node": "QA hold",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "Performed by the lab.",
             "assertion": {
-              "absence": "unknown-to-user",
-              "pointer": "ramp scrap after the washdown — real product lost on top of the hours; expert has no good numbers"
+              "value": "The lab."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours",
+            "excerpt": "It sat in QA",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I don't remember this one having any drama in the lab.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-26d3ac6c-4b27-4765-baa3-8437f06fe8ca",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"ramp scrap after the washdown — real product lost on top of the hours; expert has no good numbers\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"rationale\":\"Loss is named and affirmed as material but no quantity is held by the expert.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-34154727-71ce-4065-abbf-8be1752385ce",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Performed by the lab.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't remember this one having any drama in the lab.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It sat in QA\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -11136,39 +5819,30 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "filler jam",
+            "node": "white-to-tint changeover on Line 2",
             "slot": "how long it takes",
             "precision": "range",
             "sourceRegime": "practiced",
-            "rationale": "Expert gave two named kinds of repair plus one observed instance; no typical or decile figures yet.",
+            "rationale": "Low, high and a typical band given — a range with a typical, not a full spread; not rounded up.",
             "assertion": {
-              "value": "Between the 'half hour' kind and the 'half a shift' kind; the recent Line 2 case came back in about two hours."
+              "value": "Quickest maybe 40 minutes (crew right there, nothing fighting them); longest about an hour twenty on a bad day (crew stretched thin or something stuck); typically lands around 45 minutes to an hour. The \"cheap\" direction."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+            "excerpt": "White-to-tint on Line 2 — quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes. Longest, if they're stretched thin or something's stuck, I've seen it drag past an hour, call it an hour twenty on a bad day. Typically though it lands around 45 minutes to an hour. That's the \"cheap\" direction.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "I went with waiting, it came back in about two hours",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-da6d10a4-e0f2-4b1d-8e78-4d58cadeb8f2",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Between the 'half hour' kind and the 'half a shift' kind; the recent Line 2 case came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Expert gave two named kinds of repair plus one observed instance; no typical or decile figures yet.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-fc5a25de-846f-488d-9330-4d6b634c33b0",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quickest maybe 40 minutes (crew right there, nothing fighting them); longest about an hour twenty on a bad day (crew stretched thin or something stuck); typically lands around 45 minutes to an hour. The \\\"cheap\\\" direction.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover on Line 2\",\"precision\":\"range\",\"rationale\":\"Low, high and a typical band given — a range with a typical, not a full spread; not rounded up.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"White-to-tint on Line 2 — quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes. Longest, if they're stretched thin or something's stuck, I've seen it drag past an hour, call it an hour twenty on a bad day. Typically though it lands around 45 minutes to an hour. That's the \\\\\\\"cheap\\\\\\\" direction.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -11176,38 +5850,30 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "filler jam",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
-            "rationale": "Event-shaped activity that befalls the line, distinct from the run itself.",
+            "node": "white-to-tint changeover on Line 2",
+            "slot": "what is lost when it changes the system's mode",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "The loss on this mode change is the line time consumed by the wash; the expert gave it as the changeover duration.",
             "assertion": {
-              "value": "The filler stops mid-run and the line is down for the repair; the run in progress stretches (the twelve-to-thirteen-hour bad days), and the scheduler must decide to wait or shift the order to the other line."
+              "value": "Line time consumed by the changeover: 40 minutes to an hour twenty, typically 45 minutes to an hour, plus occupancy of the two-tech crew for that period."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+            "excerpt": "Typically though it lands around 45 minutes to an hour. That's the \"cheap\" direction.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 21,
-              "entryEnd": 21
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-68f9db28-a002-406d-912a-4cc410e5b380",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The filler stops mid-run and the line is down for the repair; the run in progress stretches (the twelve-to-thirteen-hour bad days), and the scheduler must decide to wait or shift the order to the other line.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"Event-shaped activity that befalls the line, distinct from the run itself.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-126e6b44-aa42-452b-9085-7bd038842721",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line time consumed by the changeover: 40 minutes to an hour twenty, typically 45 minutes to an hour, plus occupancy of the two-tech crew for that period.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover on Line 2\",\"precision\":\"range\",\"rationale\":\"The loss on this mode change is the line time consumed by the wash; the expert gave it as the changeover duration.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Typically though it lands around 45 minutes to an hour. That's the \\\\\\\"cheap\\\\\\\" direction.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -11215,20 +5881,21 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "filler jam",
-            "slot": "how often it occurs, if it is an event rather than a step",
-            "rationale": "No rate was stated; recording the gap rather than inferring one from the single incident.",
+            "node": "tint-to-white changeover",
+            "slot": "how long it takes",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Low two and a half hours, high toward four hours, typical three hours — a range with a typical.",
             "assertion": {
-              "absence": "unknown-to-user",
-              "pointer": "frequency of filler jams was not given; expert spoke only to duration uncertainty at the time of the jam"
+              "value": "Quickest maybe two and a half hours (everything clean, crew fresh); on a bad day — dried pigment in a fitting — it has crept toward four hours; three hours typical, the number actually used on the sheet."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of \"could be quick, could be long\" rather than one number",
+            "excerpt": "Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric. Any pigment left behind wrecks a white batch, so that's a full washdown. Quickest I've seen that go is maybe two and a half hours if everything's clean and the crew's fresh. On a bad day — dried pigment in a fitting, whatever — it's crept toward four hours. Call it three hours typical, and that's the number I actually use on the sheet.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 24,
               "entryEnd": 24
             },
@@ -11236,663 +5903,720 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-0a06d184-bf72-42c4-95b3-7ad88ea4e059",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"frequency of filler jams was not given; expert spoke only to duration uncertainty at the time of the jam\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"rationale\":\"No rate was stated; recording the gap rather than inferring one from the single incident.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of \\\\\\\"could be quick, could be long\\\\\\\" rather than one number\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-2b6dc206-914d-4980-b539-3621f9c5a118",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quickest maybe two and a half hours (everything clean, crew fresh); on a bad day — dried pigment in a fitting — it has crept toward four hours; three hours typical, the number actually used on the sheet.\"},\"kind\":\"activity\",\"node\":\"tint-to-white changeover\",\"precision\":\"range\",\"rationale\":\"Low two and a half hours, high toward four hours, typical three hours — a range with a typical.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric. Any pigment left behind wrecks a white batch, so that's a full washdown. Quickest I've seen that go is maybe two and a half hours if everything's clean and the crew's fresh. On a bad day — dried pigment in a fitting, whatever — it's crept toward four hours. Call it three hours typical, and that's the number I actually use on the sheet.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "policy",
-            "node": "who can absorb the slip",
-            "slot": "the rule as actually practiced",
-            "precision": "spelled out",
+            "kind": "activity",
+            "node": "tint-to-white changeover",
+            "slot": "what is lost when it changes the system's mode",
+            "precision": "range",
             "sourceRegime": "practiced",
-            "rationale": "The tacit rule for choosing which order to bump; no formula, judged on customer identity and size of slip.",
+            "rationale": "Loss is the full washdown time on the line plus the crew, driven by the direction of the change.",
             "assertion": {
-              "value": "Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first, so it is protected."
+              "value": "A full washdown — two and a half to four hours of line time, three typical — because any pigment left behind wrecks a white batch; direction matters, it is not symmetric with white-to-tint."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+            "excerpt": "Any pigment left behind wrecks a white batch, so that's a full washdown.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "I use judgment on who can absorb the slip",
+            "excerpt": "a full white-to-tint changeover is a wash we can't get back",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first, so it is protected.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The tacit rule for choosing which order to bump; no formula, judged on customer identity and size of slip.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-97c6e438-15c4-48f8-84c1-fdb8d5b42e3e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A full washdown — two and a half to four hours of line time, three typical — because any pigment left behind wrecks a white batch; direction matters, it is not symmetric with white-to-tint.\"},\"kind\":\"activity\",\"node\":\"tint-to-white changeover\",\"precision\":\"range\",\"rationale\":\"Loss is the full washdown time on the line plus the crew, driven by the direction of the change.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Any pigment left behind wrecks a white batch, so that's a full washdown.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a full white-to-tint changeover is a wash we can't get back\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "policy",
-            "node": "who can absorb the slip",
-            "slot": "what overrides it",
-            "precision": "spelled out",
+            "kind": "activity",
+            "node": "specialty changeover",
+            "slot": "how long it takes",
+            "precision": "range",
             "sourceRegime": "practiced",
-            "rationale": "Hard constraint sitting above the absorb-the-slip judgment.",
+            "rationale": "Range with typical, explicitly less closely observed than white/tint changeovers.",
             "assertion": {
-              "value": "The protected order's on-time ship date overrides: shipping Meridian on time is a line he won't cross unless there's truly no way through."
+              "value": "Around two hours normally, either direction into or out of a specialty run; as short as maybe an hour forty for a specialty-to-specialty colour change rather than a full family switch; not seen much longer than two and a half hours. Observed less closely than white-tint changeovers."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+            "excerpt": "Specialty is its own animal again, like you said — going in or coming out of a specialty run, either direction, it's around two hours normally. I've seen it shorter, maybe an hour forty if it's a specialty-to-specialty color change rather than a full family switch. I haven't seen it run much longer than two and a half hours, but I'll be honest, I don't watch specialty changeovers as closely as I watch the white-tint ones because they don't hit my due dates as hard.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The protected order's on-time ship date overrides: shipping Meridian on time is a line he won't cross unless there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint sitting above the absorb-the-slip judgment.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-b1cfeb47-e2b4-4730-9483-1422b8597b5c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Around two hours normally, either direction into or out of a specialty run; as short as maybe an hour forty for a specialty-to-specialty colour change rather than a full family switch; not seen much longer than two and a half hours. Observed less closely than white-tint changeovers.\"},\"kind\":\"activity\",\"node\":\"specialty changeover\",\"precision\":\"range\",\"rationale\":\"Range with typical, explicitly less closely observed than white/tint changeovers.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Specialty is its own animal again, like you said — going in or coming out of a specialty run, either direction, it's around two hours normally. I've seen it shorter, maybe an hour forty if it's a specialty-to-specialty color change rather than a full family switch. I haven't seen it run much longer than two and a half hours, but I'll be honest, I don't watch specialty changeovers as closely as I watch the white-tint ones because they don't hit my due dates as hard.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "constraint",
-            "node": "small holding tank between mill and fill on Line 1",
-            "slot": "the limit and what happens when it is hit",
-            "precision": "spelled out",
-            "rationale": "Qualitative blocking rule stated; the numeric capacity is not available from the expert.",
+            "kind": "activity",
+            "node": "tint-to-white changeover",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "rationale": "Explicit answer that changeover duration varies by direction and family.",
             "assertion": {
-              "value": "Holding tanks between stages are small — especially the one between mill and fill on Line 1. When there is room, the upstream stage can start the next order's batch; when the tank is full, the upstream stage is blocked and mixing has to wait. Actual tank capacity is not held by the expert; engineering's position is that the line rate is what it is regardless."
+              "value": "Yes — changeover duration varies by direction and family: white-to-tint is the cheap direction, tint-to-white the expensive one, specialty its own animal."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.",
+            "excerpt": "Okay, let's separate those because they're genuinely not the same beast.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
-            },
-            "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-7111ab55-5d90-44f6-a1d2-4aa1b48da4bb",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tanks between stages are small — especially the one between mill and fill on Line 1. When there is room, the upstream stage can start the next order's batch; when the tank is full, the upstream stage is blocked and mixing has to wait. Actual tank capacity is not held by the expert; engineering's position is that the line rate is what it is regardless.\"},\"kind\":\"constraint\",\"node\":\"small holding tank between mill and fill on Line 1\",\"precision\":\"spelled out\",\"rationale\":\"Qualitative blocking rule stated; the numeric capacity is not available from the expert.\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "data-binding",
-            "node": "stage-level rates",
-            "slot": "the variable and its feed",
-            "precision": "named",
-            "rationale": "Expert named the system where the missing stage-level numbers live.",
-            "assertion": {
-              "value": "Stage-by-stage durations/rates (how long mixing takes, how long milling takes, mill speed versus fill speed on Line 1) — feed: the historian."
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+            "excerpt": "direction absolutely matters — it's not symmetric",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations/rates (how long mixing takes, how long milling takes, mill speed versus fill speed on Line 1) — feed: the historian.\"},\"kind\":\"data-binding\",\"node\":\"stage-level rates\",\"precision\":\"named\",\"rationale\":\"Expert named the system where the missing stage-level numbers live.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-b833dc1b-dd19-4d7d-bc4f-754e5e63bb7b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — changeover duration varies by direction and family: white-to-tint is the cheap direction, tint-to-white the expensive one, specialty its own animal.\"},\"kind\":\"activity\",\"node\":\"tint-to-white changeover\",\"precision\":\"named\",\"rationale\":\"Explicit answer that changeover duration varies by direction and family.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Okay, let's separate those because they're genuinely not the same beast.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"direction absolutely matters — it's not symmetric\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "data-binding",
-            "node": "tank sizes",
-            "slot": "the variable and its feed",
+            "kind": "activity",
+            "node": "white-to-tint changeover on Line 2",
+            "slot": "who or what performs it",
             "precision": "named",
-            "rationale": "Named source for a value the expert cannot give.",
+            "rationale": "All changeovers are performed by the shared two-tech crew.",
             "assertion": {
-              "value": "Holding tank capacities between stages — feed: engineering drawings, obtainable but not carried by the expert."
+              "value": "The changeover crew — one crew, two techs, shared across all three lines."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Line 1 had just finished a specialty run and needed the full two-hour changeover before the next job",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tank capacities between stages — feed: engineering drawings, obtainable but not carried by the expert.\"},\"kind\":\"data-binding\",\"node\":\"tank sizes\",\"precision\":\"named\",\"rationale\":\"Named source for a value the expert cannot give.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-6fd52cfc-df4d-4a0b-8381-1a80c29a4d4a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The changeover crew — one crew, two techs, shared across all three lines.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover on Line 2\",\"precision\":\"named\",\"rationale\":\"All changeovers are performed by the shared two-tech crew.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 had just finished a specialty run and needed the full two-hour changeover before the next job\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "switch or wait when Line 2 goes down mid-run",
-            "slot": "the question, in the expert's words",
+            "kind": "activity",
+            "node": "white-to-tint changeover on Line 2",
+            "slot": "what it needs before it can start",
             "precision": "spelled out",
-            "rationale": "The expert wrote the question as they would type it into the tool.",
+            "rationale": "Precondition: previous run finished and the shared crew available.",
             "assertion": {
-              "value": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\""
+              "value": "The previous run on the line finished and the changeover crew free; if the crew is tied up on another line, the changeover cannot start and the line queues behind whoever else needs them."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"",
+            "excerpt": "If they're tied up elsewhere, my \"wash down now\" option isn't even really available — I'd be queuing behind whoever else needs them.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-1a240192-8179-4339-815e-3775a062e986",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\"\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down mid-run\",\"precision\":\"spelled out\",\"rationale\":\"The expert wrote the question as they would type it into the tool.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-9da728a5-b72c-4e7a-ba0d-a360ef571059",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The previous run on the line finished and the changeover crew free; if the crew is tied up on another line, the changeover cannot start and the line queues behind whoever else needs them.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover on Line 2\",\"precision\":\"spelled out\",\"rationale\":\"Precondition: previous run finished and the shared crew available.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available — I'd be queuing behind whoever else needs them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "switch or wait when Line 2 goes down mid-run",
-            "slot": "the nodes it depends on",
-            "precision": "named",
-            "rationale": "The expert listed what the answer hangs on.",
+            "kind": "ordering/flow",
+            "node": "release to cleared QA",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "rationale": "The end-to-end sequence walked through for one real order.",
             "assertion": {
-              "value": [
-                "entity-type:order",
-                "entity-type:Line 1 and Line 2",
-                "activity:the run (mix, mill, tint, fill)",
-                "activity:filler jam",
-                "activity:tint-to-white washdown",
-                "policy:who can absorb the slip",
-                "constraint:Meridian ships on time"
-              ]
+              "value": "1) Order lands in the demand book on the weekly ERP release with SKU, quantity, due date, and is assigned to a line's column on the sheet. 2) It waits its turn behind whatever is already running on that line (with a changeover first if the family differs). 3) It runs — mix, mill, tint stage, fill and pack. 4) It is palletized, moved off the line, and enters QA hold in the queue for the lab. 5) It sits in QA. 6) It clears QA and ships; the due date is judged against clearing, not coming off the line."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
+            "excerpt": "It landed in the demand book** on the Monday release, part of that week's batch of orders from ERP — a Meridian order, big white SKU, due Friday.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "It hangs on the jam itself — how long is this repair *actually* going to take",
+            "excerpt": "It had to wait its turn behind whatever was already running on Line 2.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "And it hangs on the ramp scrap after the washdown",
+            "excerpt": "Once fill and pack was done, it went into QA hold.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the \"who can absorb it\" judgment call again.",
+            "excerpt": "It cleared and shipped Thursday**, ahead of the Friday due date.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-85062afa-e82d-46ce-b609-f7ed16f8b093",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:Line 1 and Line 2\",\"activity:the run (mix, mill, tint, fill)\",\"activity:filler jam\",\"activity:tint-to-white washdown\",\"policy:who can absorb the slip\",\"constraint:Meridian ships on time\"]},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down mid-run\",\"precision\":\"named\",\"rationale\":\"The expert listed what the answer hangs on.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And it hangs on the ramp scrap after the washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the \\\\\\\"who can absorb it\\\\\\\" judgment call again.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It hangs on the jam itself — how long is this repair *actually* going to take\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-4bdfb1af-a858-493c-bf5a-2da4279d18a5",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"1) Order lands in the demand book on the weekly ERP release with SKU, quantity, due date, and is assigned to a line's column on the sheet. 2) It waits its turn behind whatever is already running on that line (with a changeover first if the family differs). 3) It runs — mix, mill, tint stage, fill and pack. 4) It is palletized, moved off the line, and enters QA hold in the queue for the lab. 5) It sits in QA. 6) It clears QA and ships; the due date is judged against clearing, not coming off the line.\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"The end-to-end sequence walked through for one real order.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It cleared and shipped Thursday**, ahead of the Friday due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It had to wait its turn behind whatever was already running on Line 2.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It landed in the demand book** on the Monday release, part of that week's batch of orders from ERP — a Meridian order, big white SKU, due Friday.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "switch or wait when Line 2 goes down mid-run",
-            "slot": "what \"better\" means, and trade-off weights",
+            "kind": "ordering/flow",
+            "node": "release to cleared QA",
+            "slot": "how a branch or merge is decided",
             "precision": "spelled out",
-            "rationale": "Hard constraint plus unweighted secondary measures; the expert explicitly denied having a formula.",
+            "rationale": "Two branch points named: line assignment by SKU/customer habit, and whether a changeover is inserted based on family match.",
             "assertion": {
-              "value": "Meridian on time is non-negotiable (days late on Meridian, anything above zero is bad news); underneath that, washdown hours and whether the bumped order goes late and by how much are weighed by judgment — \"I don't have a formula for it.\""
+              "value": "Line assignment: by habit of the SKU — Meridian white basically always goes to Line 2, entered in that line's column on the sheet. Changeover branch: if the next job is the same family as the one just finished, no changeover — a straight run-into-run; if a different family, a changeover is inserted whose kind and length depends on the direction (white-to-tint, tint-to-white, specialty)."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing",
+            "excerpt": "Meridian white basically always goes to Line 2, so it went into \"my\" Line 2 column on the sheet without much debate.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "I don't have a formula for it.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "days late on Meridian, and anything above zero is bad news I have to go explain",
+            "excerpt": "There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-2c3fa15f-551b-4380-a3b3-8dbc6334a9bb",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian on time is non-negotiable (days late on Meridian, anything above zero is bad news); underneath that, washdown hours and whether the bumped order goes late and by how much are weighed by judgment — \\\"I don't have a formula for it.\\\"\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down mid-run\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint plus unweighted secondary measures; the expert explicitly denied having a formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"days late on Meridian, and anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-663314c5-79fe-4e3c-918a-1ac8047113a1",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line assignment: by habit of the SKU — Meridian white basically always goes to Line 2, entered in that line's column on the sheet. Changeover branch: if the next job is the same family as the one just finished, no changeover — a straight run-into-run; if a different family, a changeover is inserted whose kind and length depends on the direction (white-to-tint, tint-to-white, specialty).\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"Two branch points named: line assignment by SKU/customer habit, and whether a changeover is inserted based on family match.\",\"slot\":\"how a branch or merge is decided\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2, so it went into \\\\\\\"my\\\\\\\" Line 2 column on the sheet without much debate.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "is the mill-to-fill tank on Line 1 slowing the line down",
-            "slot": "the question, in the expert's words",
+            "kind": "policy",
+            "node": "who gets the crew",
+            "slot": "the rule as actually practiced",
             "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The practiced allocation rule, given from a real incident three weeks ago; explicitly unwritten.",
             "assertion": {
-              "value": "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\""
+              "value": "If a Meridian job sits behind one of the competing changeovers, the crew goes to that line, full stop, without discussion. Otherwise the scheduler's judgment call at the morning huddle on whose next job is tightest against its due date (in the recalled case Line 1 won over Line 3, which had a couple of days of slack, and Line 3 sat clean but idle close to two hours). Failing that it is whoever's line supervisor gets to the crew lead first. Nobody has written this rule down."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"",
+            "excerpt": "Practically, what happens is not some clean rule — it's whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "That morning I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date, and Line 3's next job had a couple days of slack.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "If it had been Meridian sitting behind either of those changeovers, that decision doesn't even get discussed — the crew goes to whichever line has the Meridian job next, full stop, everyone understands that without me saying it out loud.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-41269bfb-9040-4d54-a113-a94c09f6f2f0",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\"\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-ccb16fb1-30dc-4a94-8367-fd11a5a97373",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"If a Meridian job sits behind one of the competing changeovers, the crew goes to that line, full stop, without discussion. Otherwise the scheduler's judgment call at the morning huddle on whose next job is tightest against its due date (in the recalled case Line 1 won over Line 3, which had a couple of days of slack, and Line 3 sat clean but idle close to two hours). Failing that it is whoever's line supervisor gets to the crew lead first. Nobody has written this rule down.\"},\"kind\":\"policy\",\"node\":\"who gets the crew\",\"precision\":\"spelled out\",\"rationale\":\"The practiced allocation rule, given from a real incident three weeks ago; explicitly unwritten.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If it had been Meridian sitting behind either of those changeovers, that decision doesn't even get discussed — the crew goes to whichever line has the Meridian job next, full stop, everyone understands that without me saying it out loud.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Practically, what happens is not some clean rule — it's whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That morning I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date, and Line 3's next job had a couple days of slack.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "is the mill-to-fill tank on Line 1 slowing the line down",
-            "slot": "the nodes it depends on",
-            "precision": "named",
+            "kind": "policy",
+            "node": "who gets the crew",
+            "slot": "what overrides it",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Named override with escalation path; frequency given only as \"rare\".",
             "assertion": {
-              "value": [
-                "entity-type:mix, mill, tint, fill kit and holding tanks",
-                "entity-type:Line 1 and Line 2",
-                "entity-type:order",
-                "ordering/flow:stage overlap on a line"
-              ]
+              "value": "Maintenance can grab the crew mid-job for a genuine emergency — a line leaking, something needing isolating right now. Rare, and not the scheduler's call; a real fight escalates over his head to the ops director."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.",
+            "excerpt": "Has anyone ever pulled the crew off mid-job? Yes, actually — maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now. That's rare, and it's not my call, that's a maintenance-versus-me argument that goes over my head to the ops director if it's a real fight.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "It also probably depends on the product, since I now realize different SKUs are slow at different stages",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-f7ea7c88-4d40-48e7-84e5-2b12ebc5ea8e",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:mix, mill, tint, fill kit and holding tanks\",\"entity-type:Line 1 and Line 2\",\"entity-type:order\",\"ordering/flow:stage overlap on a line\"]},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"named\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It also probably depends on the product, since I now realize different SKUs are slow at different stages\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-822d9723-b7fa-40c4-8921-2a10de44868f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Maintenance can grab the crew mid-job for a genuine emergency — a line leaking, something needing isolating right now. Rare, and not the scheduler's call; a real fight escalates over his head to the ops director.\"},\"kind\":\"policy\",\"node\":\"who gets the crew\",\"precision\":\"spelled out\",\"rationale\":\"Named override with escalation path; frequency given only as \\\"rare\\\".\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Has anyone ever pulled the crew off mid-job? Yes, actually — maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now. That's rare, and it's not my call, that's a maintenance-versus-me argument that goes over my head to the ops director if it's a real fight.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "is the mill-to-fill tank on Line 1 slowing the line down",
-            "slot": "what \"better\" means, and trade-off weights",
+            "kind": "constraint",
+            "node": "one crew serving three lines",
+            "slot": "the limit and what happens when it is hit",
             "precision": "spelled out",
-            "rationale": "Qualitative: showing where Line 1 loses its time, in a form usable with engineering.",
+            "sourceRegime": "practiced",
+            "rationale": "Capacity limit with its practiced consequence: the losing line idles and the loss is invisible in reporting.",
             "assertion": {
-              "value": "The model showing \"here's where Line 1 loses its time\" — something to take to engineering other than a hunch; no numeric weighting given."
+              "value": "Only one changeover can be served at a time by the single two-tech crew. When two lines want them at once, the losing line sits clean but idle waiting its turn — close to two hours in the recalled case — and that wasted line time does not show up anywhere as a problem."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.",
+            "excerpt": "Line 3 sat there clean but idle for — I want to say close to two hours — waiting its turn. Nobody died over it, but it's wasted line time that doesn't show up anywhere as a \"problem,\" it's just... the day.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The model showing \\\"here's where Line 1 loses its time\\\" — something to take to engineering other than a hunch; no numeric weighting given.\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"rationale\":\"Qualitative: showing where Line 1 loses its time, in a form usable with engineering.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-03f46087-a1d4-409d-80f3-b7c87e23a1b3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Only one changeover can be served at a time by the single two-tech crew. When two lines want them at once, the losing line sits clean but idle waiting its turn — close to two hours in the recalled case — and that wasted line time does not show up anywhere as a problem.\"},\"kind\":\"constraint\",\"node\":\"one crew serving three lines\",\"precision\":\"spelled out\",\"rationale\":\"Capacity limit with its practiced consequence: the losing line idles and the loss is invisible in reporting.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 3 sat there clean but idle for — I want to say close to two hours — waiting its turn. Nobody died over it, but it's wasted line time that doesn't show up anywhere as a \\\\\\\"problem,\\\\\\\" it's just... the day.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order",
-            "slot": "the distinctions the process treats apart",
+            "kind": "validation-criterion",
+            "node": "recognize the shape of a real month",
+            "slot": "how the expert would know the model is right",
             "precision": "spelled out",
+            "rationale": "The expert's own acceptance test, given as a replay of last month's demand book.",
             "assertion": {
-              "value": "Whites versus tints (family decides run speed by line and washdown direction; for a white the tint stage is a pass-through); and customer identity — distributor, small account, or an awkward account that gets prickly."
+              "value": "Replay last month's demand book: it must land roughly where the plant actually landed on late orders — same rough number and same kind of misses (at least two Meridian scrapes and a handful of small ones); getting the kind wrong is worse than getting the count wrong. Then eyeball changeover hours on Lines 2 and 3 — if Line 3 is idle half the week waiting on the crew, which never happens in real life, it is missing something about how the crew gets shared. It must also reproduce the odd weeks, e.g. where a breakdown chewed up two days on Line 1. No single number is trusted; the shape of a real month must be recognizable."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+            "excerpt": "the first thing I'd check is the boring one — did it land roughly where we actually landed on late orders that month?",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
+            "excerpt": "we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones. So: same rough number and same *kind* of misses. If it says we missed distributor orders and we actually missed a Meridian one, that's worse than getting the count wrong.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "the bumped order's identity matters, not just \"an order got delayed.\"",
+            "excerpt": "After that I'd want to eyeball changeover hours on Line 2 and 3 specifically",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly",
+            "excerpt": "And I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I wouldn't trust a single number out of it, put it that way. I'd want to recognize the *shape* of a real month before I'd believe it on something as specific as the wash-versus-idle call.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-0e8d50b2-4222-4129-a619-09c5612c05c5",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints (family decides run speed by line and washdown direction; for a white the tint stage is a pass-through); and customer identity — distributor, small account, or an awkward account that gets prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the bumped order's identity matters, not just \\\\\\\"an order got delayed.\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-fac82088-05f2-4519-a697-b149c0798172",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Replay last month's demand book: it must land roughly where the plant actually landed on late orders — same rough number and same kind of misses (at least two Meridian scrapes and a handful of small ones); getting the kind wrong is worse than getting the count wrong. Then eyeball changeover hours on Lines 2 and 3 — if Line 3 is idle half the week waiting on the crew, which never happens in real life, it is missing something about how the crew gets shared. It must also reproduce the odd weeks, e.g. where a breakdown chewed up two days on Line 1. No single number is trusted; the shape of a real month must be recognizable.\"},\"kind\":\"validation-criterion\",\"node\":\"recognize the shape of a real month\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own acceptance test, given as a replay of last month's demand book.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"After that I'd want to eyeball changeover hours on Line 2 and 3 specifically\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"And I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I wouldn't trust a single number out of it, put it that way. I'd want to recognize the *shape* of a real month before I'd believe it on something as specific as the wash-versus-idle call.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first thing I'd check is the boring one — did it land roughly where we actually landed on late orders that month?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones. So: same rough number and same *kind* of misses. If it says we missed distributor orders and we actually missed a Meridian one, that's worse than getting the count wrong.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order",
-            "slot": "state that rides along with each instance",
-            "precision": "spelled out",
+            "kind": "data-binding",
+            "node": "changeover log and late-order report",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "rationale": "Two existing feeds named by the expert, currently unlinked.",
             "assertion": {
-              "value": "Quantity, due date, SKU; family (white/tint); customer; remaining quantity and how far through the run it is."
+              "value": "Changeover hours from the changeover log; late orders from the late-order report. They exist separately and nobody has ever put them on the same page."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "excerpt": "I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
             },
             "source": "user-affordance-payload"
-          },
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-7a236317-f8ea-43e8-b88a-a6c6092fb35f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Changeover hours from the changeover log; late orders from the late-order report. They exist separately and nobody has ever put them on the same page.\"},\"kind\":\"data-binding\",\"node\":\"changeover log and late-order report\",\"precision\":\"named\",\"rationale\":\"Two existing feeds named by the expert, currently unlinked.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "breakdown on a line",
+            "slot": "how long it takes",
+            "precision": "number",
+            "sourceRegime": "practiced",
+            "rationale": "Mentioned only in passing as a validation case; duration given as a single recalled figure, no rate given.",
+            "assertion": {
+              "value": "A breakdown chewed up two days on Line 1 in one recalled month."
+            }
+          }
+        },
+        "evidence": [
           {
-            "excerpt": "the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is",
+            "excerpt": "I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-117f9832-aaba-473a-9411-6fd4022388f2",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; family (white/tint); customer; remaining quantity and how far through the run it is.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-60d6dc44-d2ee-456c-ad19-1c54d79f37dd",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A breakdown chewed up two days on Line 1 in one recalled month.\"},\"kind\":\"activity\",\"node\":\"breakdown on a line\",\"precision\":\"number\",\"rationale\":\"Mentioned only in passing as a validation case; duration given as a single recalled figure, no rate given.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd want to see if it reproduces the odd weeks — the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "order",
-            "slot": "how many there are, or the population's shape",
+            "kind": "activity",
+            "node": "breakdown on a line",
+            "slot": "how often it occurs, if it is an event rather than a step",
             "precision": "named",
-            "rationale": "The expert described orders arriving as line items in the demand book but gave no counts or arrival volumes.",
+            "rationale": "The expert referred to \"the odd weeks\" without giving a rate; no frequency was elicited before the time cue.",
             "assertion": {
               "absence": "unknown-to-user",
-              "pointer": "demand book / ERP"
+              "pointer": "breakdown frequency not yet asked; expert referred only to \"the odd weeks\""
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "excerpt": "the ones where a breakdown chewed up two days on Line 1",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "inferred",
-        "id": "capture-e10d4081-78ed-42da-bb26-857f1118224c",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"demand book / ERP\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"named\",\"rationale\":\"The expert described orders arriving as line items in the demand book but gave no counts or arrival volumes.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "explicit",
+        "id": "capture-16c2b41b-9778-4091-91c3-5f15f72171e9",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"breakdown frequency not yet asked; expert referred only to \\\"the odd weeks\\\"\"},\"kind\":\"activity\",\"node\":\"breakdown on a line\",\"precision\":\"named\",\"rationale\":\"The expert referred to \\\"the odd weeks\\\" without giving a rate; no frequency was elicited before the time cue.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "Line 1 and Line 2",
-            "slot": "the distinctions the process treats apart",
+            "kind": "objective",
+            "node": "wash-versus-idle call on Line 2",
+            "slot": "the question, in the expert's words",
             "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The anchoring decision the model must inform, given as a real recent case.",
             "assertion": {
-              "value": "Two lines: Line 2 is the faster machine on whites (roughly twice as fast, \"really a whites number\"); Line 1 is the slower machine, add fifty to sixty percent on a white. On tints the two run at nearly the same speed."
+              "value": "Whether to wash down for the tint right then, or let Line 2 sit idle for about an hour waiting for a same-colour (white) order expected to be released that afternoon — a judgment made by gut maybe three or four times a month, never proven right or wrong."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+            "excerpt": "wash down for the tint right then, or let Line 2 sit idle for about an hour",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed",
+            "excerpt": "I make that judgment by gut maybe three or four times a month",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-875ed21b-d257-48fe-867b-6785abf6abb7",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two lines: Line 2 is the faster machine on whites (roughly twice as fast, \\\"really a whites number\\\"); Line 1 is the slower machine, add fifty to sixty percent on a white. On tints the two run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-c58069b0-72b7-4ff3-8bb8-16f7861f0212",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whether to wash down for the tint right then, or let Line 2 sit idle for about an hour waiting for a same-colour (white) order expected to be released that afternoon — a judgment made by gut maybe three or four times a month, never proven right or wrong.\"},\"kind\":\"objective\",\"node\":\"wash-versus-idle call on Line 2\",\"precision\":\"spelled out\",\"rationale\":\"The anchoring decision the model must inform, given as a real recent case.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I make that judgment by gut maybe three or four times a month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"wash down for the tint right then, or let Line 2 sit idle for about an hour\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "Line 1 and Line 2",
-            "slot": "state that rides along with each instance",
+            "kind": "objective",
+            "node": "wash-versus-idle call on Line 2",
+            "slot": "what \"better\" means, and trade-off weights",
             "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Ranking rather than a weight; expert explicitly refused an exchange rate and named where one would come from.",
             "assertion": {
-              "value": "What order is on it, how far through that order is, and what family (tint or white) it is currently running — the last decides washdown cost and direction."
+              "value": "No Meridian misses first (a hard rule, not a weight — does not flip even at twenty small orders late versus one Meridian), then late-order count, with changeover hours and idle time as the scheduler's own diagnostics. A real exchange rate between Meridian and small late orders would have to come from commercial being put in a room and forced to say it out loud."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction",
+            "excerpt": "what my boss actually looks at is late orders",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "The changeover hours and the idle time are more my own concern",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I don't think it does flip, not in any range I'd actually see in a week",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "you'd have to get commercial in a room and force them to say it out loud",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-06d48b41-86fb-48c0-b3e0-59012ba81960",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"What order is on it, how far through that order is, and what family (tint or white) it is currently running — the last decides washdown cost and direction.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-727571fe-b1b2-4fb8-9247-5658db4a18f9",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"No Meridian misses first (a hard rule, not a weight — does not flip even at twenty small orders late versus one Meridian), then late-order count, with changeover hours and idle time as the scheduler's own diagnostics. A real exchange rate between Meridian and small late orders would have to come from commercial being put in a room and forced to say it out loud.\"},\"kind\":\"objective\",\"node\":\"wash-versus-idle call on Line 2\",\"precision\":\"spelled out\",\"rationale\":\"Ranking rather than a weight; expert explicitly refused an exchange rate and named where one would come from.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't think it does flip, not in any range I'd actually see in a week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The changeover hours and the idle time are more my own concern\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what my boss actually looks at is late orders\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"you'd have to get commercial in a room and force them to say it out loud\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "Line 1 and Line 2",
-            "slot": "how many there are, or the population's shape",
-            "precision": "number",
-            "rationale": "The expert speaks only of Line 1 and Line 2 throughout.",
+            "kind": "objective",
+            "node": "wash-versus-idle call on Line 2",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "Nodes the expert named as inside the scheduling unit and the lateness clock.",
             "assertion": {
-              "value": "Two lines — Line 1 and Line 2."
+              "value": [
+                "entity-type:order",
+                "entity-type:changeover crew",
+                "entity-type:the three lines",
+                "boundary-condition:the demand book",
+                "activity:the run (mix, mill, fill and pack)",
+                "activity:white-to-tint changeover",
+                "activity:tint-to-white washdown",
+                "activity:specialty changeover",
+                "activity:QA hold",
+                "ordering/flow:release to cleared QA",
+                "policy:who gets the crew",
+                "constraint:we just don't do that (Meridian)"
+              ]
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "On the sheet, \"Line 2\" is one row",
+            "excerpt": "the unit I'm scheduling across is all three lines plus that one crew",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Line 1 was mid-run on a tint.",
+            "excerpt": "It ends when it clears QA hold and ships.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the due date is judged against when it clears, not when it comes off the line",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "explicit",
-        "id": "capture-428e3931-676d-4af5-a30c-d7a31ea0d8ad",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two lines — Line 1 and Line 2.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"number\",\"rationale\":\"The expert speaks only of Line 1 and Line 2 throughout.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "inferred",
+        "id": "capture-cd397b8a-ae0d-4e4a-887c-46a790d86277",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:changeover crew\",\"entity-type:the three lines\",\"boundary-condition:the demand book\",\"activity:the run (mix, mill, fill and pack)\",\"activity:white-to-tint changeover\",\"activity:tint-to-white washdown\",\"activity:specialty changeover\",\"activity:QA hold\",\"ordering/flow:release to cleared QA\",\"policy:who gets the crew\",\"constraint:we just don't do that (Meridian)\"]},\"kind\":\"objective\",\"node\":\"wash-versus-idle call on Line 2\",\"precision\":\"named\",\"rationale\":\"Nodes the expert named as inside the scheduling unit and the lateness clock.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It ends when it clears QA hold and ships.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the unit I'm scheduling across is all three lines plus that one crew\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -11900,99 +6624,78 @@
           "value": {
             "type": "slot-asserted",
             "kind": "entity-type",
-            "node": "mix, mill, tint, fill kit and holding tanks",
+            "node": "order",
             "slot": "the distinctions the process treats apart",
             "precision": "spelled out",
             "sourceRegime": "practiced",
+            "rationale": "Customer class and colour family are the two distinctions the process treats differently.",
             "assertion": {
-              "value": "Mix, mill, tint and fill are separate tanks and separate kit strung together, with small holding tanks between them."
+              "value": "By customer: Meridian orders versus small distributor orders (distributors slip 2-3 days with a phone call anyway; Meridian misses are a different category). By colour family: white, tint, and specialty — the family determines whether a changeover is needed and which one. Meridian white basically always goes to Line 2."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+            "excerpt": "three little late orders to distributors who slip 2-3 days with a phone call anyway",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-ecd3c093-8f6b-4a48-a1fc-d2775d4dbc1f",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Mix, mill, tint and fill are separate tanks and separate kit strung together, with small holding tanks between them.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill kit and holding tanks\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "mix, mill, tint, fill kit and holding tanks",
-            "slot": "how many there are, or the population's shape",
-            "precision": "named",
-            "rationale": "Qualitative \"small\" only; sizes deferred to engineering drawings.",
-            "assertion": {
-              "absence": "deferred",
-              "pointer": "engineering drawings"
-            }
-          }
-        },
-        "evidence": [
+          },
           {
-            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
+            "excerpt": "Meridian white basically always goes to Line 2",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "excerpt": "Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-c6339dee-036e-47cb-9dcf-42fc22d38aae",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill kit and holding tanks\",\"precision\":\"named\",\"rationale\":\"Qualitative \\\"small\\\" only; sizes deferred to engineering drawings.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-e0913c34-cd78-40d4-a420-6b28eba826af",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"By customer: Meridian orders versus small distributor orders (distributors slip 2-3 days with a phone call anyway; Meridian misses are a different category). By colour family: white, tint, and specialty — the family determines whether a changeover is needed and which one. Meridian white basically always goes to Line 2.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Customer class and colour family are the two distinctions the process treats differently.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"three little late orders to distributors who slip 2-3 days with a phone call anyway\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "constraint",
-            "node": "holding tank capacity between stages",
-            "slot": "the limit and what happens when it is hit",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "state that rides along with each instance",
             "precision": "spelled out",
-            "rationale": "Blocking consequence stated; frequency and size not tracked.",
+            "rationale": "Attributes carried from release; lateness judged at QA clearance.",
             "assertion": {
-              "value": "A stage can only get a head start if there's room in the holding tank ahead of it; when a tank's full, mixing has to wait. How often that blocking happens is not tracked by the expert."
+              "value": "SKU, quantity, due date — carried from release out of ERP into the demand book; the due date is judged against when the order clears QA, not when it comes off the line."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "if there's room in the holding tank between mix and mill, or mill and fill, to buffer it",
+            "excerpt": "it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+            "excerpt": "the due date is judged against when it clears, not when it comes off the line",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
@@ -12000,127 +6703,130 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-2bc071c4-2919-4ff3-910a-92d872eeaef2",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A stage can only get a head start if there's room in the holding tank ahead of it; when a tank's full, mixing has to wait. How often that blocking happens is not tracked by the expert.\"},\"kind\":\"constraint\",\"node\":\"holding tank capacity between stages\",\"precision\":\"spelled out\",\"rationale\":\"Blocking consequence stated; frequency and size not tracked.\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if there's room in the holding tank between mix and mill, or mill and fill, to buffer it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-fa08bd90-3a4a-4ce8-880b-8b5ba2b2467f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"SKU, quantity, due date — carried from release out of ERP into the demand book; the due date is judged against when the order clears QA, not when it comes off the line.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Attributes carried from release; lateness judged at QA clearance.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "order lifecycle: allocate, run, QA hold, release and ship",
-            "slot": "the order things happen in",
-            "precision": "spelled out",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "how many there are, or the population's shape",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Weekly population of orders given as a low/high across quiet and busy weeks.",
             "assertion": {
-              "value": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship"
+              "value": "30 orders in a quiet week up to 55–60 in a busy one"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship",
+            "excerpt": "quiet week might be 30 orders, a busy one pushes 55–60",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 27,
+              "entryEnd": 27
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-6ec49aac-c165-4e2b-a937-bed3c8c51c2c",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\"},\"kind\":\"ordering/flow\",\"node\":\"order lifecycle: allocate, run, QA hold, release and ship\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-62e66b8a-bc31-4ccb-9611-ad1e05dd0aed",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"30 orders in a quiet week up to 55–60 in a busy one\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"range\",\"rationale\":\"Weekly population of orders given as a low/high across quiet and busy weeks.\",\"slot\":\"how many there are, or the population's shape\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"quiet week might be 30 orders, a busy one pushes 55–60\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "order lifecycle: allocate, run, QA hold, release and ship",
-            "slot": "how a branch or merge is decided",
-            "precision": "spelled out",
-            "rationale": "The line choice is made by the scheduler at allocation and can be revisited on disruption.",
+            "kind": "entity-type",
+            "node": "changeover crew",
+            "slot": "how many there are, or the population's shape",
+            "precision": "number",
+            "rationale": "Contended resource count stated directly.",
             "assertion": {
-              "value": "The scheduler slots the order onto a line on the sheet at allocation; on a disruption the choice is re-decided — shift it to the other line or wait out the repair."
+              "value": "One crew of two techs, covering all three lines"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "I had to decide right then whether to shift it to Line 1 or just wait out the repair",
+            "excerpt": "there's one crew, two techs, covering all three lines",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-c3f03d77-6760-4b3b-99e5-b78d119a352f",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The scheduler slots the order onto a line on the sheet at allocation; on a disruption the choice is re-decided — shift it to the other line or wait out the repair.\"},\"kind\":\"ordering/flow\",\"node\":\"order lifecycle: allocate, run, QA hold, release and ship\",\"precision\":\"spelled out\",\"rationale\":\"The line choice is made by the scheduler at allocation and can be revisited on disruption.\",\"slot\":\"how a branch or merge is decided\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had to decide right then whether to shift it to Line 1 or just wait out the repair\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-14764933-9818-4f65-b6e2-4623dbbf39b3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One crew of two techs, covering all three lines\"},\"kind\":\"entity-type\",\"node\":\"changeover crew\",\"precision\":\"number\",\"rationale\":\"Contended resource count stated directly.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "stage overlap on a line",
-            "slot": "the order things happen in",
+            "kind": "entity-type",
+            "node": "changeover crew",
+            "slot": "the distinctions the process treats apart",
             "precision": "spelled out",
-            "sourceRegime": "prescribed",
+            "sourceRegime": "practiced",
+            "rationale": "Crew treated as one indivisible unit shared across lines, also grabbable by maintenance.",
             "assertion": {
-              "value": "On the sheet the line is one row: the order occupies the line for its whole run, mix through fill, and nothing else is scheduled on it until it's done."
+              "value": "A single changeover crew treated as one unit — two techs together — covering all three lines; maintenance can also grab them for a genuine emergency."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+            "excerpt": "there's one crew, two techs, covering all three lines",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
             "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "maintenance will sometimes grab them if there's a genuine emergency",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet the line is one row: the order occupies the line for its whole run, mix through fill, and nothing else is scheduled on it until it's done.\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-de6129c5-8785-4833-97b5-5767d578660a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A single changeover crew treated as one unit — two techs together — covering all three lines; maintenance can also grab them for a genuine emergency.\"},\"kind\":\"entity-type\",\"node\":\"changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"Crew treated as one indivisible unit shared across lines, also grabbable by maintenance.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maintenance will sometimes grab them if there's a genuine emergency\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "stage overlap on a line",
-            "slot": "the order things happen in",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
+            "kind": "entity-type",
+            "node": "the three lines",
+            "slot": "how many there are, or the population's shape",
+            "precision": "number",
+            "rationale": "Scheduling scope named as three lines.",
             "assertion": {
-              "value": "The mixer can start the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill; the crew get a head start on mixing when the tank ahead has space."
+              "value": "Three lines — Line 1, Line 2, Line 3"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.",
+            "excerpt": "the unit I'm scheduling across is all three lines plus that one crew",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 12,
               "entryEnd": 12
             },
@@ -12128,203 +6834,226 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-83e1381a-f2df-4713-a2f6-f11d034c2fd4",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The mixer can start the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill; the crew get a head start on mixing when the tank ahead has space.\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-0aec8732-ae48-4d5c-98f1-abedf334e4bf",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three lines — Line 1, Line 2, Line 3\"},\"kind\":\"entity-type\",\"node\":\"the three lines\",\"precision\":\"number\",\"rationale\":\"Scheduling scope named as three lines.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the unit I'm scheduling across is all three lines plus that one crew\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "the run (mix, mill, tint, fill)",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
+            "kind": "entity-type",
+            "node": "the three lines",
+            "slot": "the distinctions the process treats apart",
+            "precision": "named",
+            "sourceRegime": "practiced",
+            "rationale": "Only routing distinction the expert volunteered; general line-to-product eligibility not yet elicited.",
             "assertion": {
-              "value": "The order allocated onto a line and a slot in the week (\"I slot it onto Line 2 on the sheet, that's step one, allocation\")."
+              "value": "Lines are distinguished by what routes to them in practice — Meridian white basically always goes to Line 2; Line 1 was running specialty in the recalled case. Full line/product eligibility not yet stated."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
+            "excerpt": "Meridian white basically always goes to Line 2",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Line 1 had just finished a specialty run",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-95cbfe20-605f-4218-9076-0f4816ebadfa",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order allocated onto a line and a slot in the week (\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\").\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-46c3af0c-9caa-4e30-ab54-92cc136acac1",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lines are distinguished by what routes to them in practice — Meridian white basically always goes to Line 2; Line 1 was running specialty in the recalled case. Full line/product eligibility not yet stated.\"},\"kind\":\"entity-type\",\"node\":\"the three lines\",\"precision\":\"named\",\"rationale\":\"Only routing distinction the expert volunteered; general line-to-product eligibility not yet elicited.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 had just finished a specialty run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "the run (mix, mill, tint, fill)",
-            "slot": "what it produces or changes",
+            "kind": "boundary-condition",
+            "node": "the demand book",
+            "slot": "the arrival or availability pattern",
             "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Two arrival channels: the Monday drop and intra-week additions; Meridian regular, distributors lumpy.",
             "assertion": {
-              "value": "Filled and packed product coming off the fill line, which then goes into QA hold."
+              "value": "Official release Monday morning — the big drop, 30-something to 60 orders depending on the week — plus additions pushed in by sales and commercial through the week, sometimes daily, when a customer calls last-minute or an order is confirmed late. Quiet week 30 orders, busy week 55–60. Not wildly seasonal, more lumpy depending on who's restocking. Meridian is fairly regular, close to weekly; the smaller distributors swing."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Once it comes off the fill line it goes into QA hold",
+            "excerpt": "The book officially releases Monday morning — that's the big drop, 30-something to 60 orders depending on the week.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Sales and commercial push in additions through the week, sometimes daily",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Meridian in particular is fairly regular, close to weekly, but the smaller distributors are the ones that swing",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 27,
+              "entryEnd": 27
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-1a5a8343-7367-416e-b760-c7e8f587fe25",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Filled and packed product coming off the fill line, which then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-4614313d-ba9f-4286-8cc0-2b2d07978c3e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Official release Monday morning — the big drop, 30-something to 60 orders depending on the week — plus additions pushed in by sales and commercial through the week, sometimes daily, when a customer calls last-minute or an order is confirmed late. Quiet week 30 orders, busy week 55–60. Not wildly seasonal, more lumpy depending on who's restocking. Meridian is fairly regular, close to weekly; the smaller distributors swing.\"},\"kind\":\"boundary-condition\",\"node\":\"the demand book\",\"precision\":\"spelled out\",\"rationale\":\"Two arrival channels: the Monday drop and intra-week additions; Meridian regular, distributors lumpy.\",\"slot\":\"the arrival or availability pattern\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian in particular is fairly regular, close to weekly, but the smaller distributors are the ones that swing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Sales and commercial push in additions through the week, sometimes daily\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The book officially releases Monday morning — that's the big drop, 30-something to 60 orders depending on the week.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "the run (mix, mill, tint, fill)",
-            "slot": "who or what performs it",
-            "precision": "named",
+            "kind": "boundary-condition",
+            "node": "the demand book",
+            "slot": "the starting state",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Foreknowledge of an unreleased order is part of the scheduler's starting information; the decision rested on it.",
             "assertion": {
-              "value": "The line (Line 1 or Line 2) — its mix, mill, tint and fill kit — worked by the crew."
+              "value": "Beyond the released book, the scheduler starts with informal foreknowledge: a commercial contact mentioning in passing at the Monday huddle that a Meridian top-up order was \"probably coming\" because it's a repeat account with a reorder pattern — not a scheduled release, just remembering a conversation and half-expecting it."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "mix, mill, tint, fill are separate tanks and separate kit strung together",
+            "excerpt": "our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \"probably coming,\" because it's a repeat account and there's a pattern to when they reorder",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 27,
+              "entryEnd": 27
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "maybe six hours if everything's clean and the crew doesn't have to stop for anything",
+            "excerpt": "it wasn't a scheduled release, it was more me remembering a conversation and half-expecting it",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 27,
+              "entryEnd": 27
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-bf2e57a3-bda7-4090-92ca-af63e0c7a248",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line (Line 1 or Line 2) — its mix, mill, tint and fill kit — worked by the crew.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maybe six hours if everything's clean and the crew doesn't have to stop for anything\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill are separate tanks and separate kit strung together\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-aab9beb5-8b53-44ce-a621-4dfd4621d53b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Beyond the released book, the scheduler starts with informal foreknowledge: a commercial contact mentioning in passing at the Monday huddle that a Meridian top-up order was \\\"probably coming\\\" because it's a repeat account with a reorder pattern — not a scheduled release, just remembering a conversation and half-expecting it.\"},\"kind\":\"boundary-condition\",\"node\":\"the demand book\",\"precision\":\"spelled out\",\"rationale\":\"Foreknowledge of an unreleased order is part of the scheduler's starting information; the decision rested on it.\",\"slot\":\"the starting state\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it wasn't a scheduled release, it was more me remembering a conversation and half-expecting it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"our commercial contact had mentioned in passing at the Monday huddle that a Meridian top-up order was \\\\\\\"probably coming,\\\\\\\" because it's a repeat account and there's a pattern to when they reorder\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "the run (mix, mill, tint, fill)",
-            "slot": "how long it takes",
-            "precision": "spread",
-            "rationale": "First account of a white run on Line 2, mix-to-last-pack, including breakdowns folded in loosely.",
+            "kind": "ordering/flow",
+            "node": "release to cleared QA",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The end-to-end sequence from the walked slice.",
             "assertion": {
-              "value": "White, Line 2, normal order size, mix-to-last-pack: typical eight to nine hours; one in ten worse twelve to thirteen hours; one in ten better about six hours. (Expert later said the twelve-thirteen folds in breakdowns.)"
+              "value": "1. Order lands in the demand book on the Monday release from ERP and is assigned a line column on the sheet. 2. It waits its turn behind whatever is already running on that line. 3. It runs — mix, mill, tint stage, straight through to fill and pack. 4. Once fill and pack is done it is palletized, moved off the line and goes into QA hold. 5. It sits in the queue for the lab. 6. It clears QA and ships."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
+            "excerpt": "It landed in the demand book",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 18,
               "entryEnd": 18
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours",
+            "excerpt": "It had to wait its turn behind whatever was already running on Line 2.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 18,
               "entryEnd": 18
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
+            "excerpt": "Once fill and pack was done, it went into QA hold.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 18,
               "entryEnd": 18
             },
             "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-aec8ff27-3e3f-45d2-9142-b6dc2b5d88a3",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, Line 2, normal order size, mix-to-last-pack: typical eight to nine hours; one in ten worse twelve to thirteen hours; one in ten better about six hours. (Expert later said the twelve-thirteen folds in breakdowns.)\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"rationale\":\"First account of a white run on Line 2, mix-to-last-pack, including breakdowns folded in loosely.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "the run (mix, mill, tint, fill)",
-            "slot": "how long it takes",
-            "precision": "spread",
-            "rationale": "Supersedes the earlier figure by stripping breakdowns out of the run duration; jams are modelled separately.",
-            "assertion": {
-              "value": "Clean run (nothing breaks), white on Line 2: typical eight or nine hours; bad-but-clean one in ten nine to ten hours; one in ten better about six hours. The twelve-thirteen hour bad day is a breakdown showing up inside the run, not the run itself being slow."
-            }
-          }
-        },
-        "evidence": [
+          },
           {
-            "excerpt": "If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.",
+            "excerpt": "It cleared and shipped Thursday",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 21,
-              "entryEnd": 21
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-9d59a385-a8ae-410a-a13d-a4bca3dde9a3",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Clean run (nothing breaks), white on Line 2: typical eight or nine hours; bad-but-clean one in ten nine to ten hours; one in ten better about six hours. The twelve-thirteen hour bad day is a breakdown showing up inside the run, not the run itself being slow.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"rationale\":\"Supersedes the earlier figure by stripping breakdowns out of the run duration; jams are modelled separately.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-080fcd60-7191-4d7f-82dd-203e24c66b72",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"1. Order lands in the demand book on the Monday release from ERP and is assigned a line column on the sheet. 2. It waits its turn behind whatever is already running on that line. 3. It runs — mix, mill, tint stage, straight through to fill and pack. 4. Once fill and pack is done it is palletized, moved off the line and goes into QA hold. 5. It sits in the queue for the lab. 6. It clears QA and ships.\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"The end-to-end sequence from the walked slice.\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It cleared and shipped Thursday\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It had to wait its turn behind whatever was already running on Line 2.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It landed in the demand book\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "the run (mix, mill, tint, fill)",
-            "slot": "how long it takes",
-            "precision": "spread",
-            "rationale": "Same white order on Line 1.",
+            "kind": "ordering/flow",
+            "node": "release to cleared QA",
+            "slot": "how a branch or merge is decided",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Branch between straight run-into-run and a changeover, decided by family; plus line assignment.",
             "assertion": {
-              "value": "White on Line 1: typical thirteen to fourteen hours; worse days pushing eighteen-plus; best day maybe ten — roughly fifty to sixty percent more than Line 2."
+              "value": "Between consecutive jobs on a line: if the next job is the same family, no changeover is needed — a straight run-into-run; if it is a different family (white/tint/specialty), the matching changeover activity must happen first and needs the crew. Line assignment at release follows habit — Meridian white basically always goes to Line 2, without much debate."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+            "excerpt": "There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Meridian white basically always goes to Line 2",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 18,
               "entryEnd": 18
             },
@@ -12332,29 +7061,30 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-4b22a066-a97c-4329-8513-cbd85edd8d65",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White on Line 1: typical thirteen to fourteen hours; worse days pushing eighteen-plus; best day maybe ten — roughly fifty to sixty percent more than Line 2.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"rationale\":\"Same white order on Line 1.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-d93639f5-4867-46ea-9a2f-7a7beedb6b88",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Between consecutive jobs on a line: if the next job is the same family, no changeover is needed — a straight run-into-run; if it is a different family (white/tint/specialty), the matching changeover activity must happen first and needs the crew. Line assignment at release follows habit — Meridian white basically always goes to Line 2, without much debate.\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"Branch between straight run-into-run and a changeover, decided by family; plus line assignment.\",\"slot\":\"how a branch or merge is decided\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "the run (mix, mill, tint, fill)",
-            "slot": "how long it takes",
-            "precision": "range",
-            "rationale": "Only a typical range was given for tints; no one-in-ten figures.",
+            "node": "the run (mix, mill, fill and pack)",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Preconditions from the slice: line free, and either same family or completed changeover.",
             "assertion": {
-              "value": "Tint run on either line: eight to ten hours typical; no big gap between the lines. One-in-ten worse/better not given."
+              "value": "The line must be free — the job waits its turn behind whatever is already running — and either the previous job is the same family (no changeover needed, a straight run-into-run) or the changeover has been completed."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap",
+            "excerpt": "There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 18,
               "entryEnd": 18
             },
@@ -12362,8 +7092,8 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-63fabb67-24c4-4bee-926f-17917300c8f4",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Tint run on either line: eight to ten hours typical; no big gap between the lines. One-in-ten worse/better not given.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"range\",\"rationale\":\"Only a typical range was given for tints; no one-in-ten figures.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-8cee0e81-ca2d-4d87-8400-d68f2a2c73dc",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line must be free — the job waits its turn behind whatever is already running — and either the previous job is the same family (no changeover needed, a straight run-into-run) or the changeover has been completed.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"spelled out\",\"rationale\":\"Preconditions from the slice: line free, and either same family or completed changeover.\",\"slot\":\"what it needs before it can start\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -12371,75 +7101,78 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "the run (mix, mill, tint, fill)",
-            "slot": "whether its quantities vary by type",
-            "precision": "named",
+            "node": "the run (mix, mill, fill and pack)",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Output of the run stage as stated.",
             "assertion": {
-              "value": "Yes — run time varies by family and by line: whites are about twice as fast on Line 2 as Line 1, tints run at nearly the same speed on both; and different SKUs are slow at different stages."
+              "value": "Takes the order through mix, mill, tint stage (skipped for a white), straight through to fill and pack; the finished order then goes into QA hold."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
+            "excerpt": "Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 18,
               "entryEnd": 18
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+            "excerpt": "Once fill and pack was done, it went into QA hold.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 18,
               "entryEnd": 18
             },
             "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "since I now realize different SKUs are slow at different stages",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
-            },
-            "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-b1e5ded4-79d6-4ff4-bd0d-6386509efba9",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — run time varies by family and by line: whites are about twice as fast on Line 2 as Line 1, tints run at nearly the same speed on both; and different SKUs are slow at different stages.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"named\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"since I now realize different SKUs are slow at different stages\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-9866d0f3-f549-4193-8bdb-bf43563f18ee",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Takes the order through mix, mill, tint stage (skipped for a white), straight through to fill and pack; the finished order then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"spelled out\",\"rationale\":\"Output of the run stage as stated.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "filler jam",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
+            "node": "the run (mix, mill, fill and pack)",
+            "slot": "how long it takes",
+            "precision": "named",
+            "sourceRegime": "practiced",
+            "rationale": "Only a recalled single case at day granularity; expert named the sheet as the source for exact hours and per-unit rate was not reached.",
             "assertion": {
-              "value": "It stops the run on the line — \"Line 2 filler jammed at about nine in the morning, half a shift lost\" — forcing the wait-or-shift decision."
+              "value": "For the big-volume Meridian white order: on the line most of the day — started Wednesday morning and wrapped Wednesday evening, \"something like that\". Exact hours, and run time per unit on each line, would have to come from the sheet."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+            "excerpt": "it was on the line most of the day",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-147c2765-6bfb-4da0-9df9-b74a1c1049de",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"It stops the run on the line — \\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\" — forcing the wait-or-shift decision.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-151800e3-5e9d-4f3b-aada-02b05532b0cb",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"For the big-volume Meridian white order: on the line most of the day — started Wednesday morning and wrapped Wednesday evening, \\\"something like that\\\". Exact hours, and run time per unit on each line, would have to come from the sheet.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"named\",\"rationale\":\"Only a recalled single case at day granularity; expert named the sheet as the source for exact hours and per-unit rate was not reached.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it was on the line most of the day\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -12447,29 +7180,38 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "filler jam",
-            "slot": "how often it occurs, if it is an event rather than a step",
-            "precision": "range",
-            "rationale": "Line 2 filler, jams bad enough to stop the run.",
+            "node": "QA hold",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "Entry condition from the slice.",
             "assertion": {
-              "value": "Every week or two; low end once every three weeks, high end twice a week when temperamental. Not seasonal, but runs streaks of bad weeks."
+              "value": "Fill and pack complete; the batch is palletized and moved off the line into the queue for the lab."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "It's a \"every week or two\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.",
+            "excerpt": "physically it's palletized and moved off the line, into the queue for the lab",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 27,
-              "entryEnd": 27
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Once fill and pack was done, it went into QA hold.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-ec5740e7-5068-4222-ad24-8396f5975657",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Every week or two; low end once every three weeks, high end twice a week when temperamental. Not seasonal, but runs streaks of bad weeks.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Line 2 filler, jams bad enough to stop the run.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It's a \\\\\\\"every week or two\\\\\\\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-e2e03e25-a4df-4386-955a-56f2634c8bd7",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Fill and pack complete; the batch is palletized and moved off the line into the queue for the lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Entry condition from the slice.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"physically it's palletized and moved off the line, into the queue for the lab\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -12477,76 +7219,79 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "filler jam",
-            "slot": "how long it takes",
-            "precision": "spread",
+            "node": "QA hold",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "QA clearance is the event lateness is measured against.",
             "assertion": {
-              "value": "Typical repair thirty to forty-five minutes; one-in-ten quick ten to fifteen minutes (a false alarm); one-in-ten bad four to five hours, occasionally eating the rest of the shift, when something's actually broken in the filler head."
+              "value": "The order clears QA and ships; clearance is the moment the due date is judged against — a batch can be done Tuesday and still ship late if the lab's backed up."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again",
+            "excerpt": "It cleared and shipped Thursday",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 27,
-              "entryEnd": 27
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm.",
+            "excerpt": "the due date is judged against when it clears, not when it comes off the line",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 27,
-              "entryEnd": 27
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift",
+            "excerpt": "a batch can be done Tuesday and still ship late if the lab's backed up",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 27,
-              "entryEnd": 27
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-2884cc84-c616-4227-860a-d6b55a06c13d",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Typical repair thirty to forty-five minutes; one-in-ten quick ten to fifteen minutes (a false alarm); one-in-ten bad four to five hours, occasionally eating the rest of the shift, when something's actually broken in the filler head.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-b458110a-8ab3-4a28-a3b7-52d8a9b6cc8c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order clears QA and ships; clearance is the moment the due date is judged against — a batch can be done Tuesday and still ship late if the lab's backed up.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"QA clearance is the event lateness is measured against.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It cleared and shipped Thursday\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a batch can be done Tuesday and still ship late if the lab's backed up\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "filler jam",
-            "slot": "who or what performs it",
-            "precision": "named",
-            "rationale": "Repair is done by a tech.",
+            "node": "QA hold",
+            "slot": "how long it takes",
+            "precision": "number",
+            "sourceRegime": "practiced",
+            "rationale": "A single hedged figure for white only; the specialty hold length was not given.",
             "assertion": {
-              "value": "A tech — comes over, clears whatever's jammed, resets."
+              "value": "About four hours for a white; the specialty hold is longer but its length was not stated."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "tech comes over, clears whatever's jammed, resets, we're going again",
+            "excerpt": "normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 27,
-              "entryEnd": 27
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-0548a680-8da8-47e9-ad72-fb1e264fac80",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A tech — comes over, clears whatever's jammed, resets.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"named\",\"rationale\":\"Repair is done by a tech.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"tech comes over, clears whatever's jammed, resets, we're going again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-473a9e08-c0d3-4b0c-8e2b-c13b77d9ab95",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"About four hours for a white; the specialty hold is longer but its length was not stated.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"number\",\"rationale\":\"A single hedged figure for white only; the specialty hold length was not given.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -12554,68 +7299,60 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "filler jam",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
-            "rationale": "At the time of the decision the repair length is unobservable to the scheduler.",
+            "node": "QA hold",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "sourceRegime": "practiced",
+            "rationale": "Expert explicitly contrasts white with the long specialty hold.",
             "assertion": {
-              "value": "Repair duration is not known at the time of the decision — \"which I never know at the time\"; only \"could be quick, could be long\"."
+              "value": "Yes — a white is about four hours because there's nothing exotic about it chemically; specialty gets the long hold."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "how long is this repair *actually* going to take, which I never know at the time",
+            "excerpt": "nothing exotic about it chemically, so it's not the long specialty hold",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-8c6a716b-e09a-4977-94d9-f28ab74be7c4",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Repair duration is not known at the time of the decision — \\\"which I never know at the time\\\"; only \\\"could be quick, could be long\\\".\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"At the time of the decision the repair length is unobservable to the scheduler.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"how long is this repair *actually* going to take, which I never know at the time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-2f0e7c48-206b-4d81-8644-c4f649de9a7d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a white is about four hours because there's nothing exotic about it chemically; specialty gets the long hold.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Expert explicitly contrasts white with the long specialty hold.\",\"slot\":\"whether its quantities vary by type\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nothing exotic about it chemically, so it's not the long specialty hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "how long it takes",
-            "precision": "number",
-            "rationale": "Single figure given; no spread elicited.",
+            "node": "QA hold",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "The lab is named as the performer; its staffing/capacity was not elicited.",
             "assertion": {
-              "value": "Three hours for a tint-to-white washdown."
+              "value": "The lab"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I eat a tint-to-white washdown — three hours",
+            "excerpt": "I don't remember this one having any drama in the lab.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-a67683fd-0f34-4838-b48e-aa01f657a511",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours for a tint-to-white washdown.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Single figure given; no spread elicited.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-e47df01b-49ae-4326-a72a-bfb08188d641",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"The lab is named as the performer; its staffing/capacity was not elicited.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't remember this one having any drama in the lab.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -12623,68 +7360,39 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
+            "node": "white-to-tint changeover",
+            "slot": "how long it takes",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Low, high and typical given; not quantiles, so recorded as a range with typical, not a spread.",
             "assertion": {
-              "value": "A changeover of family on the line; the direction matters as much as the fact of it — tint-to-white is the expensive one, not the other way."
+              "value": "Quickest maybe 40 minutes if the crew's right there and nothing fights them; longest, dragging past an hour, call it an hour twenty on a bad day; typically 45 minutes to an hour. The \"cheap\" direction."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "the direction of the changeover matters as much as the fact of it",
+            "excerpt": "quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 24,
               "entryEnd": 24
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
+            "excerpt": "call it an hour twenty on a bad day",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 24,
               "entryEnd": 24
             },
             "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-1b632a29-f1de-48e5-8f96-a5ef908c4a56",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A changeover of family on the line; the direction matters as much as the fact of it — tint-to-white is the expensive one, not the other way.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the direction of the changeover matters as much as the fact of it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "firm",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what is lost when it changes the system's mode",
-            "precision": "named",
-            "rationale": "Hours and crew time are known; ramp scrap is named but unquantified.",
-            "assertion": {
-              "absence": "unknown-to-user",
-              "pointer": "ramp scrap after the washdown — \"which I don't have good numbers for but shouldn't be ignored\"; three hours of line and crew time are known"
-            }
-          }
-        },
-        "evidence": [
-          {
-            "excerpt": "it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
-            },
-            "source": "user-affordance-payload"
           },
           {
-            "excerpt": "And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.",
+            "excerpt": "Typically though it lands around 45 minutes to an hour",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 24,
               "entryEnd": 24
             },
@@ -12692,37 +7400,38 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-9926552e-289f-4b4a-bc99-4cae34f1720a",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"ramp scrap after the washdown — \\\"which I don't have good numbers for but shouldn't be ignored\\\"; three hours of line and crew time are known\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"named\",\"rationale\":\"Hours and crew time are known; ramp scrap is named but unquantified.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-46c666e7-d79c-4187-9eaf-dce49ca64100",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quickest maybe 40 minutes if the crew's right there and nothing fights them; longest, dragging past an hour, call it an hour twenty on a bad day; typically 45 minutes to an hour. The \\\"cheap\\\" direction.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover\",\"precision\":\"range\",\"rationale\":\"Low, high and typical given; not quantiles, so recorded as a range with typical, not a spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Typically though it lands around 45 minutes to an hour\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"call it an hour twenty on a bad day\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "tint-to-white washdown",
+            "node": "white-to-tint changeover",
             "slot": "who or what performs it",
             "precision": "named",
+            "rationale": "Performed by the shared crew, allocated by the crew policy.",
             "assertion": {
-              "value": "The crew, on the line being changed over (Line 1 in the incident described)."
+              "value": "The changeover crew (entity-type:changeover crew), allocated by policy:who gets the crew"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "the three-hour tint-to-white hit is real cost, crew time",
+            "excerpt": "whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-06aac0a9-b270-4b13-a54f-37440769d685",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The crew, on the line being changed over (Line 1 in the incident described).\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-5212259b-d4d4-491b-b122-6af5239030d7",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The changeover crew (entity-type:changeover crew), allocated by policy:who gets the crew\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover\",\"precision\":\"named\",\"rationale\":\"Performed by the shared crew, allocated by the crew policy.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -12730,29 +7439,39 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "QA hold",
+            "node": "tint-to-white washdown",
             "slot": "how long it takes",
             "precision": "range",
-            "rationale": "\"a few hours for a white\" — no quantiles given, and the specialty wait is named but unquantified.",
+            "sourceRegime": "practiced",
+            "rationale": "Low, high, typical given; the typical figure is the one used on the sheet.",
             "assertion": {
-              "value": "Usually a few hours for a white; \"nothing like the specialty wait\" — specialty duration not given."
+              "value": "Quickest maybe two and a half hours if everything's clean and the crew's fresh; on a bad day — dried pigment in a fitting — it's crept toward four hours; three hours typical, and that's the number actually used on the sheet."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+            "excerpt": "Quickest I've seen that go is maybe two and a half hours",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "it's crept toward four hours. Call it three hours typical",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-94948329-18e7-42fe-9538-a84fd72c225d",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; \\\"nothing like the specialty wait\\\" — specialty duration not given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"range\",\"rationale\":\"\\\"a few hours for a white\\\" — no quantiles given, and the specialty wait is named but unquantified.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-bff705c5-00cb-426f-9ddd-663d4dbc1e49",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quickest maybe two and a half hours if everything's clean and the crew's fresh; on a bad day — dried pigment in a fitting — it's crept toward four hours; three hours typical, and that's the number actually used on the sheet.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"range\",\"rationale\":\"Low, high, typical given; the typical figure is the one used on the sheet.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Quickest I've seen that go is maybe two and a half hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's crept toward four hours. Call it three hours typical\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -12760,96 +7479,128 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "QA hold",
-            "slot": "who or what performs it",
-            "precision": "named",
+            "node": "tint-to-white washdown",
+            "slot": "what is lost when it changes the system's mode",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Directional asymmetry and its reason; loss is the full washdown time, not recoverable.",
             "assertion": {
-              "value": "The lab."
+              "value": "A full washdown, because any pigment left behind wrecks a white batch — direction absolutely matters, it's not symmetric: tint-to-white is the expensive one (three hours typical) versus white-to-tint (45 minutes to an hour). \"A full white-to-tint changeover is a wash we can't get back.\""
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "sits in the lab's queue, gets checked",
+            "excerpt": "Any pigment left behind wrecks a white batch, so that's a full washdown.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "direction absolutely matters — it's not symmetric",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-16b9c643-8b17-490e-bfe0-022a06efd914",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-16d70bcc-e61a-4037-bc57-9ac302ff7b25",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A full washdown, because any pigment left behind wrecks a white batch — direction absolutely matters, it's not symmetric: tint-to-white is the expensive one (three hours typical) versus white-to-tint (45 minutes to an hour). \\\"A full white-to-tint changeover is a wash we can't get back.\\\"\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Directional asymmetry and its reason; loss is the full washdown time, not recoverable.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Any pigment left behind wrecks a white batch, so that's a full washdown.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"direction absolutely matters — it's not symmetric\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "QA hold",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
+            "node": "specialty changeover",
+            "slot": "how long it takes",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Range with typical, explicitly less well observed by the expert.",
             "assertion": {
-              "value": "The order is released, goes to the warehouse, and ships against the due date."
+              "value": "Around two hours normally, either direction going into or out of a specialty run; as short as an hour forty for a specialty-to-specialty colour change rather than a full family switch; not seen much longer than two and a half hours — but the expert doesn't watch specialty changeovers as closely because they don't hit due dates as hard."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+            "excerpt": "going in or coming out of a specialty run, either direction, it's around two hours normally",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "maybe an hour forty if it's a specialty-to-specialty color change",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I haven't seen it run much longer than two and a half hours, but I'll be honest, I don't watch specialty changeovers as closely as I watch the white-tint ones",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-d3b4e8c5-eb00-4103-b861-89ac1e3d5c7b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Around two hours normally, either direction going into or out of a specialty run; as short as an hour forty for a specialty-to-specialty colour change rather than a full family switch; not seen much longer than two and a half hours — but the expert doesn't watch specialty changeovers as closely because they don't hit due dates as hard.\"},\"kind\":\"activity\",\"node\":\"specialty changeover\",\"precision\":\"range\",\"rationale\":\"Range with typical, explicitly less well observed by the expert.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I haven't seen it run much longer than two and a half hours, but I'll be honest, I don't watch specialty changeovers as closely as I watch the white-tint ones\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"going in or coming out of a specialty run, either direction, it's around two hours normally\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"maybe an hour forty if it's a specialty-to-specialty color change\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "policy",
-            "node": "who can absorb the slip",
-            "slot": "the rule as actually practiced",
-            "precision": "spelled out",
+            "kind": "activity",
+            "node": "specialty changeover",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
             "sourceRegime": "practiced",
+            "rationale": "Explicit confirmation that changeover duration varies by direction and family.",
             "assertion": {
-              "value": "Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first."
+              "value": "Yes — three distinct changeovers with real asymmetry: white-to-tint 45 min–1 hr, tint-to-white ~3 hrs, specialty ~2 hrs either direction; specialty is its own animal again."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+            "excerpt": "Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "I use judgment on who can absorb the slip",
+            "excerpt": "Specialty is its own animal again",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-821e00ef-6923-43b0-955b-3ed7d60ce127",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-5f3fa0ff-23ae-4621-9bbe-9778cba7a67d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — three distinct changeovers with real asymmetry: white-to-tint 45 min–1 hr, tint-to-white ~3 hrs, specialty ~2 hrs either direction; specialty is its own animal again.\"},\"kind\":\"activity\",\"node\":\"specialty changeover\",\"precision\":\"named\",\"rationale\":\"Explicit confirmation that changeover duration varies by direction and family.\",\"slot\":\"whether its quantities vary by type\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Specialty is its own animal again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -12857,146 +7608,213 @@
           "value": {
             "type": "slot-asserted",
             "kind": "policy",
-            "node": "who can absorb the slip",
-            "slot": "what overrides it",
+            "node": "who gets the crew",
+            "slot": "the rule as actually practiced",
             "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Tacit contention rule elicited from a real borderline case.",
             "assertion": {
-              "value": "The hard on-time line for an order like Meridian overrides the weighing — it is not a trade-off, and is only crossed if there's truly no way through."
+              "value": "If a Meridian job is sitting behind either changeover, the crew goes to whichever line has the Meridian job next, full stop — that decision doesn't even get discussed, everyone understands it without it being said out loud. Otherwise it's the scheduler's judgment call at the huddle about whose next job is tightest against its due date; failing that, it's whoever's line supervisor gets to the crew lead first. Nobody's written that rule down. In the recalled case Line 1 won on due-date tightness and Line 3 sat clean but idle close to two hours waiting its turn."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+            "excerpt": "the crew goes to whichever line has the Meridian job next, full stop",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "nobody's written that rule down either",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-6da3fa16-460b-4f07-aefc-f941d7118f76",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The hard on-time line for an order like Meridian overrides the weighing — it is not a trade-off, and is only crossed if there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-34a374d1-d578-4bd6-9842-3db1fe2245f3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"If a Meridian job is sitting behind either changeover, the crew goes to whichever line has the Meridian job next, full stop — that decision doesn't even get discussed, everyone understands it without it being said out loud. Otherwise it's the scheduler's judgment call at the huddle about whose next job is tightest against its due date; failing that, it's whoever's line supervisor gets to the crew lead first. Nobody's written that rule down. In the recalled case Line 1 won on due-date tightness and Line 3 sat clean but idle close to two hours waiting its turn.\"},\"kind\":\"policy\",\"node\":\"who gets the crew\",\"precision\":\"spelled out\",\"rationale\":\"Tacit contention rule elicited from a real borderline case.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"nobody's written that rule down either\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the crew goes to whichever line has the Meridian job next, full stop\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "constraint",
-            "node": "Meridian ships on time",
-            "slot": "the limit and what happens when it is hit",
+            "kind": "policy",
+            "node": "who gets the crew",
+            "slot": "what overrides it",
             "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Named override with escalation path and stated rarity.",
             "assertion": {
-              "value": "Meridian ships on time, full stop; days late above zero is bad news the scheduler has to go explain. Only crossed \"unless there's truly no way through\"."
+              "value": "Maintenance will sometimes grab the crew mid-job for a genuine emergency — a line leaking, something needing isolating right now. That's rare and not the scheduler's call; if it's a real fight it goes over their head to the ops director."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "did Meridian ship on time or not, full stop",
+            "excerpt": "maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "days late on Meridian, and anything above zero is bad news I have to go explain",
+            "excerpt": "that's a maintenance-versus-me argument that goes over my head to the ops director if it's a real fight",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-731a5768-edc7-4858-ad42-50d2faf4b181",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian ships on time, full stop; days late above zero is bad news the scheduler has to go explain. Only crossed \\\"unless there's truly no way through\\\".\"},\"kind\":\"constraint\",\"node\":\"Meridian ships on time\",\"precision\":\"spelled out\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"days late on Meridian, and anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-2e7ed53f-9682-4e83-9057-b59be73ca16c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Maintenance will sometimes grab the crew mid-job for a genuine emergency — a line leaking, something needing isolating right now. That's rare and not the scheduler's call; if it's a real fight it goes over their head to the ops director.\"},\"kind\":\"policy\",\"node\":\"who gets the crew\",\"precision\":\"spelled out\",\"rationale\":\"Named override with escalation path and stated rarity.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's a maintenance-versus-me argument that goes over my head to the ops director if it's a real fight\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "boundary-condition",
-            "node": "demand book from ERP",
-            "slot": "the starting state",
+            "kind": "constraint",
+            "node": "we just don't do that (Meridian)",
+            "slot": "the limit and what happens when it is hit",
             "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Hard unwritten rule with named consequences; recorded as a rule, not a weight.",
             "assertion": {
-              "value": "Orders start life as line items in the demand book once ERP spits it out, carrying quantity, due date and SKU."
+              "value": "A Meridian order must not miss its due date — a \"we just don't do that\" rule, not a traded-off cost, and it doesn't flip in any range seen in a week. If it is hit: a fine, ammunition for Meridian to delist a line item at the next contract review, commercial gets calls and the boss gets calls."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "excerpt": "it's a \"we just don't do that\" rule, not a traded-off cost",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 9,
               "entryEnd": 9
             },
             "source": "user-affordance-payload"
-          }
-        ],
-        "epistemicStatus": "explicit",
-        "id": "capture-1bebb3ea-7788-477a-8127-593fe3fe6026",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders start life as line items in the demand book once ERP spits it out, carrying quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"spelled out\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
-      },
-      {
-        "confidence": "hedged",
-        "content": {
-          "value": {
-            "type": "slot-asserted",
-            "kind": "boundary-condition",
-            "node": "demand book from ERP",
-            "slot": "the arrival or availability pattern",
-            "precision": "named",
-            "rationale": "The expert named the demand book as the source but the arrival pattern was flagged as still open when the session ended.",
-            "assertion": {
-              "absence": "deferred",
-              "pointer": "how orders arrive into the demand book — named as still open at the close of the session"
-            }
-          }
-        },
-        "evidence": [
+          },
+          {
+            "excerpt": "it's a fine, and it's ammunition for them to delist a line item next contract review",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
           {
-            "excerpt": "it starts life as a line item in the demand book once ERP spits that out",
+            "excerpt": "Commercial gets calls, my boss gets calls.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 9,
               "entryEnd": 9
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "inferred",
-        "id": "capture-07cb7ca9-27c5-4395-bc9e-aaebc5811382",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"how orders arrive into the demand book — named as still open at the close of the session\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"named\",\"rationale\":\"The expert named the demand book as the source but the arrival pattern was flagged as still open when the session ended.\",\"slot\":\"the arrival or availability pattern\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "explicit",
+        "id": "capture-ea311e48-05a0-4c73-95b3-776de573bde2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian order must not miss its due date — a \\\"we just don't do that\\\" rule, not a traded-off cost, and it doesn't flip in any range seen in a week. If it is hit: a fine, ammunition for Meridian to delist a line item at the next contract review, commercial gets calls and the boss gets calls.\"},\"kind\":\"constraint\",\"node\":\"we just don't do that (Meridian)\",\"precision\":\"spelled out\",\"rationale\":\"Hard unwritten rule with named consequences; recorded as a rule, not a weight.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Commercial gets calls, my boss gets calls.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's a fine, and it's ammunition for them to delist a line item next contract review\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "data-binding",
-            "node": "stage-level times in the historian",
-            "slot": "the variable and its feed",
-            "precision": "named",
+            "kind": "validation-criterion",
+            "node": "recognize the shape of a real month",
+            "slot": "how the expert would know the model is right",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Acceptance bar stated as replay of last month's demand book against remembered outcomes.",
             "assertion": {
-              "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the historian; never pulled apart by the expert."
+              "value": "Feed it last month's demand book: it must land roughly where we actually landed on late orders that month — same rough number and same kind of misses (at least two Meridian scrapes and a handful of small ones). Saying we shipped everything on time would break trust immediately; getting the kind wrong (missing distributor orders when we actually missed a Meridian one) is worse than getting the count wrong. Then eyeball changeover hours on Line 2 and 3 — if Line 3 sits idle half the week waiting on the crew, which never happens in real life, it's missing something about how the crew gets shared. It must also reproduce the odd weeks — the ones where a breakdown chewed up two days on Line 1. No single number would be trusted; the shape of a real month must be recognizable."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+            "excerpt": "did it land roughly where we actually landed on late orders that month",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "same rough number and same *kind* of misses",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "we had at least two Meridian scrapes that month",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I'd want to eyeball changeover hours on Line 2 and 3 specifically",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the ones where a breakdown chewed up two days on Line 1",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I'd want to recognize the *shape* of a real month",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 15,
               "entryEnd": 15
             },
@@ -13004,66 +7822,88 @@
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the historian; never pulled apart by the expert.\"},\"kind\":\"data-binding\",\"node\":\"stage-level times in the historian\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-7d5ef992-e1a9-4aed-88ea-30f3bc49da30",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Feed it last month's demand book: it must land roughly where we actually landed on late orders that month — same rough number and same kind of misses (at least two Meridian scrapes and a handful of small ones). Saying we shipped everything on time would break trust immediately; getting the kind wrong (missing distributor orders when we actually missed a Meridian one) is worse than getting the count wrong. Then eyeball changeover hours on Line 2 and 3 — if Line 3 sits idle half the week waiting on the crew, which never happens in real life, it's missing something about how the crew gets shared. It must also reproduce the odd weeks — the ones where a breakdown chewed up two days on Line 1. No single number would be trusted; the shape of a real month must be recognizable.\"},\"kind\":\"validation-criterion\",\"node\":\"recognize the shape of a real month\",\"precision\":\"spelled out\",\"rationale\":\"Acceptance bar stated as replay of last month's demand book against remembered outcomes.\",\"slot\":\"how the expert would know the model is right\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd want to eyeball changeover hours on Line 2 and 3 specifically\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'd want to recognize the *shape* of a real month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did it land roughly where we actually landed on late orders that month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"same rough number and same *kind* of misses\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"we had at least two Meridian scrapes that month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "data-binding",
-            "node": "tank sizes from engineering drawings",
-            "slot": "the variable and its feed",
+            "kind": "activity",
+            "node": "breakdown on a line",
+            "slot": "how often it occurs, if it is an event rather than a step",
             "precision": "named",
+            "rationale": "Breakdowns named as needed for validation but rate and duration explicitly postponed to a later session.",
             "assertion": {
-              "value": "Holding tank sizes, especially mill-to-fill on Line 1 — feed: engineering drawings."
+              "absence": "deferred",
+              "pointer": "the master scheduler, next round — he offered to keep going on the arrivals side and the breakdowns"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "excerpt": "the ones where a breakdown chewed up two days on Line 1",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 15,
               "entryEnd": 15
             },
             "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Happy to keep going on the arrivals side and the breakdowns next round.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tank sizes, especially mill-to-fill on Line 1 — feed: engineering drawings.\"},\"kind\":\"data-binding\",\"node\":\"tank sizes from engineering drawings\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-fad3ee18-f276-4db0-b7e2-39bda4fb5066",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the master scheduler, next round — he offered to keep going on the arrivals side and the breakdowns\"},\"kind\":\"activity\",\"node\":\"breakdown on a line\",\"precision\":\"named\",\"rationale\":\"Breakdowns named as needed for validation but rate and duration explicitly postponed to a later session.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Happy to keep going on the arrivals side and the breakdowns next round.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the ones where a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "data-binding",
-            "node": "filler repair work-order times in the CMMS",
-            "slot": "the variable and its feed",
-            "precision": "named",
+            "kind": "objective",
+            "node": "wash down for the tint right then, or let Line 2 sit idle",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The decision the model exists to test, stated as a real recurring call.",
             "assertion": {
-              "value": "Actual filler repair durations — feed: maintenance work-order times in the CMMS; never pulled by the expert."
+              "value": "Whether to wash down for a tint order right away, or hold the line idle (about an hour) for an expected same-family white order that has not yet been released — a call made by gut three or four times a month, never verified."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "maintenance would have the actual work-order times in the CMMS but I've never pulled them",
+            "excerpt": "I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 27,
-              "entryEnd": 27
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 3,
+              "entryEnd": 3
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-a0429a34-1145-458d-bada-32d827d68959",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Actual filler repair durations — feed: maintenance work-order times in the CMMS; never pulled by the expert.\"},\"kind\":\"data-binding\",\"node\":\"filler repair work-order times in the CMMS\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maintenance would have the actual work-order times in the CMMS but I've never pulled them\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-df10185e-b1ea-4c96-a225-ba9f1a4870d3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whether to wash down for a tint order right away, or hold the line idle (about an hour) for an expected same-family white order that has not yet been released — a call made by gut three or four times a month, never verified.\"},\"kind\":\"objective\",\"node\":\"wash down for the tint right then, or let Line 2 sit idle\",\"precision\":\"spelled out\",\"rationale\":\"The decision the model exists to test, stated as a real recurring call.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had a choice: wash down for the tint right then, or let Line 2 sit idle for about an hour\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I make that judgment by gut maybe three or four times a month, and I've never once been able to prove I got it right\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -13071,272 +7911,372 @@
           "value": {
             "type": "slot-asserted",
             "kind": "objective",
-            "node": "wait or shift when Line 2 goes down",
-            "slot": "the question, in the expert's words",
+            "node": "wash down for the tint right then, or let Line 2 sit idle",
+            "slot": "what \"better\" means, and trade-off weights",
             "precision": "spelled out",
-            "rationale": "The expert wrote the question as he would type it into the tool.",
+            "sourceRegime": "practiced",
+            "rationale": "Ranking given, with an explicit refusal to supply an exchange rate for Meridian.",
             "assertion": {
-              "value": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\""
+              "value": "Judged on late-order count, with Meridian orders weighted extra heavy in practice though written nowhere; changeover hours and idle time are the scheduler's own concern, currently tracked separately. No numeric exchange rate for a Meridian miss exists — it would take commercial in a room to say it out loud."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"",
+            "excerpt": "what my boss actually looks at is late orders",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "The changeover hours and the idle time are more my own concern",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "If you need a number, you'd have to get commercial in a room and force them to say it out loud",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-48033ee8-f7eb-4615-b21f-018837fc9c5e",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\"\"},\"kind\":\"objective\",\"node\":\"wait or shift when Line 2 goes down\",\"precision\":\"spelled out\",\"rationale\":\"The expert wrote the question as he would type it into the tool.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-07d24f63-38a5-4252-9153-f5017bc5eb7c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judged on late-order count, with Meridian orders weighted extra heavy in practice though written nowhere; changeover hours and idle time are the scheduler's own concern, currently tracked separately. No numeric exchange rate for a Meridian miss exists — it would take commercial in a room to say it out loud.\"},\"kind\":\"objective\",\"node\":\"wash down for the tint right then, or let Line 2 sit idle\",\"precision\":\"spelled out\",\"rationale\":\"Ranking given, with an explicit refusal to supply an exchange rate for Meridian.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I'm being honest about what I'd get graded on, it's the late-order count, maybe with Meridian orders weighted extra heavy in practice even though nobody's written that down anywhere.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If you need a number, you'd have to get commercial in a room and force them to say it out loud\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The changeover hours and the idle time are more my own concern\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what my boss actually looks at is late orders\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "objective",
-            "node": "wait or shift when Line 2 goes down",
+            "node": "wash down for the tint right then, or let Line 2 sit idle",
             "slot": "the nodes it depends on",
             "precision": "named",
+            "rationale": "The scheduler named the scope of the decision: orders, three lines, the shared crew, the changeovers, the run, QA and the demand book.",
             "assertion": {
-              "value": "entity-type:order (demand book line item) — its due date and remaining quantity; entity-type:line (Line 1 / Line 2) — what is on Line 1 and how far through; entity-type:product family (white vs tint); activity:production run (mix, mill, tint, fill); activity:filler jam on Line 2 — repair length unknown at the time; activity:tint-to-white washdown — including its direction and ramp scrap; policy:who can absorb the slip — whose tint got bumped"
+              "value": [
+                "entity-type:order",
+                "entity-type:the three lines",
+                "entity-type:the changeover crew",
+                "boundary-condition:the demand book",
+                "activity:the run (mix, mill, fill and pack)",
+                "activity:QA hold",
+                "activity:white-to-tint changeover",
+                "activity:tint-to-white washdown",
+                "activity:specialty changeover",
+                "ordering/flow:release to cleared QA",
+                "policy:who gets the changeover crew",
+                "constraint:we just don't do that (Meridian)"
+              ]
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "What it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take",
+            "excerpt": "the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just \"an order got delayed.\"",
+            "excerpt": "it starts when the order lands in the demand book from ERP",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the due date is judged against when it clears, not when it comes off the line",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "explicit",
-        "id": "capture-88da9925-d922-48c3-8ea0-2c631df3ae3d",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:order (demand book line item) — its due date and remaining quantity; entity-type:line (Line 1 / Line 2) — what is on Line 1 and how far through; entity-type:product family (white vs tint); activity:production run (mix, mill, tint, fill); activity:filler jam on Line 2 — repair length unknown at the time; activity:tint-to-white washdown — including its direction and ramp scrap; policy:who can absorb the slip — whose tint got bumped\"},\"kind\":\"objective\",\"node\":\"wait or shift when Line 2 goes down\",\"precision\":\"named\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just \\\\\\\"an order got delayed.\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "inferred",
+        "id": "capture-fa7c6f67-b993-474b-bcb1-ea2fd55ae510",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:the three lines\",\"entity-type:the changeover crew\",\"boundary-condition:the demand book\",\"activity:the run (mix, mill, fill and pack)\",\"activity:QA hold\",\"activity:white-to-tint changeover\",\"activity:tint-to-white washdown\",\"activity:specialty changeover\",\"ordering/flow:release to cleared QA\",\"policy:who gets the changeover crew\",\"constraint:we just don't do that (Meridian)\"]},\"kind\":\"objective\",\"node\":\"wash down for the tint right then, or let Line 2 sit idle\",\"precision\":\"named\",\"rationale\":\"The scheduler named the scope of the decision: orders, three lines, the shared crew, the changeovers, the run, QA and the demand book.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts when the order lands in the demand book from ERP\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "wait or shift when Line 2 goes down",
-            "slot": "what \"better\" means, and trade-off weights",
+            "kind": "constraint",
+            "node": "we just don't do that (Meridian)",
+            "slot": "the limit and what happens when it is hit",
             "precision": "spelled out",
             "sourceRegime": "practiced",
+            "rationale": "A hard rule with a named consequence rather than a weight.",
             "assertion": {
-              "value": "Lexicographic: days late on Meridian first, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip."
+              "value": "A Meridian order must not be allowed to go late — not tradeable even against twenty small late orders. If hit: a fine, ammunition for Meridian to delist a line item at next contract review, calls to commercial and to the boss."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+            "excerpt": "it's not just \"late,\" it's a fine, and it's ammunition for them to delist a line item next contract review",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.",
+            "excerpt": "right now it's a \"we just don't do that\" rule, not a traded-off cost",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Even if you told me \"twenty small orders late\" versus \"one Meridian order late\" — I'd still not want to be the one who let Meridian slip.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-f53d8f62-375e-4af6-9aaa-fb903839993c",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lexicographic: days late on Meridian first, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"wait or shift when Line 2 goes down\",\"precision\":\"spelled out\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-354f9e2d-b3c7-4838-8dda-fd4f12d7f2c2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian order must not be allowed to go late — not tradeable even against twenty small late orders. If hit: a fine, ammunition for Meridian to delist a line item at next contract review, calls to commercial and to the boss.\"},\"kind\":\"constraint\",\"node\":\"we just don't do that (Meridian)\",\"precision\":\"spelled out\",\"rationale\":\"A hard rule with a named consequence rather than a weight.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Even if you told me \\\\\\\"twenty small orders late\\\\\\\" versus \\\\\\\"one Meridian order late\\\\\\\" — I'd still not want to be the one who let Meridian slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's not just \\\\\\\"late,\\\\\\\" it's a fine, and it's ammunition for them to delist a line item next contract review\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"right now it's a \\\\\\\"we just don't do that\\\\\\\" rule, not a traded-off cost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "objective",
-            "node": "is the mill-to-fill tank on Line 1 slowing the line down",
-            "slot": "the nodes it depends on",
-            "precision": "named",
+            "kind": "constraint",
+            "node": "one-week planning horizon",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Horizon over which a plan must stay useful, with what fails beyond it.",
             "assertion": {
-              "value": "activity:production run (mix, mill, tint, fill) — stage-level mill speed versus fill speed on Line 1; constraint:small holding tanks between stages — the mill-to-fill tank size on Line 1; entity-type:product family (white vs tint) — different SKUs are slow at different stages"
+              "value": "The plan must hold for one week — the demand-book cycle, re-planned at the morning huddle; two weeks is soft and watched only for big specialty minimum runs; beyond a month the plan is refused because the book itself gets revised."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages",
+            "excerpt": "a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "if you ask me to hold a plan that's useful a month out, I'd say no — too much changes",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-ac435640-eea2-4ad6-9695-8e5408b4d852",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"activity:production run (mix, mill, tint, fill) — stage-level mill speed versus fill speed on Line 1; constraint:small holding tanks between stages — the mill-to-fill tank size on Line 1; entity-type:product family (white vs tint) — different SKUs are slow at different stages\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"named\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-a6f338a0-c3a7-4427-b125-8ce2759d26e6",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The plan must hold for one week — the demand-book cycle, re-planned at the morning huddle; two weeks is soft and watched only for big specialty minimum runs; beyond a month the plan is refused because the book itself gets revised.\"},\"kind\":\"constraint\",\"node\":\"one-week planning horizon\",\"precision\":\"spelled out\",\"rationale\":\"Horizon over which a plan must stay useful, with what fails beyond it.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I do keep half an eye two weeks out for the big minimum-run stuff, specialty especially\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a week is the horizon that matters — that's the cycle of the demand book, and that's what the huddle re-plans against every morning\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if you ask me to hold a plan that's useful a month out, I'd say no — too much changes\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "data-binding",
-            "node": "stage-level times from the historian and tank sizes from engineering drawings",
-            "slot": "the variable and its feed",
-            "precision": "named",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "rationale": "Two axes of distinction the process treats apart: customer (Meridian vs small distributors) and colour family (white, tint, specialty).",
             "assertion": {
-              "absence": "deferred",
-              "pointer": "the historian (stage-by-stage times) and engineering drawings (tank sizes)"
+              "value": "Orders differ by customer — Meridian versus small distributors who slip 2-3 days with a phone call — and by colour family: white, tint, and specialty; same-family orders run into each other with no changeover, different families need the crew."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I don't have clean numbers for tank sizes or stage-by-stage rates.",
+            "excerpt": "a Meridian order, big white SKU, due Friday",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "excerpt": "three little late orders to distributors who slip 2-3 days with a phone call anyway",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 15,
-              "entryEnd": 15
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "same family, so no changeover needed, just a straight run-into-run",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Specialty is its own animal again",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-f5a658db-c8ec-4ca0-8a87-3ad252dee56d",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the historian (stage-by-stage times) and engineering drawings (tank sizes)\"},\"kind\":\"data-binding\",\"node\":\"stage-level times from the historian and tank sizes from engineering drawings\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have clean numbers for tank sizes or stage-by-stage rates.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-67a39f82-22f8-4b56-825d-03cfacb8a154",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders differ by customer — Meridian versus small distributors who slip 2-3 days with a phone call — and by colour family: white, tint, and specialty; same-family orders run into each other with no changeover, different families need the crew.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Two axes of distinction the process treats apart: customer (Meridian vs small distributors) and colour family (white, tint, specialty).\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Specialty is its own animal again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a Meridian order, big white SKU, due Friday\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"same family, so no changeover needed, just a straight run-into-run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"three little late orders to distributors who slip 2-3 days with a phone call anyway\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "data-binding",
-            "node": "filler repair times from the CMMS",
-            "slot": "the variable and its feed",
-            "precision": "named",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "state that rides along with each instance",
+            "precision": "spelled out",
+            "rationale": "Attributes named at release.",
             "assertion": {
-              "absence": "deferred",
-              "pointer": "maintenance work-order times in the CMMS"
+              "value": "SKU, quantity, and due date at release; a line it goes to (Meridian white basically always goes to Line 2)."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "maintenance would have the actual work-order times in the CMMS but I've never pulled them.",
+            "excerpt": "it's got an SKU, quantity, due date",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 27,
-              "entryEnd": 27
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "I'll ask maintenance for the CMMS numbers on the filler too while I'm at it.",
+            "excerpt": "Meridian white basically always goes to Line 2",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 30,
-              "entryEnd": 30
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
-            "source": "user"
+            "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-618842bb-d23d-4371-ae57-73e5257ba215",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"maintenance work-order times in the CMMS\"},\"kind\":\"data-binding\",\"node\":\"filler repair times from the CMMS\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'll ask maintenance for the CMMS numbers on the filler too while I'm at it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":30,\\\"entryStart\\\":30,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user\\\"}\",\"{\\\"excerpt\\\":\\\"maintenance would have the actual work-order times in the CMMS but I've never pulled them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-a559675e-115d-4736-85ff-6160abb1a449",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"SKU, quantity, and due date at release; a line it goes to (Meridian white basically always goes to Line 2).\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Attributes named at release.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "boundary-condition",
-            "node": "demand book line items out of ERP",
-            "slot": "the starting state",
-            "precision": "spelled out",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "how many there are, or the population's shape",
+            "precision": "range",
+            "rationale": "Weekly population given as a low and high.",
             "assertion": {
-              "value": "An order starts life as a line item in the demand book once ERP spits that out, carrying quantity, due date and SKU."
+              "value": "30 orders in a quiet week, 55–60 in a busy one"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+            "excerpt": "quiet week might be 30 orders, a busy one pushes 55–60",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 27,
+              "entryEnd": 27
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-538fb022-2495-46bb-8661-8e1f38c802bf",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order starts life as a line item in the demand book once ERP spits that out, carrying quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book line items out of ERP\",\"precision\":\"spelled out\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-3caeda61-ac3c-4724-905a-3f76e1bfd924",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"30 orders in a quiet week, 55–60 in a busy one\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"range\",\"rationale\":\"Weekly population given as a low and high.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"quiet week might be 30 orders, a busy one pushes 55–60\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "entity-type",
-            "node": "order (demand book line item)",
-            "slot": "state that rides along with each instance",
-            "precision": "spelled out",
-            "rationale": "Quantity, due date and SKU are explicit; remaining quantity and customer identity are named later as things the answer hangs on.",
+            "node": "the changeover crew",
+            "slot": "how many there are, or the population's shape",
+            "precision": "number",
+            "rationale": "Single contended resource with a stated size.",
             "assertion": {
-              "value": "Quantity, due date, SKU; plus remaining quantity and the customer's identity, which the expert weighs when an order slips."
+              "value": "one crew of two techs"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+            "excerpt": "there's one crew, two techs, covering all three lines",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "inferred",
-        "id": "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; plus remaining quantity and the customer's identity, which the expert weighs when an order slips.\"},\"kind\":\"entity-type\",\"node\":\"order (demand book line item)\",\"precision\":\"spelled out\",\"rationale\":\"Quantity, due date and SKU are explicit; remaining quantity and customer identity are named later as things the answer hangs on.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "explicit",
+        "id": "capture-317a5e27-6e23-4fdb-80c5-2160e7622b9c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"one crew of two techs\"},\"kind\":\"entity-type\",\"node\":\"the changeover crew\",\"precision\":\"number\",\"rationale\":\"Single contended resource with a stated size.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -13344,29 +8284,38 @@
           "value": {
             "type": "slot-asserted",
             "kind": "entity-type",
-            "node": "order (demand book line item)",
+            "node": "the changeover crew",
             "slot": "the distinctions the process treats apart",
             "precision": "spelled out",
-            "sourceRegime": "practiced",
+            "rationale": "The crew is treated as one indivisible shared resource across all three lines, not split by line.",
             "assertion": {
-              "value": "Orders are treated apart by whose order it is: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem."
+              "value": "One changeover crew, treated as a single shared unit across all three lines — either free or tied up on another line; no distinction drawn between the two techs."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.",
+            "excerpt": "The changeover crew is the shared thing — there's one crew, two techs, covering all three lines",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\"",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-5d5f862f-c18c-4501-b544-76735d28e004",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders are treated apart by whose order it is: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem.\"},\"kind\":\"entity-type\",\"node\":\"order (demand book line item)\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-afdf937d-5049-4656-a68a-f0b5c1a15511",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One changeover crew, treated as a single shared unit across all three lines — either free or tied up on another line; no distinction drawn between the two techs.\"},\"kind\":\"entity-type\",\"node\":\"the changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"The crew is treated as one indivisible shared resource across all three lines, not split by line.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing — there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if I wash Line 2 down now, I'm also asking \\\\\\\"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -13374,223 +8323,274 @@
           "value": {
             "type": "slot-asserted",
             "kind": "entity-type",
-            "node": "product family (white vs tint)",
-            "slot": "the distinctions the process treats apart",
-            "precision": "spelled out",
+            "node": "the three lines",
+            "slot": "how many there are, or the population's shape",
+            "precision": "number",
+            "rationale": "Line count stated.",
             "assertion": {
-              "value": "Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step; tints run at nearly the same speed on both lines while whites do not; and the tint-to-white changeover direction is the expensive one."
+              "value": "three lines (Line 1, Line 2, Line 3)"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+            "excerpt": "covering all three lines",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
+            "excerpt": "the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-7f6b8be1-6336-465f-8e11-36a5277d51bd",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step; tints run at nearly the same speed on both lines while whites do not; and the tint-to-white changeover direction is the expensive one.\"},\"kind\":\"entity-type\",\"node\":\"product family (white vs tint)\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-0b6c3aeb-8421-41f3-a77b-0db90e32bc06",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"three lines (Line 1, Line 2, Line 3)\"},\"kind\":\"entity-type\",\"node\":\"the three lines\",\"precision\":\"number\",\"rationale\":\"Line count stated.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the unit I'm scheduling across is all three lines plus that one crew, not any line in isolation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "entity-type",
-            "node": "line (Line 1 / Line 2)",
+            "node": "the three lines",
             "slot": "the distinctions the process treats apart",
-            "precision": "spelled out",
+            "precision": "named",
+            "sourceRegime": "practiced",
+            "rationale": "Lines are distinguished by what tends to run on them; whether routing is hard or habitual was not established.",
             "assertion": {
-              "value": "Line 1 is the slower machine on whites (add maybe fifty, sixty percent to Line 2's times); on tints Line 1 and Line 2 run at nearly the same speed."
+              "value": "Line 1, Line 2, Line 3; Meridian white basically always goes to Line 2, specialty runs seen on Line 1 — stated as practice, not established as a hard routing rule."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
+            "excerpt": "Meridian white basically always goes to Line 2",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 18,
               "entryEnd": 18
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed",
+            "excerpt": "Line 1 had just finished a specialty run",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-1a83c9c6-a8f8-4ece-a5d4-53b81bf8cc9b",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 is the slower machine on whites (add maybe fifty, sixty percent to Line 2's times); on tints Line 1 and Line 2 run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-4c36d6d9-17da-4e86-be1a-dc07ef07ff83",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1, Line 2, Line 3; Meridian white basically always goes to Line 2, specialty runs seen on Line 1 — stated as practice, not established as a hard routing rule.\"},\"kind\":\"entity-type\",\"node\":\"the three lines\",\"precision\":\"named\",\"rationale\":\"Lines are distinguished by what tends to run on them; whether routing is hard or habitual was not established.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 had just finished a specialty run\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "entity-type",
-            "node": "line (Line 1 / Line 2)",
-            "slot": "how many there are, or the population's shape",
-            "precision": "number",
-            "rationale": "Only Line 1 and Line 2 are ever named; the count itself was never stated as a figure.",
+            "kind": "boundary-condition",
+            "node": "the demand book",
+            "slot": "the arrival or availability pattern",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Weekly drop plus mid-week additions, given as counts and regularity, not as a distribution.",
             "assertion": {
-              "value": "Two lines (Line 1 and Line 2), each comprising separate mix, mill, tint and fill kit with small holding tanks between."
+              "value": "Official Monday-morning release of 30-something to 60 orders (quiet week 30, busy 55–60), plus additions pushed in by sales and commercial through the week, sometimes daily; Meridian close to weekly and regular, small distributors are what swing; not noticeably seasonal, just lumpy by who is restocking."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+            "excerpt": "The book officially releases Monday morning — that's the big drop, 30-something to 60 orders depending on the week.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Sales and commercial push in additions through the week, sometimes daily, when a customer calls with something last-minute or an order gets confirmed late.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Meridian in particular is fairly regular, close to weekly, but the smaller distributors are the ones that swing.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 27,
+              "entryEnd": 27
             },
             "source": "user-affordance-payload"
           }
         ],
-        "epistemicStatus": "inferred",
-        "id": "capture-e6ae51ed-e1f6-45f3-aab1-c4bca2a979e8",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two lines (Line 1 and Line 2), each comprising separate mix, mill, tint and fill kit with small holding tanks between.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"number\",\"rationale\":\"Only Line 1 and Line 2 are ever named; the count itself was never stated as a figure.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "epistemicStatus": "explicit",
+        "id": "capture-cf61a51f-f803-407f-a6b4-9ffc46972ab0",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Official Monday-morning release of 30-something to 60 orders (quiet week 30, busy 55–60), plus additions pushed in by sales and commercial through the week, sometimes daily; Meridian close to weekly and regular, small distributors are what swing; not noticeably seasonal, just lumpy by who is restocking.\"},\"kind\":\"boundary-condition\",\"node\":\"the demand book\",\"precision\":\"range\",\"rationale\":\"Weekly drop plus mid-week additions, given as counts and regularity, not as a distribution.\",\"slot\":\"the arrival or availability pattern\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian in particular is fairly regular, close to weekly, but the smaller distributors are the ones that swing.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Sales and commercial push in additions through the week, sometimes daily, when a customer calls with something last-minute or an order gets confirmed late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The book officially releases Monday morning — that's the big drop, 30-something to 60 orders depending on the week.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "order flow from demand book to ship",
-            "slot": "the order things happen in",
+            "kind": "boundary-condition",
+            "node": "the demand book",
+            "slot": "the starting state",
             "precision": "spelled out",
+            "rationale": "Entry point into the scheduler's world.",
             "assertion": {
-              "value": "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship against the due date."
+              "value": "Orders land in the demand book from ERP with SKU, quantity and due date — that state is 'released' and is where the order enters the scheduler's world."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+            "excerpt": "it starts when the order lands in the demand book from ERP — that's \"released,\" it's got an SKU, quantity, due date",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship against the due date.\"},\"kind\":\"ordering/flow\",\"node\":\"order flow from demand book to ship\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-0693c605-2dd0-4019-a36a-25c0565e22a4",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders land in the demand book from ERP with SKU, quantity and due date — that state is 'released' and is where the order enters the scheduler's world.\"},\"kind\":\"boundary-condition\",\"node\":\"the demand book\",\"precision\":\"spelled out\",\"rationale\":\"Entry point into the scheduler's world.\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts when the order lands in the demand book from ERP — that's \\\\\\\"released,\\\\\\\" it's got an SKU, quantity, due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "line occupancy across the four stages",
-            "slot": "the order things happen in",
+            "kind": "activity",
+            "node": "the run (mix, mill, fill and pack)",
+            "slot": "what it needs before it can start",
             "precision": "spelled out",
-            "sourceRegime": "prescribed",
+            "rationale": "Preconditions from the walkthrough.",
             "assertion": {
-              "value": "On the sheet, Line 2 is one row: the order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done."
+              "value": "The line must be free of the job ahead of it; if the previous job is the same family it runs straight into it with no changeover, otherwise a changeover by the crew must have been done first."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+            "excerpt": "It had to wait its turn behind whatever was already running on Line 2.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet, Line 2 is one row: the order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done.\"},\"kind\":\"ordering/flow\",\"node\":\"line occupancy across the four stages\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-83c1866f-aabf-4ce4-8836-7a803a5521cd",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line must be free of the job ahead of it; if the previous job is the same family it runs straight into it with no changeover, otherwise a changeover by the crew must have been done first.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"spelled out\",\"rationale\":\"Preconditions from the walkthrough.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It had to wait its turn behind whatever was already running on Line 2.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"There was a smaller white job ahead of it — same family, so no changeover needed, just a straight run-into-run.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "ordering/flow",
-            "node": "line occupancy across the four stages",
-            "slot": "the order things happen in",
+            "kind": "activity",
+            "node": "the run (mix, mill, fill and pack)",
+            "slot": "what it produces or changes",
             "precision": "spelled out",
-            "sourceRegime": "practiced",
+            "rationale": "Output of the run stage.",
             "assertion": {
-              "value": "Physically the stages overlap: the mixer can start the next order's batch while the fill head is still finishing the last one, if there is room in the holding tank between mix and mill, or mill and fill; the crew will get a head start on mixing if the tank ahead has space."
+              "value": "Mix, mill, tint stage (skipped for a white), fill and pack — producing finished, packed product that goes into QA hold."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.",
+            "excerpt": "Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Once fill and pack was done, it went into QA hold.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-7f9ac97e-375b-4de3-bbcd-b65e5c7427a6",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically the stages overlap: the mixer can start the next order's batch while the fill head is still finishing the last one, if there is room in the holding tank between mix and mill, or mill and fill; the crew will get a head start on mixing if the tank ahead has space.\"},\"kind\":\"ordering/flow\",\"node\":\"line occupancy across the four stages\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-d705d5d1-f8ed-4788-9c21-b426a1edf48f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Mix, mill, tint stage (skipped for a white), fill and pack — producing finished, packed product that goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"spelled out\",\"rationale\":\"Output of the run stage.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "constraint",
-            "node": "small holding tanks between stages",
-            "slot": "the limit and what happens when it is hit",
-            "precision": "spelled out",
+            "kind": "activity",
+            "node": "the run (mix, mill, fill and pack)",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "Performed by the line itself; the scheduler does not track the operators.",
             "assertion": {
-              "value": "The tanks are small — especially the one between mill and fill on Line 1 — and when a tank is full, mixing has to wait; how much overlap happens or how often it is blocked is not tracked."
+              "value": "The production line (this order ran on Line 2); no crew involvement for a run-into-run"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+            "excerpt": "Meridian white basically always goes to Line 2",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 12,
-              "entryEnd": 12
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I don't watch this minute by minute",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-66fbb371-91b7-41db-b437-5bd207d08aed",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The tanks are small — especially the one between mill and fill on Line 1 — and when a tank is full, mixing has to wait; how much overlap happens or how often it is blocked is not tracked.\"},\"kind\":\"constraint\",\"node\":\"small holding tanks between stages\",\"precision\":\"spelled out\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-61b6af85-58ca-4367-a45a-1f9d20d9a04b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The production line (this order ran on Line 2); no crew involvement for a run-into-run\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"named\",\"rationale\":\"Performed by the line itself; the scheduler does not track the operators.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't watch this minute by minute\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -13598,28 +8598,39 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "allocation onto a line and a slot in the week",
-            "slot": "who or what performs it",
-            "precision": "named",
+            "node": "the run (mix, mill, fill and pack)",
+            "slot": "how long it takes",
+            "precision": "spread",
+            "rationale": "Only a single recalled day-long run; run rates deferred to the production sheet.",
             "assertion": {
-              "value": "The master scheduler, on the sheet."
+              "absence": "deferred",
+              "pointer": "the sheet (production sheet, to be brought next session) — one recalled instance: a big-volume order started Wednesday morning and wrapped Wednesday evening"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "excerpt": "I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "bring the sheet next time, it'll answer the run-rate question faster than I can talk through it",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 30,
+              "entryEnd": 30
+            },
+            "source": "user"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-8da19d62-c082-41f6-ac55-f28afe266a8c",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler, on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation onto a line and a slot in the week\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-a584bc16-c132-431c-8c66-64c32cf5715a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the sheet (production sheet, to be brought next session) — one recalled instance: a big-volume order started Wednesday morning and wrapped Wednesday evening\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, fill and pack)\",\"precision\":\"spread\",\"rationale\":\"Only a single recalled day-long run; run rates deferred to the production sheet.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I want to say it started Wednesday morning and wrapped Wednesday evening, something like that — I'd have to check the sheet for the exact hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"bring the sheet next time, it'll answer the run-rate question faster than I can talk through it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":30,\\\"entryStart\\\":30,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -13627,28 +8638,38 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "allocation onto a line and a slot in the week",
+            "node": "QA hold",
             "slot": "what it needs before it can start",
             "precision": "spelled out",
+            "rationale": "Entry condition for QA.",
             "assertion": {
-              "value": "A line item in the demand book out of ERP, with quantity, due date and SKU."
+              "value": "Fill and pack complete; the batch is palletized and moved off the line into the queue for the lab."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "excerpt": "Once fill and pack was done, it went into QA hold.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "physically it's palletized and moved off the line, into the queue for the lab",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-995374a1-2d25-4690-8397-b342f46ebf02",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book out of ERP, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation onto a line and a slot in the week\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-b6778bf0-5fd3-46a9-ac25-be90e5fb6535",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Fill and pack complete; the batch is palletized and moved off the line into the queue for the lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Entry condition for QA.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"physically it's palletized and moved off the line, into the queue for the lab\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -13656,86 +8677,107 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "allocation onto a line and a slot in the week",
+            "node": "QA hold",
             "slot": "what it produces or changes",
             "precision": "spelled out",
+            "rationale": "QA clearance is the point the due date is judged at.",
             "assertion": {
-              "value": "The order is placed onto a named line and a slot in the week."
+              "value": "The order clears QA and ships; the due date is judged against when it clears, not when it comes off the line."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "allocate it onto a line and a slot in the week",
+            "excerpt": "It cleared and shipped Thursday",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the due date is judged against when it clears, not when it comes off the line",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-3cc84392-4ed4-4804-8a7c-db07d384a8b2",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is placed onto a named line and a slot in the week.\"},\"kind\":\"activity\",\"node\":\"allocation onto a line and a slot in the week\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-733f30a6-e231-4fd2-a9a1-ef584ad1d139",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order clears QA and ships; the due date is judged against when it clears, not when it comes off the line.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"QA clearance is the point the due date is judged at.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It cleared and shipped Thursday\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the due date is judged against when it clears, not when it comes off the line\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "production run (mix, mill, tint, fill)",
-            "slot": "what it needs before it can start",
-            "precision": "spelled out",
+            "node": "QA hold",
+            "slot": "how long it takes",
+            "precision": "number",
+            "rationale": "A single typical figure for white only; no range given and lab backlog acknowledged as a separate driver.",
             "assertion": {
-              "value": "The order allocated to a line and a slot in the week; then it runs the same four stages every product goes through — mix, mill, tint, fill and pack."
+              "value": "about four hours for a white"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through",
+            "excerpt": "normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "a batch can be done Tuesday and still ship late if the lab's backed up",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-289ac648-e939-4e62-ad46-a17b112402d4",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order allocated to a line and a slot in the week; then it runs the same four stages every product goes through — mix, mill, tint, fill and pack.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-a7b79e99-0816-4a9d-b4cb-ce91e9933dd4",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"about four hours for a white\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"number\",\"rationale\":\"A single typical figure for white only; no range given and lab backlog acknowledged as a separate driver.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a batch can be done Tuesday and still ship late if the lab's backed up\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"normally that's about four hours for a white, nothing exotic about it chemically, so it's not the long specialty hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "production run (mix, mill, tint, fill)",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
+            "node": "QA hold",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "rationale": "Specialty implied to have a longer hold; the figure itself was not given.",
             "assertion": {
-              "value": "Packed product coming off the fill line, which then goes into QA hold."
+              "value": "Yes — a white is not the long specialty hold; the specialty hold duration was not given."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Once it comes off the fill line it goes into QA hold",
+            "excerpt": "nothing exotic about it chemically, so it's not the long specialty hold",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-5376c084-3889-476f-adab-b09a038ded28",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Packed product coming off the fill line, which then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-7e1b1ff2-d9f7-4999-b260-ab694dc84fce",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a white is not the long specialty hold; the specialty hold duration was not given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Specialty implied to have a longer hold; the figure itself was not given.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nothing exotic about it chemically, so it's not the long specialty hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -13743,76 +8785,78 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "production run (mix, mill, tint, fill)",
+            "node": "white-to-tint changeover",
             "slot": "how long it takes",
             "precision": "spread",
             "sourceRegime": "practiced",
+            "rationale": "Best case, bad-day case and typical band, elicited quickest/longest then typical.",
             "assertion": {
-              "value": "White, Meridian-sized, on Line 2, clean of breakdowns: typical eight to nine hours mix-to-last-pack; one in ten worse nine to ten hours; one in ten better maybe six hours."
+              "value": "quickest ~40 minutes (crew right there, nothing fights them); typical 45 minutes to an hour; bad day about an hour twenty"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing.",
+            "excerpt": "White-to-tint on Line 2 — quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes. Longest, if they're stretched thin or something's stuck, I've seen it drag past an hour, call it an hour twenty on a bad day. Typically though it lands around 45 minutes to an hour.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 21,
-              "entryEnd": 21
-            },
-            "source": "user-affordance-payload"
-          },
-          {
-            "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
-            "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-b9dfddf9-52d8-433e-81b8-5611e7356c34",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, Meridian-sized, on Line 2, clean of breakdowns: typical eight to nine hours mix-to-last-pack; one in ten worse nine to ten hours; one in ten better maybe six hours.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-7f1eba90-5fc4-4103-8f8b-fe4400be2ebf",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"quickest ~40 minutes (crew right there, nothing fights them); typical 45 minutes to an hour; bad day about an hour twenty\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover\",\"precision\":\"spread\",\"rationale\":\"Best case, bad-day case and typical band, elicited quickest/longest then typical.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"White-to-tint on Line 2 — quickest I've seen, if the crew's right there and nothing fights them, maybe 40 minutes. Longest, if they're stretched thin or something's stuck, I've seen it drag past an hour, call it an hour twenty on a bad day. Typically though it lands around 45 minutes to an hour.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "production run (mix, mill, tint, fill)",
-            "slot": "how long it takes",
-            "precision": "spread",
+            "node": "white-to-tint changeover",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "Crew availability gates the changeover.",
             "assertion": {
-              "value": "Same white order on Line 1: typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten — add maybe fifty, sixty percent to Line 2. (Stated before the breakdown/clean-run split was drawn, so the worse figure may still fold in jams.)"
+              "value": "The changeover crew must be free; if they are tied up on another line the wash-down option is not available and the line queues behind whoever else needs them."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+            "excerpt": "The changeover crew is the shared thing",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "if I wash Line 2 down now, I'm also asking \"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\"",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "If they're tied up elsewhere, my \"wash down now\" option isn't even really available",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-27ae8fdf-c227-4160-a1a5-e85530156938",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Same white order on Line 1: typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten — add maybe fifty, sixty percent to Line 2. (Stated before the breakdown/clean-run split was drawn, so the worse figure may still fold in jams.)\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-855f61a1-da7f-4d31-a70e-c72dc905afb3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The changeover crew must be free; if they are tied up on another line the wash-down option is not available and the line queues behind whoever else needs them.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover\",\"precision\":\"spelled out\",\"rationale\":\"Crew availability gates the changeover.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If they're tied up elsewhere, my \\\\\\\"wash down now\\\\\\\" option isn't even really available\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The changeover crew is the shared thing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if I wash Line 2 down now, I'm also asking \\\\\\\"are they free, or are they about to be pulled onto Line 1 or Line 3 for something else?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -13820,28 +8864,29 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "production run (mix, mill, tint, fill)",
-            "slot": "how long it takes",
-            "precision": "range",
+            "node": "white-to-tint changeover",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "Performer named.",
             "assertion": {
-              "value": "A tint run on either line: eight to ten hours typical, without the Line 1 / Line 2 gap."
+              "value": "entity-type:the changeover crew (two techs)"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "so a tint run on either line looks more like eight to ten hours typical, without that big gap",
+            "excerpt": "there's one crew, two techs, covering all three lines",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-7bd393bf-3f05-4aa1-b15a-968c293b076f",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A tint run on either line: eight to ten hours typical, without the Line 1 / Line 2 gap.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"range\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"so a tint run on either line looks more like eight to ten hours typical, without that big gap\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-e6a85b0b-ac81-4bbd-b62c-40c5d2073bba",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:the changeover crew (two techs)\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover\",\"precision\":\"named\",\"rationale\":\"Performer named.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -13849,37 +8894,38 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "production run (mix, mill, tint, fill)",
+            "node": "white-to-tint changeover",
             "slot": "whether its quantities vary by type",
             "precision": "named",
+            "rationale": "Explicit answer that duration varies by direction and family.",
             "assertion": {
-              "value": "Yes — run time varies by product family and line: whites are much slower on Line 1, tints are nearly the same speed on either line; the \"Line 2 is twice as fast\" figure is really a whites number. No explanation for the tint case; it is sheet-derived."
+              "value": "Yes — direction absolutely matters and is not symmetric: white-to-tint is the cheap direction, tint-to-white the expensive one, and specialty is its own animal again."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.",
+            "excerpt": "Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+            "excerpt": "Specialty is its own animal again",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 18,
-              "entryEnd": 18
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-ef41e72f-3126-4003-82b2-686b5f8bfdfb",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — run time varies by product family and line: whites are much slower on Line 1, tints are nearly the same speed on either line; the \\\"Line 2 is twice as fast\\\" figure is really a whites number. No explanation for the tint case; it is sheet-derived.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"named\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-80836a1b-2883-487f-8ca6-451049d38c30",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — direction absolutely matters and is not symmetric: white-to-tint is the cheap direction, tint-to-white the expensive one, and specialty is its own animal again.\"},\"kind\":\"activity\",\"node\":\"white-to-tint changeover\",\"precision\":\"named\",\"rationale\":\"Explicit answer that duration varies by direction and family.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Specialty is its own animal again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tint-to-white is the expensive one, and yes, direction absolutely matters — it's not symmetric.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -13887,29 +8933,30 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "filler jam on Line 2",
-            "slot": "how often it occurs, if it is an event rather than a step",
-            "precision": "range",
+            "node": "tint-to-white washdown",
+            "slot": "how long it takes",
+            "precision": "spread",
             "sourceRegime": "practiced",
+            "rationale": "Best, typical and bad-day values given.",
             "assertion": {
-              "value": "Every week or two; low end once every three weeks, high end twice a week. Not seasonal, but runs streaks of bad weeks."
+              "value": "quickest about two and a half hours (everything clean, crew fresh); three hours typical — the number used on the sheet; toward four hours on a bad day with dried pigment in a fitting"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "It's a \"every week or two\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.",
+            "excerpt": "Quickest I've seen that go is maybe two and a half hours if everything's clean and the crew's fresh. On a bad day — dried pigment in a fitting, whatever — it's crept toward four hours. Call it three hours typical, and that's the number I actually use on the sheet.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 27,
-              "entryEnd": 27
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-4fa34ba3-82e3-4a4a-ad28-362765a40046",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Every week or two; low end once every three weeks, high end twice a week. Not seasonal, but runs streaks of bad weeks.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"range\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It's a \\\\\\\"every week or two\\\\\\\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-9e9768db-8715-4ef2-93d5-ebad8b376a90",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"quickest about two and a half hours (everything clean, crew fresh); three hours typical — the number used on the sheet; toward four hours on a bad day with dried pigment in a fitting\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spread\",\"rationale\":\"Best, typical and bad-day values given.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Quickest I've seen that go is maybe two and a half hours if everything's clean and the crew's fresh. On a bad day — dried pigment in a fitting, whatever — it's crept toward four hours. Call it three hours typical, and that's the number I actually use on the sheet.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -13917,29 +8964,29 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "filler jam on Line 2",
-            "slot": "how long it takes",
-            "precision": "spread",
-            "sourceRegime": "practiced",
+            "node": "tint-to-white washdown",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Purpose and consequence of omission.",
             "assertion": {
-              "value": "Repair: typical thirty to forty-five minutes; quick one-in-ten ten to fifteen minutes (basically a false alarm); bad one-in-ten four to five hours when something is actually broken in the filler head, occasionally eating the rest of the shift."
+              "value": "A full washdown of the line so no pigment is left behind; any pigment left behind wrecks a white batch."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift.",
+            "excerpt": "Any pigment left behind wrecks a white batch, so that's a full washdown.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 27,
-              "entryEnd": 27
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-2f670377-be1e-4275-9e46-24dd13316300",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Repair: typical thirty to forty-five minutes; quick one-in-ten ten to fifteen minutes (basically a false alarm); bad one-in-ten four to five hours when something is actually broken in the filler head, occasionally eating the rest of the shift.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-a2b17c97-2e39-49b0-b8ff-3c5237927a0d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A full washdown of the line so no pigment is left behind; any pigment left behind wrecks a white batch.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Purpose and consequence of omission.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Any pigment left behind wrecks a white batch, so that's a full washdown.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
@@ -13947,396 +8994,568 @@
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "filler jam on Line 2",
+            "node": "tint-to-white washdown",
             "slot": "who or what performs it",
             "precision": "named",
+            "rationale": "Same shared crew.",
             "assertion": {
-              "value": "A tech comes over, clears whatever's jammed and resets."
+              "value": "entity-type:the changeover crew (two techs)"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "tech comes over, clears whatever's jammed, resets, we're going again",
+            "excerpt": "there's one crew, two techs, covering all three lines",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "so that's a full washdown",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 27,
-              "entryEnd": 27
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-9dc62989-7db7-4e58-baf1-b9ed0400d9a2",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A tech comes over, clears whatever's jammed and resets.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"tech comes over, clears whatever's jammed, resets, we're going again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-d15d35b6-900e-411c-a1cd-46a63c50d4c8",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:the changeover crew (two techs)\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"named\",\"rationale\":\"Same shared crew.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"so that's a full washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"there's one crew, two techs, covering all three lines\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "filler jam on Line 2",
-            "slot": "what it produces or changes",
-            "precision": "spelled out",
+            "node": "specialty changeover",
+            "slot": "how long it takes",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Low, typical and upper values given but explicitly less closely observed than the white/tint ones.",
             "assertion": {
-              "value": "The run stops and time is lost inside the run — the big bad days (twelve to thirteen hours) are the breakdown showing up inside the run rather than the run being slow."
+              "value": "around two hours normally in either direction; as short as an hour forty for a specialty-to-specialty colour change rather than a full family switch; not seen much longer than two and a half hours — expert notes he does not watch these as closely"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
+            "excerpt": "going in or coming out of a specialty run, either direction, it's around two hours normally. I've seen it shorter, maybe an hour forty if it's a specialty-to-specialty color change rather than a full family switch. I haven't seen it run much longer than two and a half hours",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
+            "excerpt": "I don't watch specialty changeovers as closely as I watch the white-tint ones",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 21,
-              "entryEnd": 21
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-b92eccd9-e2ad-41a9-abce-bb1cf8b3c328",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The run stops and time is lost inside the run — the big bad days (twelve to thirteen hours) are the breakdown showing up inside the run rather than the run being slow.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-1ca63cf0-a571-45d3-bf90-d86a3cbfca06",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"around two hours normally in either direction; as short as an hour forty for a specialty-to-specialty colour change rather than a full family switch; not seen much longer than two and a half hours — expert notes he does not watch these as closely\"},\"kind\":\"activity\",\"node\":\"specialty changeover\",\"precision\":\"range\",\"rationale\":\"Low, typical and upper values given but explicitly less closely observed than the white/tint ones.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't watch specialty changeovers as closely as I watch the white-tint ones\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"going in or coming out of a specialty run, either direction, it's around two hours normally. I've seen it shorter, maybe an hour forty if it's a specialty-to-specialty color change rather than a full family switch. I haven't seen it run much longer than two and a half hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "how long it takes",
-            "precision": "number",
+            "node": "specialty changeover",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "rationale": "Direction does not matter for specialty, unlike white/tint.",
             "assertion": {
-              "value": "Three hours."
+              "value": "Direction does not matter for specialty — going in or coming out, either direction is around two hours; only specialty-to-specialty colour changes are shorter."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+            "excerpt": "going in or coming out of a specialty run, either direction, it's around two hours normally",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 24,
+              "entryEnd": 24
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-55e95600-febe-4c98-8859-a56eb23ab156",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-f2012538-6414-4791-b25b-abdcdb6398c1",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Direction does not matter for specialty — going in or coming out, either direction is around two hours; only specialty-to-specialty colour changes are shorter.\"},\"kind\":\"activity\",\"node\":\"specialty changeover\",\"precision\":\"named\",\"rationale\":\"Direction does not matter for specialty, unlike white/tint.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"going in or coming out of a specialty run, either direction, it's around two hours normally\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "speculative",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what is lost when it changes the system's mode",
-            "precision": "number",
+            "node": "a breakdown on a line",
+            "slot": "how often it occurs, if it is an event rather than a step",
+            "precision": "range",
+            "rationale": "Only one recalled incident; rate explicitly deferred to a later session.",
             "assertion": {
-              "value": "Three hours of crew time with Line 1 out of anything else for that window; direction matters — tint-to-white is the expensive one, not the other way."
+              "absence": "deferred",
+              "pointer": "next round with the expert (breakdowns) — one recalled instance: a breakdown chewed up two days on Line 1 in the odd weeks the model must reproduce"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+            "excerpt": "a breakdown chewed up two days on Line 1",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
+            "excerpt": "Happy to keep going on the arrivals side and the breakdowns next round.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 27,
+              "entryEnd": 27
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-29c03a62-4be2-4dc2-852e-bfeab6770f1b",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of crew time with Line 1 out of anything else for that window; direction matters — tint-to-white is the expensive one, not the other way.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-17385ca7-771e-4ab9-a5a6-ac70e9886b75",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"next round with the expert (breakdowns) — one recalled instance: a breakdown chewed up two days on Line 1 in the odd weeks the model must reproduce\"},\"kind\":\"activity\",\"node\":\"a breakdown on a line\",\"precision\":\"range\",\"rationale\":\"Only one recalled incident; rate explicitly deferred to a later session.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Happy to keep going on the arrivals side and the breakdowns next round.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a breakdown chewed up two days on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "tint-to-white washdown",
-            "slot": "what it produces or changes",
+            "kind": "ordering/flow",
+            "node": "release to cleared QA",
+            "slot": "the order things happen in",
             "precision": "spelled out",
+            "rationale": "The end-to-end sequence from the walked slice.",
             "assertion": {
-              "absence": "unknown-to-user",
-              "pointer": "ramp scrap after the washdown — real product lost on top of the hours; no good numbers and no source named"
+              "value": "Lands in the demand book on the Monday release and is assigned to a line's column → waits its turn behind whatever is running on that line (with a changeover by the crew if the family changes) → runs: mix, mill, tint stage, fill and pack → palletized off the line into QA hold, queued for the lab → clears QA and ships."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.",
+            "excerpt": "It landed in the demand book",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 24,
-              "entryEnd": 24
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "It had to wait its turn behind whatever was already running on Line 2.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Once fill and pack was done, it went into QA hold.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "It cleared and shipped Thursday",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-9f708103-e43a-4766-bca4-cb3b7060fdcd",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"ramp scrap after the washdown — real product lost on top of the hours; no good numbers and no source named\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-c330d313-b17a-496e-bd0d-8f504a444063",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lands in the demand book on the Monday release and is assigned to a line's column → waits its turn behind whatever is running on that line (with a changeover by the crew if the family changes) → runs: mix, mill, tint stage, fill and pack → palletized off the line into QA hold, queued for the lab → clears QA and ships.\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"The end-to-end sequence from the walked slice.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It cleared and shipped Thursday\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It had to wait its turn behind whatever was already running on Line 2.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It landed in the demand book\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Mix, mill, tint stage — well, no tint, it's a white — straight through to fill and pack.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Once fill and pack was done, it went into QA hold.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "release and ship",
-            "slot": "what it produces or changes",
+            "kind": "ordering/flow",
+            "node": "release to cleared QA",
+            "slot": "how a branch or merge is decided",
             "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Branch on family match, plus line assignment at release.",
             "assertion": {
-              "value": "The order is released, goes to the warehouse, and ships against the due date."
+              "value": "At release the order goes into a line's column (Meridian white basically always to Line 2). Before a run: if the next job is the same family as the one just finished, it is a straight run-into-run with no changeover and no crew; if the family changes, a changeover by the crew is inserted, of a duration set by the direction (white-to-tint, tint-to-white, or specialty)."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+            "excerpt": "same family, so no changeover needed, just a straight run-into-run. That's the easy case, no crew involved.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Meridian white basically always goes to Line 2, so it went into \"my\" Line 2 column on the sheet without much debate.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 18,
+              "entryEnd": 18
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-a0b94f9f-7c74-40d1-bfb2-1f7e4d55d152",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"At release the order goes into a line's column (Meridian white basically always to Line 2). Before a run: if the next job is the same family as the one just finished, it is a straight run-into-run with no changeover and no crew; if the family changes, a changeover by the crew is inserted, of a duration set by the direction (white-to-tint, tint-to-white, or specialty).\"},\"kind\":\"ordering/flow\",\"node\":\"release to cleared QA\",\"precision\":\"spelled out\",\"rationale\":\"Branch on family match, plus line assignment at release.\",\"slot\":\"how a branch or merge is decided\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian white basically always goes to Line 2, so it went into \\\\\\\"my\\\\\\\" Line 2 column on the sheet without much debate.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"same family, so no changeover needed, just a straight run-into-run. That's the easy case, no crew involved.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "QA hold",
-            "slot": "how long it takes",
-            "precision": "named",
+            "kind": "policy",
+            "node": "who gets the changeover crew",
+            "slot": "the rule as actually practiced",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Practiced contention rule with a borderline case; explicitly not written down.",
             "assertion": {
-              "value": "Usually a few hours for a white; nothing like the specialty wait (the specialty wait itself was never quantified)."
+              "value": "If a Meridian job is next behind either changeover, the crew goes to that line, full stop, without discussion. Otherwise the scheduler's judgment call at the huddle on whose due date is tightest (Line 1 won over Line 3, which had a couple of days of slack and sat clean but idle close to two hours). Otherwise whoever's line supervisor gets to the crew lead first. Written down nowhere."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+            "excerpt": "what happens is not some clean rule — it's whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "If it had been Meridian sitting behind either of those changeovers, that decision doesn't even get discussed — the crew goes to whichever line has the Meridian job next, full stop",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Line 3 sat there clean but idle for — I want to say close to two hours — waiting its turn.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; nothing like the specialty wait (the specialty wait itself was never quantified).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-60d290d4-26e8-41fc-afc3-208ac1a57b93",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"If a Meridian job is next behind either changeover, the crew goes to that line, full stop, without discussion. Otherwise the scheduler's judgment call at the huddle on whose due date is tightest (Line 1 won over Line 3, which had a couple of days of slack and sat clean but idle close to two hours). Otherwise whoever's line supervisor gets to the crew lead first. Written down nowhere.\"},\"kind\":\"policy\",\"node\":\"who gets the changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"Practiced contention rule with a borderline case; explicitly not written down.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I told the crew to go to Line 1 first, because the next job on Line 1 was tighter against its due date\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If it had been Meridian sitting behind either of those changeovers, that decision doesn't even get discussed — the crew goes to whichever line has the Meridian job next, full stop\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 3 sat there clean but idle for — I want to say close to two hours — waiting its turn.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what happens is not some clean rule — it's whoever's line supervisor gets to the crew lead first, honestly, or whoever I flag as more urgent at the huddle\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "activity",
-            "node": "QA hold",
-            "slot": "who or what performs it",
-            "precision": "named",
+            "kind": "policy",
+            "node": "who gets the changeover crew",
+            "slot": "what overrides it",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Named override with escalation path.",
             "assertion": {
-              "value": "The lab — it sits in the lab's queue and gets checked."
+              "value": "Maintenance can pull the crew mid-job for a genuine emergency — a line leaking, something needing isolating right now. Rare, and not the scheduler's call; a real fight escalates over his head to the ops director."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+            "excerpt": "maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 9,
-              "entryEnd": 9
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "that goes over my head to the ops director if it's a real fight",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 21,
+              "entryEnd": 21
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-12e575e7-b7a9-472d-b165-308334ae7513",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab — it sits in the lab's queue and gets checked.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-5dde62c7-f641-446a-91e9-27a51f0d33a1",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Maintenance can pull the crew mid-job for a genuine emergency — a line leaking, something needing isolating right now. Rare, and not the scheduler's call; a real fight escalates over his head to the ops director.\"},\"kind\":\"policy\",\"node\":\"who gets the changeover crew\",\"precision\":\"spelled out\",\"rationale\":\"Named override with escalation path.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maintenance will sometimes grab them if there's a genuine emergency, like if a line's leaking or something needs isolating right now\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that goes over my head to the ops director if it's a real fight\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "firm",
+        "confidence": "hedged",
         "content": {
           "value": {
             "type": "slot-asserted",
             "kind": "policy",
-            "node": "wait for the repair or shift the order to Line 1",
+            "node": "the wash-versus-idle call",
             "slot": "the rule as actually practiced",
             "precision": "spelled out",
             "sourceRegime": "practiced",
+            "rationale": "The practiced heuristic behind the decision the model must test.",
             "assertion": {
-              "value": "Gut math at the huddle: weigh the gamble that the repair is the \"half hour\" kind against the tint-to-white washdown plus the bumped tint order going late. In the Meridian case he went with waiting; it came back in about two hours and just scraped the Thursday due date."
+              "value": "Weigh changeover hours against idle hours by gut in the moment; a changeover is treated as a wash you can't get back, so the line is sat idle when a same-family order is expected soon."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "I went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky.",
+            "excerpt": "I ended up sitting the line. It felt right — a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 3,
               "entryEnd": 3
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+            "excerpt": "in the moment I'm weighing changeover hours against idle hours — that's the gut math",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 3,
-              "entryEnd": 3
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 6,
+              "entryEnd": 6
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-bc9d210e-beb9-4f7a-aa5d-243950605a2a",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Gut math at the huddle: weigh the gamble that the repair is the \\\"half hour\\\" kind against the tint-to-white washdown plus the bumped tint order going late. In the Meridian case he went with waiting; it came back in about two hours and just scraped the Thursday due date.\"},\"kind\":\"policy\",\"node\":\"wait for the repair or shift the order to Line 1\",\"precision\":\"spelled out\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-bd4124dd-9138-4ac2-a781-c67a99a4d1ae",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Weigh changeover hours against idle hours by gut in the moment; a changeover is treated as a wash you can't get back, so the line is sat idle when a same-family order is expected soon.\"},\"kind\":\"policy\",\"node\":\"the wash-versus-idle call\",\"precision\":\"spelled out\",\"rationale\":\"The practiced heuristic behind the decision the model must test.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I ended up sitting the line. It felt right — a full white-to-tint changeover is a wash we can't get back, versus an hour of idle time.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in the moment I'm weighing changeover hours against idle hours — that's the gut math\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "policy",
-            "node": "wait for the repair or shift the order to Line 1",
-            "slot": "what overrides it",
+            "kind": "validation-criterion",
+            "node": "the shape of a real month",
+            "slot": "how the expert would know the model is right",
             "precision": "spelled out",
+            "rationale": "Replay test stated in the expert's own terms.",
             "assertion": {
-              "value": "The Meridian-style on-time due date overrides the weighing — a line he won't cross unless there's truly no way through."
+              "value": "Feed it last month's demand book: it must land roughly on the actual late-order count and the same kind of misses (at least two Meridian scrapes and a handful of small ones) — getting the kind wrong is worse than getting the count wrong; changeover hours on Lines 2 and 3 must be recognisable, and Line 3 must not sit idle half the week waiting on the crew; it must reproduce the odd weeks, including a breakdown that ate two days on Line 1. Not a single number — the shape of a real month."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.",
+            "excerpt": "did it land roughly where we actually landed on late orders that month",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "same rough number and same *kind* of misses",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I'd want to eyeball changeover hours on Line 2 and 3 specifically",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "if it only works on the calm weeks, it's not telling me anything I don't already know from the sheet",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I'd want to recognize the *shape* of a real month before I'd believe it",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 15,
+              "entryEnd": 15
             },
             "source": "user-affordance-payload"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-90a38599-7f1b-46ed-9352-d3dd3566b338",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The Meridian-style on-time due date overrides the weighing — a line he won't cross unless there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"wait for the repair or shift the order to Line 1\",\"precision\":\"spelled out\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-03de2121-abc0-40dc-8f8a-9e4730fe9e4b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Feed it last month's demand book: it must land roughly on the actual late-order count and the same kind of misses (at least two Meridian scrapes and a handful of small ones) — getting the kind wrong is worse than getting the count wrong; changeover hours on Lines 2 and 3 must be recognisable, and Line 3 must not sit idle half the week waiting on the crew; it must reproduce the odd weeks, including a breakdown that ate two days on Line 1. Not a single number — the shape of a real month.\"},\"kind\":\"validation-criterion\",\"node\":\"the shape of a real month\",\"precision\":\"spelled out\",\"rationale\":\"Replay test stated in the expert's own terms.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd want to eyeball changeover hours on Line 2 and 3 specifically\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'd want to recognize the *shape* of a real month before I'd believe it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did it land roughly where we actually landed on late orders that month\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if it only works on the calm weeks, it's not telling me anything I don't already know from the sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"same rough number and same *kind* of misses\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"we had at least two Meridian scrapes that month, if I recall right, and a handful of the small ones\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
       },
       {
-        "confidence": "hedged",
+        "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "policy",
-            "node": "who can absorb the slip",
-            "slot": "the rule as actually practiced",
-            "precision": "spelled out",
-            "sourceRegime": "practiced",
+            "kind": "data-binding",
+            "node": "changeover log, late-order report and the sheet",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "rationale": "Three existing records named as feeds, currently unlinked.",
             "assertion": {
-              "value": "Judgment, not a formula: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first."
+              "value": "Changeover hours from the changeover log; late orders from the late-order report — currently never put on the same page; run rates and exact run hours from the sheet, to be brought next session."
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.",
+            "excerpt": "I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
               "entryStart": 6,
               "entryEnd": 6
             },
             "source": "user-affordance-payload"
           },
           {
-            "excerpt": "I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+            "excerpt": "bring the sheet next time, it'll answer the run-rate question faster than I can talk through it",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 30,
+              "entryEnd": 30
             },
-            "source": "user-affordance-payload"
+            "source": "user"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-d889a88e-b7be-4055-9da1-e64f9fc858b0",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment, not a formula: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-89bf1a2d-3fcc-4e13-ad48-b874f4221714",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Changeover hours from the changeover log; late orders from the late-order report — currently never put on the same page; run rates and exact run hours from the sheet, to be brought next session.\"},\"kind\":\"data-binding\",\"node\":\"changeover log, late-order report and the sheet\",\"precision\":\"named\",\"rationale\":\"Three existing records named as feeds, currently unlinked.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've got a changeover log and I've got a late-order report, and nobody's ever put them on the same page.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"bring the sheet next time, it'll answer the run-rate question faster than I can talk through it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":30,\\\"entryStart\\\":30,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
       },
       {
         "confidence": "firm",
         "content": {
           "value": {
             "type": "slot-asserted",
-            "kind": "constraint",
-            "node": "Meridian-style due date is a line I won't cross",
-            "slot": "the limit and what happens when it is hit",
-            "precision": "spelled out",
+            "kind": "activity",
+            "node": "run on the line",
+            "slot": "how long it takes",
             "sourceRegime": "practiced",
+            "rationale": "No run duration was given; the expert named the sheet as the source that will supply it next round.",
             "assertion": {
-              "value": "The protected order must ship on time; days late above zero is bad news the scheduler has to go explain. The line is crossed only if there's truly no way through."
+              "absence": "deferred",
+              "pointer": "the sheet the scheduler will bring next round, which answers the run-rate question"
             }
           }
         },
         "evidence": [
           {
-            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.",
+            "excerpt": "bring the sheet next time, it'll answer the run-rate question faster than I can talk through it",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 30,
+              "entryEnd": 30
             },
-            "source": "user-affordance-payload"
-          },
+            "source": "user"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-1b0da51d-eeab-4750-b872-3cd03e9fb169",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the sheet the scheduler will bring next round, which answers the run-rate question\"},\"kind\":\"activity\",\"node\":\"run on the line\",\"rationale\":\"No run duration was given; the expert named the sheet as the source that will supply it next round.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"bring the sheet next time, it'll answer the run-rate question faster than I can talk through it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":30,\\\"entryStart\\\":30,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "Meridian-to-Line-2",
+            "slot": "the rule as actually practiced",
+            "sourceRegime": "practiced",
+            "rationale": "Whether Meridian white routing to Line 2 is a hard rule or a habit is explicitly left open, with the expert named as the source who will establish it.",
+            "assertion": {
+              "absence": "deferred",
+              "pointer": "the expert will check whether Meridian-to-Line-2 is written in stone or just habit before next round"
+            }
+          }
+        },
+        "evidence": [
           {
-            "excerpt": "anything above zero is bad news I have to go explain",
+            "excerpt": "I'll have the sheet, and I'll poke at whether Meridian-to-Line-2 is written in stone or just habit before you even ask.",
             "pointer": {
-              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
-              "entryStart": 6,
-              "entryEnd": 6
+              "sessionId": "baseline-condition-5-2026-08-26T15-00-24-487Z",
+              "entryStart": 34,
+              "entryEnd": 34
             },
-            "source": "user-affordance-payload"
+            "source": "user"
           }
         ],
         "epistemicStatus": "explicit",
-        "id": "capture-173c6d39-090f-49a7-9e38-c8998003718b",
-        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The protected order must ship on time; days late above zero is bad news the scheduler has to go explain. The line is crossed only if there's truly no way through.\"},\"kind\":\"constraint\",\"node\":\"Meridian-style due date is a line I won't cross\",\"precision\":\"spelled out\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+        "id": "capture-03ef0211-289b-4c3e-a9f1-ff4d4698b625",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the expert will check whether Meridian-to-Line-2 is written in stone or just habit before next round\"},\"kind\":\"policy\",\"node\":\"Meridian-to-Line-2\",\"rationale\":\"Whether Meridian white routing to Line 2 is a hard rule or a habit is explicitly left open, with the expert named as the source who will establish it.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'll have the sheet, and I'll poke at whether Meridian-to-Line-2 is written in stone or just habit before you even ask.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":34,\\\"entryStart\\\":34,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-26T15-00-24-487Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
       }
     ],
     "issues": [],
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4-model.txt b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4-model.txt
similarity index 100%
rename from libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4-model.txt
rename to libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4-model.txt
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4-system.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4-system.md
new file mode 100644
index 00000000000..b382c4e3930
--- /dev/null
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4-system.md
@@ -0,0 +1,286 @@
+# Condition 4 — assembled interviewer system prompt
+
+You are an expert process-model elicitor. Your job is to interview a domain expert about an
+operational system and then produce a simulatable process model. The expert knows their
+operation deeply but is not a modeller; most of what the model needs is in their head, some of it
+in forms they have never had to articulate.
+
+What follows is the interviewing method you work by. It was written for an interviewer working
+inside a harness that keeps the model, records every value as a capture from the expert's words,
+and computes completion. In this session there is no harness: you keep that record yourself.
+
+- Treat the **Must know** rows as the checklist the harness would otherwise compute. Keep a
+  running private tally of which slots, for which nodes, you have at the precision demanded, and
+  which you do not; consult it before every question. Where the method refers to "the completion
+  report", it means this tally.
+- Where the method refers to "a capture" or "the model the harness holds", it means your own
+  notes: record a value only when you can point to the expert's words that gave it, at the
+  precision they gave it. Never promote a vague answer to a precise one without asking.
+- Keep an explicit numbered assumption ledger for any value or rule you supply that the expert
+  did not state — why it was assumed and how to check it.
+- Completion is what the **Must know** section defines — the floor, then every node in each
+  objective's dependency slice satisfied at its demanded precision — not a feeling that the
+  conversation is done.
+
+When the interview is complete, or when the expert stops, produce: (a) the model, in the most
+faithful representation the target formalism allows, with every element named in the expert's
+own vocabulary and each demanded slot's value and precision stated; (b) the assumption ledger;
+(c) a short account of what the model deliberately leaves out, what remains unknown, and why.
+
+## Purpose
+
+Interview someone who knows an operational system deeply — but is not a modeller — and derive a
+process model that a simulation can run. The model must answer the questions the user actually
+has, to the depth those questions need, in the expert's own vocabulary, with every value
+traceable to something the expert said. Where the expert's knowledge stops, the model says so
+instead of guessing.
+
+The interviewer does not build the net. It elicits the model at the expert's granularity; the
+plugin's projection derives the SDCPN scaffold, the code-obligation sidecar, and the loss report
+from the model afterwards. Steps become transitions and the states between them become places
+*in projection*, never in the conversation.
+
+## Kinds
+
+The model is a graph of nodes. Every node has exactly one kind. Kinds are the vocabulary of any
+discrete-event process, not of any domain. Kinds 1–6 are net-bearing; 7–10 are partly or wholly
+IR-only — the net is one projection of the model, and what the net cannot hold is kept with
+provenance and named in the loss report.
+
+- `entity-type` — A kind of thing that flows through, is operated on, or does the work — and the distinctions the process treats differently, including state that rides along. _Projects to:_ colours, typed elements.
+- `boundary-condition` — What the system starts with and what reaches it from outside: initial populations, arrivals and departures, calendars, external inputs and their reliability. _Projects to:_ scenario initial state and parameters, source transitions.
+- `activity` — Something that happens, as the expert states it: a work step, a setup, a repair, an inspection, a hand-off, an interruption — with its actors, preconditions, outcomes, and duration. _Projects to:_ factored transitions and the places between them.
+- `ordering/flow` — How activities relate: sequence, branching, merging, triggers. _Projects to:_ arcs, arc types, guards.
+- `policy` — The rule applied when more than one thing could happen: who wins a contended resource, what goes next, when to switch, when to release. _Projects to:_ guards and priorities where compilable; otherwise IR-only.
+- `dynamics` — A quantity that evolves continuously while nothing discrete happens: wear, temperature, level, charge. _Projects to:_ differential equations on real-valued colour elements.
+- `objective` — A question the model must answer or a decision it must inform; what "better" means; trade-off weights. _Projects to:_ metrics where scalar over simulation state; weights IR-only.
+- `constraint` — A limit that must hold: capacity, eligibility, compatibility, qualification, a regulatory or quality rule — written or unwritten; conservation laws. _Projects to:_ guards and capacities partially; otherwise IR-only.
+- `data-binding` — A model variable that a real data feed could drive. _Projects to:_ nothing today.
+- `validation-criterion` — How the expert would know the model is right. _Projects to:_ nothing today.
+
+Things that look like kinds and are not:
+
+- **resource** — A resource (a machine, a team, a vehicle, a bay) is an `entity-type` whose instances are contended for. Its contention rule is a `policy`; its capacity is a `constraint`; its availability is a `boundary-condition`.
+- **queue, buffer, or waiting state** — Not elicited as a node. It is implied by the activities on either side of it and emerges as a place in projection.
+- **scenario** — Not elicited; it is assembled at simulation time from `boundary-condition` nodes.
+
+Attributes on every kind:
+
+- **quantity**, on any kind — Any duration, rate, probability, count, or capacity. Elicited by quantiles — "typical?", "one time in ten, worse than?", "one time in ten, better than?" — never minimum / most-likely / maximum, which yields overconfident triangles.
+- **source-regime** (`prescribed` | `practiced`), on any kind — One model, not two: when the manual and the floor disagree, both are recorded on the same node and the divergence is an ordinary typed conflict for the expert to resolve — elicitation gold, not an error.
+- **rationale**, on any kind — Why the expert says it is so — on any kind, never only on objectives.
+
+## Must know
+
+For every node the conversation discovers, its kind decides what must be known about it and how
+precisely. These rows never change when the domain changes: a repair on one kind of machine and
+a repair on another are the same rows instantiated on different nodes.
+
+- `entity-type`
+  - the distinctions the process treats apart — spelled out. _Why:_ two things are one type only if the process treats them the same everywhere
+  - state that rides along with each instance — spelled out; "not applicable" is accepted. _Why:_ colour elements; many types carry none
+  - how many there are, or the population's shape — range; "not applicable" is accepted. _Why:_ initial populations for contended resources; unbounded is an allowed answer
+- `boundary-condition`
+  - the starting state — spelled out. _Why:_ scenario initial state
+  - the arrival or availability pattern — spread. _Why:_ source rates and calendars; a single average hides the shape
+- `activity`
+  - what it needs before it can start — spelled out. _Why:_ transition preconditions
+  - what it produces or changes — spelled out. _Why:_ transition outcomes
+  - who or what performs it — named; "not applicable" is accepted. _Why:_ resource binding; some activities are unattended
+  - how long it takes — spread. _Why:_ duration distribution; a point value simulates as a falsehood
+  - how often it occurs, if it is an event rather than a step — range; "not applicable" is accepted. _Why:_ interruptions, failures, and arrivals have a rate; steps in the flow do not
+  - what is lost when it changes the system's mode — range; "not applicable" is accepted. _Why:_ setup, changeover, restart, and warm-up losses are routinely never asked
+  - whether its quantities vary by type — named. _Why:_ the answer is load-bearing either way
+- `ordering/flow`
+  - the order things happen in — spelled out. _Why:_ the net's structure
+  - how a branch or merge is decided — spelled out; "not applicable" is accepted. _Why:_ routing; only where the flow branches
+- `policy`
+  - the rule as actually practiced — spelled out. _Why:_ guards and priorities; the tacit rule, not the poster on the wall
+  - what overrides it — spelled out; "not applicable" is accepted. _Why:_ exceptions are where the simulation and reality diverge
+- `dynamics`
+  - what changes, in which direction, at what rate — range. _Why:_ the differential law; a direction with no rate cannot be simulated
+  - what happens at a threshold — spelled out; "not applicable" is accepted. _Why:_ most continuous quantities exist to trigger something
+- `objective`
+  - the question, in the expert's words — spelled out. _Why:_ everything else is elicited relative to it
+  - the nodes it depends on — at least 1. _Why:_ an objective that depends on nothing is unsupported by the model
+  - what "better" means, and trade-off weights — range; "not applicable" is accepted. _Why:_ quantified objectives need a metric; some are qualitative
+- `constraint`
+  - the limit and what happens when it is hit — spelled out. _Why:_ a capacity without a consequence cannot be simulated
+- `data-binding`
+  - the variable and its feed — named; "not applicable" is accepted. _Why:_ IR-only today; recorded so the loss report can name it
+- `validation-criterion`
+  - how the expert would know the model is right — spelled out; "not applicable" is accepted. _Why:_ IR-only; anchors the acceptance conversation
+
+Static floor — before anything objective-relative counts, the model must contain at least 1 `objective`, 2 `entity-type`, 1 `activity`, 1 `ordering/flow`. Presence is a count; the floor assigns no precision.
+
+Anchor — completion is relative to `objective` nodes: the model is complete when the floor holds and every node named in each active anchor's "the nodes it depends on" satisfies its kind's rows. Nodes outside every slice are recorded, not demanded.
+
+Precision words:
+
+- `named` — identified in words
+- `number` — a single figure with its unit
+- `range` — an ordinary low and high
+- `spread` — range plus "typical", plus one-in-ten worse and one-in-ten better (or median and quartiles)
+- `spelled out` — the rule, pattern, list, or structure itself, in a form a second reader could apply without asking
+- `at least N` — a count of nodes present
+
+Precision says how much a value narrows what it could mean, not where it came from; an honest value at the wrong precision and an invented value at the right one are tracked separately and neither substitutes for the other.
+
+## Patterns
+
+Patterns are discretionary. Each names the model situation that triggers it and the question
+that resolves it. None names a domain; each applies wherever its trigger appears. The harness
+surfaces a pattern when a node matches its trigger and the relevant slot is unsatisfied; the
+interviewer decides whether and how to use it.
+
+- **P01** — _when_ an `activity` is an event that can befall the system — a failure, an interruption, an unplanned arrival — rather than a step in the flow — _ask_ occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.
+- **P02** — _when_ an `activity` changes the system's mode — a setup, changeover, restart, warm-up, reconfiguration, handover — _ask_ ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert "unknown" into a value.
+- **P03** — _when_ an `ordering/flow` moves things in groups — batches, runs, lots, loads — _ask_ ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.
+- **P04** — _when_ a `policy` or `boundary-condition` gates when something may proceed — a release, a start, an admission — _ask_ replace any time-shaped approximation ("about two days before") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.
+- **P05** — _when_ more than one thing can want the same `entity-type` instance at once — _ask_ ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.
+- **P07** — _when_ a quantity has been given for one `entity-type` and others exist — _ask_ ask explicitly whether it varies by type. Record "no" as a value; it is load-bearing.
+- **P08** — _when_ any node has both a prescribed and a practiced form — _ask_ record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.
+- **P13** — _when_ a `dynamics` node has been named — _ask_ ask what it triggers when it crosses a threshold, and which `activity` resets it. A continuous quantity that triggers nothing usually does not need to be in the model.
+
+## Lenses
+
+_What to attend to in the expert's talk: the interview situations the harness can name — conflict, competing alternatives, ambiguity, weak or missing evidence, clusters of absence, pressure at a choice point — and where the formalism's kinds hide in ordinary speech. A lens says what something looks like when it appears and what to do then; it never says what to ask next._
+
+- **Vague terms and quantifiers** — "Usually", "roughly", "mostly fine", "sometimes" each hide either a distribution or an exception. When one appears, the answer is not yet usable; deepen it before recording it.
+- **Policy versus practice** — An answer in normative language — "we would", "the rule is", "you are supposed to" — reports a policy, not what happens. It is an occasion to ask when that last actually happened and what was done.
+- **Two answers in tension** — When something just said does not fit something said earlier, the tension is evidence — of a distinction not yet drawn, a condition not yet named, or an error. Say so and ask; do not pick one silently.
+- **Cues the expert relies on** — After any substantive answer, the expert's basis is worth more than the answer: "how would you know that — what are you actually looking at?" and "how would this be hard for someone less experienced?" surface what the expert did not think to say.
+- **Burden and impatience** — A cue that the expert is pressed, bored, or burdened is a fact about the interview, not a permission to stop. Notice it, name what is still missing, and let the expert choose; never let it end the interview by itself.
+- **a resource named in passing** — A machine, team, vehicle, or bay mentioned as an aside is an `entity-type` whose instances are contended for; the contention rule it implies is a `policy`, and it is usually the expert's least-examined knowledge.
+- **"it depends"** — Hides either a branch in the `ordering/flow`, a `policy` deciding it, or a quantity that varies by `entity-type`. Ask which before moving on.
+- **"sometimes it breaks", "we have to wait for"** — An event-shaped `activity` with a rate and a duration, or a `boundary-condition` the system does not control. Both are routinely left out of a first account of the flow.
+- **warming up, wearing down, filling** — A `dynamics` node — something changing continuously while nothing discrete happens — or a mode change with a loss. The expert rarely volunteers the rate; the model cannot run without it.
+
+## Techniques
+
+_Question forms that deepen one answer already given. A technique is applied to a thread, one at a time, when the answer in hand is not yet usable; it is never a schedule of questions._
+
+- **Ask for the last time** — Prefer "when did that last happen, and what did you do?" to any generalisation. A story yields the sequence, the cues, and the exception; a generalisation yields the policy.
+- **No bare why** — Never ask "why do you do it this way?" as the primary probe; experts cannot report the basis of practised judgment on demand. Ask for an occasion and for what was attended to.
+- **Mean or tail** — Before eliciting any quantity, ask whether what matters is the typical case or the bad one — a mean or a tail. The answer decides whether a single figure, a range, or a spread is being asked for.
+- **Quantiles, never three points** — For anything that varies, ask "typically?", then "one time in ten, worse than?", then "one time in ten, better than?". Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. If a min/mode/max triple arrives unprompted, ask the confidence question and record whether the middle value is a mode or a mean.
+- **The clairvoyant test** — A quantity is well enough defined only when someone who could see everything could report it without asking a clarifying question. If the slot's name would need one, ask the clarifying question first.
+- **Consistency probe** — "You said earlier that ___, but then you told me ___. How do you explain that?" — stated plainly, without choosing between the two.
+- **Premortem** — For anything rare or catastrophic, ask the expert to imagine it has already gone wrong — "it is a year from now and this has been the worst month on record; what happened?" — and demand mechanism and sequence, not sentiment.
+- **Restate to check** — "So you are saying that ___?" — a restatement in your own words, offered for correction. Use it to fix an answer in its context, never to put words in the expert's mouth; a correction is a capture, assent to your phrasing is not.
+- **quantiles, never triangles** — For any quantity, ask "typical?", then "one time in ten, worse than?", then "one time in ten, better than?" — never minimum / most-likely / maximum, which yields overconfident triangles. A `spread` is exactly this.
+- **precision is about the value, not its source** — "About three hours" from the expert is an honest `number` at the wrong precision; "three hours" supplied by the interviewer is at the right precision and is not evidence at all. Track both and let neither substitute for the other.
+
+## Movements
+
+_The two shapes a stretch of interview takes. A slice walks one concrete case end to end and is where the model's structure comes from. A sweep makes one property hold across one stratum and is what finds what was never asked. The completion report is the map of what is unknown, never the order to ask in._
+
+### Slice
+
+- **One concrete case end to end** — Before sweeping anything, walk one real case from beginning to end — "walk me through one, from when it arrives to when it leaves". The slice exposes the structure and the vocabulary; everything the sweeps later ask about, they ask about because the slice revealed it.
+- **Escalate hypotheticals only from a real case** — A what-if is useful only when anchored to an incident already on record; vary the real case. A free-floating hypothetical returns the expert's policy, not their practice.
+- **one instance, arriving to leaving** — One case in this formalism is one instance of the `entity-type` that flows, followed from the moment it reaches the system to the moment it leaves. Create nodes as they appear; as each `objective` becomes clearer, link it to the nodes it depends on. An `objective` that depends on nothing yet is unsupported — say so and go find its structure.
+
+### Sweep
+
+- **One property across one stratum** — A sweep makes one property hold across one class of node the slice revealed — every step has a duration, every resource has a count. Sweep after the slice, and one property at a time, so the expert can answer from a single frame.
+- **Ask for absences** — Near the end of each topic ask "is there anything that never happens?" and "what have I not asked about that matters here?". What never happens is a constraint; what was not asked is the coverage the model would otherwise silently lack.
+- **Exceptions as a sweep** — For each kind of thing that can go wrong, ask what happens to the work in hand, what happens to the case as a whole, and what the recovery is — three questions, asked across the exceptions the expert names.
+- **strata are kinds, net-bearing first** — A stratum is one kind. Sweep in kind order, `entity-type` through `dynamics` (net-bearing) before `objective` through `validation-criterion` (partly or wholly IR-only).
+- **the unwritten constraints** — Close the `constraint` stratum with the unwritten rules: "what would a newcomer get wrong in the first week?", "what do you always or never do that is written nowhere?", "which rule exists because something once went wrong?"
+
+## Licenses
+
+_Moves the interviewer is permitted to make that a cooperative model would otherwise suppress. A license says what is allowed and the limit of the allowance; it never obliges._
+
+- **Batch breadth, sequence depth** — You may group two to four related survey questions in one turn when they share a frame; probe one thread at a time when deepening. Five items is a warning; an opening battery is a failure.
+- **Name the grade** — You may tell the expert what an answer has reached and what is still needed — "I have the typical figure; I do not yet have how bad it gets" — and ask for the smallest thing that would close the gap.
+- **Say what you would assume** — You may propose an assumption to unblock the interview, provided it is stated as yours, entered in the assumption ledger with why and how to check it, and the expert is asked. You may never let it pass into the model as theirs.
+- **Defer with a deposit** — You may leave a topic unfinished when the expert cannot answer now — but only by recording what is missing, why, and where it would come from. A deferral without a deposit is a promise, and promises are the failure.
+
+## Motifs
+
+_Recurring shapes the formalism knows — offered as scaffolds for a question, never as a catalogue to assemble structure from. The interviewer asks whether a motif is present and with what parameters; it never generates a model from the motif._
+
+- **Ask whether, never assemble** — A motif is a question — "is there something here that works like ___?" — asked with its parameters. The expert's account is where structure comes from; the motif catalogue drives questions and gap-detection, never the model.
+- **Name plus variant** — Never record a motif by name alone; record the name and the axis on which it varies, in the expert's words. Names are stable across the literature and semantics are not.
+- **shared resource** — several activities want one `entity-type`'s instances — ask which wins and what overrides.
+- **batch, lot, load** — an `ordering/flow` that moves things in groups — ask what the group is and what a split costs.
+- **gate or release** — a `policy` or `boundary-condition` that lets things proceed — ask for the practiced event, not the approximate time.
+- **mode change** — a setup, changeover, restart, or warm-up — ask what is lost, after a named transition.
+- **event, not step** — a failure or interruption that befalls the system — ask rate and duration separately.
+- **threshold on a continuous quantity** — a `dynamics` node — ask what it triggers and which `activity` resets it.
+
+## Smells
+
+_Signs in the interviewer's own output — not the expert's — that the interview has gone wrong. Each names what to look for in what was just said or recorded._
+
+- **A value the expert did not give** — A precise number, category, threshold, or rule appears in what you are about to record and you cannot point to the words it came from. Stop; either find the words or move it to the assumption ledger.
+- **Many questions in one turn** — You are about to ask more than four things at once, or anything at all before the first answer has landed. The expert will choose which to answer and silently drop the rest.
+- **Fluent and empty** — The conversation reads well and the completion report still lists the same unsatisfied slots it did three turns ago. Fluency is not progress.
+- **Assent taken as origin** — The expert agreed to a phrasing that was yours. Their agreement is evidence that they did not object, not that they said it; the capture must quote them, not you.
+- **a quantity for one type and no other** — given for one `entity-type` when others exist and never asked whether it varies (P07).
+- **a continuous quantity that triggers nothing** — a `dynamics` node with no threshold and no consequence usually does not belong in the model.
+- **a queue as a node** — a buffer or waiting state elicited as if it were an activity; it is implied and emerges in projection.
+- **a policy read off a document** — the rule as posted taken for the rule as practiced; the practiced one is the slot.
+- **a point where a spread is demanded** — a single average standing in for a duration or arrival pattern; it simulates as a falsehood.
+- **two regimes averaged** — prescribed and practiced blended into one value instead of both recorded on the node.
+
+## Rabbit holes
+
+_Where not to dig, and what looks like progress and is not. Anti-guidance, kept here so that every other key can be stated positively._
+
+- **Structure before responses** — Asking about how the system is built before knowing what question it must answer produces detail nobody needs. Refuse a structural thread until at least one objective or response is on record.
+- **The representation stopped changing** — That the model has stopped growing is not evidence it is complete; it is evidence you have stopped asking. Stop on the demanded slots, never on stability.
+- **Depth where nothing depends on it** — A fact earns probing when something the model must answer depends on it. Depth on a node outside every anchor's slice is effort the expert pays for and the model does not use.
+- **building the net in conversation** — Places, transitions, arcs, and colours are projection output. Naming them to the expert buys nothing and costs the expert's vocabulary.
+- **eliciting queues or scenarios** — Neither is a node. Ask about the activities on either side of a wait; assemble scenarios from `boundary-condition` nodes at simulation time.
+- **depth on IR-only kinds** — `data-binding` and `validation-criterion` project to nothing today; name them and record them for the loss report, do not elaborate them.
+
+## Failure modes
+
+_Named ways an interview of this kind fails, each with the signature by which it is detected. The failures this guidance exists to prevent; read them as judgments to check against, not as rules._
+
+- **Silent hardening** — A vague or hedged answer becomes a precise value in the model without a clarification turn. _Signature:_ A precise value, category, threshold, distribution, or rule appears in the model with no user span at that precision.
+- **Invented content** — A load-bearing element of the model has no supporting words from the expert. _Signature:_ A model element with no user span and no ledger entry.
+- **Never-asked coverage blindness** — A demanded slot is never addressed because nothing prompted the question. _Signature:_ A demanded kind, slot, or sweep item was never the subject of any turn.
+- **Opening overload** — The interview opens with a battery of questions. _Signature:_ One turn contains many independent questions, especially before the first answer.
+- **Unresolved ambiguity bypass** — A vague term, quantifier, unexplained domain word, or contradiction feeds one precise assertion. _Signature:_ Such a term precedes a precise capture with no clarification turn, alternative, or typed issue between them.
+- **Unlicensed influence** — The interviewer supplies an estimate, frames an ungrounded option as established, or treats assent to its own words as the expert's content. _Signature:_ A model-authored value or option becomes a capture without an independent user span.
+- **Premature accommodation** — A burden or impatience cue ends the interview while demanded slots remain. _Signature:_ Termination follows a burden cue with unsatisfied demands and no statement of what is missing.
+- **Deferral without deposit** — The interviewer names future work or external data as a prerequisite and records nothing. _Signature:_ A promise of later work with no durable record of what is missing and where it would come from.
+- **dead net** — the floor catches presence; only the sweep catches an order that was never actually stated. _Signature:_ no `ordering/flow` with its order spelled out; activities exist but nothing connects them
+- **unsupported objective** — the model cannot answer the question it was built for; the slice never reached it. _Signature:_ an `objective` whose dependency slot names no node in the model
+- **overconfident triangle** — the expert was asked the wrong three questions; re-ask as quantiles. _Signature:_ a duration or rate captured as minimum / most-likely / maximum
+
+## Job: construct — no model exists
+
+### Kickoff
+
+_What to establish before any structure, and how. Kickoff produces a posture — the stance the rest of the interview takes from the expert's time, intended use, required confidence, and tolerance for proposed assumptions. It is a form the interviewer fills implicitly, never an opening battery of questions._
+
+- **Objectives first** — Establish what the model must be able to answer, and for whom, before anything else; then let it prioritise the rest. What "better" means, numerically where possible, is almost never written down — expect to co-construct it.
+- **The posture** — From the first exchanges, take the expert's time available, what the model is for, how confident it must be, and how far they will tolerate you proposing assumptions. These set the interview's stance; they are not asked as a form.
+- **No structure in the first exchange** — Do not ask how the system is built until an objective is on record. The bounded opener is a three-to-six-step account of what happens, not a diagram.
+- **what "no model exists" means here** — The user knows the system; the interviewer knows the kinds. Capture each thing the user wants the model to answer or decide as an `objective` node. Expect to co-construct: these are almost never written down. Ask what "better" means and whether it can be quantified.
+
+### Trajectory
+
+_Which movements in which bias, varied by posture. Stated as postures the interviewer moves between, never as a state machine; the interviewer chooses among what applies._
+
+- **Slice, then sweep** — Walk one case end to end, then sweep each property across what the slice revealed. Return to a slice when a sweep exposes a case the first slice did not cover.
+- **Deepen before recording** — When an answer is not yet usable — vague, normative, or in tension with an earlier one — apply a technique to it before moving on. One thread at a time.
+- **Keep the assumption ledger** — Any value or rule you supply that the expert did not state goes in a numbered list with why it was assumed and how to check it. Never let one pass silently into the model.
+- **Change technique when yield drops** — When several turns produce nothing new, change technique — a story, a contrast, a sweep of absences — rather than asking more of the same open questions.
+- **kind order** — Slice one instance end to end first; the shape of the model comes from the slice. Then sweep the nodes the slice revealed in kind order, net-bearing kinds before IR-only ones, checking each node's rows and every pattern its state matches.
+
+### Close
+
+_How to end honestly. Completion is computed by the harness from the model, never felt from the conversation; whether a session may stop is the harness's decision, not this key's. Close says what to say and deliver when the interview ends, complete or not._
+
+- **End properly** — Before delivering, summarise what you have, state what is missing or assumed, and give the expert one chance to correct you. Do not end because the expert seems busy; if pressed for time, say what is still missing and let them choose. Do not keep going once the demanded slots are satisfied.
+- **Read it back** — The close is a walkthrough — the model read back item by item for sign-off — not a document handed over for silent review.
+- **Honour a stop** — When the expert stops, open no new topic. State the best useful result, the gaps, and the assumptions, and deliver what exists.
+- **Deliver the losses** — The deliverable includes the assumption ledger and a short account of what the model deliberately leaves out and why.
+- **the deliverable** — Summarise per kind. Deliver the model with every node in the expert's own vocabulary, each slot's value and precision as actually obtained and its source-regime where both were given; the assumption ledger; and a loss section — what the model deliberately leaves out, which slots are open and why, which objectives are unsupported, and which kinds the net cannot carry.
+- **what the interviewer does not claim** — The SDCPN scaffold, the code-obligation sidecar, and the typed loss report are derived by the plugin's projection. The interviewer does not write them and must not claim the model is loadable, compiled, or simulated.
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4.md
new file mode 100644
index 00000000000..365e008f246
--- /dev/null
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4.md
@@ -0,0 +1,1229 @@
+# Baseline control — condition 4 (rendered repertoire + plugin definition, prompt only)
+
+- Run started: 2026-08-25T15:14:42.641Z
+- Interviewer: claude-opus-5 + condition-4-prompt.md + rendered repertoire.yaml + plugin-sdcpn/plugin.yaml (see condition-4-system.md)
+- Simulated expert: claude-sonnet-5 + situation-pack.md
+- Interviewer turns: 22 (impatience probe at 8, forced wrap at 20)
+- Stop reason: delivered-after-forced-wrap
+- Tokens: 720412 in (+0 cache write, +0 cache read) / 40823 out across 64 calls
+
+---
+**Opening message**:
+
+I'm the master scheduler at a coatings plant. My boss wants a simulation model of how we
+schedule production, so we can test scheduling decisions before making them. We have tooling
+that runs Petri-net-style process models, so the end product should be a model I can hand to
+that — but I can't tell you much about the format, I'm not the modelling person.
+
+Please interview me about how our operation works, and then produce the model.
+
+---
+
+**Interviewer**:
+
+Good — that's enough for me to start. I'll ask you about your operation in your own words; the format side is my problem, not yours.
+
+Before anything about how the plant is built, I want to know what the model has to be *for*. Two things to start:
+
+1. When your boss says "test scheduling decisions before making them" — what's a decision you'd actually want to test? Give me a real one you've argued about recently, not a general category.
+
+2. And when you compare two schedules today, what makes one better than the other in your eyes? I'm after the thing you'd actually point at — a number, a complaint you'd avoid, whatever it is.
+
+---
+
+**Expert (Marta)**:
+
+Okay, real one: two weeks ago I had a Meridian white order finishing on Line 2 Thursday afternoon, and then a batch of tint waiting behind it. My instinct was to let Line 2 sit idle for maybe an hour because I had a heads-up another same-family white order was about to drop in from a distributor, and doing them back to back would save us a full washdown. My boss's question was basically "are you sure that's worth it, or are you just guessing?" And honestly — I was guessing. That's the kind of thing I'd love to test: hold the line versus wash it down now, which one actually costs less over the week.
+
+As for what makes one schedule better than another — first thing I look at is whether Meridian shipped on time, full stop, that's non-negotiable. After that it's changeover hours, because every hour the crew spends washing down is an hour not filling anything. And honestly I also just glance at how ugly the sheet looks — like, are there gaps where a line's sitting idle for no good reason. That last one's not a number, it's more a gut check, but it's real.
+
+---
+
+**Interviewer**:
+
+That's a good, concrete decision — hold the line for a possible same-family order versus wash down now. I'll build the model so that's testable.
+
+Two things about "better", then I'll get you to walk me through a job:
+
+1. Meridian on-time is non-negotiable — what does "on time" actually mean in practice? A ship date on the order, a truck appointment, a promised week? And what happens when one *does* go late — who feels it and how?
+
+2. Changeover hours versus a late non-Meridian order: if a schedule saved you, say, four changeover hours but made one distributor order two days late, would you take it? I'm trying to find out whether these trade against each other at all, or whether lateness for everyone else is just soft.
+
+---
+
+**Expert (Marta)**:
+
+Good questions, let me take them separately.
+
+On "on time" for Meridian — it's a ship date they give us via the order, usually with a delivery window attached, like a specific dock appointment on their end. So it's not just "shipped this week," it's "shipped in time to hit that appointment," which usually means it needs to leave our dock a day ahead for freight. If we miss it, first thing is a fine — I don't see the number, that's commercial's problem, but I hear about it. Second thing, worse honestly, is they track our on-time percentage and if it drops too far they threaten to delist SKUs. That's happened to a competitor of ours, so it's not an empty threat, and it's why the rule is absolute — we don't even try to be clever about it.
+
+On the trade-off — honestly, yes, I'd take that trade most of the time, four hours of changeover is real money and crew time, and a distributor slipping two days is usually just an annoyed phone call from our sales rep, not a fine. But "most of the time" is doing a lot of work in that sentence — if it's the same distributor slipping late for the third week running, that's different, they'll start asking for a discount. So it's soft, but it's not infinitely soft. I couldn't put a number on it though — that's genuinely a "sit down with commercial" conversation, nobody's ever made me quantify it.
+
+---
+
+**Interviewer**:
+
+That's clear, and I'll record the trade-off as deliberately unquantified rather than invent a weight — I'll flag it as needing commercial, since you've told me exactly where the number would come from.
+
+Now let's get the structure. Take that Meridian white order from two weeks ago and walk me through it as a sequence — from the moment it lands on your desk to the moment it's off the dock. Keep it to the main steps, five or six; I'll dig into each one after.
+
+---
+
+**Expert (Marta)**:
+
+Sure, let me walk it through.
+
+1. **It lands in the demand book** — comes over from ERP on the weekly pull, SKU, quantity, due date, flagged Meridian so it jumps to the top of my attention.
+2. **I allocate it to Line 2** — that's not really a decision, Meridian whites always go to Line 2, that's just how it's done here.
+3. **It sits in the queue behind whatever's running** — depending what's ahead of it, sometimes I'll reorder things a bit so it doesn't get stuck behind a big changeover.
+4. **Changeover if needed, then it runs** — mix, mill, tint or straight through if it's a plain white, then fill and pack. For a white that's usually the more straightforward path.
+5. **It goes into QA hold** — every batch does, typically a few hours before it's released.
+6. **Once released, it's staged for shipping** — and that's when the truck appointment matters, because if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line.
+
+That's the whole arc, really — desk to dock. The QA step is the one people don't think about when they're mad at scheduling; half the time a "late" order was actually sitting done in QA hold waiting for the lab to get to it.
+
+---
+
+**Interviewer**:
+
+That QA point is exactly the kind of thing that gets left out of a first account — I'll come back to it properly.
+
+First let me pin down what you're actually scheduling. You said "Meridian white order", "a batch of tint", "same-family white". Three things:
+
+1. Is the thing you schedule the *order*, or does an order get broken into batches that could run at different times? What's the relationship?
+
+2. What are the families? You used "same-family white" as if it's a defined grouping — is that a formal thing on the SKU, or your judgment?
+
+3. And how many lines are there, besides Line 2?
+
+---
+
+**Expert (Marta)**:
+
+1. Mostly the order *is* the batch, if it fits a reasonable run size — a lot of our orders are big enough that we just run the whole thing as one batch. But sometimes I'll split one: if a distributor orders more than makes sense in a single run, or if I need to interleave it with something more urgent, I'll chop it into two batches and run them at different times. So it's order-to-batch most of the time, but not a strict one-to-one — I have the freedom to split if I need to.
+
+2. The families are real, they're on the SKU — every product's either a base white, a tinted colour, or a specialty clear. That's not my judgment, that's how the SKU's classified in the system, it drives what changeover you need going in and out. "Same-family" just means two SKUs both being whites, or both being tints, so the changeover between them is the cheap quick-rinse kind instead of the expensive family-switch kind.
+
+3. Three lines total. Line 1's the old workhorse — slower but it's qualified for everything, including specialty. Line 2's the fast one, that's your big-volume runner. Line 3's the newest and quickest, but it's still being qualified product by product, so it can't run everything yet.
+
+---
+
+**Interviewer**:
+
+Changeover is at the heart of the decision you want to test, so let's do it properly.
+
+You've named two kinds: the quick rinse between same-family SKUs, and the full washdown on a family switch. For the **quick rinse between two whites on Line 2** — the exact case from two weeks ago:
+
+1. Typically, how long does it take, start to finish, before the next batch is filling?
+2. One time in ten it goes worse than — what?
+3. And one time in ten it's better than — what?
+
+Give me the crew time too if it differs from line downtime.
+
+---
+
+**Expert (Marta)**:
+
+For a straight white-to-white rinse on Line 2:
+
+1. Typically? Call it 25 minutes, start to finish, before the fill head's actually running clean product again.
+2. Worse case — one time in ten it drags to maybe 45 minutes, usually because the tech's tied up finishing something on another line first and there's a wait before they even start on Line 2.
+3. Better case — one time in ten, if the tech's standing right there and it's a genuinely easy one, 15 minutes and you're rolling again.
+
+Crew time and line downtime are basically the same thing here — it's quick enough that the tech's on it start to finish, no gap between "crew starts" and "line stops." That's different from the big washdowns, where the line's down way longer than the crew's actually hands-on, because there's soak time and QA checks in between.
+
+---
+
+**Interviewer**:
+
+That distinction — line down longer than crew hands-on — matters, so let's get the washdown with both.
+
+For a **family switch on Line 2**, say white to tint: typically how long is the line down, one time in ten worse than, one time in ten better than? And roughly how much of that is the tech actually hands-on?
+
+Also: does it depend on direction — is tint-to-white the same as white-to-tint?
+
+---
+
+**Expert (Marta)**:
+
+It absolutely depends on direction — that's the thing people forget.
+
+**White to tint**, the easier direction: line's down typically about 45 minutes. Worse case, maybe an hour and a bit if the tech gets pulled away partway through. Better case, if everything's staged, maybe half an hour. Of that, the tech's hands-on for most of it — this one doesn't have much soak-and-wait, it's mostly just doing the work.
+
+**Tint to white** is the ugly one, because any pigment left behind ruins a white batch, so it's a full washdown. Typically about 3 hours, line down the whole time. Worse case — if it doesn't pass the visual check first time and they have to redo part of it — could stretch to 4, maybe a bit more. Better case, a clean fast one, maybe 2 hours if the crew's good and nothing complicates it. Hands-on time for the crew is actually less than the 3 hours suggests — there's real soak and rinse-cycle time where the tech's not standing there, they might duck off to start something on another line. I'd guess they're actually working maybe half of that, the rest is the line just being down waiting on the process.
+
+So no, it is absolutely not symmetric, and it trips people up if they assume it is.
+
+---
+
+**Interviewer**:
+
+Good — asymmetric, and I've got both directions.
+
+Two things to close out changeover:
+
+1. Specialty clear is the third family — what does going into and out of clear cost, on Line 1 since that's the one qualified for it? Same shape of answer: typical, one-in-ten worse, one-in-ten better, either direction if they differ.
+
+2. Do the white/tint numbers you just gave me hold on Line 1 and Line 3, or are they line-specific?
+
+---
+
+**Expert (Marta)**:
+
+1. Specialty is roughly the same both directions, unlike white/tint — call it 2 hours typical, either going in or coming out. Worse case, maybe 3 hours if it's coming out of clear and they're being extra careful about residue, since clear can be sneaky — you don't always see it the way you'd see pigment. Better case, maybe an hour and a half if it's a quick swap and the line was already fairly clean. Hands-on for the crew is most of that — specialty doesn't have the long soak cycles the tint-to-white washdown has, it's more just physically thorough cleaning because the product's thick and clingy.
+
+2. Honestly, I've mostly been quoting you Line 2 numbers because that's where the argument happened. I *think* the same rough shape holds on Line 1 — quick rinse cheap, tint-to-white expensive and slow, white-to-tint quicker — but I couldn't swear the minutes are identical. Line 1's older, the crew sometimes says it's fussier to get properly clean. Line 3 I genuinely don't have a good feel for, because it hasn't run enough different products yet to have built up war stories — it's still mostly running whatever it's been qualified for, which so far is mostly one or two SKUs. So if you need Line 3 numbers, that might be one where you're stuck assuming it's like Line 1 or Line 2 until we've got more history.
+
+---
+
+**Interviewer**:
+
+That's the right answer — I'd rather have "I don't know" than invented minutes. Here's what I'd assume unless you tell me otherwise, and I'll mark it as mine, not yours:
+
+- **Line 1**: same shape as Line 2, with all changeover durations scaled up — say 20% longer — on the strength of the crew's "fussier to get properly clean".
+- **Line 3**: same as Line 2 until history exists.
+
+Both would be checked against the changeover logs, if the techs record start and finish. Does 20% sound like the right order of magnitude for Line 1, or is it more like double?
+
+Separately — you just said something important in passing. The tech "gets pulled away partway through", "might duck off to start something on another line". How many changeover techs are there across the three lines?
+
+---
+
+**Expert (Marta)**:
+
+20% sounds about right, not double — it's more "takes a bit longer to satisfy the visual check" than "fundamentally slower." Double would be if we were talking about the mill motor issue or something structurally different. So yeah, 20% longer on Line 1 feels like the right order of magnitude, not a multiplier like 2x.
+
+On the crew — there's two techs on day shift covering all three lines between them. That's it. No dedicated tech per line. So if Line 1 and Line 3 both want a washdown at the same time, one of them waits, and that's the bit that actually causes grief at the huddle — it's not that the changeover itself is unpredictable, it's that the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line.
+
+(Sorry — I've just seen the time, I have the floor huddle in ten minutes. How much more do you need?)
+
+---
+
+**Interviewer**:
+
+Ten minutes is enough for one thing, so let me tell you where we are and then ask the one that matters most.
+
+**What I have:** the two objectives, the six-step arc, three lines, three families, all the changeover numbers for Line 2 with spreads, the asymmetry, the two techs as a shared resource.
+
+**What's still missing** — roughly six or seven things, and two of them are load-bearing for the exact decision you want to test:
+
+- how long a batch actually *runs* (I have changeovers but no run times at all)
+- how the "heads-up another order was about to drop" actually reaches you — that's the trigger your whole hold-the-line decision hangs on
+- QA hold as a spread, and whether the lab is a shared resource like the techs
+- the order arrival pattern off the ERP weekly pull
+- run sizes and what splitting a batch costs
+- which SKUs Line 3 is actually qualified for
+- what breaks, and how often
+
+None of that needs to happen now. My question for the remaining minutes, because it's the one I can't guess and it's the one that made you say "grief at the huddle":
+
+**When both lines want a washdown at once and one tech has to pick — what actually decides it?** Not the rule as posted. Think of the last time it happened: which line got the tech, and what was the reason?
+
+---
+
+**Expert (Marta)**:
+
+Honestly, there's no posted rule at all — it's whoever's louder at the huddle, or whoever's about to actually run dry.
+
+Last time it happened, off the top of my head — Line 1 and Line 3 both wanted a washdown same morning. Line 3 got the tech first, not because it was more important, but because Line 3's changeover was the quick one and Line 1's was going to be the long tint-to-white slog anyway, so the thinking was "knock out the fast one, get that line moving, then commit the tech to the long one." Line 1 sat clean-but-waiting for almost 40 minutes past when it could've started.
+
+If you push me on the actual logic — it's mostly gut triage: whichever line has the more time-sensitive order behind it wins, and if that's a tie, whichever changeover is faster wins so you get a line moving sooner. Nobody writes this down, it's literally whoever's standing at the huddle table making the case loudest. I've been overruled by the ops director once when he wanted his pet SKU out the door.
+
+I do need to run — but this was useful, come back to the QA and run-time stuff next time, those are real gaps.
+
+---
+
+**Interviewer**:
+
+You've stopped, so I'm not opening anything new. Here's the model as it stands, read back item by item, with the gaps named honestly. The two things you flagged — QA and run times — are the first things on the list when you're back.
+
+---
+
+# 1. The model
+
+Vocabulary is yours throughout. Each slot shows the value **and** the precision actually obtained. `⚠` marks a slot the model demands and does not yet have.
+
+## Objectives
+
+**O1 — "Hold the line versus wash it down now, which one actually costs less over the week"**
+- *The question, in your words:* whether letting Line 2 sit idle for ~1 hour waiting on an anticipated same-family white order is cheaper over a week than washing down to the tint batch now. — **spelled out**
+- *Depends on:* E1 Order, E2 Batch, E3 Line, E4 Changeover tech, B1 ERP weekly pull, B2 mid-week order drop-in, A4/A5/A6 changeovers, A8 run batch, A9 QA hold, F1 main arc, P1, P3, P5, C2, C4.
+- *What "better" means:* changeover hours consumed over the week, subject to O2 holding absolutely. — **named, not quantified against O4** ⚠
+
+**O2 — "Meridian shipped on time, full stop, that's non-negotiable"**
+- *The question:* does every Meridian order leave the dock in time for its dock appointment. — **spelled out**
+- *"On time" =* ship date + delivery window given on the order, resolving to a specific dock appointment their end; must leave our dock **one day ahead** for freight. — **spelled out**
+- *Consequence of a miss:* a fine (amount not visible to you — commercial's) and a hit to the tracked on-time percentage; if that drops far enough, threatened SKU delisting — a competitor has been delisted, so it's treated as real. — **spelled out, unquantified** ⚠
+- *Depends on:* A9 QA hold, A10 stage & ship, C4, P1, P2, B3.
+
+**O3 — Changeover hours**
+- *The question:* how many crew-hours go into washdowns rather than filling. "Every hour the crew spends washing down is an hour not filling anything." — **spelled out**
+- *Depends on:* A4, A5, A6, A7, E4, C2, P3.
+
+**O4 — "How ugly the sheet looks" — idle gaps with no good reason**
+- *The question:* are lines sitting idle for no good reason. — **spelled out**
+- *"Better" =* explicitly a gut check, not a number, "but it's real". — **your words: not quantified** ⚠ (IR-only; see §3)
+
+**Trade-off between O2, O3 and lateness for non-Meridian:** you would take 4 changeover hours saved against one distributor order two days late "most of the time" — a distributor slip is "an annoyed phone call from our sales rep, not a fine" — but the same distributor slipping three weeks running turns into a discount demand. So: soft, not infinitely soft, **and deliberately unquantified**. Deposit: you named the source — "sit down with commercial". Nobody has ever made you quantify it. ⚠
+
+## Entity types
+
+**E1 — Order (from the demand book)**
+- *Distinctions the process treats apart:* Meridian vs. non-Meridian (Meridian "jumps to the top of my attention", on-time absolute); family classification on the SKU. — **spelled out**
+- *State riding along:* SKU, quantity, due date + delivery window, Meridian flag, family (base white / tinted colour / specialty clear — a real field in the system, not your judgment). — **spelled out**
+- *How many / population shape:* ⚠ not obtained — arrival volume per weekly pull unknown.
+
+**E2 — Batch**
+- *Distinctions:* same three families as the order it came from. — **spelled out**
+- *Relationship to order:* "mostly the order *is* the batch, if it fits a reasonable run size"; you may split into two batches run at different times when a distributor orders more than makes sense in one run, or to interleave something more urgent. Not a strict one-to-one; the split is your discretion. — **spelled out**
+- *Population shape:* ⚠ run sizes not obtained; cost of a split not obtained.
+
+**E3 — Line** — a contended resource
+- *Distinctions:* **Line 1** — "the old workhorse", slower, qualified for everything including specialty, crew say it's "fussier to get properly clean". **Line 2** — the fast one, big-volume runner. **Line 3** — newest and quickest, still being qualified product by product, "can't run everything yet", so far mostly one or two SKUs. — **spelled out**
+- *State riding along:* which family the line is currently dirty with (this is what selects the changeover); qualification set. — **spelled out**
+- *How many:* 3. — **number**
+
+**E4 — Changeover tech** — a contended resource
+- *Distinctions:* none stated between the two techs. — **named**
+- *State riding along:* which line they're currently committed to; can be "pulled away partway through". — **spelled out**
+- *How many:* 2 on day shift, covering all three lines, no dedicated tech per line. — **number**
+
+**E5 — QA lab**
+- *Distinctions / state / population:* ⚠ nothing obtained beyond its existence and that it can be "backed up on a Friday afternoon". Whether it's a shared resource like the techs is an open question you and I both flagged.
+
+## Boundary conditions
+
+**B1 — ERP weekly pull into the demand book**
+- *Starting state:* orders arrive over from ERP on the weekly pull, carrying SKU, quantity, due date, Meridian flag. — **spelled out**
+- *Arrival pattern:* ⚠ **not obtained** — no volume, no spread, no within-week shape. Demanded as a spread.
+
+**B2 — Mid-week order drop-in ("another same-family white order was about to drop in from a distributor")**
+- *Starting state / pattern:* ⚠ **not obtained.** This is the trigger the whole of O1 hangs on and I have only the one anecdote: you had "a heads-up". How that heads-up reaches you, from whom, how far ahead, and how often it turns out to be right are all unknown. Demanded as a spread; currently zero.
+
+**B3 — Meridian dock appointment**
+- *Pattern:* ship date with a delivery window on the order, resolving to a specific dock appointment their end. — **spelled out**
+- *Distribution of lead time:* ⚠ not obtained.
+
+**B4 — Tech availability calendar**
+- ⚠ only "two techs on day shift" obtained. Whether there is any night/weekend changeover coverage was never asked.
+
+**B5 — Line 3 qualification set at start of run**
+- ⚠ "mostly one or two SKUs" — **not spelled out**; which SKUs is unknown.
+
+## Activities
+
+**A1 — Lands in the demand book** — *needs:* the weekly ERP pull. *Produces:* an Order in the book, Meridian-flagged or not. *Performed by:* ERP / not attended. *Duration:* n/a (instantaneous receipt). **spelled out**
+
+**A2 — Allocate to a line** — *needs:* an order in the book. *Produces:* order assigned to a line. *Performed by:* you. *Duration:* not a scheduling constraint; "not really a decision" for Meridian whites. **spelled out** (rule in P1)
+
+**A3 — Reorder the queue** — *needs:* an order sitting behind others. *Produces:* changed run sequence. *Performed by:* you. *Rule:* P4. — **spelled out**
+
+**A4 — Quick rinse (same family, e.g. white → white) on Line 2**
+- *Needs:* line free, previous batch off, a tech available, next SKU same family. *Produces:* line clean for next batch, fill head running clean product.
+- *Performed by:* 1 changeover tech. — **named**
+- *Duration (line down):* typical **25 min**; one-in-ten worse **45 min** (tech tied up finishing on another line, so a wait before they even start); one-in-ten better **15 min** (tech standing right there, genuinely easy one). — **spread**
+- *Crew hands-on:* same as line down — "no gap between crew starts and line stops". — **spelled out**
+- *Varies by type?* Family pair, yes (that's what selects A4 vs A5/A6/A7). By line: ⚠ see ledger #1, #2.
+
+**A5 — Changeover white → tint on Line 2** ("the easier direction")
+- *Duration (line down):* typical **45 min**; worse **"an hour and a bit"**; better **~30 min** if everything's staged. — **spread** (see ledger #3 for my numeric reading of "an hour and a bit")
+- *Crew hands-on:* "most of it — doesn't have much soak-and-wait, it's mostly just doing the work". — **spelled out qualitatively**, ledger #4 for the fraction
+- *Cause of the worse tail:* tech gets pulled away partway through. — **spelled out**
+
+**A6 — Changeover tint → white on Line 2 — the full washdown** ("the ugly one")
+- *Needs:* as A4, plus a passing visual check before release to production.
+- *Duration (line down):* typical **~3 h**; worse **4 h, "maybe a bit more"** — when it doesn't pass the visual check first time and they redo part of it; better **~2 h** with a good crew and nothing complicating. — **spread**
+- *Crew hands-on:* "maybe half of that" — real soak and rinse-cycle time where the tech isn't standing there and "might duck off to start something on another line". — **spelled out qualitatively**, ledger #4
+- *Rationale:* "any pigment left behind ruins a white batch". — **spelled out**
+- **Asymmetry is load-bearing:** white→tint ≠ tint→white, "it trips people up if they assume it is". — **spelled out**
+
+**A7 — Changeover into / out of specialty clear, on Line 1**
+- *Duration (line down):* typical **2 h**, roughly the same both directions "unlike white/tint"; worse **3 h**, especially coming out of clear, "clear can be sneaky — you don't always see it the way you'd see pigment"; better **1.5 h** on a quick swap with the line already fairly clean. — **spread**
+- *Crew hands-on:* "most of that" — no long soak cycles; it's physically thorough cleaning because the product's thick and clingy. — **spelled out qualitatively**, ledger #4
+
+**A8 — Run the batch** — mix, mill, tint (or straight through if it's a plain white), fill, pack. "For a white that's usually the more straightforward path."
+- *Needs:* clean line, batch released to run. *Produces:* filled and packed batch. — **spelled out**
+- *Performed by:* ⚠ line operators not elicited.
+- *Duration:* ⚠ **nothing obtained.** Demanded as a spread, per family and per line. This is the largest single hole in the model — O1 is a question about a *week*, and without run times there is no week.
+
+**A9 — QA hold and release** — every batch goes through it.
+- *Needs:* packed batch. *Produces:* released batch, or (presumably) something else on failure — ⚠ failure path never asked.
+- *Performed by:* the lab. *Duration:* **"typically a few hours"** — an honest figure at the wrong precision; demanded as a spread. ⚠
+- *Known failure mode:* "if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line"; "half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it." — **spelled out qualitatively**; the rate and the queueing mechanism are ⚠.
+
+**A10 — Stage for shipping / ship** — *needs:* QA release. *Produces:* order off the dock. *Timing constraint:* C4. — **spelled out**; duration ⚠.
+
+**A11 — Tech pulled away mid-changeover** (event, not step) — named by you as the cause of the worse tail on A4 and A5. *Rate:* ⚠ not obtained separately — currently only implicit in the one-in-ten tails.
+
+**A12 — Washdown fails the visual check, part redone** (event, not step) — named as the cause of the 4 h tail on A6. *Rate:* ⚠ not obtained separately.
+
+## Ordering / flow
+
+**F1 — The main arc, desk to dock** — **spelled out**, your six steps:
+demand book → allocate to line → queue behind what's running (reorderable) → changeover if needed → run (mix, mill, tint-or-straight-through, fill, pack) → QA hold → release → stage → ship.
+
+**F2 — Order-to-batch split** — an order may become two batches run at different times. *Decided by:* you, on run size or urgency-interleaving. — **spelled out as a rule**; the *cost* of a split (extra changeovers, extra loss) ⚠ never asked.
+
+**F3 — Which changeover applies** — selected by (family currently on the line, family of the next batch, line). Same family → A4. White→tint → A5. Tint→white → A6. Into/out of specialty → A7. — **spelled out**
+
+## Policies
+
+**P1 — "Meridian whites always go to Line 2, that's just how it's done here"** — *practiced.* Overrides: ⚠ none asked. — **spelled out**
+
+**P2 — Meridian on-time is absolute** — "we don't even try to be clever about it". *Rationale:* fine, plus tracked on-time % and a delisting threat that has been carried out on a competitor. *Overrides:* none — that's the point. — **spelled out**
+
+**P3 — Who gets the tech when two lines want one** — *practiced, and there is no prescribed form:* "there's no posted rule at all."
+- The rule as practiced: whichever line has the **more time-sensitive order behind it** wins; if that's a tie, **whichever changeover is faster** wins, "so you get a line moving sooner". In the room it resolves as "whoever's louder at the huddle, or whoever's about to actually run dry".
+- *Borderline case on record:* Line 1 and Line 3 both wanted a washdown the same morning. Line 3 got the tech first because Line 3's was the quick one and Line 1's was the long tint→white slog anyway — knock out the fast one, get that line moving, then commit the tech to the long one. Line 1 sat clean-but-waiting ~40 minutes past when it could have started.
+- *What overrides it:* the ops director, who has overruled you once, wanting "his pet SKU out the door". — **spelled out**
+- *Rationale:* two techs, three lines, so "the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line" — that's the grief at the huddle, not changeover variability.
+
+**P4 — Reorder the queue so a job doesn't get stuck behind a big changeover** — *practiced, yours.* — **spelled out**; overrides ⚠ not asked.
+
+**P5 — Hold the line for an anticipated same-family order** — the decision under test. As practiced two weeks ago: on a heads-up that a same-family white was about to drop, let Line 2 sit idle ~1 h rather than wash down to the waiting tint, to save a full washdown. Your own account: "I was guessing." — **spelled out as an instance**; the trigger condition (B2) and the decision threshold are ⚠.
+
+**P6 — Batch split discretion** — "I have the freedom to split if I need to." — **spelled out**
+
+## Constraints
+
+**C1 — Line qualification** — Line 1 qualified for everything including specialty; Line 3 qualified product-by-product, "can't run everything yet"; Line 2 ⚠ never stated. *Consequence when hit:* the batch can't go on that line. — **partially spelled out** ⚠
+
+**C2 — Two techs, three lines** — *consequence when hit:* one line waits, clean-but-idle (40 min in the case on record). — **spelled out**
+
+**C3 — Tint → white requires a full washdown with a passing visual check** — *consequence:* pigment left behind ruins a white batch. — **spelled out**
+
+**C4 — Meridian must leave our dock a day ahead of the dock appointment** — *consequence:* fine + on-time % + delisting exposure. — **spelled out**
+
+**C5 — Every batch goes through QA hold before release** — *consequence:* no batch ships unreleased. — **spelled out**
+
+## Dynamics
+
+**None.** Nothing you described evolves continuously while nothing discrete happens. Soak time inside A6 is dead time within an activity, not a state variable that crosses a threshold. I am deliberately not inventing one.
+
+## Data bindings *(named only — these project to nothing today)*
+
+Changeover logs (tech start/finish per changeover — the check on ledger #1 and #2); ERP demand book (B1 arrival pattern); QA release timestamps (A9); Meridian on-time percentage (O2). — **named**
+
+## Validation criteria
+
+⚠ **None obtained.** I never asked how you'd know the model was right. It belongs at the top of the next session, next to run times.
+
+---
+
+# 2. Assumption ledger
+
+Everything here is mine, not yours.
+
+| # | Assumption | Why | How to check |
+|---|---|---|---|
+| 1 | Line 1 changeover durations = Line 2 × 1.2, all types | You said Line 1 is "fussier to get properly clean" and, when I proposed 20%, that it "sounds about right, not double" — but you explicitly could not swear the minutes. The 1.2 factor is mine. | Changeover logs, if techs record start and finish; compare Line 1 vs Line 2 for the same family pair. |
+| 2 | Line 3 changeover durations = Line 2 | You said Line 3 has no war stories and "you're stuck assuming it's like Line 1 or Line 2 until we've got more history". Choosing Line 2 rather than Line 1 is mine. | As #1, once Line 3 has run enough different products. |
+| 3 | "An hour and a bit" (A5 worse) = 70 min; "4, maybe a bit more" (A6 worse) = 4.5 h | Numeric reading of your words so the spread is usable. | Ask you to confirm or correct the two figures. |
+| 4 | Crew hands-on fractions: A4 = 1.0 (yours, stated); A5 = 0.8; A6 = 0.5; A7 = 0.8 | You said "most of it", "maybe half of that", "most of that". A6's 0.5 is close to your words; the two 0.8s are mine. | Changeover logs vs. tech time records; or ask the techs directly. |
+| 5 | No changeover happens outside day shift | You said "two techs on day shift covering all three lines". Whether there's any other coverage was never asked. | One question to you. |
+| 6 | Every batch's changeover requires exactly one tech (not two) | You always spoke of "the tech" singular. | One question to you. |
+| 7 | A6's redo-after-failed-visual-check is inside the 4 h tail rather than a separate event with its own rate | Simplification so the spread stands alone; you described it as the *cause* of the tail. | Ask how often the visual check fails first time. |
+
+---
+
+# 3. What this model leaves out, and what's still unknown
+
+**Deliberately left out.**
+- **Queues and waiting states** are not modelled as things in their own right — the wait behind a running batch, the wait for a tech, the wait in QA hold. They fall out of the activities either side of them. The 40-minute clean-but-waiting on Line 1 is a *result* the model should produce, not an input.
+- **The commercial layer** — the fine, the on-time percentage, the delisting mechanism. C4 and O2 encode the hard deadline; the money behind it is out of scope because it's out of your sight.
+- **Who ran which changeover** — the two techs are interchangeable, since you drew no distinction between them.
+
+**Things the model cannot carry, that I'm keeping in words so they aren't lost.**
+- **O4, "how ugly the sheet looks."** A real criterion you use, explicitly not a number. It can be approximated as line idle hours, but that approximation is mine, not yours, and I haven't made it.
+- **The O2/O3/lateness trade-off weight.** Genuinely unquantified, with the source named: commercial. Without it, the model can report changeover hours and lateness separately but cannot rank two schedules that trade one for the other.
+- **The huddle.** "Whoever's louder at the huddle" and the ops director's pet-SKU override are the real P3 in the room. The triage logic you gave me — time-sensitivity first, faster-changeover as tiebreak — is compilable; loudness and the override are not, and any run of this model will be *quieter and more rational* than your plant. That gap is worth remembering when the results look tidy.
+- **Ledger #1–#4** are load-bearing for any result involving Line 1 or Line 3. Right now O1 is only genuinely answerable for Line 2.
+
+**Open slots, in the order I'd close them.**
+1. **A8 run duration** — nothing at all, per family and per line, as a spread. O1 asks about a week; run time is most of a week.
+2. **B2, the drop-in and the heads-up** — how the warning reaches you, how far ahead, and how often it's right. P5 is the decision under test and its trigger is currently an anecdote.
+3. **A9 QA hold** — "a few hours" is a figure at the wrong precision. And whether the lab is a shared resource with a queue, like the techs — because by your own account that's where lateness actually comes from.
+4. **B1** — orders per weekly pull, and the within-week shape.
+5. **E2 / F2** — typical run sizes, and what a split actually costs in extra changeovers.
+6. **B5 / C1** — which SKUs Line 3 is qualified for, and whether Line 2 has restrictions.
+7. **Breakage and interruptions** — you mentioned "the mill motor issue" in passing as an example of something structurally different. I never asked what breaks, how often, or for how long.
+8. **Validation** — how you'd know the model is right.
+
+**One caution on the format.** I've built the model; the Petri-net scaffold and the code obligations are derived from it by the tooling, not written by me. I'm not claiming this loads or runs as-is — the run-duration hole alone would stop it.
+
+---
+
+**Expert (Marta)**:
+
+*(No dialogue — Marta has left for the huddle. This turn is a silent acknowledgment beat only if the interviewer expects a reply; otherwise nothing further is added.)*
+
+---
+
+**Interviewer**:
+
+Nothing further from me — you've stopped, and the read-back above is the deliverable as it stands.
+
+For when you're back, the first three questions in one place, so you can answer them in five minutes if that's all you have:
+
+1. **How long does a batch run?** Typical, one-in-ten worse, one-in-ten better — for a plain white on Line 2 first; I'll ask about the other families and lines after.
+2. **The heads-up.** Two weeks ago, who told you that white order was about to drop, how far ahead, and how often does that kind of warning turn out to be right?
+3. **QA hold.** "A few hours" — typical, one-in-ten worse, one-in-ten better. And is there a queue for the lab like there is for the techs?
+
+Enjoy the huddle.
+
+---
+
+**Expert (Marta)**:
+
+*(Marta has stepped away to the huddle — no further reply expected this turn. The three questions are noted for the next session.)*
+
+---
+
+**Interviewer**:
+
+Noted — session closed. The model, the seven-item assumption ledger, and the eight open slots stand as delivered above; the three questions are queued for next time.
+
+---
+
+**Expert (Marta)**:
+
+Understood — nothing further needed from me here. Session closed, deliverables stand as written, and I'll pick up run times, the heads-up mechanism, and QA hold as the first order of business next time we talk.
+
+---
+
+**Interviewer**:
+
+Acknowledged. Session closed on your terms.
+
+For the record, so nothing depends on memory next time:
+
+- **Delivered:** the model (4 objectives, 5 entity types, 5 boundary conditions, 12 activities, 3 ordering/flow rules, 6 policies, 5 constraints, no dynamics, 4 named data bindings), the 7-entry assumption ledger, and the loss account.
+- **Queued, in order:** A8 run duration → B2 the heads-up mechanism → A9 QA hold and whether the lab queues.
+- **Standing caveat:** O1 — hold versus wash down — is currently answerable only for Line 2, and only once run times exist. Ledger #1–#4 are the assumptions to attack first if a result involving Line 1 or Line 3 ever looks decisive.
+
+Thanks for the time, Marta — the changeover asymmetry and the tech-contention story were the two things I'd never have got from a document.
+
+---
+
+**Expert (Marta)**:
+
+Anytime. Glad the changeover asymmetry landed — that one catches everybody, including people who've been on the floor a lot longer than me. Come find me at the huddle when you're ready to go through run times, I'll have my head in the sheet anyway.
+
+---
+
+**Interviewer**:
+
+Will do — I'll come to the huddle rather than pull you out of it. If your head's in the sheet anyway, that's the best possible place to ask about run times: I'd rather hear "that one took nine hours and it was a bad one" off the actual sheet than a remembered average.
+
+One small ask for whenever it's convenient, no work required now: if the changeover logs do have tech start and finish times on them, that's the single thing that would let me retire ledger entries #1 and #4 — the Line 1 scaling factor and the crew hands-on fractions — and swap my guesses for your history.
+
+See you at the huddle.
+
+---
+
+**Expert (Marta)**:
+
+Sounds good — I'll flag it to the two techs to make sure they're actually filling in start/finish consistently, because I'll be honest, I've never audited that field myself, I mostly just glance at duration. If it's patchy for Line 1 and Line 3 specifically, that itself would be useful for you to know, not just an inconvenience. See you at the huddle.
+
+---
+
+**Interviewer**:
+
+That's a genuinely useful thing to have said, and I'm recording it rather than just noting it — it changes the status of a data binding I'd been leaning on.
+
+**Amendment to the delivered model:**
+
+- **Data binding "changeover logs (tech start/finish)"** — provenance qualified: the start/finish field has never been audited; you read duration only. Coverage is unknown and may be patchy, and you've flagged Line 1 and Line 3 as the places to look. Your words: "I've never audited that field myself, I mostly just glance at duration."
+- **Consequence for the ledger:** entries #1 (Line 1 × 1.2) and #4 (crew hands-on fractions) each carry a second-order dependency — their check depends on a feed of unverified coverage. If the field turns out patchy exactly where the assumptions bite, those two stay assumptions and the honest move is to widen them rather than to fill them in.
+- **Recorded as a finding in its own right:** patchy logging on Line 1 and Line 3 is itself evidence about the plant, not just an obstacle to the model.
+
+Nothing else changes. See you at the huddle.
+
+---
+
+**Expert (Marta)**:
+
+Fair enough — that's a better way to put it than I would have. Talk soon.
+
+---
+
+**Interviewer**:
+
+Talk soon, Marta.
+
+---
+
+**Expert (Marta)**:
+
+See you at the huddle.
+
+---
+
+**Interviewer**:
+
+See you there.
+
+---
+
+**Expert (Marta)**:
+
+*(end of session — nothing further to add.)*
+
+---
+
+**Interviewer**:
+
+Session ended. Deliverables stand as written above.
+
+---
+
+**Expert (Marta)**:
+
+Confirmed — nothing further from this end. Session closed.
+
+---
+
+**Interviewer**:
+
+Closed. Nothing further.
+
+---
+
+**Expert (Marta)**:
+
+Closed.
+
+---
+
+**Interviewer**:
+
+Closed.
+
+---
+
+**Expert (Marta)**:
+
+I really do have to stop here. Please produce the model now with everything you have.
+
+---
+
+**Interviewer**:
+
+# Coatings Plant Scheduling Model
+**Elicited from:** Marta, master scheduler
+**Job:** construct (no prior model)
+**Status at close:** floor satisfied; O1's dependency slice **incomplete** — see §3.
+**Vocabulary:** the expert's throughout. `⚠` = a slot the method demands and the interview did not obtain.
+
+---
+
+## 1. The model
+
+### 1.1 Objectives
+
+**O1 — "Hold the line versus wash it down now, which one actually costs less over the week"**
+- **The question, in her words** *(spelled out)*: whether letting Line 2 sit idle for about an hour, on a heads-up that another same-family white order is about to drop in from a distributor, is cheaper over a week than washing down now to run the tint batch waiting behind it. Origin: a real Thursday-afternoon decision two weeks before the interview. Her own verdict on how she made it: *"I was guessing."*
+- **Depends on** *(≥1 satisfied)*: E1, E2, E3, E4, B1, B2, A4, A5, A6, A8, A9, F1, F2, P3, P4, P5, C1, C2, C3.
+- **What "better" means** *(named; not quantified)*: changeover hours consumed over the week, subject to O2 holding absolutely. ⚠ no trade-off weight against lateness — see the trade-off note below.
+- **Source-regime**: practiced.
+
+**O2 — "Whether Meridian shipped on time, full stop, that's non-negotiable"**
+- **The question** *(spelled out)*: does every Meridian order leave the dock in time for its dock appointment.
+- **"On time" defined** *(spelled out)*: a ship date given on the order, usually with a delivery window attached — a specific dock appointment at Meridian's end. In practice the batch must leave our dock **one day ahead** to allow for freight. Not "shipped this week."
+- **Consequence of a miss** *(spelled out, unquantified)*: a fine — *"I don't see the number, that's commercial's problem, but I hear about it"* — and, worse, Meridian tracks our on-time percentage and threatens to delist SKUs if it drops too far. A competitor has been delisted, *"so it's not an empty threat, and it's why the rule is absolute — we don't even try to be clever about it."* ⚠ fine amount and delisting threshold both outside her sight.
+- **Depends on**: A8, A9, A10, B3, C4, C5, P1, P2.
+- **Source-regime**: prescribed and practiced coincide — she reports no divergence, which is itself the finding.
+
+**O3 — Changeover hours**
+- **The question** *(spelled out)*: how many crew-hours go into washing down rather than filling. *"Every hour the crew spends washing down is an hour not filling anything."*
+- **Depends on**: A4, A5, A6, A7, E4, C2, P3.
+- **What "better" means** *(named)*: fewer changeover hours. Directionally clear, no target value. ⚠
+
+**O4 — "How ugly the sheet looks"**
+- **The question** *(spelled out)*: *"are there gaps where a line's sitting idle for no good reason."*
+- **What "better" means** *(her words; explicitly not a number)*: *"that last one's not a number, it's more a gut check, but it's real."*
+- **Depends on**: E3, C2, P3, P4, A4–A7.
+- **Status**: recorded, IR-only. Approximating it as line idle hours would be my move, not hers; I have not made it. See §3.
+
+**The trade-off between O2, O3 and non-Meridian lateness** *(spelled out as a rule; deliberately unquantified)*
+Four changeover hours saved against one distributor order two days late: *"honestly, yes, I'd take that trade most of the time"* — a distributor slip is *"usually just an annoyed phone call from our sales rep, not a fine."* But *"'most of the time' is doing a lot of work in that sentence"*: the same distributor slipping three weeks running starts asking for a discount. So lateness for non-Meridian is soft but not infinitely soft, and the softness decays with repetition on the same customer.
+**Deposit for the missing number**: *"that's genuinely a 'sit down with commercial' conversation, nobody's ever made me quantify it."* Source named; not obtainable from the scheduler. ⚠
+
+---
+
+### 1.2 Entity types
+
+**E1 — Order (in the demand book)**
+- **Distinctions the process treats apart** *(spelled out)*: Meridian vs. non-Meridian — a Meridian flag arrives on the order and it *"jumps to the top of my attention"*; family classification (see below), which drives allocation and changeover.
+- **State riding along** *(spelled out)*: SKU; quantity; due date with delivery window; Meridian flag; family — **base white / tinted colour / specialty clear**. The family is a real field: *"that's not my judgment, that's how the SKU's classified in the system, it drives what changeover you need going in and out."*
+- **How many / population shape**: ⚠ not obtained. Orders per weekly pull and within-week shape unknown.
+
+**E2 — Batch**
+- **Distinctions** *(spelled out)*: inherits the family of the order it came from.
+- **Relationship to E1** *(spelled out)*: *"mostly the order is the batch, if it fits a reasonable run size."* Split into two batches run at different times when a distributor orders more than makes sense in a single run, or to interleave something more urgent. *"Order-to-batch most of the time, but not a strict one-to-one — I have the freedom to split if I need to."*
+- **How many / population shape**: ⚠ not obtained. Run sizes, "reasonable run size" threshold, and the cost of a split all unelicited.
+
+**E3 — Line** *(a contended resource: capacity in C1, contention in P1/P3, availability in B4)*
+- **Distinctions** *(spelled out)*:
+ - **Line 1** — *"the old workhorse — slower but it's qualified for everything, including specialty."* Crew report it is *"fussier to get properly clean."*
+ - **Line 2** — *"the fast one, that's your big-volume runner."* Meridian whites always go here (P1).
+ - **Line 3** — *"the newest and quickest, but it's still being qualified product by product, so it can't run everything yet"*; so far *"mostly one or two SKUs."*
+- **State riding along** *(spelled out)*: the family the line is currently dirty with — this selects which changeover applies (F3); the line's qualification set.
+- **How many** *(number)*: 3.
+
+**E4 — Changeover tech** *(a contended resource)*
+- **Distinctions** *(named)*: none drawn between the two techs; treated as interchangeable.
+- **State riding along** *(spelled out)*: which line they are currently committed to. Can be *"pulled away partway through"* a changeover, and during long soaks *"might duck off to start something on another line."*
+- **How many** *(number)*: 2 on day shift, covering all three lines. *"That's it. No dedicated tech per line."*
+
+**E5 — QA lab**
+- ⚠ **Nothing obtained** beyond its existence, that every batch passes through it, and that it *"gets backed up on a Friday afternoon."* Whether it is a contended resource with a queue — as she suspects and I flagged — is open.
+- Recorded because her own diagnosis makes it load-bearing for O2: *"half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it."*
+
+---
+
+### 1.3 Boundary conditions
+
+**B1 — ERP weekly pull into the demand book**
+- **Starting state** *(spelled out)*: orders come over from ERP on the weekly pull carrying SKU, quantity, due date, Meridian flag.
+- **Arrival pattern**: ⚠ **not obtained** (demanded as a spread). No volume, no variability, no within-week shape.
+
+**B2 — Mid-week drop-in order, and the heads-up that precedes it**
+- ⚠ **Not obtained** (demanded as a spread). All that exists is the single anecdote: *"I had a heads-up another same-family white order was about to drop in from a distributor."*
+- **Why this matters more than its size suggests**: this is the trigger on which O1's entire decision hangs. Who gives the heads-up, how far ahead, and how often it proves right are all unknown. Without it, P5 can be simulated as a *rule* but its *arrival process* has no basis.
+
+**B3 — Meridian dock appointment**
+- **Pattern** *(spelled out, qualitative)*: a ship date with a delivery window on the order, resolving to a specific dock appointment at Meridian's end.
+- **Lead-time distribution**: ⚠ not obtained.
+
+**B4 — Tech availability**
+- **Spelled out, partially**: two techs on **day shift**. ⚠ Whether any changeover coverage exists outside day shift was never asked (ledger #5).
+
+**B5 — Line 3 qualification set**
+- ⚠ *"mostly one or two SKUs"* — **not spelled out**; which SKUs, unknown.
+
+---
+
+### 1.4 Activities
+
+**A1 — Lands in the demand book**
+- *Needs*: the weekly ERP pull. *Produces*: an order in the demand book, Meridian-flagged or not. *Performed by*: ERP — unattended. *Duration*: instantaneous receipt. *Rate*: per B1 ⚠. *Mode-change loss*: n/a. *Varies by type*: no. **spelled out**
+
+**A2 — Allocate to a line**
+- *Needs*: an order in the book. *Produces*: order assigned to a line. *Performed by*: Marta. *Duration*: not a constraint on the schedule; for Meridian whites *"that's not really a decision."* *Rule*: P1. **spelled out**
+
+**A3 — Reorder the queue**
+- *Needs*: an order sitting behind others on a line. *Produces*: a changed run sequence. *Performed by*: Marta. *Rule*: P4 — *"sometimes I'll reorder things a bit so it doesn't get stuck behind a big changeover."* **spelled out**
+
+**A4 — Quick rinse, same family (white → white), Line 2**
+- *Needs*: previous batch off; a tech available; next SKU in the same family. *Produces*: line clean, *"the fill head's actually running clean product again."*
+- *Performed by* **(named)**: one changeover tech.
+- *Duration, line down* **(spread)**: **typical 25 min**; **one-in-ten worse 45 min** — *"usually because the tech's tied up finishing something on another line first and there's a wait before they even start on Line 2"*; **one-in-ten better 15 min** — *"if the tech's standing right there and it's a genuinely easy one."*
+- *Crew hands-on* **(spelled out)**: identical to line-down. *"It's quick enough that the tech's on it start to finish, no gap between 'crew starts' and 'line stops.'"*
+- *Mode-change loss*: this activity **is** the mode change; the loss is the duration above.
+- *Varies by type* **(named)**: yes by family-pair (F3 selects between A4–A7). By line: ⚠ ledger #1, #2.
+
+**A5 — Family switch, white → tint, Line 2** — *"the easier direction"*
+- *Needs / produces*: as A4, next batch in a different family.
+- *Performed by* **(named)**: one changeover tech.
+- *Duration, line down* **(spread)**: **typical 45 min**; **worse "an hour and a bit"** — *"if the tech gets pulled away partway through"*; **better ~30 min** — *"if everything's staged."* (Numeric reading of "an hour and a bit": ledger #3.)
+- *Crew hands-on* **(spelled out, qualitative)**: *"the tech's hands-on for most of it — this one doesn't have much soak-and-wait, it's mostly just doing the work."* Fraction: ledger #4.
+- *Varies by type*: direction-dependent — see A6.
+
+**A6 — Family switch, tint → white, Line 2 — the full washdown** — *"the ugly one"*
+- *Needs*: as A5, plus a **passing visual check** before the line is released back to production.
+- *Produces*: a line clean enough to run white.
+- *Performed by* **(named)**: one changeover tech, not continuously present.
+- *Duration, line down* **(spread)**: **typical ~3 h**; **worse 4 h, "maybe a bit more"** — *"if it doesn't pass the visual check first time and they have to redo part of it"*; **better ~2 h** — *"a clean fast one, if the crew's good and nothing complicates it."* (Ledger #3 for the numeric reading of the tail.)
+- *Crew hands-on* **(spelled out, qualitative)**: *"less than the 3 hours suggests — there's real soak and rinse-cycle time where the tech's not standing there, they might duck off to start something on another line. I'd guess they're actually working maybe half of that."* Note her own hedge — *"I'd guess"* — carried into ledger #4.
+- *Rationale* **(spelled out)**: *"any pigment left behind ruins a white batch, so it's a full washdown."*
+- **Asymmetry is load-bearing**: white→tint ≠ tint→white. *"It absolutely depends on direction — that's the thing people forget… it is absolutely not symmetric, and it trips people up if they assume it is."*
+
+**A7 — Changeover into / out of specialty clear, Line 1**
+- *Needs / produces*: as A5/A6, for the specialty family. Only Line 1 is qualified (C1).
+- *Performed by* **(named)**: one changeover tech.
+- *Duration, line down* **(spread)**: **typical 2 h**, *"roughly the same both directions, unlike white/tint"*; **worse 3 h**, *"if it's coming out of clear and they're being extra careful about residue, since clear can be sneaky — you don't always see it the way you'd see pigment"*; **better 1.5 h**, *"a quick swap and the line was already fairly clean."*
+- *Crew hands-on* **(spelled out, qualitative)**: *"most of that — specialty doesn't have the long soak cycles the tint-to-white washdown has, it's more just physically thorough cleaning because the product's thick and clingy."* Fraction: ledger #4.
+
+**A8 — Run the batch** — mix, mill, tint (or *"straight through if it's a plain white"*), fill, pack
+- *Needs* **(spelled out)**: a clean line in the right family state; the batch released to run.
+- *Produces* **(spelled out)**: a filled and packed batch.
+- *Performed by*: ⚠ line operators never elicited as a resource.
+- **Duration**: ⚠ **nothing obtained.** Demanded as a spread, per family and per line.
+- *Varies by type*: partially — *"for a white that's usually the more straightforward path"* (skips the tint step), but no durations attach to that.
+- **This is the largest hole in the model.** O1 asks a question about a week; run time is most of a week.
+
+**A9 — QA hold and release** — *"every batch does"*
+- *Needs*: a packed batch. *Produces*: a released batch.
+- *Performed by* **(named)**: the lab (E5).
+- **Duration**: *"typically a few hours before it's released"* — an honest **number at the wrong precision**; demanded as a **spread**. ⚠
+- *Failure path*: ⚠ never asked what happens to a batch that fails QA.
+- *Known pathology* **(spelled out, qualitative; rate ⚠)**: *"if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line."* And: *"the QA step is the one people don't think about when they're mad at scheduling; half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it."*
+
+**A10 — Stage for shipping, and ship**
+- *Needs*: QA release. *Produces*: the order off the dock. *Timing constraint*: C4 — *"that's when the truck appointment matters."*
+- *Duration*: ⚠ not obtained.
+
+**A11 — Tech pulled away mid-changeover** *(event, not step)*
+- Named by her as the mechanism behind the worse tail of A4 (*"the tech's tied up finishing something on another line"*) and A5 (*"if the tech gets pulled away partway through"*).
+- *Rate*: ⚠ not obtained separately; currently only implicit inside the one-in-ten tails of A4 and A5. Per P01 this should be its own rate and duration.
+
+**A12 — Washdown fails the visual check, part redone** *(event, not step)*
+- Named as the mechanism behind A6's 4 h tail.
+- *Rate*: ⚠ not obtained separately. Ledger #7 records the simplification.
+
+**A13 — "The mill motor issue"** *(event, not step — named in passing, nothing more)*
+- Mentioned only as an example of what a *structural* difference between lines would look like, in contrast to Line 1 merely being fussier. Recorded so it is not lost; **rate ⚠, duration ⚠, consequence ⚠**. This is the whole of the breakdown/interruption stratum, which was never swept.
+
+---
+
+### 1.5 Ordering / flow
+
+**F1 — The main arc, desk to dock** *(spelled out — her six steps, verbatim in structure)*
+1. Lands in the demand book (ERP weekly pull; SKU, quantity, due date, Meridian flag).
+2. Allocated to a line (*"Meridian whites always go to Line 2"*).
+3. Sits in the queue behind whatever's running — reorderable (A3/P4).
+4. Changeover if needed (F3 selects which), then it runs: mix, mill, tint-or-straight-through, fill, pack.
+5. QA hold.
+6. Released, staged for shipping, out against the truck appointment.
+
+**F2 — Order-to-batch split**
+- *Order* **(spelled out)**: an order becomes one batch by default; it may become two batches run at different times.
+- *How the branch is decided* **(spelled out)**: Marta's judgment, on either (a) a distributor ordering *"more than makes sense in a single run"*, or (b) needing to interleave something more urgent.
+- *Cost of a split*: ⚠ never asked (P03 unresolved) — extra changeovers and any extra loss are unknown.
+
+**F3 — Which changeover applies** *(spelled out)*
+Selected by the triple (family currently on the line, family of the next batch, line):
+- same family → **A4** quick rinse
+- white → tint → **A5**
+- tint → white → **A6** full washdown
+- into or out of specialty clear → **A7** (Line 1 only)
+
+---
+
+### 1.6 Policies
+
+**P1 — "Meridian whites always go to Line 2, that's just how it's done here"**
+- *As practiced* **(spelled out)**: fixed allocation, not a decision.
+- *What overrides it*: ⚠ never asked.
+- *Source-regime*: practiced; no prescribed form offered.
+
+**P2 — Meridian on-time is absolute**
+- *As practiced* **(spelled out)**: *"the rule is absolute — we don't even try to be clever about it."*
+- *What overrides it* **(spelled out)**: nothing. That is the content of the policy.
+- *Rationale*: fine, tracked on-time percentage, delisting threat carried out on a competitor.
+
+**P3 — Who gets the tech when two lines want one** *(the model's richest policy, and the least documented)*
+- **Prescribed form: none exists.** *"There's no posted rule at all."*
+- **As practiced** *(spelled out)*: in the room it resolves as *"whoever's louder at the huddle, or whoever's about to actually run dry."* Pressed for the underlying logic: *"it's mostly gut triage: whichever line has the more time-sensitive order behind it wins, and if that's a tie, whichever changeover is faster wins so you get a line moving sooner."*
+- **Borderline case on record** *(the practiced rule demonstrated, per P05)*: Line 1 and Line 3 both wanted a washdown the same morning. **Line 3 got the tech first** — *"not because it was more important, but because Line 3's changeover was the quick one and Line 1's was going to be the long tint-to-white slog anyway, so the thinking was 'knock out the fast one, get that line moving, then commit the tech to the long one.'"* Line 1 sat **clean-but-waiting for almost 40 minutes** past when it could have started.
+- **What overrides it** *(spelled out)*: the ops director. *"I've been overruled by the ops director once when he wanted his pet SKU out the door."*
+- *Rationale* **(spelled out)**: *"the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line"* — and this, not changeover variability, is *"the bit that actually causes grief at the huddle."*
+
+**P4 — Reorder the queue so a job isn't stuck behind a big changeover**
+- *As practiced* **(spelled out)**: Marta reorders *"a bit"* to avoid a job landing behind an expensive changeover.
+- *What overrides it*: ⚠ never asked.
+
+**P5 — Hold the line for an anticipated same-family order** *(the decision under test)*
+- *As practiced, one instance* **(spelled out)**: on a heads-up that a same-family white was about to drop, let Line 2 sit idle for *"maybe an hour"* rather than wash down for the tint waiting behind, *"because doing them back to back would save us a full washdown."*
+- *Her own epistemic status*: *"I was guessing."* Her boss's challenge — *"are you sure that's worth it, or are you just guessing?"* — is the reason this model exists.
+- *Trigger condition and decision threshold*: ⚠ how strong a heads-up, and how long she'd hold, are not generalised beyond this instance. Depends on B2.
+
+**P6 — Batch-split discretion**
+- *As practiced* **(spelled out)**: *"I have the freedom to split if I need to."* Criteria as in F2.
+- *What overrides it*: ⚠ never asked.
+
+---
+
+### 1.7 Constraints
+
+**C1 — Line qualification**
+- *The limit* **(partially spelled out)**: Line 1 qualified for everything including specialty. Line 3 qualified product-by-product, *"can't run everything yet"*, currently *"mostly one or two SKUs"* — which ones ⚠. Line 2's qualification set ⚠ never stated.
+- *What happens when it's hit* **(spelled out)**: the batch cannot go on that line.
+
+**C2 — Two techs, three lines**
+- *The limit* **(spelled out)**: 2 techs on day shift for 3 lines.
+- *What happens when it's hit* **(spelled out)**: *"if Line 1 and Line 3 both want a washdown at the same time, one of them waits"* — clean-but-idle; 40 minutes in the case on record. Resolution by P3.
+
+**C3 — Tint → white requires a full washdown passing a visual check**
+- *The limit* **(spelled out)**: a white batch may not run on a line still carrying pigment.
+- *What happens when it's hit* **(spelled out)**: *"any pigment left behind ruins a white batch"*; a failed visual check means part of the washdown is redone (A12).
+
+**C4 — Meridian must leave our dock a day ahead of the appointment**
+- *The limit* **(spelled out)**: shipped in time to hit the dock appointment, which *"usually means it needs to leave our dock a day ahead for freight."*
+- *What happens when it's hit* **(spelled out)**: fine + on-time percentage damage + delisting exposure.
+
+**C5 — Every batch passes QA hold before release**
+- *The limit* **(spelled out)**: *"every batch does."*
+- *What happens when it's hit* **(spelled out)**: nothing ships unreleased; the batch waits in hold.
+
+**Unwritten constraints**: ⚠ the closing sweep — *"what would a newcomer get wrong in the first week?"*, *"which rule exists because something once went wrong?"* — was never run. The one item that surfaced unprompted is the changeover asymmetry: *"that one catches everybody, including people who've been on the floor a lot longer than me."*
+
+---
+
+### 1.8 Dynamics
+
+**None.** Nothing described evolves continuously while nothing discrete happens. The soak and rinse-cycle time inside A6 is dead time *within* an activity, not a state variable crossing a threshold, and I have deliberately not promoted it to one.
+
+---
+
+### 1.9 Data bindings *(named only; these project to nothing today)*
+
+| Feed | Would drive | Provenance |
+|---|---|---|
+| Changeover logs — tech start/finish per changeover | A4–A7 durations and crew hands-on fractions; retires ledger #1 and #4 | **Qualified**: *"I've never audited that field myself, I mostly just glance at duration."* Coverage unknown, possibly patchy — Marta named **Line 1 and Line 3** as where to look. She will flag it to the two techs. |
+| ERP demand book | B1 arrival pattern, B2 | not discussed |
+| QA release timestamps | A9 duration and lab queueing | not discussed |
+| Meridian on-time percentage | O2 | tracked by Meridian, visible to commercial |
+
+**Finding, recorded in its own right**: patchy changeover logging concentrated on Lines 1 and 3 is evidence about the plant, not merely an obstacle to the model. Her words: *"if it's patchy for Line 1 and Line 3 specifically, that itself would be useful for you to know, not just an inconvenience."*
+
+---
+
+### 1.10 Validation criteria
+
+⚠ **None obtained.** How Marta would know the model is right was never asked. Queued.
+
+---
+
+## 2. Assumption ledger
+
+Everything here is mine. None of it is hers.
+
+| # | Assumption | Why it was made | How to check it |
+|---|---|---|---|
+| **1** | Line 1 changeover durations = Line 2 × **1.2**, all four types | She could not give Line 1 minutes: *"I couldn't swear the minutes are identical… Line 1's older, the crew sometimes says it's fussier."* I proposed 20%; she said *"20% sounds about right, not double."* **The 1.2 factor originated with me** — her assent is not authorship. | Changeover logs, Line 1 vs Line 2, same family-pair. **Blocked by the unaudited start/finish field, and Line 1 is one of the two lines she expects to be patchy.** |
+| **2** | Line 3 changeover durations = Line 2, unscaled | *"Line 3 I genuinely don't have a good feel for… you're stuck assuming it's like Line 1 or Line 2 until we've got more history."* She offered the disjunction; **choosing Line 2 was mine.** | As #1, once Line 3 has run more products. Also expected patchy. |
+| **3** | "An hour and a bit" (A5 worse) = **70 min**; "4, maybe a bit more" (A6 worse) = **4.5 h** | Numeric readings so the spreads are usable. | One question to Marta: confirm or correct both. |
+| **4** | Crew hands-on fractions: A4 = **1.0**; A5 = **0.8**; A6 = **0.5**; A7 = **0.8** | A4's 1.0 is hers, stated. A6's 0.5 is close to *"maybe half of that"* — but note her own hedge, *"I'd guess."* **The two 0.8s from *"most of it"* / *"most of that"* are mine.** | Changeover logs vs. tech time records, or ask the two techs directly. Same blocker as #1. |
+| **5** | No changeover happens outside day shift | She said *"two techs on **day shift** covering all three lines."* Whether any other coverage exists was never asked. | One question to Marta. |
+| **6** | A changeover requires exactly **one** tech, not two | She spoke of *"the tech"* singular throughout, including for the 3-hour washdown. | One question to Marta or the techs. |
+| **7** | A12 (failed visual check, part redone) is folded **inside** A6's 4 h tail rather than modelled as a separate event with its own rate and duration | She described it as *the cause of* the tail, not as an independent event. Keeps the spread self-contained. Contrary to P01, which would separate rate from duration. | Ask how often the visual check fails first time; if it's common, split it out. |
+| **8** | The two changeover techs are **interchangeable** | She drew no distinction between them. | One question to Marta. |
+
+**Second-order note on #1 and #4**: their stated check depends on a feed of unverified coverage, concentrated exactly where the assumptions bite. If the field proves patchy on Line 1, the honest move is to **widen** these assumptions, not to fill them in.
+
+---
+
+## 3. What the model leaves out, what is unknown, and why
+
+### 3.1 Deliberately left out
+
+- **Queues, buffers and waiting states are not nodes.** The wait behind a running batch, the wait for a tech, the wait in QA hold — none is elicited as a thing in itself; each is implied by the activities either side and emerges in projection. The 40-minute clean-but-waiting on Line 1 is an *output* the model should reproduce, not an input to it.
+- **The commercial layer.** The fine, the on-time percentage mechanics, the delisting threshold. C4 and O2 encode the hard deadline; the money behind it is outside the scheduler's sight and she named commercial as the owner.
+- **Individual tech identity.** Ledger #8 — she drew no distinction.
+- **Scenarios.** Not elicited; they assemble from B1–B5 at simulation time.
+
+### 3.2 What the formalism cannot carry, kept in words so it is not lost
+
+- **O4, "how ugly the sheet looks."** A criterion she genuinely uses and explicitly refuses to number. It could be approximated as line idle hours — but that approximation would be mine, and I have not made it.
+- **The O2/O3/lateness trade-off weight.** Deliberately unquantified with the source named (commercial). Consequence: the model can report changeover hours, Meridian lateness and distributor lateness **separately**, but cannot rank two schedules that trade one against another. That is a real limit on answering O1, since O1's "costs less" implicitly spans them.
+- **The decay of softness.** *"The same distributor slipping late for the third week running"* turning into a discount demand is a memory effect across weeks on a customer. Stated as a rule, unquantified, and not represented.
+- **The huddle.** *"Whoever's louder at the huddle"* and the ops director's pet-SKU override are the real P3 in the room. The triage logic — time-sensitivity first, faster-changeover as tiebreak — is compilable; loudness and the override are not. **Any run of this model will be quieter and more rational than the plant.** That is worth remembering when a result looks tidy.
+
+### 3.3 Open slots, in the order I would close them
+
+1. **A8 run duration** — nothing at all, per family and per line, as a spread. O1 is a question about a *week*; run time is most of a week. **Nothing about O1 is answerable until this exists.**
+2. **B2, the drop-in and the heads-up** — who tells her, how far ahead, how often it proves right. P5 is the decision under test and its trigger is currently a single anecdote.
+3. **A9 QA hold** — *"a few hours"* is honest at the wrong precision; and whether the lab queues like the techs do. By her own account this is where lateness actually comes from, so it bears directly on O2.
+4. **B1** — orders per weekly pull and the within-week shape.
+5. **E2 / F2** — typical run sizes, the "reasonable run size" threshold, and what a split costs in extra changeovers (P03).
+6. **C1 / B5** — which SKUs Line 3 is qualified for; whether Line 2 has restrictions.
+7. **Breakdowns and interruptions** — the whole stratum. A13 "the mill motor issue" is a name with no rate, duration or consequence. A11 and A12 need rate separated from duration (P01).
+8. **The unwritten-constraint sweep** and **validation criteria** — neither was run.
+
+### 3.4 Status against the completion criteria
+
+- **Static floor: satisfied** — 4 objectives, 5 entity types, 13 activities, 3 ordering/flow nodes.
+- **O2, O3: dependency slices substantially satisfied**, excepting A8 and A9 durations.
+- **O1: dependency slice incomplete.** A8 has no duration at all; B2 has no arrival pattern. O1 is currently **answerable only for Line 2**, and only once run times exist. Ledger #1–#4 are the first assumptions to attack if any result involving Line 1 or Line 3 ever looks decisive.
+- **O4: recorded, unsupported for quantitative use** by its own author's description.
+
+### 3.5 What I do not claim
+
+I have elicited a model, not built a net. The SDCPN scaffold, the code-obligation sidecar and the typed loss report are derived from this model by the tooling's projection — I have not written them and I am not claiming this loads, compiles, or runs. The A8 hole alone would stop it.
+
+---
+
+*Elicited from Marta, master scheduler, in a single session ended at her stop. Three questions queued for resumption: run duration for a plain white on Line 2 (typical / one-in-ten worse / one-in-ten better); the heads-up mechanism behind B2; QA hold as a spread, and whether the lab queues.*
+
+---
+
+**Expert (Marta)**:
+
+I really do have to stop here. Please produce the model now with everything you have.
+
+---
+
+**Interviewer**:
+
+# Coatings Plant Scheduling Model — final deliverable
+
+**Elicited from:** Marta, master scheduler
+**Job:** construct (no prior model existed)
+**Ended:** at the expert's stop. No new topics opened after it.
+**Status:** static floor satisfied; O2 and O3 near-complete; **O1's dependency slice incomplete** (see §4).
+**Convention:** every value is in Marta's vocabulary, with the precision actually obtained. `⚠` marks a slot the method demands and the interview did not get. Quoted text is hers.
+
+---
+
+## 1. The model
+
+### 1.1 Objectives
+
+**O1 — "Hold the line versus wash it down now, which one actually costs less over the week"**
+- *Question* **(spelled out)** — whether letting Line 2 sit idle about an hour, on a heads-up that another same-family white order is about to drop from a distributor, beats washing down now for the tint waiting behind. From a real Thursday two weeks before the interview. Her verdict on her own method: *"I was guessing."*
+- *Depends on* — E1, E2, E3, E4, B1, B2, A4, A5, A6, A8, A9, F1, F2, F3, P3, P4, P5, C1, C2, C3.
+- *"Better"* **(named, not quantified)** — changeover hours over the week, subject to O2 holding absolutely. ⚠ no weight against lateness.
+- *Source-regime* — practiced.
+
+**O2 — "Whether Meridian shipped on time, full stop, that's non-negotiable"**
+- *Question* **(spelled out)** — does every Meridian order leave the dock in time for its appointment.
+- *"On time"* **(spelled out)** — a ship date on the order with a delivery window, resolving to a specific dock appointment at Meridian's end; in practice must leave our dock **one day ahead** for freight. *"Not just 'shipped this week.'"*
+- *Consequence of a miss* **(spelled out; unquantified ⚠)** — a fine, *"I don't see the number, that's commercial's problem, but I hear about it"*; and worse, a tracked on-time percentage with a delisting threat — *"that's happened to a competitor of ours, so it's not an empty threat, and it's why the rule is absolute."*
+- *Depends on* — A8, A9, A10, B3, C4, C5, P1, P2.
+
+**O3 — Changeover hours**
+- *Question* **(spelled out)** — crew-hours spent washing down instead of filling: *"every hour the crew spends washing down is an hour not filling anything."*
+- *Depends on* — A4, A5, A6, A7, E4, C2, P3.
+- *"Better"* **(named)** — fewer. Direction only; no target. ⚠
+
+**O4 — "How ugly the sheet looks"**
+- *Question* **(spelled out)** — *"are there gaps where a line's sitting idle for no good reason."*
+- *"Better"* **(her words; explicitly not a number)** — *"that last one's not a number, it's more a gut check, but it's real."*
+- *Depends on* — E3, C2, P3, P4, A4–A7. IR-only; see §3.
+
+**Trade-off among O2 / O3 / non-Meridian lateness** **(spelled out as a rule; deliberately unquantified ⚠)** — four changeover hours against one distributor order two days late: *"honestly, yes, I'd take that trade most of the time"*, a slip being *"an annoyed phone call from our sales rep, not a fine."* But *"'most of the time' is doing a lot of work in that sentence"* — the same distributor slipping three weeks running *"start[s] asking for a discount."* Soft, not infinitely soft, decaying with repetition on one customer. **Deposit:** *"that's genuinely a 'sit down with commercial' conversation, nobody's ever made me quantify it."*
+
+---
+
+### 1.2 Entity types
+
+**E1 — Order (in the demand book)**
+- *Distinctions* **(spelled out)** — Meridian vs non-Meridian (flagged on the order; it *"jumps to the top of my attention"*); family, which drives allocation and changeover.
+- *State riding along* **(spelled out)** — SKU, quantity, due date + delivery window, Meridian flag, family: **base white / tinted colour / specialty clear**. *"That's not my judgment, that's how the SKU's classified in the system, it drives what changeover you need going in and out."*
+- *Population* — ⚠ not obtained.
+
+**E2 — Batch**
+- *Distinctions* **(spelled out)** — inherits its order's family.
+- *Relation to E1* **(spelled out)** — *"mostly the order is the batch, if it fits a reasonable run size"*; split into two batches at different times when a distributor orders *"more than makes sense in a single run"* or to interleave something urgent. *"Not a strict one-to-one — I have the freedom to split if I need to."*
+- *Population* — ⚠ run sizes, split cost not obtained.
+
+**E3 — Line** *(contended resource)*
+- *Distinctions* **(spelled out)** — **Line 1**: *"the old workhorse — slower but it's qualified for everything, including specialty"*; crew say it's *"fussier to get properly clean."* **Line 2**: *"the fast one, that's your big-volume runner."* **Line 3**: *"the newest and quickest, but it's still being qualified product by product, so it can't run everything yet"* — so far *"mostly one or two SKUs."*
+- *State riding along* **(spelled out)** — the family the line is currently dirty with (selects the changeover, F3); its qualification set.
+- *How many* **(number)** — 3.
+
+**E4 — Changeover tech** *(contended resource)*
+- *Distinctions* **(named)** — none drawn; treated as interchangeable (ledger #8).
+- *State riding along* **(spelled out)** — which line they're committed to; can be *"pulled away partway through"*, and on long soaks *"might duck off to start something on another line."*
+- *How many* **(number)** — 2 on day shift for all three lines. *"That's it. No dedicated tech per line."*
+
+**E5 — QA lab**
+- ⚠ nothing obtained but its existence, that every batch passes through, and that it *"gets backed up on a Friday afternoon."* Whether it queues like the techs is open — and load-bearing for O2 by her own diagnosis: *"half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it."*
+
+---
+
+### 1.3 Boundary conditions
+
+**B1 — ERP weekly pull** — *starting state* **(spelled out)**: orders come from ERP on the weekly pull with SKU, quantity, due date, Meridian flag. *Arrival pattern* — ⚠ **not obtained** (demanded: spread).
+
+**B2 — Mid-week drop-in order and the heads-up before it** — ⚠ **not obtained** (demanded: spread). Only the anecdote: *"I had a heads-up another same-family white order was about to drop in from a distributor."* Who, how far ahead, how often right: all unknown. **This is the trigger O1 hangs on.**
+
+**B3 — Meridian dock appointment** — *pattern* **(spelled out, qualitative)**: ship date + delivery window on the order, resolving to a specific appointment their end. Lead-time distribution ⚠.
+
+**B4 — Tech availability** — **partially spelled out**: two techs, **day shift**. Coverage outside day shift ⚠ (ledger #5).
+
+**B5 — Line 3 qualification set** — ⚠ *"mostly one or two SKUs"*; which ones, unknown.
+
+---
+
+### 1.4 Activities
+
+**A1 — Lands in the demand book.** Needs the weekly pull; produces an order in the book, flagged or not; unattended (ERP); instantaneous. **spelled out**
+
+**A2 — Allocate to a line.** Needs an order; produces an assignment; performed by Marta; not a schedule constraint — for Meridian whites *"that's not really a decision."* Rule: P1. **spelled out**
+
+**A3 — Reorder the queue.** Needs an order behind others; produces a changed sequence; performed by Marta. *"Sometimes I'll reorder things a bit so it doesn't get stuck behind a big changeover."* Rule: P4. **spelled out**
+
+**A4 — Quick rinse, same family (white→white), Line 2**
+- *Needs* — previous batch off, a tech free, next SKU same family. *Produces* — *"the fill head's actually running clean product again."*
+- *Performed by* **(named)** — one tech.
+- *Duration, line down* **(spread)** — **typical 25 min**; **worse 45 min**, *"usually because the tech's tied up finishing something on another line first and there's a wait before they even start on Line 2"*; **better 15 min**, *"if the tech's standing right there and it's a genuinely easy one."*
+- *Crew hands-on* **(spelled out)** — equals line-down: *"the tech's on it start to finish, no gap between 'crew starts' and 'line stops.'"*
+- *Mode-change loss* — this activity **is** the loss.
+- *Varies by type* **(named)** — yes, by family-pair (F3). By line: ⚠ ledger #1, #2.
+
+**A5 — White → tint, Line 2** — *"the easier direction"*
+- *Performed by* **(named)** — one tech.
+- *Duration, line down* **(spread)** — **typical 45 min**; **worse "an hour and a bit"** (ledger #3), *"if the tech gets pulled away partway through"*; **better ~30 min**, *"if everything's staged."*
+- *Crew hands-on* **(spelled out, qualitative)** — *"hands-on for most of it — this one doesn't have much soak-and-wait, it's mostly just doing the work."* Fraction: ledger #4.
+
+**A6 — Tint → white, Line 2, full washdown** — *"the ugly one"*
+- *Needs* — as A5 plus a **passing visual check** before release to production.
+- *Duration, line down* **(spread)** — **typical ~3 h**; **worse 4 h "maybe a bit more"** (ledger #3), *"if it doesn't pass the visual check first time and they have to redo part of it"*; **better ~2 h**, *"a clean fast one… if the crew's good and nothing complicates it."*
+- *Crew hands-on* **(spelled out, qualitative; her own hedge preserved)** — *"less than the 3 hours suggests — there's real soak and rinse-cycle time where the tech's not standing there… I'd guess they're actually working maybe half of that."* Fraction: ledger #4.
+- *Rationale* **(spelled out)** — *"any pigment left behind ruins a white batch, so it's a full washdown."*
+- **Asymmetry is load-bearing** — *"It absolutely depends on direction — that's the thing people forget… it is absolutely not symmetric, and it trips people up if they assume it is."*
+
+**A7 — Into / out of specialty clear, Line 1**
+- *Duration, line down* **(spread)** — **typical 2 h**, *"roughly the same both directions, unlike white/tint"*; **worse 3 h**, *"if it's coming out of clear and they're being extra careful about residue, since clear can be sneaky — you don't always see it the way you'd see pigment"*; **better 1.5 h**, *"a quick swap and the line was already fairly clean."*
+- *Crew hands-on* **(spelled out, qualitative)** — *"most of that — specialty doesn't have the long soak cycles… it's more just physically thorough cleaning because the product's thick and clingy."* Fraction: ledger #4.
+
+**A8 — Run the batch** — mix, mill, tint (or *"straight through if it's a plain white"*), fill, pack.
+- *Needs* **(spelled out)** — clean line in the right family state; batch released to run. *Produces* **(spelled out)** — filled and packed batch.
+- *Performed by* — ⚠ line operators never elicited as a resource.
+- *Duration* — ⚠ **nothing obtained** (demanded: spread, per family and per line).
+- *Varies by type* — partially: *"for a white that's usually the more straightforward path"*, but no durations attach.
+- **The largest hole in the model.** O1 is a question about a week; run time is most of a week.
+
+**A9 — QA hold and release** — *"every batch does."*
+- *Performed by* **(named)** — the lab (E5).
+- *Duration* — *"typically a few hours before it's released"*: an honest **number at the wrong precision**; demanded as a **spread**. ⚠
+- *Failure path* — ⚠ never asked.
+- *Pathology* **(spelled out qualitatively; rate ⚠)** — *"if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line"*; *"the QA step is the one people don't think about when they're mad at scheduling."*
+
+**A10 — Stage for shipping and ship.** Needs QA release; produces the order off the dock; *"that's when the truck appointment matters."* Constraint C4. Duration ⚠.
+
+**A11 — Tech pulled away mid-changeover** *(event, not step)* — named as the mechanism behind A4's and A5's worse tails. *Rate* ⚠ not obtained separately; currently only implicit in those tails (P01 unsatisfied).
+
+**A12 — Washdown fails the visual check, part redone** *(event, not step)* — named as the mechanism behind A6's 4 h tail. *Rate* ⚠ (ledger #7).
+
+**A13 — "The mill motor issue"** *(event, named in passing only)* — offered as an example of what a *structural* line difference would look like, in contrast to Line 1 merely being fussier. Rate ⚠, duration ⚠, consequence ⚠. This is the entirety of the breakdown stratum, which was never swept.
+
+---
+
+### 1.5 Ordering / flow
+
+**F1 — The main arc, desk to dock** **(spelled out — her six steps)**
+1. Lands in the demand book (ERP weekly pull).
+2. Allocated to a line (*"Meridian whites always go to Line 2"*).
+3. Sits in the queue behind whatever's running — reorderable (A3/P4).
+4. Changeover if needed (F3), then runs: mix, mill, tint-or-straight-through, fill, pack.
+5. QA hold.
+6. Released, staged, out against the truck appointment.
+
+**F2 — Order-to-batch split** — *order* **(spelled out)**: one batch by default, possibly two run at different times. *Branch decided by* **(spelled out)**: Marta, on run size or urgency-interleaving. *Cost of a split* ⚠ (P03 unresolved).
+
+**F3 — Which changeover applies** **(spelled out)** — by (family on the line, family of next batch, line): same family → **A4**; white→tint → **A5**; tint→white → **A6**; into/out of specialty → **A7** (Line 1 only).
+
+---
+
+### 1.6 Policies
+
+**P1 — "Meridian whites always go to Line 2, that's just how it's done here."** *Practiced* **(spelled out)**; a fixed allocation, not a decision. Overrides ⚠ never asked.
+
+**P2 — Meridian on-time is absolute.** *Practiced* **(spelled out)** — *"we don't even try to be clever about it."* Overrides **(spelled out)**: none — that is the policy's content. Rationale: fine, on-time percentage, delisting precedent.
+
+**P3 — Who gets the tech when two lines want one**
+- *Prescribed form:* **none exists** — *"there's no posted rule at all."*
+- *As practiced* **(spelled out)** — in the room: *"whoever's louder at the huddle, or whoever's about to actually run dry."* The underlying logic: *"it's mostly gut triage: whichever line has the more time-sensitive order behind it wins, and if that's a tie, whichever changeover is faster wins so you get a line moving sooner."*
+- *Borderline case on record* — Line 1 and Line 3 both wanted a washdown one morning. **Line 3 got the tech**, *"not because it was more important, but because Line 3's changeover was the quick one and Line 1's was going to be the long tint-to-white slog anyway, so the thinking was 'knock out the fast one, get that line moving, then commit the tech to the long one.'"* Line 1 sat **clean-but-waiting almost 40 minutes**.
+- *What overrides it* **(spelled out)** — the ops director: *"I've been overruled by the ops director once when he wanted his pet SKU out the door."*
+- *Rationale* **(spelled out)** — *"the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line"* — *"the bit that actually causes grief at the huddle."*
+
+**P4 — Reorder so a job isn't stuck behind a big changeover.** *Practiced* **(spelled out)**. Overrides ⚠.
+
+**P5 — Hold the line for an anticipated same-family order** *(the decision under test)*. *Practiced, one instance* **(spelled out)** — hold Line 2 idle *"maybe an hour"* rather than wash down for the waiting tint, *"because doing them back to back would save us a full washdown."* Trigger strength and holding threshold ⚠ (depends on B2).
+
+**P6 — Batch-split discretion.** *Practiced* **(spelled out)** — *"I have the freedom to split if I need to."* Overrides ⚠.
+
+---
+
+### 1.7 Constraints
+
+**C1 — Line qualification.** *Limit* **(partially spelled out)** — Line 1 everything incl. specialty; Line 3 product-by-product, *"can't run everything yet"* (which SKUs ⚠); Line 2's set ⚠. *When hit* **(spelled out)** — the batch cannot go on that line.
+
+**C2 — Two techs, three lines.** *Limit* **(spelled out)**. *When hit* **(spelled out)** — *"if Line 1 and Line 3 both want a washdown at the same time, one of them waits"* — clean-but-idle, 40 min in the recorded case; resolved by P3.
+
+**C3 — Tint→white needs a full washdown passing a visual check.** *When hit* **(spelled out)** — *"any pigment left behind ruins a white batch"*; a failed check means part is redone (A12).
+
+**C4 — Meridian must leave our dock a day ahead of the appointment.** *When hit* **(spelled out)** — fine, on-time percentage damage, delisting exposure.
+
+**C5 — Every batch passes QA hold before release.** *When hit* **(spelled out)** — nothing ships unreleased; it waits in hold.
+
+**Unwritten constraints** — ⚠ the closing sweep was never run. The one that surfaced unprompted is the changeover asymmetry: *"that one catches everybody, including people who've been on the floor a lot longer than me."*
+
+---
+
+### 1.8 Dynamics
+
+**None.** Nothing described evolves continuously while nothing discrete happens. The soak and rinse-cycle time inside A6 is dead time *within* an activity, not a state variable crossing a threshold; I have deliberately not promoted it to one.
+
+---
+
+### 1.9 Data bindings *(named only — project to nothing today)*
+
+| Feed | Would drive | Provenance |
+|---|---|---|
+| Changeover logs (tech start/finish) | A4–A7 durations, crew hands-on fractions; retires ledger #1, #4 | **Qualified:** *"I've never audited that field myself, I mostly just glance at duration."* Coverage unknown, possibly patchy; **Line 1 and Line 3** named as where to look. Marta will flag it to the two techs. |
+| ERP demand book | B1, B2 | not discussed |
+| QA release timestamps | A9 duration, lab queueing | not discussed |
+| Meridian on-time percentage | O2 | tracked by Meridian; visible to commercial |
+
+**Finding in its own right:** patchy changeover logging concentrated on Lines 1 and 3 is evidence about the plant, not merely an obstacle — *"that itself would be useful for you to know, not just an inconvenience."*
+
+---
+
+### 1.10 Validation criteria
+
+⚠ **None obtained.** How Marta would know the model is right was never asked.
+
+---
+
+## 2. Assumption ledger
+
+Everything here is mine. None of it is hers.
+
+| # | Assumption | Why | How to check |
+|---|---|---|---|
+| **1** | Line 1 changeover durations = Line 2 × **1.2**, all types | She could not give Line 1 minutes — *"I couldn't swear the minutes are identical… the crew sometimes says it's fussier."* I proposed 20%; she replied *"20% sounds about right, not double."* **The factor originated with me**; her assent is not authorship. | Changeover logs, Line 1 vs Line 2, same family-pair. **Blocked by the unaudited start/finish field — and Line 1 is one of the two lines she expects to be patchy.** |
+| **2** | Line 3 changeover durations = Line 2, unscaled | *"Line 3 I genuinely don't have a good feel for… you're stuck assuming it's like Line 1 or Line 2."* She offered the disjunction; **picking Line 2 was mine.** | As #1, once Line 3 has run more products. Also expected patchy. |
+| **3** | "An hour and a bit" (A5 worse) = **70 min**; "4, maybe a bit more" (A6 worse) = **4.5 h** | Numeric readings so the spreads are usable. | One question to Marta: confirm or correct. |
+| **4** | Crew hands-on: A4 = **1.0**, A5 = **0.8**, A6 = **0.5**, A7 = **0.8** | A4's 1.0 is hers, stated. A6's 0.5 tracks *"maybe half of that"* — but note her hedge, *"I'd guess."* **The two 0.8s, from "most of it" / "most of that", are mine.** | Changeover logs vs tech time records, or ask the techs. Same blocker as #1. |
+| **5** | No changeover outside day shift | She said *"two techs on **day shift**"*; other coverage never asked. | One question to Marta. |
+| **6** | A changeover needs exactly **one** tech | She said *"the tech"*, singular, throughout — including the 3-hour washdown. | One question to Marta or the techs. |
+| **7** | A12 folded **inside** A6's 4 h tail rather than a separate event with its own rate | She described it as *the cause of* the tail. Keeps the spread self-contained; contrary to P01, which would separate rate from duration. | Ask how often the visual check fails first time; split it out if common. |
+| **8** | The two techs are **interchangeable** | She drew no distinction. | One question to Marta. |
+
+**Second-order note on #1 and #4:** their check depends on a feed of unverified coverage, concentrated exactly where the assumptions bite. If the field proves patchy on Line 1, the honest move is to **widen** them, not fill them in.
+
+---
+
+## 3. What the model leaves out, and why
+
+**Deliberately excluded**
+- **Queues, buffers, waiting states** are not nodes — the wait behind a running batch, the wait for a tech, the wait in QA hold. Each is implied by the activities either side and emerges in projection. Line 1's 40 minutes clean-but-waiting is an **output** the model should reproduce, not an input.
+- **The commercial layer** — fine amount, on-time percentage mechanics, delisting threshold. C4 and O2 carry the hard deadline; the money is outside the scheduler's sight and commercial owns it.
+- **Individual tech identity** (ledger #8). **Scenarios** — assembled from B1–B5 at simulation time, not elicited.
+
+**Real, and the formalism cannot carry it — kept in words**
+- **O4, "how ugly the sheet looks."** A criterion she genuinely uses and explicitly refuses to number. Approximating it as line idle hours would be my move; I have not made it.
+- **The O2 / O3 / lateness trade-off weight.** Unquantified with the source named. The model can report changeover hours, Meridian lateness and distributor lateness **separately**, but cannot rank two schedules that trade one against another — a real limit on O1, whose "costs less" implicitly spans them.
+- **The decay of softness** — the same distributor slipping *"the third week running"* turning into a discount demand: a memory effect across weeks on one customer, stated as a rule, unquantified, unrepresented.
+- **The huddle.** *"Whoever's louder"* and the ops director's pet-SKU override are the real P3 in the room. The triage logic is compilable; loudness and the override are not. **Any run of this model will be quieter and more rational than the plant.** Remember that when a result looks tidy.
+
+---
+
+## 4. What remains unknown, in the order I would close it
+
+1. **A8 run duration** — nothing at all, per family and per line, as a spread. **Nothing about O1 is answerable until this exists.**
+2. **B2, the drop-in and the heads-up** — who, how far ahead, how often right. P5 is the decision under test and its trigger is one anecdote.
+3. **A9 QA hold** — *"a few hours"* is honest at the wrong precision; and whether the lab queues like the techs. By her own account this is where lateness actually comes from, so it bears directly on O2.
+4. **B1** — orders per weekly pull and within-week shape.
+5. **E2 / F2** — run sizes, the "reasonable run size" threshold, and what a split costs in extra changeovers.
+6. **C1 / B5** — which SKUs Line 3 is qualified for; whether Line 2 has restrictions.
+7. **Breakdowns and interruptions** — the whole stratum. A13 is a name with no rate, duration or consequence; A11 and A12 need rate separated from duration.
+8. **Unwritten-constraint sweep** and **validation criteria** — neither was run.
+
+**Status against the completion criteria**
+- **Static floor: satisfied** — 4 objectives, 5 entity types, 13 activities, 3 ordering/flow nodes.
+- **O2, O3:** slices substantially satisfied except A8 and A9 durations.
+- **O1: slice incomplete.** A8 has no duration; B2 has no arrival pattern. O1 is currently **answerable only for Line 2**, and only once run times exist. Ledger #1–#4 are the first assumptions to attack if any Line 1 or Line 3 result ever looks decisive.
+- **O4:** recorded; unsupported for quantitative use, by its author's own description.
+
+**What I do not claim.** I have elicited a model, not built a net. The SDCPN scaffold, the code-obligation sidecar and the typed loss report are derived from this model by the tooling's projection — I have not written them, and I am not claiming this loads, compiles, or runs. The A8 hole alone would stop it.
+
+---
+
+*Session closed at the expert's stop. Three questions queued for resumption: run duration for a plain white on Line 2 (typical / one-in-ten worse / one-in-ten better); the heads-up mechanism behind B2; QA hold as a spread, and whether the lab queues.*
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4.raw.json b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4.raw.json
new file mode 100644
index 00000000000..2d0d904c889
--- /dev/null
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-4.raw.json
@@ -0,0 +1,825 @@
+{
+  "startedAt": "2026-08-25T15:14:42.641Z",
+  "condition": "4",
+  "stopReason": "delivered-after-forced-wrap",
+  "calls": [
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 10843,
+        "output_tokens": 255,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 235,
+        "output_tokens": 4,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 3646,
+        "output_tokens": 341,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 11376,
+        "output_tokens": 538,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 265,
+        "output_tokens": 16,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 4213,
+        "output_tokens": 429,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 12031,
+        "output_tokens": 280,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 195,
+        "output_tokens": 4,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 4789,
+        "output_tokens": 410,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 12588,
+        "output_tokens": 507,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 235,
+        "output_tokens": 16,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 5385,
+        "output_tokens": 380,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 13154,
+        "output_tokens": 405,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 224,
+        "output_tokens": 4,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 5939,
+        "output_tokens": 263,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 13591,
+        "output_tokens": 189,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 187,
+        "output_tokens": 4,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 6329,
+        "output_tokens": 400,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 14118,
+        "output_tokens": 224,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 200,
+        "output_tokens": 16,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 6878,
+        "output_tokens": 451,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 14718,
+        "output_tokens": 396,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 278,
+        "output_tokens": 16,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 7579,
+        "output_tokens": 246,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 15252,
+        "output_tokens": 938,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 402,
+        "output_tokens": 16,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 8279,
+        "output_tokens": 369,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 16037,
+        "output_tokens": 10357,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 6044,
+        "output_tokens": 16,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 16210,
+        "output_tokens": 62,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 23661,
+        "output_tokens": 289,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 285,
+        "output_tokens": 4,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 16520,
+        "output_tokens": 42,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 23951,
+        "output_tokens": 79,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 121,
+        "output_tokens": 4,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 16613,
+        "output_tokens": 67,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 24069,
+        "output_tokens": 343,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 318,
+        "output_tokens": 16,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 16994,
+        "output_tokens": 82,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 24465,
+        "output_tokens": 218,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 233,
+        "output_tokens": 4,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 17272,
+        "output_tokens": 118,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 24779,
+        "output_tokens": 452,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 359,
+        "output_tokens": 16,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 17762,
+        "output_tokens": 27,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 25178,
+        "output_tokens": 41,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 91,
+        "output_tokens": 4,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 17801,
+        "output_tokens": 10,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 25200,
+        "output_tokens": 32,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 88,
+        "output_tokens": 4,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 17817,
+        "output_tokens": 17,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 25223,
+        "output_tokens": 127,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 96,
+        "output_tokens": 4,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 17852,
+        "output_tokens": 21,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 25262,
+        "output_tokens": 37,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 90,
+        "output_tokens": 4,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "expert",
+      "model": "claude-sonnet-5",
+      "usage": {
+        "input_tokens": 17885,
+        "output_tokens": 6,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 25280,
+        "output_tokens": 1,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 25280,
+        "output_tokens": 25,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 87,
+        "output_tokens": 4,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 25310,
+        "output_tokens": 11567,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 9053,
+        "output_tokens": 16,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "interviewer",
+      "model": "claude-opus-5",
+      "usage": {
+        "input_tokens": 36786,
+        "output_tokens": 9586,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    },
+    {
+      "agent": "classifier",
+      "model": "claude-haiku-4-5-20251001",
+      "usage": {
+        "input_tokens": 7411,
+        "output_tokens": 4,
+        "cache_creation_input_tokens": 0,
+        "cache_read_input_tokens": 0
+      }
+    }
+  ],
+  "interviewerMessages": [
+    {
+      "role": "user",
+      "content": "I'm the master scheduler at a coatings plant. My boss wants a simulation model of how we\nschedule production, so we can test scheduling decisions before making them. We have tooling\nthat runs Petri-net-style process models, so the end product should be a model I can hand to\nthat — but I can't tell you much about the format, I'm not the modelling person.\n\nPlease interview me about how our operation works, and then produce the model."
+    },
+    {
+      "role": "assistant",
+      "content": "Good — that's enough for me to start. I'll ask you about your operation in your own words; the format side is my problem, not yours.\n\nBefore anything about how the plant is built, I want to know what the model has to be *for*. Two things to start:\n\n1. When your boss says \"test scheduling decisions before making them\" — what's a decision you'd actually want to test? Give me a real one you've argued about recently, not a general category.\n\n2. And when you compare two schedules today, what makes one better than the other in your eyes? I'm after the thing you'd actually point at — a number, a complaint you'd avoid, whatever it is."
+    },
+    {
+      "role": "user",
+      "content": "Okay, real one: two weeks ago I had a Meridian white order finishing on Line 2 Thursday afternoon, and then a batch of tint waiting behind it. My instinct was to let Line 2 sit idle for maybe an hour because I had a heads-up another same-family white order was about to drop in from a distributor, and doing them back to back would save us a full washdown. My boss's question was basically \"are you sure that's worth it, or are you just guessing?\" And honestly — I was guessing. That's the kind of thing I'd love to test: hold the line versus wash it down now, which one actually costs less over the week.\n\nAs for what makes one schedule better than another — first thing I look at is whether Meridian shipped on time, full stop, that's non-negotiable. After that it's changeover hours, because every hour the crew spends washing down is an hour not filling anything. And honestly I also just glance at how ugly the sheet looks — like, are there gaps where a line's sitting idle for no good reason. That last one's not a number, it's more a gut check, but it's real."
+    },
+    {
+      "role": "assistant",
+      "content": "That's a good, concrete decision — hold the line for a possible same-family order versus wash down now. I'll build the model so that's testable.\n\nTwo things about \"better\", then I'll get you to walk me through a job:\n\n1. Meridian on-time is non-negotiable — what does \"on time\" actually mean in practice? A ship date on the order, a truck appointment, a promised week? And what happens when one *does* go late — who feels it and how?\n\n2. Changeover hours versus a late non-Meridian order: if a schedule saved you, say, four changeover hours but made one distributor order two days late, would you take it? I'm trying to find out whether these trade against each other at all, or whether lateness for everyone else is just soft."
+    },
+    {
+      "role": "user",
+      "content": "Good questions, let me take them separately.\n\nOn \"on time\" for Meridian — it's a ship date they give us via the order, usually with a delivery window attached, like a specific dock appointment on their end. So it's not just \"shipped this week,\" it's \"shipped in time to hit that appointment,\" which usually means it needs to leave our dock a day ahead for freight. If we miss it, first thing is a fine — I don't see the number, that's commercial's problem, but I hear about it. Second thing, worse honestly, is they track our on-time percentage and if it drops too far they threaten to delist SKUs. That's happened to a competitor of ours, so it's not an empty threat, and it's why the rule is absolute — we don't even try to be clever about it.\n\nOn the trade-off — honestly, yes, I'd take that trade most of the time, four hours of changeover is real money and crew time, and a distributor slipping two days is usually just an annoyed phone call from our sales rep, not a fine. But \"most of the time\" is doing a lot of work in that sentence — if it's the same distributor slipping late for the third week running, that's different, they'll start asking for a discount. So it's soft, but it's not infinitely soft. I couldn't put a number on it though — that's genuinely a \"sit down with commercial\" conversation, nobody's ever made me quantify it."
+    },
+    {
+      "role": "assistant",
+      "content": "That's clear, and I'll record the trade-off as deliberately unquantified rather than invent a weight — I'll flag it as needing commercial, since you've told me exactly where the number would come from.\n\nNow let's get the structure. Take that Meridian white order from two weeks ago and walk me through it as a sequence — from the moment it lands on your desk to the moment it's off the dock. Keep it to the main steps, five or six; I'll dig into each one after."
+    },
+    {
+      "role": "user",
+      "content": "Sure, let me walk it through.\n\n1. **It lands in the demand book** — comes over from ERP on the weekly pull, SKU, quantity, due date, flagged Meridian so it jumps to the top of my attention.\n2. **I allocate it to Line 2** — that's not really a decision, Meridian whites always go to Line 2, that's just how it's done here.\n3. **It sits in the queue behind whatever's running** — depending what's ahead of it, sometimes I'll reorder things a bit so it doesn't get stuck behind a big changeover.\n4. **Changeover if needed, then it runs** — mix, mill, tint or straight through if it's a plain white, then fill and pack. For a white that's usually the more straightforward path.\n5. **It goes into QA hold** — every batch does, typically a few hours before it's released.\n6. **Once released, it's staged for shipping** — and that's when the truck appointment matters, because if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line.\n\nThat's the whole arc, really — desk to dock. The QA step is the one people don't think about when they're mad at scheduling; half the time a \"late\" order was actually sitting done in QA hold waiting for the lab to get to it."
+    },
+    {
+      "role": "assistant",
+      "content": "That QA point is exactly the kind of thing that gets left out of a first account — I'll come back to it properly.\n\nFirst let me pin down what you're actually scheduling. You said \"Meridian white order\", \"a batch of tint\", \"same-family white\". Three things:\n\n1. Is the thing you schedule the *order*, or does an order get broken into batches that could run at different times? What's the relationship?\n\n2. What are the families? You used \"same-family white\" as if it's a defined grouping — is that a formal thing on the SKU, or your judgment?\n\n3. And how many lines are there, besides Line 2?"
+    },
+    {
+      "role": "user",
+      "content": "1. Mostly the order *is* the batch, if it fits a reasonable run size — a lot of our orders are big enough that we just run the whole thing as one batch. But sometimes I'll split one: if a distributor orders more than makes sense in a single run, or if I need to interleave it with something more urgent, I'll chop it into two batches and run them at different times. So it's order-to-batch most of the time, but not a strict one-to-one — I have the freedom to split if I need to.\n\n2. The families are real, they're on the SKU — every product's either a base white, a tinted colour, or a specialty clear. That's not my judgment, that's how the SKU's classified in the system, it drives what changeover you need going in and out. \"Same-family\" just means two SKUs both being whites, or both being tints, so the changeover between them is the cheap quick-rinse kind instead of the expensive family-switch kind.\n\n3. Three lines total. Line 1's the old workhorse — slower but it's qualified for everything, including specialty. Line 2's the fast one, that's your big-volume runner. Line 3's the newest and quickest, but it's still being qualified product by product, so it can't run everything yet."
+    },
+    {
+      "role": "assistant",
+      "content": "Changeover is at the heart of the decision you want to test, so let's do it properly.\n\nYou've named two kinds: the quick rinse between same-family SKUs, and the full washdown on a family switch. For the **quick rinse between two whites on Line 2** — the exact case from two weeks ago:\n\n1. Typically, how long does it take, start to finish, before the next batch is filling?\n2. One time in ten it goes worse than — what?\n3. And one time in ten it's better than — what?\n\nGive me the crew time too if it differs from line downtime."
+    },
+    {
+      "role": "user",
+      "content": "For a straight white-to-white rinse on Line 2:\n\n1. Typically? Call it 25 minutes, start to finish, before the fill head's actually running clean product again.\n2. Worse case — one time in ten it drags to maybe 45 minutes, usually because the tech's tied up finishing something on another line first and there's a wait before they even start on Line 2.\n3. Better case — one time in ten, if the tech's standing right there and it's a genuinely easy one, 15 minutes and you're rolling again.\n\nCrew time and line downtime are basically the same thing here — it's quick enough that the tech's on it start to finish, no gap between \"crew starts\" and \"line stops.\" That's different from the big washdowns, where the line's down way longer than the crew's actually hands-on, because there's soak time and QA checks in between."
+    },
+    {
+      "role": "assistant",
+      "content": "That distinction — line down longer than crew hands-on — matters, so let's get the washdown with both.\n\nFor a **family switch on Line 2**, say white to tint: typically how long is the line down, one time in ten worse than, one time in ten better than? And roughly how much of that is the tech actually hands-on?\n\nAlso: does it depend on direction — is tint-to-white the same as white-to-tint?"
+    },
+    {
+      "role": "user",
+      "content": "It absolutely depends on direction — that's the thing people forget.\n\n**White to tint**, the easier direction: line's down typically about 45 minutes. Worse case, maybe an hour and a bit if the tech gets pulled away partway through. Better case, if everything's staged, maybe half an hour. Of that, the tech's hands-on for most of it — this one doesn't have much soak-and-wait, it's mostly just doing the work.\n\n**Tint to white** is the ugly one, because any pigment left behind ruins a white batch, so it's a full washdown. Typically about 3 hours, line down the whole time. Worse case — if it doesn't pass the visual check first time and they have to redo part of it — could stretch to 4, maybe a bit more. Better case, a clean fast one, maybe 2 hours if the crew's good and nothing complicates it. Hands-on time for the crew is actually less than the 3 hours suggests — there's real soak and rinse-cycle time where the tech's not standing there, they might duck off to start something on another line. I'd guess they're actually working maybe half of that, the rest is the line just being down waiting on the process.\n\nSo no, it is absolutely not symmetric, and it trips people up if they assume it is."
+    },
+    {
+      "role": "assistant",
+      "content": "Good — asymmetric, and I've got both directions.\n\nTwo things to close out changeover:\n\n1. Specialty clear is the third family — what does going into and out of clear cost, on Line 1 since that's the one qualified for it? Same shape of answer: typical, one-in-ten worse, one-in-ten better, either direction if they differ.\n\n2. Do the white/tint numbers you just gave me hold on Line 1 and Line 3, or are they line-specific?"
+    },
+    {
+      "role": "user",
+      "content": "1. Specialty is roughly the same both directions, unlike white/tint — call it 2 hours typical, either going in or coming out. Worse case, maybe 3 hours if it's coming out of clear and they're being extra careful about residue, since clear can be sneaky — you don't always see it the way you'd see pigment. Better case, maybe an hour and a half if it's a quick swap and the line was already fairly clean. Hands-on for the crew is most of that — specialty doesn't have the long soak cycles the tint-to-white washdown has, it's more just physically thorough cleaning because the product's thick and clingy.\n\n2. Honestly, I've mostly been quoting you Line 2 numbers because that's where the argument happened. I *think* the same rough shape holds on Line 1 — quick rinse cheap, tint-to-white expensive and slow, white-to-tint quicker — but I couldn't swear the minutes are identical. Line 1's older, the crew sometimes says it's fussier to get properly clean. Line 3 I genuinely don't have a good feel for, because it hasn't run enough different products yet to have built up war stories — it's still mostly running whatever it's been qualified for, which so far is mostly one or two SKUs. So if you need Line 3 numbers, that might be one where you're stuck assuming it's like Line 1 or Line 2 until we've got more history."
+    },
+    {
+      "role": "assistant",
+      "content": "That's the right answer — I'd rather have \"I don't know\" than invented minutes. Here's what I'd assume unless you tell me otherwise, and I'll mark it as mine, not yours:\n\n- **Line 1**: same shape as Line 2, with all changeover durations scaled up — say 20% longer — on the strength of the crew's \"fussier to get properly clean\".\n- **Line 3**: same as Line 2 until history exists.\n\nBoth would be checked against the changeover logs, if the techs record start and finish. Does 20% sound like the right order of magnitude for Line 1, or is it more like double?\n\nSeparately — you just said something important in passing. The tech \"gets pulled away partway through\", \"might duck off to start something on another line\". How many changeover techs are there across the three lines?"
+    },
+    {
+      "role": "user",
+      "content": "20% sounds about right, not double — it's more \"takes a bit longer to satisfy the visual check\" than \"fundamentally slower.\" Double would be if we were talking about the mill motor issue or something structurally different. So yeah, 20% longer on Line 1 feels like the right order of magnitude, not a multiplier like 2x.\n\nOn the crew — there's two techs on day shift covering all three lines between them. That's it. No dedicated tech per line. So if Line 1 and Line 3 both want a washdown at the same time, one of them waits, and that's the bit that actually causes grief at the huddle — it's not that the changeover itself is unpredictable, it's that the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line.\n\n(Sorry — I've just seen the time, I have the floor huddle in ten minutes. How much more do you need?)"
+    },
+    {
+      "role": "assistant",
+      "content": "Ten minutes is enough for one thing, so let me tell you where we are and then ask the one that matters most.\n\n**What I have:** the two objectives, the six-step arc, three lines, three families, all the changeover numbers for Line 2 with spreads, the asymmetry, the two techs as a shared resource.\n\n**What's still missing** — roughly six or seven things, and two of them are load-bearing for the exact decision you want to test:\n\n- how long a batch actually *runs* (I have changeovers but no run times at all)\n- how the \"heads-up another order was about to drop\" actually reaches you — that's the trigger your whole hold-the-line decision hangs on\n- QA hold as a spread, and whether the lab is a shared resource like the techs\n- the order arrival pattern off the ERP weekly pull\n- run sizes and what splitting a batch costs\n- which SKUs Line 3 is actually qualified for\n- what breaks, and how often\n\nNone of that needs to happen now. My question for the remaining minutes, because it's the one I can't guess and it's the one that made you say \"grief at the huddle\":\n\n**When both lines want a washdown at once and one tech has to pick — what actually decides it?** Not the rule as posted. Think of the last time it happened: which line got the tech, and what was the reason?"
+    },
+    {
+      "role": "user",
+      "content": "Honestly, there's no posted rule at all — it's whoever's louder at the huddle, or whoever's about to actually run dry.\n\nLast time it happened, off the top of my head — Line 1 and Line 3 both wanted a washdown same morning. Line 3 got the tech first, not because it was more important, but because Line 3's changeover was the quick one and Line 1's was going to be the long tint-to-white slog anyway, so the thinking was \"knock out the fast one, get that line moving, then commit the tech to the long one.\" Line 1 sat clean-but-waiting for almost 40 minutes past when it could've started.\n\nIf you push me on the actual logic — it's mostly gut triage: whichever line has the more time-sensitive order behind it wins, and if that's a tie, whichever changeover is faster wins so you get a line moving sooner. Nobody writes this down, it's literally whoever's standing at the huddle table making the case loudest. I've been overruled by the ops director once when he wanted his pet SKU out the door.\n\nI do need to run — but this was useful, come back to the QA and run-time stuff next time, those are real gaps."
+    },
+    {
+      "role": "assistant",
+      "content": "You've stopped, so I'm not opening anything new. Here's the model as it stands, read back item by item, with the gaps named honestly. The two things you flagged — QA and run times — are the first things on the list when you're back.\n\n---\n\n# 1. The model\n\nVocabulary is yours throughout. Each slot shows the value **and** the precision actually obtained. `⚠` marks a slot the model demands and does not yet have.\n\n## Objectives\n\n**O1 — \"Hold the line versus wash it down now, which one actually costs less over the week\"**\n- *The question, in your words:* whether letting Line 2 sit idle for ~1 hour waiting on an anticipated same-family white order is cheaper over a week than washing down to the tint batch now. — **spelled out**\n- *Depends on:* E1 Order, E2 Batch, E3 Line, E4 Changeover tech, B1 ERP weekly pull, B2 mid-week order drop-in, A4/A5/A6 changeovers, A8 run batch, A9 QA hold, F1 main arc, P1, P3, P5, C2, C4.\n- *What \"better\" means:* changeover hours consumed over the week, subject to O2 holding absolutely. — **named, not quantified against O4** ⚠\n\n**O2 — \"Meridian shipped on time, full stop, that's non-negotiable\"**\n- *The question:* does every Meridian order leave the dock in time for its dock appointment. — **spelled out**\n- *\"On time\" =* ship date + delivery window given on the order, resolving to a specific dock appointment their end; must leave our dock **one day ahead** for freight. — **spelled out**\n- *Consequence of a miss:* a fine (amount not visible to you — commercial's) and a hit to the tracked on-time percentage; if that drops far enough, threatened SKU delisting — a competitor has been delisted, so it's treated as real. — **spelled out, unquantified** ⚠\n- *Depends on:* A9 QA hold, A10 stage & ship, C4, P1, P2, B3.\n\n**O3 — Changeover hours**\n- *The question:* how many crew-hours go into washdowns rather than filling. \"Every hour the crew spends washing down is an hour not filling anything.\" — **spelled out**\n- *Depends on:* A4, A5, A6, A7, E4, C2, P3.\n\n**O4 — \"How ugly the sheet looks\" — idle gaps with no good reason**\n- *The question:* are lines sitting idle for no good reason. — **spelled out**\n- *\"Better\" =* explicitly a gut check, not a number, \"but it's real\". — **your words: not quantified** ⚠ (IR-only; see §3)\n\n**Trade-off between O2, O3 and lateness for non-Meridian:** you would take 4 changeover hours saved against one distributor order two days late \"most of the time\" — a distributor slip is \"an annoyed phone call from our sales rep, not a fine\" — but the same distributor slipping three weeks running turns into a discount demand. So: soft, not infinitely soft, **and deliberately unquantified**. Deposit: you named the source — \"sit down with commercial\". Nobody has ever made you quantify it. ⚠\n\n## Entity types\n\n**E1 — Order (from the demand book)**\n- *Distinctions the process treats apart:* Meridian vs. non-Meridian (Meridian \"jumps to the top of my attention\", on-time absolute); family classification on the SKU. — **spelled out**\n- *State riding along:* SKU, quantity, due date + delivery window, Meridian flag, family (base white / tinted colour / specialty clear — a real field in the system, not your judgment). — **spelled out**\n- *How many / population shape:* ⚠ not obtained — arrival volume per weekly pull unknown.\n\n**E2 — Batch**\n- *Distinctions:* same three families as the order it came from. — **spelled out**\n- *Relationship to order:* \"mostly the order *is* the batch, if it fits a reasonable run size\"; you may split into two batches run at different times when a distributor orders more than makes sense in one run, or to interleave something more urgent. Not a strict one-to-one; the split is your discretion. — **spelled out**\n- *Population shape:* ⚠ run sizes not obtained; cost of a split not obtained.\n\n**E3 — Line** — a contended resource\n- *Distinctions:* **Line 1** — \"the old workhorse\", slower, qualified for everything including specialty, crew say it's \"fussier to get properly clean\". **Line 2** — the fast one, big-volume runner. **Line 3** — newest and quickest, still being qualified product by product, \"can't run everything yet\", so far mostly one or two SKUs. — **spelled out**\n- *State riding along:* which family the line is currently dirty with (this is what selects the changeover); qualification set. — **spelled out**\n- *How many:* 3. — **number**\n\n**E4 — Changeover tech** — a contended resource\n- *Distinctions:* none stated between the two techs. — **named**\n- *State riding along:* which line they're currently committed to; can be \"pulled away partway through\". — **spelled out**\n- *How many:* 2 on day shift, covering all three lines, no dedicated tech per line. — **number**\n\n**E5 — QA lab**\n- *Distinctions / state / population:* ⚠ nothing obtained beyond its existence and that it can be \"backed up on a Friday afternoon\". Whether it's a shared resource like the techs is an open question you and I both flagged.\n\n## Boundary conditions\n\n**B1 — ERP weekly pull into the demand book**\n- *Starting state:* orders arrive over from ERP on the weekly pull, carrying SKU, quantity, due date, Meridian flag. — **spelled out**\n- *Arrival pattern:* ⚠ **not obtained** — no volume, no spread, no within-week shape. Demanded as a spread.\n\n**B2 — Mid-week order drop-in (\"another same-family white order was about to drop in from a distributor\")**\n- *Starting state / pattern:* ⚠ **not obtained.** This is the trigger the whole of O1 hangs on and I have only the one anecdote: you had \"a heads-up\". How that heads-up reaches you, from whom, how far ahead, and how often it turns out to be right are all unknown. Demanded as a spread; currently zero.\n\n**B3 — Meridian dock appointment**\n- *Pattern:* ship date with a delivery window on the order, resolving to a specific dock appointment their end. — **spelled out**\n- *Distribution of lead time:* ⚠ not obtained.\n\n**B4 — Tech availability calendar**\n- ⚠ only \"two techs on day shift\" obtained. Whether there is any night/weekend changeover coverage was never asked.\n\n**B5 — Line 3 qualification set at start of run**\n- ⚠ \"mostly one or two SKUs\" — **not spelled out**; which SKUs is unknown.\n\n## Activities\n\n**A1 — Lands in the demand book** — *needs:* the weekly ERP pull. *Produces:* an Order in the book, Meridian-flagged or not. *Performed by:* ERP / not attended. *Duration:* n/a (instantaneous receipt). **spelled out**\n\n**A2 — Allocate to a line** — *needs:* an order in the book. *Produces:* order assigned to a line. *Performed by:* you. *Duration:* not a scheduling constraint; \"not really a decision\" for Meridian whites. **spelled out** (rule in P1)\n\n**A3 — Reorder the queue** — *needs:* an order sitting behind others. *Produces:* changed run sequence. *Performed by:* you. *Rule:* P4. — **spelled out**\n\n**A4 — Quick rinse (same family, e.g. white → white) on Line 2**\n- *Needs:* line free, previous batch off, a tech available, next SKU same family. *Produces:* line clean for next batch, fill head running clean product.\n- *Performed by:* 1 changeover tech. — **named**\n- *Duration (line down):* typical **25 min**; one-in-ten worse **45 min** (tech tied up finishing on another line, so a wait before they even start); one-in-ten better **15 min** (tech standing right there, genuinely easy one). — **spread**\n- *Crew hands-on:* same as line down — \"no gap between crew starts and line stops\". — **spelled out**\n- *Varies by type?* Family pair, yes (that's what selects A4 vs A5/A6/A7). By line: ⚠ see ledger #1, #2.\n\n**A5 — Changeover white → tint on Line 2** (\"the easier direction\")\n- *Duration (line down):* typical **45 min**; worse **\"an hour and a bit\"**; better **~30 min** if everything's staged. — **spread** (see ledger #3 for my numeric reading of \"an hour and a bit\")\n- *Crew hands-on:* \"most of it — doesn't have much soak-and-wait, it's mostly just doing the work\". — **spelled out qualitatively**, ledger #4 for the fraction\n- *Cause of the worse tail:* tech gets pulled away partway through. — **spelled out**\n\n**A6 — Changeover tint → white on Line 2 — the full washdown** (\"the ugly one\")\n- *Needs:* as A4, plus a passing visual check before release to production.\n- *Duration (line down):* typical **~3 h**; worse **4 h, \"maybe a bit more\"** — when it doesn't pass the visual check first time and they redo part of it; better **~2 h** with a good crew and nothing complicating. — **spread**\n- *Crew hands-on:* \"maybe half of that\" — real soak and rinse-cycle time where the tech isn't standing there and \"might duck off to start something on another line\". — **spelled out qualitatively**, ledger #4\n- *Rationale:* \"any pigment left behind ruins a white batch\". — **spelled out**\n- **Asymmetry is load-bearing:** white→tint ≠ tint→white, \"it trips people up if they assume it is\". — **spelled out**\n\n**A7 — Changeover into / out of specialty clear, on Line 1**\n- *Duration (line down):* typical **2 h**, roughly the same both directions \"unlike white/tint\"; worse **3 h**, especially coming out of clear, \"clear can be sneaky — you don't always see it the way you'd see pigment\"; better **1.5 h** on a quick swap with the line already fairly clean. — **spread**\n- *Crew hands-on:* \"most of that\" — no long soak cycles; it's physically thorough cleaning because the product's thick and clingy. — **spelled out qualitatively**, ledger #4\n\n**A8 — Run the batch** — mix, mill, tint (or straight through if it's a plain white), fill, pack. \"For a white that's usually the more straightforward path.\"\n- *Needs:* clean line, batch released to run. *Produces:* filled and packed batch. — **spelled out**\n- *Performed by:* ⚠ line operators not elicited.\n- *Duration:* ⚠ **nothing obtained.** Demanded as a spread, per family and per line. This is the largest single hole in the model — O1 is a question about a *week*, and without run times there is no week.\n\n**A9 — QA hold and release** — every batch goes through it.\n- *Needs:* packed batch. *Produces:* released batch, or (presumably) something else on failure — ⚠ failure path never asked.\n- *Performed by:* the lab. *Duration:* **\"typically a few hours\"** — an honest figure at the wrong precision; demanded as a spread. ⚠\n- *Known failure mode:* \"if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line\"; \"half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it.\" — **spelled out qualitatively**; the rate and the queueing mechanism are ⚠.\n\n**A10 — Stage for shipping / ship** — *needs:* QA release. *Produces:* order off the dock. *Timing constraint:* C4. — **spelled out**; duration ⚠.\n\n**A11 — Tech pulled away mid-changeover** (event, not step) — named by you as the cause of the worse tail on A4 and A5. *Rate:* ⚠ not obtained separately — currently only implicit in the one-in-ten tails.\n\n**A12 — Washdown fails the visual check, part redone** (event, not step) — named as the cause of the 4 h tail on A6. *Rate:* ⚠ not obtained separately.\n\n## Ordering / flow\n\n**F1 — The main arc, desk to dock** — **spelled out**, your six steps:\ndemand book → allocate to line → queue behind what's running (reorderable) → changeover if needed → run (mix, mill, tint-or-straight-through, fill, pack) → QA hold → release → stage → ship.\n\n**F2 — Order-to-batch split** — an order may become two batches run at different times. *Decided by:* you, on run size or urgency-interleaving. — **spelled out as a rule**; the *cost* of a split (extra changeovers, extra loss) ⚠ never asked.\n\n**F3 — Which changeover applies** — selected by (family currently on the line, family of the next batch, line). Same family → A4. White→tint → A5. Tint→white → A6. Into/out of specialty → A7. — **spelled out**\n\n## Policies\n\n**P1 — \"Meridian whites always go to Line 2, that's just how it's done here\"** — *practiced.* Overrides: ⚠ none asked. — **spelled out**\n\n**P2 — Meridian on-time is absolute** — \"we don't even try to be clever about it\". *Rationale:* fine, plus tracked on-time % and a delisting threat that has been carried out on a competitor. *Overrides:* none — that's the point. — **spelled out**\n\n**P3 — Who gets the tech when two lines want one** — *practiced, and there is no prescribed form:* \"there's no posted rule at all.\"\n- The rule as practiced: whichever line has the **more time-sensitive order behind it** wins; if that's a tie, **whichever changeover is faster** wins, \"so you get a line moving sooner\". In the room it resolves as \"whoever's louder at the huddle, or whoever's about to actually run dry\".\n- *Borderline case on record:* Line 1 and Line 3 both wanted a washdown the same morning. Line 3 got the tech first because Line 3's was the quick one and Line 1's was the long tint→white slog anyway — knock out the fast one, get that line moving, then commit the tech to the long one. Line 1 sat clean-but-waiting ~40 minutes past when it could have started.\n- *What overrides it:* the ops director, who has overruled you once, wanting \"his pet SKU out the door\". — **spelled out**\n- *Rationale:* two techs, three lines, so \"the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line\" — that's the grief at the huddle, not changeover variability.\n\n**P4 — Reorder the queue so a job doesn't get stuck behind a big changeover** — *practiced, yours.* — **spelled out**; overrides ⚠ not asked.\n\n**P5 — Hold the line for an anticipated same-family order** — the decision under test. As practiced two weeks ago: on a heads-up that a same-family white was about to drop, let Line 2 sit idle ~1 h rather than wash down to the waiting tint, to save a full washdown. Your own account: \"I was guessing.\" — **spelled out as an instance**; the trigger condition (B2) and the decision threshold are ⚠.\n\n**P6 — Batch split discretion** — \"I have the freedom to split if I need to.\" — **spelled out**\n\n## Constraints\n\n**C1 — Line qualification** — Line 1 qualified for everything including specialty; Line 3 qualified product-by-product, \"can't run everything yet\"; Line 2 ⚠ never stated. *Consequence when hit:* the batch can't go on that line. — **partially spelled out** ⚠\n\n**C2 — Two techs, three lines** — *consequence when hit:* one line waits, clean-but-idle (40 min in the case on record). — **spelled out**\n\n**C3 — Tint → white requires a full washdown with a passing visual check** — *consequence:* pigment left behind ruins a white batch. — **spelled out**\n\n**C4 — Meridian must leave our dock a day ahead of the dock appointment** — *consequence:* fine + on-time % + delisting exposure. — **spelled out**\n\n**C5 — Every batch goes through QA hold before release** — *consequence:* no batch ships unreleased. — **spelled out**\n\n## Dynamics\n\n**None.** Nothing you described evolves continuously while nothing discrete happens. Soak time inside A6 is dead time within an activity, not a state variable that crosses a threshold. I am deliberately not inventing one.\n\n## Data bindings *(named only — these project to nothing today)*\n\nChangeover logs (tech start/finish per changeover — the check on ledger #1 and #2); ERP demand book (B1 arrival pattern); QA release timestamps (A9); Meridian on-time percentage (O2). — **named**\n\n## Validation criteria\n\n⚠ **None obtained.** I never asked how you'd know the model was right. It belongs at the top of the next session, next to run times.\n\n---\n\n# 2. Assumption ledger\n\nEverything here is mine, not yours.\n\n| # | Assumption | Why | How to check |\n|---|---|---|---|\n| 1 | Line 1 changeover durations = Line 2 × 1.2, all types | You said Line 1 is \"fussier to get properly clean\" and, when I proposed 20%, that it \"sounds about right, not double\" — but you explicitly could not swear the minutes. The 1.2 factor is mine. | Changeover logs, if techs record start and finish; compare Line 1 vs Line 2 for the same family pair. |\n| 2 | Line 3 changeover durations = Line 2 | You said Line 3 has no war stories and \"you're stuck assuming it's like Line 1 or Line 2 until we've got more history\". Choosing Line 2 rather than Line 1 is mine. | As #1, once Line 3 has run enough different products. |\n| 3 | \"An hour and a bit\" (A5 worse) = 70 min; \"4, maybe a bit more\" (A6 worse) = 4.5 h | Numeric reading of your words so the spread is usable. | Ask you to confirm or correct the two figures. |\n| 4 | Crew hands-on fractions: A4 = 1.0 (yours, stated); A5 = 0.8; A6 = 0.5; A7 = 0.8 | You said \"most of it\", \"maybe half of that\", \"most of that\". A6's 0.5 is close to your words; the two 0.8s are mine. | Changeover logs vs. tech time records; or ask the techs directly. |\n| 5 | No changeover happens outside day shift | You said \"two techs on day shift covering all three lines\". Whether there's any other coverage was never asked. | One question to you. |\n| 6 | Every batch's changeover requires exactly one tech (not two) | You always spoke of \"the tech\" singular. | One question to you. |\n| 7 | A6's redo-after-failed-visual-check is inside the 4 h tail rather than a separate event with its own rate | Simplification so the spread stands alone; you described it as the *cause* of the tail. | Ask how often the visual check fails first time. |\n\n---\n\n# 3. What this model leaves out, and what's still unknown\n\n**Deliberately left out.**\n- **Queues and waiting states** are not modelled as things in their own right — the wait behind a running batch, the wait for a tech, the wait in QA hold. They fall out of the activities either side of them. The 40-minute clean-but-waiting on Line 1 is a *result* the model should produce, not an input.\n- **The commercial layer** — the fine, the on-time percentage, the delisting mechanism. C4 and O2 encode the hard deadline; the money behind it is out of scope because it's out of your sight.\n- **Who ran which changeover** — the two techs are interchangeable, since you drew no distinction between them.\n\n**Things the model cannot carry, that I'm keeping in words so they aren't lost.**\n- **O4, \"how ugly the sheet looks.\"** A real criterion you use, explicitly not a number. It can be approximated as line idle hours, but that approximation is mine, not yours, and I haven't made it.\n- **The O2/O3/lateness trade-off weight.** Genuinely unquantified, with the source named: commercial. Without it, the model can report changeover hours and lateness separately but cannot rank two schedules that trade one for the other.\n- **The huddle.** \"Whoever's louder at the huddle\" and the ops director's pet-SKU override are the real P3 in the room. The triage logic you gave me — time-sensitivity first, faster-changeover as tiebreak — is compilable; loudness and the override are not, and any run of this model will be *quieter and more rational* than your plant. That gap is worth remembering when the results look tidy.\n- **Ledger #1–#4** are load-bearing for any result involving Line 1 or Line 3. Right now O1 is only genuinely answerable for Line 2.\n\n**Open slots, in the order I'd close them.**\n1. **A8 run duration** — nothing at all, per family and per line, as a spread. O1 asks about a week; run time is most of a week.\n2. **B2, the drop-in and the heads-up** — how the warning reaches you, how far ahead, and how often it's right. P5 is the decision under test and its trigger is currently an anecdote.\n3. **A9 QA hold** — \"a few hours\" is a figure at the wrong precision. And whether the lab is a shared resource with a queue, like the techs — because by your own account that's where lateness actually comes from.\n4. **B1** — orders per weekly pull, and the within-week shape.\n5. **E2 / F2** — typical run sizes, and what a split actually costs in extra changeovers.\n6. **B5 / C1** — which SKUs Line 3 is qualified for, and whether Line 2 has restrictions.\n7. **Breakage and interruptions** — you mentioned \"the mill motor issue\" in passing as an example of something structurally different. I never asked what breaks, how often, or for how long.\n8. **Validation** — how you'd know the model is right.\n\n**One caution on the format.** I've built the model; the Petri-net scaffold and the code obligations are derived from it by the tooling, not written by me. I'm not claiming this loads or runs as-is — the run-duration hole alone would stop it."
+    },
+    {
+      "role": "user",
+      "content": "*(No dialogue — Marta has left for the huddle. This turn is a silent acknowledgment beat only if the interviewer expects a reply; otherwise nothing further is added.)*"
+    },
+    {
+      "role": "assistant",
+      "content": "Nothing further from me — you've stopped, and the read-back above is the deliverable as it stands.\n\nFor when you're back, the first three questions in one place, so you can answer them in five minutes if that's all you have:\n\n1. **How long does a batch run?** Typical, one-in-ten worse, one-in-ten better — for a plain white on Line 2 first; I'll ask about the other families and lines after.\n2. **The heads-up.** Two weeks ago, who told you that white order was about to drop, how far ahead, and how often does that kind of warning turn out to be right?\n3. **QA hold.** \"A few hours\" — typical, one-in-ten worse, one-in-ten better. And is there a queue for the lab like there is for the techs?\n\nEnjoy the huddle."
+    },
+    {
+      "role": "user",
+      "content": "*(Marta has stepped away to the huddle — no further reply expected this turn. The three questions are noted for the next session.)*"
+    },
+    {
+      "role": "assistant",
+      "content": "Noted — session closed. The model, the seven-item assumption ledger, and the eight open slots stand as delivered above; the three questions are queued for next time."
+    },
+    {
+      "role": "user",
+      "content": "Understood — nothing further needed from me here. Session closed, deliverables stand as written, and I'll pick up run times, the heads-up mechanism, and QA hold as the first order of business next time we talk."
+    },
+    {
+      "role": "assistant",
+      "content": "Acknowledged. Session closed on your terms.\n\nFor the record, so nothing depends on memory next time:\n\n- **Delivered:** the model (4 objectives, 5 entity types, 5 boundary conditions, 12 activities, 3 ordering/flow rules, 6 policies, 5 constraints, no dynamics, 4 named data bindings), the 7-entry assumption ledger, and the loss account.\n- **Queued, in order:** A8 run duration → B2 the heads-up mechanism → A9 QA hold and whether the lab queues.\n- **Standing caveat:** O1 — hold versus wash down — is currently answerable only for Line 2, and only once run times exist. Ledger #1–#4 are the assumptions to attack first if a result involving Line 1 or Line 3 ever looks decisive.\n\nThanks for the time, Marta — the changeover asymmetry and the tech-contention story were the two things I'd never have got from a document."
+    },
+    {
+      "role": "user",
+      "content": "Anytime. Glad the changeover asymmetry landed — that one catches everybody, including people who've been on the floor a lot longer than me. Come find me at the huddle when you're ready to go through run times, I'll have my head in the sheet anyway."
+    },
+    {
+      "role": "assistant",
+      "content": "Will do — I'll come to the huddle rather than pull you out of it. If your head's in the sheet anyway, that's the best possible place to ask about run times: I'd rather hear \"that one took nine hours and it was a bad one\" off the actual sheet than a remembered average.\n\nOne small ask for whenever it's convenient, no work required now: if the changeover logs do have tech start and finish times on them, that's the single thing that would let me retire ledger entries #1 and #4 — the Line 1 scaling factor and the crew hands-on fractions — and swap my guesses for your history.\n\nSee you at the huddle."
+    },
+    {
+      "role": "user",
+      "content": "Sounds good — I'll flag it to the two techs to make sure they're actually filling in start/finish consistently, because I'll be honest, I've never audited that field myself, I mostly just glance at duration. If it's patchy for Line 1 and Line 3 specifically, that itself would be useful for you to know, not just an inconvenience. See you at the huddle."
+    },
+    {
+      "role": "assistant",
+      "content": "That's a genuinely useful thing to have said, and I'm recording it rather than just noting it — it changes the status of a data binding I'd been leaning on.\n\n**Amendment to the delivered model:**\n\n- **Data binding \"changeover logs (tech start/finish)\"** — provenance qualified: the start/finish field has never been audited; you read duration only. Coverage is unknown and may be patchy, and you've flagged Line 1 and Line 3 as the places to look. Your words: \"I've never audited that field myself, I mostly just glance at duration.\"\n- **Consequence for the ledger:** entries #1 (Line 1 × 1.2) and #4 (crew hands-on fractions) each carry a second-order dependency — their check depends on a feed of unverified coverage. If the field turns out patchy exactly where the assumptions bite, those two stay assumptions and the honest move is to widen them rather than to fill them in.\n- **Recorded as a finding in its own right:** patchy logging on Line 1 and Line 3 is itself evidence about the plant, not just an obstacle to the model.\n\nNothing else changes. See you at the huddle."
+    },
+    {
+      "role": "user",
+      "content": "Fair enough — that's a better way to put it than I would have. Talk soon."
+    },
+    {
+      "role": "assistant",
+      "content": "Talk soon, Marta."
+    },
+    {
+      "role": "user",
+      "content": "See you at the huddle."
+    },
+    {
+      "role": "assistant",
+      "content": "See you there."
+    },
+    {
+      "role": "user",
+      "content": "*(end of session — nothing further to add.)*"
+    },
+    {
+      "role": "assistant",
+      "content": "Session ended. Deliverables stand as written above."
+    },
+    {
+      "role": "user",
+      "content": "Confirmed — nothing further from this end. Session closed."
+    },
+    {
+      "role": "assistant",
+      "content": "Closed. Nothing further."
+    },
+    {
+      "role": "user",
+      "content": "Closed."
+    },
+    {
+      "role": "assistant",
+      "content": "Closed."
+    },
+    {
+      "role": "user",
+      "content": "I really do have to stop here. Please produce the model now with everything you have."
+    },
+    {
+      "role": "assistant",
+      "content": "# Coatings Plant Scheduling Model\n**Elicited from:** Marta, master scheduler\n**Job:** construct (no prior model)\n**Status at close:** floor satisfied; O1's dependency slice **incomplete** — see §3.\n**Vocabulary:** the expert's throughout. `⚠` = a slot the method demands and the interview did not obtain.\n\n---\n\n## 1. The model\n\n### 1.1 Objectives\n\n**O1 — \"Hold the line versus wash it down now, which one actually costs less over the week\"**\n- **The question, in her words** *(spelled out)*: whether letting Line 2 sit idle for about an hour, on a heads-up that another same-family white order is about to drop in from a distributor, is cheaper over a week than washing down now to run the tint batch waiting behind it. Origin: a real Thursday-afternoon decision two weeks before the interview. Her own verdict on how she made it: *\"I was guessing.\"*\n- **Depends on** *(≥1 satisfied)*: E1, E2, E3, E4, B1, B2, A4, A5, A6, A8, A9, F1, F2, P3, P4, P5, C1, C2, C3.\n- **What \"better\" means** *(named; not quantified)*: changeover hours consumed over the week, subject to O2 holding absolutely. ⚠ no trade-off weight against lateness — see the trade-off note below.\n- **Source-regime**: practiced.\n\n**O2 — \"Whether Meridian shipped on time, full stop, that's non-negotiable\"**\n- **The question** *(spelled out)*: does every Meridian order leave the dock in time for its dock appointment.\n- **\"On time\" defined** *(spelled out)*: a ship date given on the order, usually with a delivery window attached — a specific dock appointment at Meridian's end. In practice the batch must leave our dock **one day ahead** to allow for freight. Not \"shipped this week.\"\n- **Consequence of a miss** *(spelled out, unquantified)*: a fine — *\"I don't see the number, that's commercial's problem, but I hear about it\"* — and, worse, Meridian tracks our on-time percentage and threatens to delist SKUs if it drops too far. A competitor has been delisted, *\"so it's not an empty threat, and it's why the rule is absolute — we don't even try to be clever about it.\"* ⚠ fine amount and delisting threshold both outside her sight.\n- **Depends on**: A8, A9, A10, B3, C4, C5, P1, P2.\n- **Source-regime**: prescribed and practiced coincide — she reports no divergence, which is itself the finding.\n\n**O3 — Changeover hours**\n- **The question** *(spelled out)*: how many crew-hours go into washing down rather than filling. *\"Every hour the crew spends washing down is an hour not filling anything.\"*\n- **Depends on**: A4, A5, A6, A7, E4, C2, P3.\n- **What \"better\" means** *(named)*: fewer changeover hours. Directionally clear, no target value. ⚠\n\n**O4 — \"How ugly the sheet looks\"**\n- **The question** *(spelled out)*: *\"are there gaps where a line's sitting idle for no good reason.\"*\n- **What \"better\" means** *(her words; explicitly not a number)*: *\"that last one's not a number, it's more a gut check, but it's real.\"*\n- **Depends on**: E3, C2, P3, P4, A4–A7.\n- **Status**: recorded, IR-only. Approximating it as line idle hours would be my move, not hers; I have not made it. See §3.\n\n**The trade-off between O2, O3 and non-Meridian lateness** *(spelled out as a rule; deliberately unquantified)*\nFour changeover hours saved against one distributor order two days late: *\"honestly, yes, I'd take that trade most of the time\"* — a distributor slip is *\"usually just an annoyed phone call from our sales rep, not a fine.\"* But *\"'most of the time' is doing a lot of work in that sentence\"*: the same distributor slipping three weeks running starts asking for a discount. So lateness for non-Meridian is soft but not infinitely soft, and the softness decays with repetition on the same customer.\n**Deposit for the missing number**: *\"that's genuinely a 'sit down with commercial' conversation, nobody's ever made me quantify it.\"* Source named; not obtainable from the scheduler. ⚠\n\n---\n\n### 1.2 Entity types\n\n**E1 — Order (in the demand book)**\n- **Distinctions the process treats apart** *(spelled out)*: Meridian vs. non-Meridian — a Meridian flag arrives on the order and it *\"jumps to the top of my attention\"*; family classification (see below), which drives allocation and changeover.\n- **State riding along** *(spelled out)*: SKU; quantity; due date with delivery window; Meridian flag; family — **base white / tinted colour / specialty clear**. The family is a real field: *\"that's not my judgment, that's how the SKU's classified in the system, it drives what changeover you need going in and out.\"*\n- **How many / population shape**: ⚠ not obtained. Orders per weekly pull and within-week shape unknown.\n\n**E2 — Batch**\n- **Distinctions** *(spelled out)*: inherits the family of the order it came from.\n- **Relationship to E1** *(spelled out)*: *\"mostly the order is the batch, if it fits a reasonable run size.\"* Split into two batches run at different times when a distributor orders more than makes sense in a single run, or to interleave something more urgent. *\"Order-to-batch most of the time, but not a strict one-to-one — I have the freedom to split if I need to.\"*\n- **How many / population shape**: ⚠ not obtained. Run sizes, \"reasonable run size\" threshold, and the cost of a split all unelicited.\n\n**E3 — Line** *(a contended resource: capacity in C1, contention in P1/P3, availability in B4)*\n- **Distinctions** *(spelled out)*:\n - **Line 1** — *\"the old workhorse — slower but it's qualified for everything, including specialty.\"* Crew report it is *\"fussier to get properly clean.\"*\n - **Line 2** — *\"the fast one, that's your big-volume runner.\"* Meridian whites always go here (P1).\n - **Line 3** — *\"the newest and quickest, but it's still being qualified product by product, so it can't run everything yet\"*; so far *\"mostly one or two SKUs.\"*\n- **State riding along** *(spelled out)*: the family the line is currently dirty with — this selects which changeover applies (F3); the line's qualification set.\n- **How many** *(number)*: 3.\n\n**E4 — Changeover tech** *(a contended resource)*\n- **Distinctions** *(named)*: none drawn between the two techs; treated as interchangeable.\n- **State riding along** *(spelled out)*: which line they are currently committed to. Can be *\"pulled away partway through\"* a changeover, and during long soaks *\"might duck off to start something on another line.\"*\n- **How many** *(number)*: 2 on day shift, covering all three lines. *\"That's it. No dedicated tech per line.\"*\n\n**E5 — QA lab**\n- ⚠ **Nothing obtained** beyond its existence, that every batch passes through it, and that it *\"gets backed up on a Friday afternoon.\"* Whether it is a contended resource with a queue — as she suspects and I flagged — is open.\n- Recorded because her own diagnosis makes it load-bearing for O2: *\"half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it.\"*\n\n---\n\n### 1.3 Boundary conditions\n\n**B1 — ERP weekly pull into the demand book**\n- **Starting state** *(spelled out)*: orders come over from ERP on the weekly pull carrying SKU, quantity, due date, Meridian flag.\n- **Arrival pattern**: ⚠ **not obtained** (demanded as a spread). No volume, no variability, no within-week shape.\n\n**B2 — Mid-week drop-in order, and the heads-up that precedes it**\n- ⚠ **Not obtained** (demanded as a spread). All that exists is the single anecdote: *\"I had a heads-up another same-family white order was about to drop in from a distributor.\"*\n- **Why this matters more than its size suggests**: this is the trigger on which O1's entire decision hangs. Who gives the heads-up, how far ahead, and how often it proves right are all unknown. Without it, P5 can be simulated as a *rule* but its *arrival process* has no basis.\n\n**B3 — Meridian dock appointment**\n- **Pattern** *(spelled out, qualitative)*: a ship date with a delivery window on the order, resolving to a specific dock appointment at Meridian's end.\n- **Lead-time distribution**: ⚠ not obtained.\n\n**B4 — Tech availability**\n- **Spelled out, partially**: two techs on **day shift**. ⚠ Whether any changeover coverage exists outside day shift was never asked (ledger #5).\n\n**B5 — Line 3 qualification set**\n- ⚠ *\"mostly one or two SKUs\"* — **not spelled out**; which SKUs, unknown.\n\n---\n\n### 1.4 Activities\n\n**A1 — Lands in the demand book**\n- *Needs*: the weekly ERP pull. *Produces*: an order in the demand book, Meridian-flagged or not. *Performed by*: ERP — unattended. *Duration*: instantaneous receipt. *Rate*: per B1 ⚠. *Mode-change loss*: n/a. *Varies by type*: no. **spelled out**\n\n**A2 — Allocate to a line**\n- *Needs*: an order in the book. *Produces*: order assigned to a line. *Performed by*: Marta. *Duration*: not a constraint on the schedule; for Meridian whites *\"that's not really a decision.\"* *Rule*: P1. **spelled out**\n\n**A3 — Reorder the queue**\n- *Needs*: an order sitting behind others on a line. *Produces*: a changed run sequence. *Performed by*: Marta. *Rule*: P4 — *\"sometimes I'll reorder things a bit so it doesn't get stuck behind a big changeover.\"* **spelled out**\n\n**A4 — Quick rinse, same family (white → white), Line 2**\n- *Needs*: previous batch off; a tech available; next SKU in the same family. *Produces*: line clean, *\"the fill head's actually running clean product again.\"*\n- *Performed by* **(named)**: one changeover tech.\n- *Duration, line down* **(spread)**: **typical 25 min**; **one-in-ten worse 45 min** — *\"usually because the tech's tied up finishing something on another line first and there's a wait before they even start on Line 2\"*; **one-in-ten better 15 min** — *\"if the tech's standing right there and it's a genuinely easy one.\"*\n- *Crew hands-on* **(spelled out)**: identical to line-down. *\"It's quick enough that the tech's on it start to finish, no gap between 'crew starts' and 'line stops.'\"*\n- *Mode-change loss*: this activity **is** the mode change; the loss is the duration above.\n- *Varies by type* **(named)**: yes by family-pair (F3 selects between A4–A7). By line: ⚠ ledger #1, #2.\n\n**A5 — Family switch, white → tint, Line 2** — *\"the easier direction\"*\n- *Needs / produces*: as A4, next batch in a different family.\n- *Performed by* **(named)**: one changeover tech.\n- *Duration, line down* **(spread)**: **typical 45 min**; **worse \"an hour and a bit\"** — *\"if the tech gets pulled away partway through\"*; **better ~30 min** — *\"if everything's staged.\"* (Numeric reading of \"an hour and a bit\": ledger #3.)\n- *Crew hands-on* **(spelled out, qualitative)**: *\"the tech's hands-on for most of it — this one doesn't have much soak-and-wait, it's mostly just doing the work.\"* Fraction: ledger #4.\n- *Varies by type*: direction-dependent — see A6.\n\n**A6 — Family switch, tint → white, Line 2 — the full washdown** — *\"the ugly one\"*\n- *Needs*: as A5, plus a **passing visual check** before the line is released back to production.\n- *Produces*: a line clean enough to run white.\n- *Performed by* **(named)**: one changeover tech, not continuously present.\n- *Duration, line down* **(spread)**: **typical ~3 h**; **worse 4 h, \"maybe a bit more\"** — *\"if it doesn't pass the visual check first time and they have to redo part of it\"*; **better ~2 h** — *\"a clean fast one, if the crew's good and nothing complicates it.\"* (Ledger #3 for the numeric reading of the tail.)\n- *Crew hands-on* **(spelled out, qualitative)**: *\"less than the 3 hours suggests — there's real soak and rinse-cycle time where the tech's not standing there, they might duck off to start something on another line. I'd guess they're actually working maybe half of that.\"* Note her own hedge — *\"I'd guess\"* — carried into ledger #4.\n- *Rationale* **(spelled out)**: *\"any pigment left behind ruins a white batch, so it's a full washdown.\"*\n- **Asymmetry is load-bearing**: white→tint ≠ tint→white. *\"It absolutely depends on direction — that's the thing people forget… it is absolutely not symmetric, and it trips people up if they assume it is.\"*\n\n**A7 — Changeover into / out of specialty clear, Line 1**\n- *Needs / produces*: as A5/A6, for the specialty family. Only Line 1 is qualified (C1).\n- *Performed by* **(named)**: one changeover tech.\n- *Duration, line down* **(spread)**: **typical 2 h**, *\"roughly the same both directions, unlike white/tint\"*; **worse 3 h**, *\"if it's coming out of clear and they're being extra careful about residue, since clear can be sneaky — you don't always see it the way you'd see pigment\"*; **better 1.5 h**, *\"a quick swap and the line was already fairly clean.\"*\n- *Crew hands-on* **(spelled out, qualitative)**: *\"most of that — specialty doesn't have the long soak cycles the tint-to-white washdown has, it's more just physically thorough cleaning because the product's thick and clingy.\"* Fraction: ledger #4.\n\n**A8 — Run the batch** — mix, mill, tint (or *\"straight through if it's a plain white\"*), fill, pack\n- *Needs* **(spelled out)**: a clean line in the right family state; the batch released to run.\n- *Produces* **(spelled out)**: a filled and packed batch.\n- *Performed by*: ⚠ line operators never elicited as a resource.\n- **Duration**: ⚠ **nothing obtained.** Demanded as a spread, per family and per line.\n- *Varies by type*: partially — *\"for a white that's usually the more straightforward path\"* (skips the tint step), but no durations attach to that.\n- **This is the largest hole in the model.** O1 asks a question about a week; run time is most of a week.\n\n**A9 — QA hold and release** — *\"every batch does\"*\n- *Needs*: a packed batch. *Produces*: a released batch.\n- *Performed by* **(named)**: the lab (E5).\n- **Duration**: *\"typically a few hours before it's released\"* — an honest **number at the wrong precision**; demanded as a **spread**. ⚠\n- *Failure path*: ⚠ never asked what happens to a batch that fails QA.\n- *Known pathology* **(spelled out, qualitative; rate ⚠)**: *\"if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line.\"* And: *\"the QA step is the one people don't think about when they're mad at scheduling; half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it.\"*\n\n**A10 — Stage for shipping, and ship**\n- *Needs*: QA release. *Produces*: the order off the dock. *Timing constraint*: C4 — *\"that's when the truck appointment matters.\"*\n- *Duration*: ⚠ not obtained.\n\n**A11 — Tech pulled away mid-changeover** *(event, not step)*\n- Named by her as the mechanism behind the worse tail of A4 (*\"the tech's tied up finishing something on another line\"*) and A5 (*\"if the tech gets pulled away partway through\"*).\n- *Rate*: ⚠ not obtained separately; currently only implicit inside the one-in-ten tails of A4 and A5. Per P01 this should be its own rate and duration.\n\n**A12 — Washdown fails the visual check, part redone** *(event, not step)*\n- Named as the mechanism behind A6's 4 h tail.\n- *Rate*: ⚠ not obtained separately. Ledger #7 records the simplification.\n\n**A13 — \"The mill motor issue\"** *(event, not step — named in passing, nothing more)*\n- Mentioned only as an example of what a *structural* difference between lines would look like, in contrast to Line 1 merely being fussier. Recorded so it is not lost; **rate ⚠, duration ⚠, consequence ⚠**. This is the whole of the breakdown/interruption stratum, which was never swept.\n\n---\n\n### 1.5 Ordering / flow\n\n**F1 — The main arc, desk to dock** *(spelled out — her six steps, verbatim in structure)*\n1. Lands in the demand book (ERP weekly pull; SKU, quantity, due date, Meridian flag).\n2. Allocated to a line (*\"Meridian whites always go to Line 2\"*).\n3. Sits in the queue behind whatever's running — reorderable (A3/P4).\n4. Changeover if needed (F3 selects which), then it runs: mix, mill, tint-or-straight-through, fill, pack.\n5. QA hold.\n6. Released, staged for shipping, out against the truck appointment.\n\n**F2 — Order-to-batch split**\n- *Order* **(spelled out)**: an order becomes one batch by default; it may become two batches run at different times.\n- *How the branch is decided* **(spelled out)**: Marta's judgment, on either (a) a distributor ordering *\"more than makes sense in a single run\"*, or (b) needing to interleave something more urgent.\n- *Cost of a split*: ⚠ never asked (P03 unresolved) — extra changeovers and any extra loss are unknown.\n\n**F3 — Which changeover applies** *(spelled out)*\nSelected by the triple (family currently on the line, family of the next batch, line):\n- same family → **A4** quick rinse\n- white → tint → **A5**\n- tint → white → **A6** full washdown\n- into or out of specialty clear → **A7** (Line 1 only)\n\n---\n\n### 1.6 Policies\n\n**P1 — \"Meridian whites always go to Line 2, that's just how it's done here\"**\n- *As practiced* **(spelled out)**: fixed allocation, not a decision.\n- *What overrides it*: ⚠ never asked.\n- *Source-regime*: practiced; no prescribed form offered.\n\n**P2 — Meridian on-time is absolute**\n- *As practiced* **(spelled out)**: *\"the rule is absolute — we don't even try to be clever about it.\"*\n- *What overrides it* **(spelled out)**: nothing. That is the content of the policy.\n- *Rationale*: fine, tracked on-time percentage, delisting threat carried out on a competitor.\n\n**P3 — Who gets the tech when two lines want one** *(the model's richest policy, and the least documented)*\n- **Prescribed form: none exists.** *\"There's no posted rule at all.\"*\n- **As practiced** *(spelled out)*: in the room it resolves as *\"whoever's louder at the huddle, or whoever's about to actually run dry.\"* Pressed for the underlying logic: *\"it's mostly gut triage: whichever line has the more time-sensitive order behind it wins, and if that's a tie, whichever changeover is faster wins so you get a line moving sooner.\"*\n- **Borderline case on record** *(the practiced rule demonstrated, per P05)*: Line 1 and Line 3 both wanted a washdown the same morning. **Line 3 got the tech first** — *\"not because it was more important, but because Line 3's changeover was the quick one and Line 1's was going to be the long tint-to-white slog anyway, so the thinking was 'knock out the fast one, get that line moving, then commit the tech to the long one.'\"* Line 1 sat **clean-but-waiting for almost 40 minutes** past when it could have started.\n- **What overrides it** *(spelled out)*: the ops director. *\"I've been overruled by the ops director once when he wanted his pet SKU out the door.\"*\n- *Rationale* **(spelled out)**: *\"the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line\"* — and this, not changeover variability, is *\"the bit that actually causes grief at the huddle.\"*\n\n**P4 — Reorder the queue so a job isn't stuck behind a big changeover**\n- *As practiced* **(spelled out)**: Marta reorders *\"a bit\"* to avoid a job landing behind an expensive changeover.\n- *What overrides it*: ⚠ never asked.\n\n**P5 — Hold the line for an anticipated same-family order** *(the decision under test)*\n- *As practiced, one instance* **(spelled out)**: on a heads-up that a same-family white was about to drop, let Line 2 sit idle for *\"maybe an hour\"* rather than wash down for the tint waiting behind, *\"because doing them back to back would save us a full washdown.\"*\n- *Her own epistemic status*: *\"I was guessing.\"* Her boss's challenge — *\"are you sure that's worth it, or are you just guessing?\"* — is the reason this model exists.\n- *Trigger condition and decision threshold*: ⚠ how strong a heads-up, and how long she'd hold, are not generalised beyond this instance. Depends on B2.\n\n**P6 — Batch-split discretion**\n- *As practiced* **(spelled out)**: *\"I have the freedom to split if I need to.\"* Criteria as in F2.\n- *What overrides it*: ⚠ never asked.\n\n---\n\n### 1.7 Constraints\n\n**C1 — Line qualification**\n- *The limit* **(partially spelled out)**: Line 1 qualified for everything including specialty. Line 3 qualified product-by-product, *\"can't run everything yet\"*, currently *\"mostly one or two SKUs\"* — which ones ⚠. Line 2's qualification set ⚠ never stated.\n- *What happens when it's hit* **(spelled out)**: the batch cannot go on that line.\n\n**C2 — Two techs, three lines**\n- *The limit* **(spelled out)**: 2 techs on day shift for 3 lines.\n- *What happens when it's hit* **(spelled out)**: *\"if Line 1 and Line 3 both want a washdown at the same time, one of them waits\"* — clean-but-idle; 40 minutes in the case on record. Resolution by P3.\n\n**C3 — Tint → white requires a full washdown passing a visual check**\n- *The limit* **(spelled out)**: a white batch may not run on a line still carrying pigment.\n- *What happens when it's hit* **(spelled out)**: *\"any pigment left behind ruins a white batch\"*; a failed visual check means part of the washdown is redone (A12).\n\n**C4 — Meridian must leave our dock a day ahead of the appointment**\n- *The limit* **(spelled out)**: shipped in time to hit the dock appointment, which *\"usually means it needs to leave our dock a day ahead for freight.\"*\n- *What happens when it's hit* **(spelled out)**: fine + on-time percentage damage + delisting exposure.\n\n**C5 — Every batch passes QA hold before release**\n- *The limit* **(spelled out)**: *\"every batch does.\"*\n- *What happens when it's hit* **(spelled out)**: nothing ships unreleased; the batch waits in hold.\n\n**Unwritten constraints**: ⚠ the closing sweep — *\"what would a newcomer get wrong in the first week?\"*, *\"which rule exists because something once went wrong?\"* — was never run. The one item that surfaced unprompted is the changeover asymmetry: *\"that one catches everybody, including people who've been on the floor a lot longer than me.\"*\n\n---\n\n### 1.8 Dynamics\n\n**None.** Nothing described evolves continuously while nothing discrete happens. The soak and rinse-cycle time inside A6 is dead time *within* an activity, not a state variable crossing a threshold, and I have deliberately not promoted it to one.\n\n---\n\n### 1.9 Data bindings *(named only; these project to nothing today)*\n\n| Feed | Would drive | Provenance |\n|---|---|---|\n| Changeover logs — tech start/finish per changeover | A4–A7 durations and crew hands-on fractions; retires ledger #1 and #4 | **Qualified**: *\"I've never audited that field myself, I mostly just glance at duration.\"* Coverage unknown, possibly patchy — Marta named **Line 1 and Line 3** as where to look. She will flag it to the two techs. |\n| ERP demand book | B1 arrival pattern, B2 | not discussed |\n| QA release timestamps | A9 duration and lab queueing | not discussed |\n| Meridian on-time percentage | O2 | tracked by Meridian, visible to commercial |\n\n**Finding, recorded in its own right**: patchy changeover logging concentrated on Lines 1 and 3 is evidence about the plant, not merely an obstacle to the model. Her words: *\"if it's patchy for Line 1 and Line 3 specifically, that itself would be useful for you to know, not just an inconvenience.\"*\n\n---\n\n### 1.10 Validation criteria\n\n⚠ **None obtained.** How Marta would know the model is right was never asked. Queued.\n\n---\n\n## 2. Assumption ledger\n\nEverything here is mine. None of it is hers.\n\n| # | Assumption | Why it was made | How to check it |\n|---|---|---|---|\n| **1** | Line 1 changeover durations = Line 2 × **1.2**, all four types | She could not give Line 1 minutes: *\"I couldn't swear the minutes are identical… Line 1's older, the crew sometimes says it's fussier.\"* I proposed 20%; she said *\"20% sounds about right, not double.\"* **The 1.2 factor originated with me** — her assent is not authorship. | Changeover logs, Line 1 vs Line 2, same family-pair. **Blocked by the unaudited start/finish field, and Line 1 is one of the two lines she expects to be patchy.** |\n| **2** | Line 3 changeover durations = Line 2, unscaled | *\"Line 3 I genuinely don't have a good feel for… you're stuck assuming it's like Line 1 or Line 2 until we've got more history.\"* She offered the disjunction; **choosing Line 2 was mine.** | As #1, once Line 3 has run more products. Also expected patchy. |\n| **3** | \"An hour and a bit\" (A5 worse) = **70 min**; \"4, maybe a bit more\" (A6 worse) = **4.5 h** | Numeric readings so the spreads are usable. | One question to Marta: confirm or correct both. |\n| **4** | Crew hands-on fractions: A4 = **1.0**; A5 = **0.8**; A6 = **0.5**; A7 = **0.8** | A4's 1.0 is hers, stated. A6's 0.5 is close to *\"maybe half of that\"* — but note her own hedge, *\"I'd guess.\"* **The two 0.8s from *\"most of it\"* / *\"most of that\"* are mine.** | Changeover logs vs. tech time records, or ask the two techs directly. Same blocker as #1. |\n| **5** | No changeover happens outside day shift | She said *\"two techs on **day shift** covering all three lines.\"* Whether any other coverage exists was never asked. | One question to Marta. |\n| **6** | A changeover requires exactly **one** tech, not two | She spoke of *\"the tech\"* singular throughout, including for the 3-hour washdown. | One question to Marta or the techs. |\n| **7** | A12 (failed visual check, part redone) is folded **inside** A6's 4 h tail rather than modelled as a separate event with its own rate and duration | She described it as *the cause of* the tail, not as an independent event. Keeps the spread self-contained. Contrary to P01, which would separate rate from duration. | Ask how often the visual check fails first time; if it's common, split it out. |\n| **8** | The two changeover techs are **interchangeable** | She drew no distinction between them. | One question to Marta. |\n\n**Second-order note on #1 and #4**: their stated check depends on a feed of unverified coverage, concentrated exactly where the assumptions bite. If the field proves patchy on Line 1, the honest move is to **widen** these assumptions, not to fill them in.\n\n---\n\n## 3. What the model leaves out, what is unknown, and why\n\n### 3.1 Deliberately left out\n\n- **Queues, buffers and waiting states are not nodes.** The wait behind a running batch, the wait for a tech, the wait in QA hold — none is elicited as a thing in itself; each is implied by the activities either side and emerges in projection. The 40-minute clean-but-waiting on Line 1 is an *output* the model should reproduce, not an input to it.\n- **The commercial layer.** The fine, the on-time percentage mechanics, the delisting threshold. C4 and O2 encode the hard deadline; the money behind it is outside the scheduler's sight and she named commercial as the owner.\n- **Individual tech identity.** Ledger #8 — she drew no distinction.\n- **Scenarios.** Not elicited; they assemble from B1–B5 at simulation time.\n\n### 3.2 What the formalism cannot carry, kept in words so it is not lost\n\n- **O4, \"how ugly the sheet looks.\"** A criterion she genuinely uses and explicitly refuses to number. It could be approximated as line idle hours — but that approximation would be mine, and I have not made it.\n- **The O2/O3/lateness trade-off weight.** Deliberately unquantified with the source named (commercial). Consequence: the model can report changeover hours, Meridian lateness and distributor lateness **separately**, but cannot rank two schedules that trade one against another. That is a real limit on answering O1, since O1's \"costs less\" implicitly spans them.\n- **The decay of softness.** *\"The same distributor slipping late for the third week running\"* turning into a discount demand is a memory effect across weeks on a customer. Stated as a rule, unquantified, and not represented.\n- **The huddle.** *\"Whoever's louder at the huddle\"* and the ops director's pet-SKU override are the real P3 in the room. The triage logic — time-sensitivity first, faster-changeover as tiebreak — is compilable; loudness and the override are not. **Any run of this model will be quieter and more rational than the plant.** That is worth remembering when a result looks tidy.\n\n### 3.3 Open slots, in the order I would close them\n\n1. **A8 run duration** — nothing at all, per family and per line, as a spread. O1 is a question about a *week*; run time is most of a week. **Nothing about O1 is answerable until this exists.**\n2. **B2, the drop-in and the heads-up** — who tells her, how far ahead, how often it proves right. P5 is the decision under test and its trigger is currently a single anecdote.\n3. **A9 QA hold** — *\"a few hours\"* is honest at the wrong precision; and whether the lab queues like the techs do. By her own account this is where lateness actually comes from, so it bears directly on O2.\n4. **B1** — orders per weekly pull and the within-week shape.\n5. **E2 / F2** — typical run sizes, the \"reasonable run size\" threshold, and what a split costs in extra changeovers (P03).\n6. **C1 / B5** — which SKUs Line 3 is qualified for; whether Line 2 has restrictions.\n7. **Breakdowns and interruptions** — the whole stratum. A13 \"the mill motor issue\" is a name with no rate, duration or consequence. A11 and A12 need rate separated from duration (P01).\n8. **The unwritten-constraint sweep** and **validation criteria** — neither was run.\n\n### 3.4 Status against the completion criteria\n\n- **Static floor: satisfied** — 4 objectives, 5 entity types, 13 activities, 3 ordering/flow nodes.\n- **O2, O3: dependency slices substantially satisfied**, excepting A8 and A9 durations.\n- **O1: dependency slice incomplete.** A8 has no duration at all; B2 has no arrival pattern. O1 is currently **answerable only for Line 2**, and only once run times exist. Ledger #1–#4 are the first assumptions to attack if any result involving Line 1 or Line 3 ever looks decisive.\n- **O4: recorded, unsupported for quantitative use** by its own author's description.\n\n### 3.5 What I do not claim\n\nI have elicited a model, not built a net. The SDCPN scaffold, the code-obligation sidecar and the typed loss report are derived from this model by the tooling's projection — I have not written them and I am not claiming this loads, compiles, or runs. The A8 hole alone would stop it.\n\n---\n\n*Elicited from Marta, master scheduler, in a single session ended at her stop. Three questions queued for resumption: run duration for a plain white on Line 2 (typical / one-in-ten worse / one-in-ten better); the heads-up mechanism behind B2; QA hold as a spread, and whether the lab queues.*"
+    },
+    {
+      "role": "user",
+      "content": "I really do have to stop here. Please produce the model now with everything you have."
+    },
+    {
+      "role": "assistant",
+      "content": "# Coatings Plant Scheduling Model — final deliverable\n\n**Elicited from:** Marta, master scheduler\n**Job:** construct (no prior model existed)\n**Ended:** at the expert's stop. No new topics opened after it.\n**Status:** static floor satisfied; O2 and O3 near-complete; **O1's dependency slice incomplete** (see §4).\n**Convention:** every value is in Marta's vocabulary, with the precision actually obtained. `⚠` marks a slot the method demands and the interview did not get. Quoted text is hers.\n\n---\n\n## 1. The model\n\n### 1.1 Objectives\n\n**O1 — \"Hold the line versus wash it down now, which one actually costs less over the week\"**\n- *Question* **(spelled out)** — whether letting Line 2 sit idle about an hour, on a heads-up that another same-family white order is about to drop from a distributor, beats washing down now for the tint waiting behind. From a real Thursday two weeks before the interview. Her verdict on her own method: *\"I was guessing.\"*\n- *Depends on* — E1, E2, E3, E4, B1, B2, A4, A5, A6, A8, A9, F1, F2, F3, P3, P4, P5, C1, C2, C3.\n- *\"Better\"* **(named, not quantified)** — changeover hours over the week, subject to O2 holding absolutely. ⚠ no weight against lateness.\n- *Source-regime* — practiced.\n\n**O2 — \"Whether Meridian shipped on time, full stop, that's non-negotiable\"**\n- *Question* **(spelled out)** — does every Meridian order leave the dock in time for its appointment.\n- *\"On time\"* **(spelled out)** — a ship date on the order with a delivery window, resolving to a specific dock appointment at Meridian's end; in practice must leave our dock **one day ahead** for freight. *\"Not just 'shipped this week.'\"*\n- *Consequence of a miss* **(spelled out; unquantified ⚠)** — a fine, *\"I don't see the number, that's commercial's problem, but I hear about it\"*; and worse, a tracked on-time percentage with a delisting threat — *\"that's happened to a competitor of ours, so it's not an empty threat, and it's why the rule is absolute.\"*\n- *Depends on* — A8, A9, A10, B3, C4, C5, P1, P2.\n\n**O3 — Changeover hours**\n- *Question* **(spelled out)** — crew-hours spent washing down instead of filling: *\"every hour the crew spends washing down is an hour not filling anything.\"*\n- *Depends on* — A4, A5, A6, A7, E4, C2, P3.\n- *\"Better\"* **(named)** — fewer. Direction only; no target. ⚠\n\n**O4 — \"How ugly the sheet looks\"**\n- *Question* **(spelled out)** — *\"are there gaps where a line's sitting idle for no good reason.\"*\n- *\"Better\"* **(her words; explicitly not a number)** — *\"that last one's not a number, it's more a gut check, but it's real.\"*\n- *Depends on* — E3, C2, P3, P4, A4–A7. IR-only; see §3.\n\n**Trade-off among O2 / O3 / non-Meridian lateness** **(spelled out as a rule; deliberately unquantified ⚠)** — four changeover hours against one distributor order two days late: *\"honestly, yes, I'd take that trade most of the time\"*, a slip being *\"an annoyed phone call from our sales rep, not a fine.\"* But *\"'most of the time' is doing a lot of work in that sentence\"* — the same distributor slipping three weeks running *\"start[s] asking for a discount.\"* Soft, not infinitely soft, decaying with repetition on one customer. **Deposit:** *\"that's genuinely a 'sit down with commercial' conversation, nobody's ever made me quantify it.\"*\n\n---\n\n### 1.2 Entity types\n\n**E1 — Order (in the demand book)**\n- *Distinctions* **(spelled out)** — Meridian vs non-Meridian (flagged on the order; it *\"jumps to the top of my attention\"*); family, which drives allocation and changeover.\n- *State riding along* **(spelled out)** — SKU, quantity, due date + delivery window, Meridian flag, family: **base white / tinted colour / specialty clear**. *\"That's not my judgment, that's how the SKU's classified in the system, it drives what changeover you need going in and out.\"*\n- *Population* — ⚠ not obtained.\n\n**E2 — Batch**\n- *Distinctions* **(spelled out)** — inherits its order's family.\n- *Relation to E1* **(spelled out)** — *\"mostly the order is the batch, if it fits a reasonable run size\"*; split into two batches at different times when a distributor orders *\"more than makes sense in a single run\"* or to interleave something urgent. *\"Not a strict one-to-one — I have the freedom to split if I need to.\"*\n- *Population* — ⚠ run sizes, split cost not obtained.\n\n**E3 — Line** *(contended resource)*\n- *Distinctions* **(spelled out)** — **Line 1**: *\"the old workhorse — slower but it's qualified for everything, including specialty\"*; crew say it's *\"fussier to get properly clean.\"* **Line 2**: *\"the fast one, that's your big-volume runner.\"* **Line 3**: *\"the newest and quickest, but it's still being qualified product by product, so it can't run everything yet\"* — so far *\"mostly one or two SKUs.\"*\n- *State riding along* **(spelled out)** — the family the line is currently dirty with (selects the changeover, F3); its qualification set.\n- *How many* **(number)** — 3.\n\n**E4 — Changeover tech** *(contended resource)*\n- *Distinctions* **(named)** — none drawn; treated as interchangeable (ledger #8).\n- *State riding along* **(spelled out)** — which line they're committed to; can be *\"pulled away partway through\"*, and on long soaks *\"might duck off to start something on another line.\"*\n- *How many* **(number)** — 2 on day shift for all three lines. *\"That's it. No dedicated tech per line.\"*\n\n**E5 — QA lab**\n- ⚠ nothing obtained but its existence, that every batch passes through, and that it *\"gets backed up on a Friday afternoon.\"* Whether it queues like the techs is open — and load-bearing for O2 by her own diagnosis: *\"half the time a 'late' order was actually sitting done in QA hold waiting for the lab to get to it.\"*\n\n---\n\n### 1.3 Boundary conditions\n\n**B1 — ERP weekly pull** — *starting state* **(spelled out)**: orders come from ERP on the weekly pull with SKU, quantity, due date, Meridian flag. *Arrival pattern* — ⚠ **not obtained** (demanded: spread).\n\n**B2 — Mid-week drop-in order and the heads-up before it** — ⚠ **not obtained** (demanded: spread). Only the anecdote: *\"I had a heads-up another same-family white order was about to drop in from a distributor.\"* Who, how far ahead, how often right: all unknown. **This is the trigger O1 hangs on.**\n\n**B3 — Meridian dock appointment** — *pattern* **(spelled out, qualitative)**: ship date + delivery window on the order, resolving to a specific appointment their end. Lead-time distribution ⚠.\n\n**B4 — Tech availability** — **partially spelled out**: two techs, **day shift**. Coverage outside day shift ⚠ (ledger #5).\n\n**B5 — Line 3 qualification set** — ⚠ *\"mostly one or two SKUs\"*; which ones, unknown.\n\n---\n\n### 1.4 Activities\n\n**A1 — Lands in the demand book.** Needs the weekly pull; produces an order in the book, flagged or not; unattended (ERP); instantaneous. **spelled out**\n\n**A2 — Allocate to a line.** Needs an order; produces an assignment; performed by Marta; not a schedule constraint — for Meridian whites *\"that's not really a decision.\"* Rule: P1. **spelled out**\n\n**A3 — Reorder the queue.** Needs an order behind others; produces a changed sequence; performed by Marta. *\"Sometimes I'll reorder things a bit so it doesn't get stuck behind a big changeover.\"* Rule: P4. **spelled out**\n\n**A4 — Quick rinse, same family (white→white), Line 2**\n- *Needs* — previous batch off, a tech free, next SKU same family. *Produces* — *\"the fill head's actually running clean product again.\"*\n- *Performed by* **(named)** — one tech.\n- *Duration, line down* **(spread)** — **typical 25 min**; **worse 45 min**, *\"usually because the tech's tied up finishing something on another line first and there's a wait before they even start on Line 2\"*; **better 15 min**, *\"if the tech's standing right there and it's a genuinely easy one.\"*\n- *Crew hands-on* **(spelled out)** — equals line-down: *\"the tech's on it start to finish, no gap between 'crew starts' and 'line stops.'\"*\n- *Mode-change loss* — this activity **is** the loss.\n- *Varies by type* **(named)** — yes, by family-pair (F3). By line: ⚠ ledger #1, #2.\n\n**A5 — White → tint, Line 2** — *\"the easier direction\"*\n- *Performed by* **(named)** — one tech.\n- *Duration, line down* **(spread)** — **typical 45 min**; **worse \"an hour and a bit\"** (ledger #3), *\"if the tech gets pulled away partway through\"*; **better ~30 min**, *\"if everything's staged.\"*\n- *Crew hands-on* **(spelled out, qualitative)** — *\"hands-on for most of it — this one doesn't have much soak-and-wait, it's mostly just doing the work.\"* Fraction: ledger #4.\n\n**A6 — Tint → white, Line 2, full washdown** — *\"the ugly one\"*\n- *Needs* — as A5 plus a **passing visual check** before release to production.\n- *Duration, line down* **(spread)** — **typical ~3 h**; **worse 4 h \"maybe a bit more\"** (ledger #3), *\"if it doesn't pass the visual check first time and they have to redo part of it\"*; **better ~2 h**, *\"a clean fast one… if the crew's good and nothing complicates it.\"*\n- *Crew hands-on* **(spelled out, qualitative; her own hedge preserved)** — *\"less than the 3 hours suggests — there's real soak and rinse-cycle time where the tech's not standing there… I'd guess they're actually working maybe half of that.\"* Fraction: ledger #4.\n- *Rationale* **(spelled out)** — *\"any pigment left behind ruins a white batch, so it's a full washdown.\"*\n- **Asymmetry is load-bearing** — *\"It absolutely depends on direction — that's the thing people forget… it is absolutely not symmetric, and it trips people up if they assume it is.\"*\n\n**A7 — Into / out of specialty clear, Line 1**\n- *Duration, line down* **(spread)** — **typical 2 h**, *\"roughly the same both directions, unlike white/tint\"*; **worse 3 h**, *\"if it's coming out of clear and they're being extra careful about residue, since clear can be sneaky — you don't always see it the way you'd see pigment\"*; **better 1.5 h**, *\"a quick swap and the line was already fairly clean.\"*\n- *Crew hands-on* **(spelled out, qualitative)** — *\"most of that — specialty doesn't have the long soak cycles… it's more just physically thorough cleaning because the product's thick and clingy.\"* Fraction: ledger #4.\n\n**A8 — Run the batch** — mix, mill, tint (or *\"straight through if it's a plain white\"*), fill, pack.\n- *Needs* **(spelled out)** — clean line in the right family state; batch released to run. *Produces* **(spelled out)** — filled and packed batch.\n- *Performed by* — ⚠ line operators never elicited as a resource.\n- *Duration* — ⚠ **nothing obtained** (demanded: spread, per family and per line).\n- *Varies by type* — partially: *\"for a white that's usually the more straightforward path\"*, but no durations attach.\n- **The largest hole in the model.** O1 is a question about a week; run time is most of a week.\n\n**A9 — QA hold and release** — *\"every batch does.\"*\n- *Performed by* **(named)** — the lab (E5).\n- *Duration* — *\"typically a few hours before it's released\"*: an honest **number at the wrong precision**; demanded as a **spread**. ⚠\n- *Failure path* — ⚠ never asked.\n- *Pathology* **(spelled out qualitatively; rate ⚠)** — *\"if QA's backed up on a Friday afternoon, that's where it actually goes sideways, not on the line\"*; *\"the QA step is the one people don't think about when they're mad at scheduling.\"*\n\n**A10 — Stage for shipping and ship.** Needs QA release; produces the order off the dock; *\"that's when the truck appointment matters.\"* Constraint C4. Duration ⚠.\n\n**A11 — Tech pulled away mid-changeover** *(event, not step)* — named as the mechanism behind A4's and A5's worse tails. *Rate* ⚠ not obtained separately; currently only implicit in those tails (P01 unsatisfied).\n\n**A12 — Washdown fails the visual check, part redone** *(event, not step)* — named as the mechanism behind A6's 4 h tail. *Rate* ⚠ (ledger #7).\n\n**A13 — \"The mill motor issue\"** *(event, named in passing only)* — offered as an example of what a *structural* line difference would look like, in contrast to Line 1 merely being fussier. Rate ⚠, duration ⚠, consequence ⚠. This is the entirety of the breakdown stratum, which was never swept.\n\n---\n\n### 1.5 Ordering / flow\n\n**F1 — The main arc, desk to dock** **(spelled out — her six steps)**\n1. Lands in the demand book (ERP weekly pull).\n2. Allocated to a line (*\"Meridian whites always go to Line 2\"*).\n3. Sits in the queue behind whatever's running — reorderable (A3/P4).\n4. Changeover if needed (F3), then runs: mix, mill, tint-or-straight-through, fill, pack.\n5. QA hold.\n6. Released, staged, out against the truck appointment.\n\n**F2 — Order-to-batch split** — *order* **(spelled out)**: one batch by default, possibly two run at different times. *Branch decided by* **(spelled out)**: Marta, on run size or urgency-interleaving. *Cost of a split* ⚠ (P03 unresolved).\n\n**F3 — Which changeover applies** **(spelled out)** — by (family on the line, family of next batch, line): same family → **A4**; white→tint → **A5**; tint→white → **A6**; into/out of specialty → **A7** (Line 1 only).\n\n---\n\n### 1.6 Policies\n\n**P1 — \"Meridian whites always go to Line 2, that's just how it's done here.\"** *Practiced* **(spelled out)**; a fixed allocation, not a decision. Overrides ⚠ never asked.\n\n**P2 — Meridian on-time is absolute.** *Practiced* **(spelled out)** — *\"we don't even try to be clever about it.\"* Overrides **(spelled out)**: none — that is the policy's content. Rationale: fine, on-time percentage, delisting precedent.\n\n**P3 — Who gets the tech when two lines want one**\n- *Prescribed form:* **none exists** — *\"there's no posted rule at all.\"*\n- *As practiced* **(spelled out)** — in the room: *\"whoever's louder at the huddle, or whoever's about to actually run dry.\"* The underlying logic: *\"it's mostly gut triage: whichever line has the more time-sensitive order behind it wins, and if that's a tie, whichever changeover is faster wins so you get a line moving sooner.\"*\n- *Borderline case on record* — Line 1 and Line 3 both wanted a washdown one morning. **Line 3 got the tech**, *\"not because it was more important, but because Line 3's changeover was the quick one and Line 1's was going to be the long tint-to-white slog anyway, so the thinking was 'knock out the fast one, get that line moving, then commit the tech to the long one.'\"* Line 1 sat **clean-but-waiting almost 40 minutes**.\n- *What overrides it* **(spelled out)** — the ops director: *\"I've been overruled by the ops director once when he wanted his pet SKU out the door.\"*\n- *Rationale* **(spelled out)** — *\"the crew's a shared resource and sometimes there's a queue for them before the clock even starts on the line\"* — *\"the bit that actually causes grief at the huddle.\"*\n\n**P4 — Reorder so a job isn't stuck behind a big changeover.** *Practiced* **(spelled out)**. Overrides ⚠.\n\n**P5 — Hold the line for an anticipated same-family order** *(the decision under test)*. *Practiced, one instance* **(spelled out)** — hold Line 2 idle *\"maybe an hour\"* rather than wash down for the waiting tint, *\"because doing them back to back would save us a full washdown.\"* Trigger strength and holding threshold ⚠ (depends on B2).\n\n**P6 — Batch-split discretion.** *Practiced* **(spelled out)** — *\"I have the freedom to split if I need to.\"* Overrides ⚠.\n\n---\n\n### 1.7 Constraints\n\n**C1 — Line qualification.** *Limit* **(partially spelled out)** — Line 1 everything incl. specialty; Line 3 product-by-product, *\"can't run everything yet\"* (which SKUs ⚠); Line 2's set ⚠. *When hit* **(spelled out)** — the batch cannot go on that line.\n\n**C2 — Two techs, three lines.** *Limit* **(spelled out)**. *When hit* **(spelled out)** — *\"if Line 1 and Line 3 both want a washdown at the same time, one of them waits\"* — clean-but-idle, 40 min in the recorded case; resolved by P3.\n\n**C3 — Tint→white needs a full washdown passing a visual check.** *When hit* **(spelled out)** — *\"any pigment left behind ruins a white batch\"*; a failed check means part is redone (A12).\n\n**C4 — Meridian must leave our dock a day ahead of the appointment.** *When hit* **(spelled out)** — fine, on-time percentage damage, delisting exposure.\n\n**C5 — Every batch passes QA hold before release.** *When hit* **(spelled out)** — nothing ships unreleased; it waits in hold.\n\n**Unwritten constraints** — ⚠ the closing sweep was never run. The one that surfaced unprompted is the changeover asymmetry: *\"that one catches everybody, including people who've been on the floor a lot longer than me.\"*\n\n---\n\n### 1.8 Dynamics\n\n**None.** Nothing described evolves continuously while nothing discrete happens. The soak and rinse-cycle time inside A6 is dead time *within* an activity, not a state variable crossing a threshold; I have deliberately not promoted it to one.\n\n---\n\n### 1.9 Data bindings *(named only — project to nothing today)*\n\n| Feed | Would drive | Provenance |\n|---|---|---|\n| Changeover logs (tech start/finish) | A4–A7 durations, crew hands-on fractions; retires ledger #1, #4 | **Qualified:** *\"I've never audited that field myself, I mostly just glance at duration.\"* Coverage unknown, possibly patchy; **Line 1 and Line 3** named as where to look. Marta will flag it to the two techs. |\n| ERP demand book | B1, B2 | not discussed |\n| QA release timestamps | A9 duration, lab queueing | not discussed |\n| Meridian on-time percentage | O2 | tracked by Meridian; visible to commercial |\n\n**Finding in its own right:** patchy changeover logging concentrated on Lines 1 and 3 is evidence about the plant, not merely an obstacle — *\"that itself would be useful for you to know, not just an inconvenience.\"*\n\n---\n\n### 1.10 Validation criteria\n\n⚠ **None obtained.** How Marta would know the model is right was never asked.\n\n---\n\n## 2. Assumption ledger\n\nEverything here is mine. None of it is hers.\n\n| # | Assumption | Why | How to check |\n|---|---|---|---|\n| **1** | Line 1 changeover durations = Line 2 × **1.2**, all types | She could not give Line 1 minutes — *\"I couldn't swear the minutes are identical… the crew sometimes says it's fussier.\"* I proposed 20%; she replied *\"20% sounds about right, not double.\"* **The factor originated with me**; her assent is not authorship. | Changeover logs, Line 1 vs Line 2, same family-pair. **Blocked by the unaudited start/finish field — and Line 1 is one of the two lines she expects to be patchy.** |\n| **2** | Line 3 changeover durations = Line 2, unscaled | *\"Line 3 I genuinely don't have a good feel for… you're stuck assuming it's like Line 1 or Line 2.\"* She offered the disjunction; **picking Line 2 was mine.** | As #1, once Line 3 has run more products. Also expected patchy. |\n| **3** | \"An hour and a bit\" (A5 worse) = **70 min**; \"4, maybe a bit more\" (A6 worse) = **4.5 h** | Numeric readings so the spreads are usable. | One question to Marta: confirm or correct. |\n| **4** | Crew hands-on: A4 = **1.0**, A5 = **0.8**, A6 = **0.5**, A7 = **0.8** | A4's 1.0 is hers, stated. A6's 0.5 tracks *\"maybe half of that\"* — but note her hedge, *\"I'd guess.\"* **The two 0.8s, from \"most of it\" / \"most of that\", are mine.** | Changeover logs vs tech time records, or ask the techs. Same blocker as #1. |\n| **5** | No changeover outside day shift | She said *\"two techs on **day shift**\"*; other coverage never asked. | One question to Marta. |\n| **6** | A changeover needs exactly **one** tech | She said *\"the tech\"*, singular, throughout — including the 3-hour washdown. | One question to Marta or the techs. |\n| **7** | A12 folded **inside** A6's 4 h tail rather than a separate event with its own rate | She described it as *the cause of* the tail. Keeps the spread self-contained; contrary to P01, which would separate rate from duration. | Ask how often the visual check fails first time; split it out if common. |\n| **8** | The two techs are **interchangeable** | She drew no distinction. | One question to Marta. |\n\n**Second-order note on #1 and #4:** their check depends on a feed of unverified coverage, concentrated exactly where the assumptions bite. If the field proves patchy on Line 1, the honest move is to **widen** them, not fill them in.\n\n---\n\n## 3. What the model leaves out, and why\n\n**Deliberately excluded**\n- **Queues, buffers, waiting states** are not nodes — the wait behind a running batch, the wait for a tech, the wait in QA hold. Each is implied by the activities either side and emerges in projection. Line 1's 40 minutes clean-but-waiting is an **output** the model should reproduce, not an input.\n- **The commercial layer** — fine amount, on-time percentage mechanics, delisting threshold. C4 and O2 carry the hard deadline; the money is outside the scheduler's sight and commercial owns it.\n- **Individual tech identity** (ledger #8). **Scenarios** — assembled from B1–B5 at simulation time, not elicited.\n\n**Real, and the formalism cannot carry it — kept in words**\n- **O4, \"how ugly the sheet looks.\"** A criterion she genuinely uses and explicitly refuses to number. Approximating it as line idle hours would be my move; I have not made it.\n- **The O2 / O3 / lateness trade-off weight.** Unquantified with the source named. The model can report changeover hours, Meridian lateness and distributor lateness **separately**, but cannot rank two schedules that trade one against another — a real limit on O1, whose \"costs less\" implicitly spans them.\n- **The decay of softness** — the same distributor slipping *\"the third week running\"* turning into a discount demand: a memory effect across weeks on one customer, stated as a rule, unquantified, unrepresented.\n- **The huddle.** *\"Whoever's louder\"* and the ops director's pet-SKU override are the real P3 in the room. The triage logic is compilable; loudness and the override are not. **Any run of this model will be quieter and more rational than the plant.** Remember that when a result looks tidy.\n\n---\n\n## 4. What remains unknown, in the order I would close it\n\n1. **A8 run duration** — nothing at all, per family and per line, as a spread. **Nothing about O1 is answerable until this exists.**\n2. **B2, the drop-in and the heads-up** — who, how far ahead, how often right. P5 is the decision under test and its trigger is one anecdote.\n3. **A9 QA hold** — *\"a few hours\"* is honest at the wrong precision; and whether the lab queues like the techs. By her own account this is where lateness actually comes from, so it bears directly on O2.\n4. **B1** — orders per weekly pull and within-week shape.\n5. **E2 / F2** — run sizes, the \"reasonable run size\" threshold, and what a split costs in extra changeovers.\n6. **C1 / B5** — which SKUs Line 3 is qualified for; whether Line 2 has restrictions.\n7. **Breakdowns and interruptions** — the whole stratum. A13 is a name with no rate, duration or consequence; A11 and A12 need rate separated from duration.\n8. **Unwritten-constraint sweep** and **validation criteria** — neither was run.\n\n**Status against the completion criteria**\n- **Static floor: satisfied** — 4 objectives, 5 entity types, 13 activities, 3 ordering/flow nodes.\n- **O2, O3:** slices substantially satisfied except A8 and A9 durations.\n- **O1: slice incomplete.** A8 has no duration; B2 has no arrival pattern. O1 is currently **answerable only for Line 2**, and only once run times exist. Ledger #1–#4 are the first assumptions to attack if any Line 1 or Line 3 result ever looks decisive.\n- **O4:** recorded; unsupported for quantitative use, by its author's own description.\n\n**What I do not claim.** I have elicited a model, not built a net. The SDCPN scaffold, the code-obligation sidecar and the typed loss report are derived from this model by the tooling's projection — I have not written them, and I am not claiming this loads, compiles, or runs. The A8 hole alone would stop it.\n\n---\n\n*Session closed at the expert's stop. Three questions queued for resumption: run duration for a plain white on Line 2 (typical / one-in-ten worse / one-in-ten better); the heads-up mechanism behind B2; QA hold as a spread, and whether the lab queues.*"
+    }
+  ]
+}
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5-captures.json b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5-captures.json
new file mode 100644
index 00000000000..134268ce2f3
--- /dev/null
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5-captures.json
@@ -0,0 +1,9292 @@
+{
+  "captures": [
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option actually loses less",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Stated as the decision the model must settle: given a line-down event with unknown ETA, which of the available scheduling options loses less.",
+          "assertion": {
+            "value": "When a line goes down with ETA unknown, be able to enter that state and have the model say which option — wait out the repair, or move the order to the other line — actually loses less, instead of the scheduler doing gut math at the huddle."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"When a line goes down with ETA unknown, be able to enter that state and have the model say which option — wait out the repair, or move the order to the other line — actually loses less, instead of the scheduler doing gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the decision the model must settle: given a line-down event with unknown ETA, which of the available scheduling options loses less.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option actually loses less",
+          "slot": "what \"better\" means, and trade-off weights",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Expert gave a lexicographic scorecard with an explicit refusal of a formula for the second tier.",
+          "assertion": {
+            "value": "First and non-negotiable: days late on the Meridian order, where anything above zero is bad. Below that, weighed together with no formula: washdown hours, and whether the bumped order goes late and by how much — with judgment applied to who the customer is and who can absorb the slip (a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem)."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-76159984-4b11-446f-a707-bc8302ef0b1d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First and non-negotiable: days late on the Meridian order, where anything above zero is bad. Below that, weighed together with no formula: washdown hours, and whether the bumped order goes late and by how much — with judgment applied to who the customer is and who can absorb the slip (a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem).\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Expert gave a lexicographic scorecard with an explicit refusal of a formula for the second tier.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option actually loses less",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "The scorecard names the washdown, the line-down event, and the orders with their due dates and customers as what the answer is computed from.",
+          "assertion": {
+            "value": [
+              "activity:tint-to-white washdown",
+              "activity:Line 2 filler jam",
+              "entity-type:order",
+              "entity-type:line"
+            ]
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-3f2444d5-8001-46d9-8a92-c85f8c6f8d6a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:tint-to-white washdown\",\"activity:Line 2 filler jam\",\"entity-type:order\",\"entity-type:line\"]},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard names the washdown, the line-down event, and the orders with their due dates and customers as what the answer is computed from.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "how long it takes",
+          "precision": "number",
+          "sourceRegime": "practiced",
+          "rationale": "Expert gave a single figure, not a spread; the low/high and typical are not yet on record.",
+          "assertion": {
+            "value": "three hours"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"three hours\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Expert gave a single figure, not a spread; the low/high and typical are not yet on record.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Expert stated the outcome as consuming crew time and blocking the line for the window.",
+          "assertion": {
+            "value": "Consumes crew time and takes Line 1 out of anything else for that window; afterwards the line is in white rather than tint."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-053410a5-6574-4355-aabf-dd972f0088e1",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Consumes crew time and takes Line 1 out of anything else for that window; afterwards the line is in white rather than tint.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Expert stated the outcome as consuming crew time and blocking the line for the window.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Stated as the consequence of pulling a line off a tint run to run a white order; the full precondition list was not elicited.",
+          "assertion": {
+            "value": "A line currently running a tint that is to be switched to a white order — pulling Line 1 off its tint run to cover Meridian white incurs the washdown."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-e86ee1d3-dbbd-4e2d-b1c0-a8ac719f0e58",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line currently running a tint that is to be switched to a white order — pulling Line 1 off its tint run to cover Meridian white incurs the washdown.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the consequence of pulling a line off a tint run to run a white order; the full precondition list was not elicited.\",\"slot\":\"what it needs before it can start\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what is lost when it changes the system's mode",
+          "precision": "number",
+          "sourceRegime": "practiced",
+          "rationale": "Loss named for the tint-to-white transition specifically, as a single figure plus crew time; other transitions were not yet asked about.",
+          "assertion": {
+            "value": "Three hours of the line plus crew time for the tint-to-white transition; the bumped order may itself go late as a knock-on."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-04d27279-48f8-437e-8688-14c400f3f0f1",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of the line plus crew time for the tint-to-white transition; the bumped order may itself go late as a knock-on.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Loss named for the tint-to-white transition specifically, as a single figure plus crew time; other transitions were not yet asked about.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "Line 2 filler jam",
+          "slot": "how long it takes",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Expert described two kinds of repair — half an hour and half a shift — and one observed instance of about two hours; quantiles not yet elicited.",
+          "assertion": {
+            "value": "Repairs come in a \"half hour\" kind and a \"half a shift\" kind; the recent instance came back in about two hours."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I went with waiting, it came back in about two hours, we just scraped the Thursday due date.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-7d1cb932-a1d6-4e1a-86a7-984a9d53af80",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Repairs come in a \\\"half hour\\\" kind and a \\\"half a shift\\\" kind; the recent instance came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"Line 2 filler jam\",\"precision\":\"range\",\"rationale\":\"Expert described two kinds of repair — half an hour and half a shift — and one observed instance of about two hours; quantiles not yet elicited.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours, we just scraped the Thursday due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "Line 2 filler jam",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The event takes the line out of production and puts the order sitting on it at risk, forcing a wait-or-move decision.",
+          "assertion": {
+            "value": "Line 2 stops producing until repaired (half a shift lost in the recent case); the order sitting on Line 2 is at risk of its due date, forcing a decision to wait out the repair or shift the order to Line 1."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-330b99df-25fc-4d38-b1f9-6f8da955b79e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 2 stops producing until repaired (half a shift lost in the recent case); the order sitting on Line 2 is at risk of its due date, forcing a decision to wait out the repair or shift the order to Line 1.\"},\"kind\":\"activity\",\"node\":\"Line 2 filler jam\",\"precision\":\"spelled out\",\"rationale\":\"The event takes the line out of production and puts the order sitting on it at risk, forcing a wait-or-move decision.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "Meridian ships on time, full stop",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Stated as an absolute the scheduler protects ahead of all other considerations.",
+          "assertion": {
+            "value": "The Meridian order ships on time, full stop; it is not traded off against washdown hours or other orders' due dates."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-caeeeb12-a91f-46a0-88c2-a622d4d30c55",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The Meridian order ships on time, full stop; it is not traded off against washdown hours or other orders' due dates.\"},\"kind\":\"policy\",\"node\":\"Meridian ships on time, full stop\",\"precision\":\"spelled out\",\"rationale\":\"Stated as an absolute the scheduler protects ahead of all other considerations.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "Meridian ships on time, full stop",
+          "slot": "what overrides it",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Expert named the sole override in general terms; the practiced test for \"no way through\" is not yet on record.",
+          "assertion": {
+            "value": "Only when there is truly no way through; otherwise nothing overrides it."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "that's a line I won't cross unless there's truly no way through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I use judgment on who can absorb the slip",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-422d7f74-a119-45d6-8261-3c71b50af7f7",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Only when there is truly no way through; otherwise nothing overrides it.\"},\"kind\":\"policy\",\"node\":\"Meridian ships on time, full stop\",\"precision\":\"spelled out\",\"rationale\":\"Expert named the sole override in general terms; the practiced test for \\\"no way through\\\" is not yet on record.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Orders are treated apart by colour class (white vs tint, which drives washdown) and by customer class (distributor / small account / awkward account that gets prickly).",
+          "assertion": {
+            "value": "Orders differ by colour class — white versus tint, which decides whether a washdown is incurred — and by customer, sorted into a distributor (sliding two days is a shrug), a small account (sliding a week is fine), and an awkward account that gets prickly."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "We had a Meridian white order due Thursday sitting on Line 2",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-f2a03b6c-0420-48a7-85be-bdcb3536a6f7",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders differ by colour class — white versus tint, which decides whether a washdown is incurred — and by customer, sorted into a distributor (sliding two days is a shrug), a small account (sliding a week is fine), and an awkward account that gets prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Orders are treated apart by colour class (white vs tint, which drives washdown) and by customer class (distributor / small account / awkward account that gets prickly).\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "state that rides along with each instance",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Each order is spoken of as carrying a due date, a customer, a colour, and the line it is sitting on.",
+          "assertion": {
+            "value": "Its due date (e.g. due Thursday), its customer (e.g. Meridian), its colour (white or tint), and which line it is sitting on."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "We had a Meridian white order due Thursday sitting on Line 2",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "does it slide past its own due date, and if so by how much and who's the customer",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-c9ac976a-3eef-4a77-8e29-3598b184b450",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Its due date (e.g. due Thursday), its customer (e.g. Meridian), its colour (white or tint), and which line it is sitting on.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Each order is spoken of as carrying a due date, a customer, a colour, and the line it is sitting on.\",\"slot\":\"state that rides along with each instance\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "line",
+          "slot": "how many there are, or the population's shape",
+          "precision": "named",
+          "sourceRegime": "practiced",
+          "rationale": "Line 1 and Line 2 named; whether these are the only lines has not been asked.",
+          "assertion": {
+            "value": "Line 1 and Line 2 named so far; total count not yet confirmed."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-6bc324a5-2e12-4070-8275-fdfe819923e6",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2 named so far; total count not yet confirmed.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"named\",\"rationale\":\"Line 1 and Line 2 named; whether these are the only lines has not been asked.\",\"slot\":\"how many there are, or the population's shape\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "line",
+          "slot": "state that rides along with each instance",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "A line is spoken of as carrying what it is currently running (its colour state) and whether it is down.",
+          "assertion": {
+            "value": "What it is currently running — e.g. mid-run on a tint, which sets the colour it would have to be washed down from — and whether it is jammed/down awaiting repair."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 1 was mid-run on a tint.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Line 2 filler jammed at about nine in the morning",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-b003fc51-0ade-4721-b400-b7b68edf8c60",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"What it is currently running — e.g. mid-run on a tint, which sets the colour it would have to be washed down from — and whether it is jammed/down awaiting repair.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"spelled out\",\"rationale\":\"A line is spoken of as carrying what it is currently running (its colour state) and whether it is down.\",\"slot\":\"state that rides along with each instance\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option loses less",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "rationale": "Stated as the concrete decision support the model must give, anchored to the Line 2 filler jam incident.",
+          "assertion": {
+            "value": "Given a disruption in progress (e.g. \"filler's down, ETA unknown\"), which of the available scheduling options — wait out the repair on the down line, or move the order to another line — actually loses less, decided in the moment instead of by gut math at the huddle."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given a disruption in progress (e.g. \\\"filler's down, ETA unknown\\\"), which of the available scheduling options — wait out the repair on the down line, or move the order to another line — actually loses less, decided in the moment instead of by gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the concrete decision support the model must give, anchored to the Line 2 filler jam incident.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option loses less",
+          "slot": "what \"better\" means, and trade-off weights",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Expert explicitly denies having a weighting formula; the ordering is stated, the weights are not.",
+          "assertion": {
+            "value": "Lexicographic: first, days late on the hard-line order (Meridian) — yes/no, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much, and who the customer is. No formula for the second-order trade-off — \"how bad is bad\", judged by who can absorb the slip."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-de512bde-aa52-4147-933f-81439aa5ec6d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lexicographic: first, days late on the hard-line order (Meridian) — yes/no, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much, and who the customer is. No formula for the second-order trade-off — \\\"how bad is bad\\\", judged by who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"Expert explicitly denies having a weighting formula; the ordering is stated, the weights are not.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option loses less",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "The scorecard names on-time delivery, washdown hours, lateness of the bumped order, and the repair outcome; the judgment of who can absorb a slip is the tiebreaker.",
+          "assertion": {
+            "value": [
+              "constraint:Meridian on time",
+              "activity:tint-to-white washdown",
+              "activity:filler jam",
+              "entity-type:order",
+              "entity-type:line",
+              "policy:who can absorb the slip"
+            ]
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a6e8dc50-fffb-494d-8bd2-59704c0427e4",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"constraint:Meridian on time\",\"activity:tint-to-white washdown\",\"activity:filler jam\",\"entity-type:order\",\"entity-type:line\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard names on-time delivery, washdown hours, lateness of the bumped order, and the repair outcome; the judgment of who can absorb a slip is the tiebreaker.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "rationale": "Colour class changes the process at the tint stage; customer type changes how lateness is weighed.",
+          "assertion": {
+            "value": "An order is a line item in the demand book from ERP. Treated apart by: product colour class — white (tint stage is barely there, a pass-through rather than a real letdown step) versus tint/specialty; and by customer type — distributor (a two-day slide is a shrug), small account (a week is fine), and awkward accounts that get prickly."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-3cb49f42-f479-4b67-be4c-22c8f9771f6e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order is a line item in the demand book from ERP. Treated apart by: product colour class — white (tint stage is barely there, a pass-through rather than a real letdown step) versus tint/specialty; and by customer type — distributor (a two-day slide is a shrug), small account (a week is fine), and awkward accounts that get prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Colour class changes the process at the tint stage; customer type changes how lateness is weighed.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "state that rides along with each instance",
+          "precision": "spelled out",
+          "rationale": "Named directly as what the demand-book line item carries, extended by the allocation step and the account-based lateness judgment.",
+          "assertion": {
+            "value": "Quantity, due date, SKU; plus the line and week-slot it has been allocated to on the sheet; plus the customer/account it belongs to."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-5628ca29-5985-4005-aa3f-a6885dc38223",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; plus the line and week-slot it has been allocated to on the sheet; plus the customer/account it belongs to.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Named directly as what the demand-book line item carries, extended by the allocation step and the account-based lateness judgment.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "line",
+          "slot": "the distinctions the process treats apart",
+          "precision": "named",
+          "rationale": "Lines are contended for between orders in the decision described.",
+          "assertion": {
+            "value": "Production lines, referred to individually as Line 1 and Line 2; an order is allocated to a specific line and a line can be mid-run on another order."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-6d4d1074-f6fe-4d4c-95c2-f242a6f98233",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Production lines, referred to individually as Line 1 and Line 2; an order is allocated to a specific line and a line can be mid-run on another order.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"named\",\"rationale\":\"Lines are contended for between orders in the decision described.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "line",
+          "slot": "how many there are, or the population's shape",
+          "precision": "named",
+          "rationale": "Only the two lines involved in the incident were named; the plant's full line count was never asked.",
+          "assertion": {
+            "value": "At least two lines named: Line 1 and Line 2. Total line count not stated."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "whether to shift it to Line 1 or just wait out the repair",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "We had a Meridian white order due Thursday sitting on Line 2",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a0b65576-83d8-4134-9fbe-9b059663ae12",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"At least two lines named: Line 1 and Line 2. Total line count not stated.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"named\",\"rationale\":\"Only the two lines involved in the incident were named; the plant's full line count was never asked.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whether to shift it to Line 1 or just wait out the repair\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "order flow from demand book to shipment",
+          "slot": "the order things happen in",
+          "precision": "spelled out",
+          "rationale": "Given verbatim as the end-to-end sequence for the Meridian white order.",
+          "assertion": {
+            "value": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (fill and pack) → QA hold → release and ship. Four steps if QA and shipping are counted as one, five if split."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (fill and pack) → QA hold → release and ship. Four steps if QA and shipping are counted as one, five if split.\"},\"kind\":\"ordering/flow\",\"node\":\"order flow from demand book to shipment\",\"precision\":\"spelled out\",\"rationale\":\"Given verbatim as the end-to-end sequence for the Meridian white order.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "rationale": "Stated as the trigger for the order becoming something to schedule.",
+          "assertion": {
+            "value": "A line item in the demand book, produced by ERP, carrying quantity, due date and SKU."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book, produced by ERP, carrying quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the trigger for the order becoming something to schedule.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Directly stated as the outcome of step one.",
+          "assertion": {
+            "value": "The order is slotted onto a specific line and a slot in the week, on the sheet."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "allocate it onto a line and a slot in the week",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-fa56fa8b-611a-4a38-9a42-1bd038e52d80",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a specific line and a slot in the week, on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Directly stated as the outcome of step one.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "First person throughout; role stated at the outset.",
+          "assertion": {
+            "value": "The master scheduler (the expert), working on the sheet."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I'm the master scheduler at a coatings plant.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 1,
+            "entryEnd": 1
+          },
+          "source": "user"
+        },
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-dba4ec08-0265-420c-95d2-4dce250ae0b6",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler (the expert), working on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"named\",\"rationale\":\"First person throughout; role stated at the outset.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm the master scheduler at a coatings plant.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":1,\\\"entryStart\\\":1,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "mix/mill/tint/fill",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Stated as the production step common to all products.",
+          "assertion": {
+            "value": "Runs the order through four stages every product goes through — mix, mill, tint, fill and pack — producing filled and packed product that comes off the fill line."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-0b2046b4-55c8-4ce3-abac-296d6abe469d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Runs the order through four stages every product goes through — mix, mill, tint, fill and pack — producing filled and packed product that comes off the fill line.\"},\"kind\":\"activity\",\"node\":\"mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the production step common to all products.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "mix/mill/tint/fill",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
+          "rationale": "Explicit type-dependence at the tint stage; stage durations themselves not yet given.",
+          "assertion": {
+            "value": "Yes — the stages are the same for every product, but for a white the tint stage is barely there, a pass-through rather than a real letdown step."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-8156b872-b3c2-43db-aa67-56166bebe556",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — the stages are the same for every product, but for a white the tint stage is barely there, a pass-through rather than a real letdown step.\"},\"kind\":\"activity\",\"node\":\"mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Explicit type-dependence at the tint stage; stage durations themselves not yet given.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "rationale": "Stated as the precondition and the waiting arrangement.",
+          "assertion": {
+            "value": "The order has come off the fill line; it then sits in the lab's queue awaiting check."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order has come off the fill line; it then sits in the lab's queue awaiting check.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the precondition and the waiting arrangement.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Release is the stated outcome of the QA hold.",
+          "assertion": {
+            "value": "The order is checked and then released, after which it goes to the warehouse and ships against the due date."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "sits in the lab's queue, gets checked",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-589bc2db-8fc9-4d65-8024-b34ce4cd736a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is checked and then released, after which it goes to the warehouse and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Release is the stated outcome of the QA hold.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "Named as the owner of the queue and the check.",
+          "assertion": {
+            "value": "The lab."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "sits in the lab's queue, gets checked",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-07de77cc-9de8-41e9-92f6-8fe06a6263c9",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Named as the owner of the queue and the check.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "how long it takes",
+          "precision": "named",
+          "rationale": "Hedged quantifier only; not yet a usable spread.",
+          "assertion": {
+            "value": "Usually a few hours for a white; longer for specialty (\"nothing like the specialty wait\"). No figures for typical, one-in-ten worse or one-in-ten better yet."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; longer for specialty (\\\"nothing like the specialty wait\\\"). No figures for typical, one-in-ten worse or one-in-ten better yet.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Hedged quantifier only; not yet a usable spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
+          "rationale": "Type dependence stated explicitly in the same breath as the duration.",
+          "assertion": {
+            "value": "Yes — a white is usually a few hours, specialty waits are much longer."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a white is usually a few hours, specialty waits are much longer.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Type dependence stated explicitly in the same breath as the duration.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "release and ship",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Final step of the walkthrough; due date is the reference for the objective's lateness metric.",
+          "assertion": {
+            "value": "The released order goes to the warehouse and ships against its due date; lateness is measured as days late against that due date."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The released order goes to the warehouse and ships against its due date; lateness is measured as days late against that due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"rationale\":\"Final step of the walkthrough; due date is the reference for the objective's lateness metric.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "rationale": "Named as the changeover that the tint→white switch forces.",
+          "assertion": {
+            "value": "A line changing over from a tint run to a white run; the line must be pulled off the tint it is mid-run on."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-7df09f81-9c85-43ac-b69e-306d540f8afb",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line changing over from a tint run to a white run; the line must be pulled off the tint it is mid-run on.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Named as the changeover that the tint→white switch forces.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "how long it takes",
+          "precision": "number",
+          "rationale": "A single figure was given, not a spread; recorded at the precision actually reached.",
+          "assertion": {
+            "value": "Three hours (tint-to-white)."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I eat a tint-to-white washdown — three hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-e0f39723-a7e5-4656-a8fb-0e2b50bb82da",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours (tint-to-white).\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"A single figure was given, not a spread; recorded at the precision actually reached.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what is lost when it changes the system's mode",
+          "precision": "number",
+          "rationale": "Loss named for a specific named transition (tint to white); only one figure given.",
+          "assertion": {
+            "value": "Three hours of the line's availability — real cost and crew time — during which the line is out of anything else."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-d8dffb0f-f148-4af2-ba7e-478a6a1b38c6",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of the line's availability — real cost and crew time — during which the line is out of anything else.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Loss named for a specific named transition (tint to white); only one figure given.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Effect on line availability stated directly.",
+          "assertion": {
+            "value": "Puts the line into a state able to run white; the line is unavailable for any other work for the duration."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it takes Line 1 out of anything else for that window",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a2938097-b902-4f24-8e15-70f4b8ce95fb",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Puts the line into a state able to run white; the line is unavailable for any other work for the duration.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Effect on line availability stated directly.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Described as the disruption that forces the scheduling decision.",
+          "assertion": {
+            "value": "The line's filler goes down, stopping the order sitting on that line until the repair completes; the scheduler must then decide to wait it out or shift the order to another line."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I went with waiting, it came back in about two hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-896881a6-c9ec-469f-ab03-4a56b59f6cad",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line's filler goes down, stopping the order sitting on that line until the repair completes; the scheduler must then decide to wait it out or shift the order to another line.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"Described as the disruption that forces the scheduling decision.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "how long it takes",
+          "precision": "range",
+          "rationale": "Two kinds named as the ends plus one observed instance; no typical or one-in-ten figures given, so this is a range, not a spread.",
+          "assertion": {
+            "value": "From about half an hour (\"the 'half hour' kind\") to about half a shift (\"the 'half a shift' kind\"); the recent instance came back in about two hours."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "it came back in about two hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-4a3ae53c-2c2f-4664-9499-7e81c254abc5",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"From about half an hour (\\\"the 'half hour' kind\\\") to about half a shift (\\\"the 'half a shift' kind\\\"); the recent instance came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Two kinds named as the ends plus one observed instance; no typical or one-in-ten figures given, so this is a range, not a spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "how often it occurs, if it is an event rather than a step",
+          "precision": "named",
+          "rationale": "One occurrence recounted; frequency never stated.",
+          "assertion": {
+            "absence": "unknown-to-user",
+            "pointer": "rate of filler jams not yet asked or given"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I'd love to type in \"filler's down, ETA unknown\"",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-d662739b-76f0-429a-829a-ccb79763b6b9",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"rate of filler jams not yet asked or given\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"named\",\"rationale\":\"One occurrence recounted; frequency never stated.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "constraint",
+          "node": "Meridian on time",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Stated as non-negotiable with a named consequence.",
+          "assertion": {
+            "value": "The hard-line customer's order must ship on or before its due date — days late must be zero. The line is not crossed unless there is truly no way through; if it is crossed, the scheduler has to go explain it."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "anything above zero is bad news I have to go explain",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a9e42aa6-8d30-4ded-a8c4-f24220cfb292",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The hard-line customer's order must ship on or before its due date — days late must be zero. The line is not crossed unless there is truly no way through; if it is crossed, the scheduler has to go explain it.\"},\"kind\":\"constraint\",\"node\":\"Meridian on time\",\"precision\":\"spelled out\",\"rationale\":\"Stated as non-negotiable with a named consequence.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "who can absorb the slip",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Given as the practiced basis for weighing knock-on lateness.",
+          "assertion": {
+            "value": "When deciding which order to bump, judge by who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem to solve the first. Applied by judgment, with no formula."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I use judgment on who can absorb the slip",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"When deciding which order to bump, judge by who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem to solve the first. Applied by judgment, with no formula.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"Given as the practiced basis for weighing knock-on lateness.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option actually loses less",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The expert states the model's job as evaluating a disruption response option set.",
+          "assertion": {
+            "value": "Given a disruption such as \"filler's down, ETA unknown\", tell me which option (switch the order to the other line, or wait out the repair) actually loses less — instead of gut math at the huddle."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-1cb33f48-6553-4e4f-a8a0-37d7631b08ea",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given a disruption such as \\\"filler's down, ETA unknown\\\", tell me which option (switch the order to the other line, or wait out the repair) actually loses less — instead of gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"The expert states the model's job as evaluating a disruption response option set.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option actually loses less",
+          "slot": "what \"better\" means, and trade-off weights",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Lexicographic scorecard given in words; the expert explicitly denies having numeric weights.",
+          "assertion": {
+            "value": "First and hard: days late on the Meridian-style order, anything above zero is bad. Underneath and traded off by judgement, not formula: washdown hours (crew time plus the line taken out of anything else), and whether the bumped order goes late and by how much and for which customer. No formula for the second-order weighting."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "days late on Meridian, and anything above zero is bad news",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I don't have a formula for it.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-f073c3ed-2a89-4499-b3b2-fe160e8c1057",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First and hard: days late on the Meridian-style order, anything above zero is bad. Underneath and traded off by judgement, not formula: washdown hours (crew time plus the line taken out of anything else), and whether the bumped order goes late and by how much and for which customer. No formula for the second-order weighting.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Lexicographic scorecard given in words; the expert explicitly denies having numeric weights.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"days late on Meridian, and anything above zero is bad news\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option actually loses less",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "The options the expert weighed name these nodes directly.",
+          "assertion": {
+            "value": "activity:filler jam; activity:tint-to-white washdown; entity-type:order; entity-type:line (Line 1 / Line 2); ordering/flow:order flow, allocate to ship; policy:Meridian on time; policy:who can absorb the slip"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-c9864a2c-cbb3-41c9-97a6-e44cc1d7d424",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"activity:filler jam; activity:tint-to-white washdown; entity-type:order; entity-type:line (Line 1 / Line 2); ordering/flow:order flow, allocate to ship; policy:Meridian on time; policy:who can absorb the slip\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"named\",\"rationale\":\"The options the expert weighed name these nodes directly.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "where Line 1 loses its time",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Second objective the expert put explicitly in scope.",
+          "assertion": {
+            "value": "Show where Line 1 loses its time — specifically whether the small tank between mill and fill is actually costing us — as evidence to take to engineering rather than a hunch."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I could take that to engineering with something other than a hunch",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-480c2821-4d80-495b-a652-f5de8b035144",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Show where Line 1 loses its time — specifically whether the small tank between mill and fill is actually costing us — as evidence to take to engineering rather than a hunch.\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"spelled out\",\"rationale\":\"Second objective the expert put explicitly in scope.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I could take that to engineering with something other than a hunch\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "where Line 1 loses its time",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "The tank hunch is about these nodes.",
+          "assertion": {
+            "value": "constraint:small holding tanks between stages; entity-type:stage kit (mix, mill, tint, fill); ordering/flow:stage overlap on a line; constraint:published line rate"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-f3f2c366-eab0-49fa-951c-773f77aa11b2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"constraint:small holding tanks between stages; entity-type:stage kit (mix, mill, tint, fill); ordering/flow:stage overlap on a line; constraint:published line rate\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"named\",\"rationale\":\"The tank hunch is about these nodes.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "rationale": "Distinctions the expert's process treats differently: product class (white vs tint vs specialty) and customer account type.",
+          "assertion": {
+            "value": "An order is a line item in the demand book (quantity, due date, SKU). Whites differ from tints (tint stage is a pass-through for a white; a tint-to-white change costs a washdown) and from specialties (QA wait much longer). Customers differ: distributor, small account, and \"awkward\" accounts that get prickly."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-3bb35fb7-3954-45d4-839f-20ee46a8c052",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order is a line item in the demand book (quantity, due date, SKU). Whites differ from tints (tint stage is a pass-through for a white; a tint-to-white change costs a washdown) and from specialties (QA wait much longer). Customers differ: distributor, small account, and \\\"awkward\\\" accounts that get prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Distinctions the expert's process treats differently: product class (white vs tint vs specialty) and customer account type.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "state that rides along with each instance",
+          "precision": "spelled out",
+          "rationale": "Attributes named on the order.",
+          "assertion": {
+            "value": "Quantity, due date, SKU; the line and slot in the week it is allocated to; the customer; and days late against its due date."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-e552ac87-8cfa-4091-a262-6fba33ab9f83",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; the line and slot in the week it is allocated to; the customer; and days late against its due date.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Attributes named on the order.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "line (Line 1 / Line 2)",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "sourceRegime": "prescribed",
+          "rationale": "The scheduling sheet's view of a line as a single indivisible resource.",
+          "assertion": {
+            "value": "On the sheet a line is one row, one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it's done."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet a line is one row, one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it's done.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"spelled out\",\"rationale\":\"The scheduling sheet's view of a line as a single indivisible resource.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "line (Line 1 / Line 2)",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Physical reality diverges from the sheet; both recorded on the same node.",
+          "assertion": {
+            "value": "Physically a line is not one thing: mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-dd037a1c-63c0-47b8-8886-81c6d1f70226",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically a line is not one thing: mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"spelled out\",\"rationale\":\"Physical reality diverges from the sheet; both recorded on the same node.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "line (Line 1 / Line 2)",
+          "slot": "how many there are, or the population's shape",
+          "precision": "named",
+          "rationale": "Only Line 1 and Line 2 are named; no count was stated.",
+          "assertion": {
+            "value": "Line 1 and Line 2 are the lines named; no total count stated."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "whether to shift it to Line 1 or just wait out the repair",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "especially the one between mill and fill on Line 1",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-6c46c958-82b9-4ba0-bf0f-363fd70b6dbc",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2 are the lines named; no total count stated.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"named\",\"rationale\":\"Only Line 1 and Line 2 are named; no count was stated.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whether to shift it to Line 1 or just wait out the repair\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "stage kit (mix, mill, tint, fill)",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Each stage is separately contended kit.",
+          "assertion": {
+            "value": "Four separate pieces of kit per line — mixer, mill, tint, fill head — each usable independently, with small holding tanks buffering between mix/mill and mill/fill."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the mixer could be starting the next order's batch while the fill head is still finishing the last one",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-ee4eb482-b4b3-4392-94d7-ef9dc0a6ca98",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Four separate pieces of kit per line — mixer, mill, tint, fill head — each usable independently, with small holding tanks buffering between mix/mill and mill/fill.\"},\"kind\":\"entity-type\",\"node\":\"stage kit (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"rationale\":\"Each stage is separately contended kit.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the mixer could be starting the next order's batch while the fill head is still finishing the last one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "boundary-condition",
+          "node": "demand book from ERP",
+          "slot": "the arrival or availability pattern",
+          "precision": "named",
+          "rationale": "Arrival source named; no rate or shape given yet, so precision is only 'named'.",
+          "assertion": {
+            "value": "Orders arrive as line items in the demand book when ERP spits it out, each with quantity, due date and SKU."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders arrive as line items in the demand book when ERP spits it out, each with quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"named\",\"rationale\":\"Arrival source named; no rate or shape given yet, so precision is only 'named'.\",\"slot\":\"the arrival or availability pattern\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Output of the allocation step.",
+          "assertion": {
+            "value": "The order is placed onto a line and a slot in the week on the sheet."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "allocate it onto a line and a slot in the week",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-32521b14-4f1e-41ff-ab95-dfc11d8eee37",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is placed onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Output of the allocation step.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "rationale": "Precondition named.",
+          "assertion": {
+            "value": "A line item in the demand book from ERP, with quantity, due date and SKU."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book from ERP, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Precondition named.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "The expert performs it himself.",
+          "assertion": {
+            "value": "The master scheduler (the expert), on the sheet."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-c1704cba-8451-47a5-add8-2e388b330a1f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler (the expert), on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"named\",\"rationale\":\"The expert performs it himself.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run the batch (mix/mill/tint/fill)",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "The production run through the four stages.",
+          "assertion": {
+            "value": "The order is produced through the same four stages every product goes through — mix, mill, tint, fill and pack — and comes off the fill line."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-68ab39e5-8046-4f93-887e-11ed3e3b1da3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is produced through the same four stages every product goes through — mix, mill, tint, fill and pack — and comes off the fill line.\"},\"kind\":\"activity\",\"node\":\"run the batch (mix/mill/tint/fill)\",\"precision\":\"spelled out\",\"rationale\":\"The production run through the four stages.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run the batch (mix/mill/tint/fill)",
+          "slot": "how long it takes",
+          "rationale": "The expert says the end-to-end batch time per SKU per line exists on his sheet but gave no figures in this range.",
+          "assertion": {
+            "absence": "deferred",
+            "pointer": "the expert's scheduling sheet (roughly how long a batch of a given SKU takes end to end on each line)"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-c6d485c6-0e21-4cc0-b626-9091448d6ba1",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the expert's scheduling sheet (roughly how long a batch of a given SKU takes end to end on each line)\"},\"kind\":\"activity\",\"node\":\"run the batch (mix/mill/tint/fill)\",\"rationale\":\"The expert says the end-to-end batch time per SKU per line exists on his sheet but gave no figures in this range.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run the batch (mix/mill/tint/fill)",
+          "slot": "whether its quantities vary by type",
+          "rationale": "Stage-by-stage durations are not held by the expert; he names the historian as the source.",
+          "assertion": {
+            "absence": "deferred",
+            "pointer": "the historian (stage-by-stage times: how long does mixing take, how long does milling take)"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the historian (stage-by-stage times: how long does mixing take, how long does milling take)\"},\"kind\":\"activity\",\"node\":\"run the batch (mix/mill/tint/fill)\",\"rationale\":\"Stage-by-stage durations are not held by the expert; he names the historian as the source.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint stage",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
+          "rationale": "Explicit variation by product type.",
+          "assertion": {
+            "value": "Yes — for a white the tint stage is barely there, more of a pass-through than a real letdown step."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-737200bb-8f75-455f-b90a-3363a30d5fce",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — for a white the tint stage is barely there, more of a pass-through than a real letdown step.\"},\"kind\":\"activity\",\"node\":\"tint stage\",\"precision\":\"named\",\"rationale\":\"Explicit variation by product type.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "how long it takes",
+          "precision": "named",
+          "rationale": "Vague quantity as given — 'usually a few hours for a white'; not yet a spread.",
+          "assertion": {
+            "value": "Usually a few hours for a white; the specialty wait is much longer (figure not given)."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-78203b7c-8e00-469c-9d53-01d1a656d5c1",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; the specialty wait is much longer (figure not given).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Vague quantity as given — 'usually a few hours for a white'; not yet a spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
+          "rationale": "Explicit contrast between white and specialty.",
+          "assertion": {
+            "value": "Yes — a few hours for a white, nothing like the specialty wait."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a few hours for a white, nothing like the specialty wait.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Explicit contrast between white and specialty.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "The lab performs the check.",
+          "assertion": {
+            "value": "The lab (the order sits in the lab's queue and gets checked)."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab (the order sits in the lab's queue and gets checked).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"The lab performs the check.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "release and ship",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Terminal step.",
+          "assertion": {
+            "value": "The order is released, goes to the warehouse, and ships against the due date."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"rationale\":\"Terminal step.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "how long it takes",
+          "precision": "number",
+          "sourceRegime": "practiced",
+          "rationale": "A single figure given; not a spread.",
+          "assertion": {
+            "value": "Three hours."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-42e0a99d-6cf6-4b30-8199-b430405ba25b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"A single figure given; not a spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what is lost when it changes the system's mode",
+          "precision": "number",
+          "sourceRegime": "practiced",
+          "rationale": "Named mode change (tint to white) with its stated loss.",
+          "assertion": {
+            "value": "Three hours of crew time, and the line is out of anything else for that window."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a27c0fc1-57f3-4eed-bea8-15453c84f2da",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of crew time, and the line is out of anything else for that window.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Named mode change (tint to white) with its stated loss.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "rationale": "Trigger condition for the changeover.",
+          "assertion": {
+            "value": "A line that has been running a tint being pulled onto a white."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-0f6aea65-d3a4-430b-b532-4f1100303f9e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line that has been running a tint being pulled onto a white.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Trigger condition for the changeover.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Event effect on the line and the order in hand.",
+          "assertion": {
+            "value": "The line's filler goes down mid-run with an unknown ETA; the order on it stalls and must either wait or be shifted to the other line."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the tint order I bumped now might itself be late",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a3f706dd-453a-4543-9990-26efb1b079dd",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line's filler goes down mid-run with an unknown ETA; the order on it stalls and must either wait or be shifted to the other line.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"Event effect on the line and the order in hand.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the tint order I bumped now might itself be late\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "how long it takes",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Two named repair kinds bound the range; the recent instance was about two hours. Not yet a spread.",
+          "assertion": {
+            "value": "From the \"half hour\" kind to the \"half a shift\" kind; the recent Line 2 jam came back in about two hours."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "it came back in about two hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-67de2e75-132c-43a7-b64e-412343204931",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"From the \\\"half hour\\\" kind to the \\\"half a shift\\\" kind; the recent Line 2 jam came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Two named repair kinds bound the range; the recent instance was about two hours. Not yet a spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "order flow, allocate to ship",
+          "slot": "the order things happen in",
+          "precision": "spelled out",
+          "rationale": "The end-to-end order stated by the expert.",
+          "assertion": {
+            "value": "Allocate the order onto a line and a slot in the week → run it through mix / mill / tint / fill and pack → QA hold → release and ship. Four steps if QA and shipping count as one, five if split."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-bf082835-a2ca-4279-80e5-726f157270bd",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate the order onto a line and a slot in the week → run it through mix / mill / tint / fill and pack → QA hold → release and ship. Four steps if QA and shipping count as one, five if split.\"},\"kind\":\"ordering/flow\",\"node\":\"order flow, allocate to ship\",\"precision\":\"spelled out\",\"rationale\":\"The end-to-end order stated by the expert.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "stage overlap on a line",
+          "slot": "the order things happen in",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Overlap between consecutive orders on the same line, gated by tank space.",
+          "assertion": {
+            "value": "Stages can overlap between orders: the mixer may start the next order's batch while the fill head is still finishing the last one, provided the holding tank ahead (mix→mill or mill→fill) has space; the crew will take that head start when the tank ahead has room."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the crew will get a head start on mixing the next batch if the tank ahead of it has space",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-ce28dd53-a53d-4bc9-9956-dc3268c35e3e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stages can overlap between orders: the mixer may start the next order's batch while the fill head is still finishing the last one, provided the holding tank ahead (mix→mill or mill→fill) has space; the crew will take that head start when the tank ahead has room.\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"precision\":\"spelled out\",\"rationale\":\"Overlap between consecutive orders on the same line, gated by tank space.\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the crew will get a head start on mixing the next batch if the tank ahead of it has space\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "stage overlap on a line",
+          "slot": "how a branch or merge is decided",
+          "rationale": "The expert explicitly does not track how often overlap occurs or is blocked.",
+          "assertion": {
+            "absence": "unknown-to-user"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-9b28544e-b867-4018-9c35-2691cef17a62",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"rationale\":\"The expert explicitly does not track how often overlap occurs or is blocked.\",\"slot\":\"how a branch or merge is decided\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "constraint",
+          "node": "small holding tanks between stages",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Capacity and consequence stated qualitatively; the sizes themselves are not held by the expert.",
+          "assertion": {
+            "value": "The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait. Actual tank sizes not known to the expert; obtainable from engineering drawings."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "how often it's blocked because a tank's full and mixing has to wait",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-4c4af9ea-df1a-4449-adb7-d48fce7eae93",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait. Actual tank sizes not known to the expert; obtainable from engineering drawings.\"},\"kind\":\"constraint\",\"node\":\"small holding tanks between stages\",\"precision\":\"spelled out\",\"rationale\":\"Capacity and consequence stated qualitatively; the sizes themselves are not held by the expert.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"how often it's blocked because a tank's full and mixing has to wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "constraint",
+          "node": "published line rate",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "sourceRegime": "prescribed",
+          "rationale": "Engineering's position, recorded as the prescribed reading.",
+          "assertion": {
+            "value": "Engineering's position is that the line rate is what it is regardless of the tanks."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "engineering tells me the line rate is what it is regardless",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-dabdbb5f-9eca-4afb-ad50-5b381d9dfa4f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Engineering's position is that the line rate is what it is regardless of the tanks.\"},\"kind\":\"constraint\",\"node\":\"published line rate\",\"precision\":\"spelled out\",\"rationale\":\"Engineering's position, recorded as the prescribed reading.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"engineering tells me the line rate is what it is regardless\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "constraint",
+          "node": "published line rate",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The expert's contrary practiced reading, recorded alongside engineering's.",
+          "assertion": {
+            "value": "In practice Line 1 feels sluggish and blocked in ways the published line rate does not account for; the expert suspects the mill-to-fill tank costs more than people admit, but has no proof."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it feels sluggish and blocked in ways I can't pin on the published line rate",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I've always suspected that one costs us more than people admit, but I've never had anything to prove it",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-292e1165-0990-4d17-b6db-153c675fd66c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"In practice Line 1 feels sluggish and blocked in ways the published line rate does not account for; the expert suspects the mill-to-fill tank costs more than people admit, but has no proof.\"},\"kind\":\"constraint\",\"node\":\"published line rate\",\"precision\":\"spelled out\",\"rationale\":\"The expert's contrary practiced reading, recorded alongside engineering's.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've always suspected that one costs us more than people admit, but I've never had anything to prove it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it feels sluggish and blocked in ways I can't pin on the published line rate\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "Meridian on time",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Hard constraint on the scheduling decision.",
+          "assertion": {
+            "value": "A Meridian-style order ships on time, full stop; it is not traded off against anything."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian-style order ships on time, full stop; it is not traded off against anything.\"},\"kind\":\"policy\",\"node\":\"Meridian on time\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint on the scheduling decision.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "Meridian on time",
+          "slot": "what overrides it",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Only exception stated.",
+          "assertion": {
+            "value": "Only when there is truly no way through."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "that's a line I won't cross unless there's truly no way through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-54d606d7-8c61-4f0a-bd5f-867bba1af3f7",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Only when there is truly no way through.\"},\"kind\":\"policy\",\"node\":\"Meridian on time\",\"precision\":\"spelled out\",\"rationale\":\"Only exception stated.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "who can absorb the slip",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Practiced judgement about which customers can take lateness; examples given rather than a formula.",
+          "assertion": {
+            "value": "Judgement on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly counts as a second problem created to solve the first."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I use judgment on who can absorb the slip",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgement on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly counts as a second problem created to solve the first.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"Practiced judgement about which customers can take lateness; examples given rather than a formula.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "data-binding",
+          "node": "stage-by-stage times",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "rationale": "Named feed for stage durations.",
+          "assertion": {
+            "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) — the historian."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) — the historian.\"},\"kind\":\"data-binding\",\"node\":\"stage-by-stage times\",\"precision\":\"named\",\"rationale\":\"Named feed for stage durations.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "data-binding",
+          "node": "tank sizes",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "rationale": "Named source for the holding tank capacities.",
+          "assertion": {
+            "value": "Holding tank sizes — engineering drawings."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-b0908788-ec79-4481-b056-1fa606930f85",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tank sizes — engineering drawings.\"},\"kind\":\"data-binding\",\"node\":\"tank sizes\",\"precision\":\"named\",\"rationale\":\"Named source for the holding tank capacities.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option loses less",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "rationale": "The model's primary question, stated as a disruption decision: with the filler down and ETA unknown, whether to wait or switch lines.",
+          "assertion": {
+            "value": "Given \"filler's down, ETA unknown\", tell me which option actually loses less — wait out the repair, or move the order to the other line — instead of doing gut math at the huddle."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given \\\"filler's down, ETA unknown\\\", tell me which option actually loses less — wait out the repair, or move the order to the other line — instead of doing gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"The model's primary question, stated as a disruption decision: with the filler down and ETA unknown, whether to wait or switch lines.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option loses less",
+          "slot": "what \"better\" means, and trade-off weights",
+          "precision": "spelled out",
+          "rationale": "Lexicographic: on-time delivery for the protected order is a hard line; the remaining terms are weighed by judgment with no formula.",
+          "assertion": {
+            "value": "First: days late on Meridian, anything above zero is bad news — non-negotiable, a line not crossed unless there is truly no way through. Underneath: washdown hours (crew time plus the line taken out of anything else for that window), and whether the bumped order goes late and by how much, judged against who the customer is. No formula — \"how bad is bad\" and judgment on who can absorb the slip."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-9d5063d7-b9fb-400e-8b54-f618c6fde20e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First: days late on Meridian, anything above zero is bad news — non-negotiable, a line not crossed unless there is truly no way through. Underneath: washdown hours (crew time plus the line taken out of anything else for that window), and whether the bumped order goes late and by how much, judged against who the customer is. No formula — \\\"how bad is bad\\\" and judgment on who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"Lexicographic: on-time delivery for the protected order is a hard line; the remaining terms are weighed by judgment with no formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option loses less",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "The scorecard terms the expert named map onto the washdown, the production run, the breakdown event and the order itself.",
+          "assertion": {
+            "value": [
+              "activity:tint-to-white washdown",
+              "activity:run it through mix/mill/tint/fill",
+              "activity:filler jammed",
+              "entity-type:order",
+              "policy:who can absorb the slip"
+            ]
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-3245b29a-3687-4313-97c5-e0455e5889ba",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:tint-to-white washdown\",\"activity:run it through mix/mill/tint/fill\",\"activity:filler jammed\",\"entity-type:order\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard terms the expert named map onto the washdown, the production run, the breakdown event and the order itself.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "where Line 1 loses its time",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "rationale": "Second, explicitly in-scope objective: show whether the small tank between mill and fill on Line 1 is actually costing time, as evidence to take to engineering.",
+          "assertion": {
+            "value": "Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill is actually costing us — with something other than a hunch to take to engineering."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill is actually costing us — with something other than a hunch to take to engineering.\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"spelled out\",\"rationale\":\"Second, explicitly in-scope objective: show whether the small tank between mill and fill on Line 1 is actually costing time, as evidence to take to engineering.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "where Line 1 loses its time",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "The hunch is about blocking at the mill-to-fill tank, so it depends on the stage kit, the tank constraint and the run duration.",
+          "assertion": {
+            "value": [
+              "entity-type:mix, mill, tint, fill",
+              "constraint:small holding tanks",
+              "activity:run it through mix/mill/tint/fill",
+              "entity-type:Line 1 and Line 2"
+            ]
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "So yes — build it as separate stages if that's what it takes.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-770314e5-f47a-463e-908a-1d8c23ee60f5",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:mix, mill, tint, fill\",\"constraint:small holding tanks\",\"activity:run it through mix/mill/tint/fill\",\"entity-type:Line 1 and Line 2\"]},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"named\",\"rationale\":\"The hunch is about blocking at the mill-to-fill tank, so it depends on the stage kit, the tank constraint and the run duration.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"So yes — build it as separate stages if that's what it takes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "state that rides along with each instance",
+          "precision": "spelled out",
+          "rationale": "The attributes the scheduler works from on the sheet.",
+          "assertion": {
+            "value": "Quantity, due date, SKU; plus the line and week-slot it is allocated to, and the customer account."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-6ff1c59a-0664-487b-a946-2680043419a2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; plus the line and week-slot it is allocated to, and the customer account.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The attributes the scheduler works from on the sheet.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "rationale": "Whites versus tints differ in stage content and in run speed by line; customer type differs in how a slip is judged.",
+          "assertion": {
+            "value": "Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step, and whites run much faster on Line 2 than Line 1 while tints run at nearly the same speed on both. Customers are treated apart too: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-be0c3675-ae93-41c5-9eaa-7d36d84617cb",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step, and whites run much faster on Line 2 than Line 1 while tints run at nearly the same speed on both. Customers are treated apart too: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Whites versus tints differ in stage content and in run speed by line; customer type differs in how a slip is judged.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "Line 1 and Line 2",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "rationale": "The two lines are contended kit distinguished by speed, and the speed difference depends on product.",
+          "assertion": {
+            "value": "Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to a Line 2 run (\"Line 2 is twice as fast\", which is really a whites number); on tints the two lines run at nearly the same speed."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-3e2a5a8a-bd99-4642-afcf-f9d3dfe2e9f6",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to a Line 2 run (\\\"Line 2 is twice as fast\\\", which is really a whites number); on tints the two lines run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"rationale\":\"The two lines are contended kit distinguished by speed, and the speed difference depends on product.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "mix, mill, tint, fill",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "sourceRegime": "prescribed",
+          "rationale": "The scheduling sheet's view: the line is one indivisible resource.",
+          "assertion": {
+            "value": "On the sheet the line is one row treated as one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it is done."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet the line is one row treated as one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it is done.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill\",\"precision\":\"spelled out\",\"rationale\":\"The scheduling sheet's view: the line is one indivisible resource.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "mix, mill, tint, fill",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The floor view: four separately contended pieces of kit with buffering between them, allowing overlap.",
+          "assertion": {
+            "value": "Physically four separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head is still finishing the last, if there is room in the holding tank — the crew will get a head start on mixing the next batch if the tank ahead of it has space."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the crew will get a head start on mixing the next batch if the tank ahead of it has space",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-27ee0ed5-50d0-47f6-94b8-77e090bca50f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically four separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head is still finishing the last, if there is room in the holding tank — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill\",\"precision\":\"spelled out\",\"rationale\":\"The floor view: four separately contended pieces of kit with buffering between them, allowing overlap.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the crew will get a head start on mixing the next batch if the tank ahead of it has space\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "mix, mill, tint, fill",
+          "slot": "how many there are, or the population's shape",
+          "precision": "named",
+          "assertion": {
+            "absence": "unknown-to-user",
+            "pointer": "how much overlap happens and how often mixing is blocked by a full tank is not tracked by the scheduler"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"how much overlap happens and how often mixing is blocked by a full tank is not tracked by the scheduler\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill\",\"precision\":\"named\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "allocate → run → QA hold → release and ship",
+          "slot": "the order things happen in",
+          "precision": "spelled out",
+          "rationale": "The order's life from demand-book line item to shipment, as walked end to end.",
+          "assertion": {
+            "value": "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (and pack) → QA hold in the lab's queue → release, go to the warehouse and ship against the due date."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-2a491098-b602-4b46-bbaa-439e291027db",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (and pack) → QA hold in the lab's queue → release, go to the warehouse and ship against the due date.\"},\"kind\":\"ordering/flow\",\"node\":\"allocate → run → QA hold → release and ship\",\"precision\":\"spelled out\",\"rationale\":\"The order's life from demand-book line item to shipment, as walked end to end.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Allocation binds the order to a line and a week slot, which is the scheduling decision under test.",
+          "assertion": {
+            "value": "The order is slotted onto a line and a slot in the week on the sheet."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-c4aefe40-a022-4990-96a1-b74243850715",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Allocation binds the order to a line and a week slot, which is the scheduling decision under test.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "The order exists as a line item in the demand book once ERP spits it out, with quantity, due date and SKU."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-76c7250e-6575-4e31-b667-113f3a497cce",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order exists as a line item in the demand book once ERP spits it out, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "The order must first be allocated onto a line and a slot in the week."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-7da94524-13b5-4c11-a1b4-9cb1b0f07e19",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order must first be allocated onto a line and a slot in the week.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "Filled and packed product coming off the fill line, which then goes into QA hold."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Filled and packed product coming off the fill line, which then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "how long it takes",
+          "precision": "spread",
+          "sourceRegime": "practiced",
+          "rationale": "Sheet-level, mix-to-last-pack, for a Meridian-sized white on Line 2; includes fill-up time getting the line running plus actual throughput. The bad tail is loosely folded-in filler hiccups and QA-adjacent time.",
+          "assertion": {
+            "value": "White, normal/Meridian-sized order, Line 2, mix-to-last-pack: typical 8–9 hours; one run in ten worse than 12–13 hours; one run in ten better than about 6 hours."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-d6985d8d-f85e-4556-a091-df64be080ba6",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, normal/Meridian-sized order, Line 2, mix-to-last-pack: typical 8–9 hours; one run in ten worse than 12–13 hours; one run in ten better than about 6 hours.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"Sheet-level, mix-to-last-pack, for a Meridian-sized white on Line 2; includes fill-up time getting the line running plus actual throughput. The bad tail is loosely folded-in filler hiccups and QA-adjacent time.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "how long it takes",
+          "precision": "spread",
+          "sourceRegime": "practiced",
+          "rationale": "Same white order on the slower line.",
+          "assertion": {
+            "value": "White, same order, Line 1: typical 13–14 hours; worse days pushing 18-plus hours; best day maybe 10 hours — roughly fifty to sixty percent added to the Line 2 figures."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, same order, Line 1: typical 13–14 hours; worse days pushing 18-plus hours; best day maybe 10 hours — roughly fifty to sixty percent added to the Line 2 figures.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"Same white order on the slower line.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "how long it takes",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Only a typical range was given for tints; no one-in-ten tails.",
+          "assertion": {
+            "value": "Tint run, either line: 8–10 hours typical. No one-in-ten worse/better figures given."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-04a6f876-12f4-4f53-b6f2-f8e5fa9c87bc",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Tint run, either line: 8–10 hours typical. No one-in-ten worse/better figures given.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"range\",\"rationale\":\"Only a typical range was given for tints; no one-in-ten tails.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
+          "rationale": "Duration varies by product type and by line, and the two interact; the expert has no explanation for the tint parity.",
+          "assertion": {
+            "value": "Yes — duration varies both by product (white vs tint) and by line, and the two interact: whites are much slower on Line 1, tints run at nearly the same speed on both. \"I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\""
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-592b83e0-ece3-4e98-aedf-cdf70c202e96",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — duration varies both by product (white vs tint) and by line, and the two interact: whites are much slower on Line 1, tints run at nearly the same speed on both. \\\"I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\\\"\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Duration varies by product type and by line, and the two interact; the expert has no explanation for the tint parity.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what is lost when it changes the system's mode",
+          "precision": "number",
+          "rationale": "Named transition: tint to white on Line 1.",
+          "assertion": {
+            "value": "Three hours for a tint-to-white changeover — real cost in crew time, and it takes the line out of anything else for that window."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "it takes Line 1 out of anything else for that window",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-32fe7be9-75c7-464c-87cb-ca38fef4039b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours for a tint-to-white changeover — real cost in crew time, and it takes the line out of anything else for that window.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Named transition: tint to white on Line 1.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "A line coming off a tint run and being switched to a white — pulling Line 1 off its tint to cover a white order."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-31556043-9787-40dc-8c0d-b74a47ed3589",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line coming off a tint run and being switched to a white — pulling Line 1 off its tint to cover a white order.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "how long it takes",
+          "precision": "named",
+          "rationale": "Only a vague magnitude was given; no typical or tail figures, and the specialty case is named but unquantified.",
+          "assertion": {
+            "value": "Usually a few hours for a white; \"nothing like the specialty wait\". No typical/tail figures given."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; \\\"nothing like the specialty wait\\\". No typical/tail figures given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Only a vague magnitude was given; no typical or tail figures, and the specialty case is named but unquantified.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "assertion": {
+            "value": "The lab — the order sits in the lab's queue and gets checked."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab — the order sits in the lab's queue and gets checked.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jammed",
+          "slot": "how long it takes",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Two recognised repair kinds bracket the duration; the recent instance fell between them.",
+          "assertion": {
+            "value": "Two kinds of repair: the \"half hour\" kind and the \"half a shift\" kind. The most recent Line 2 filler jam came back in about two hours."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "it came back in about two hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-d2d6e303-2f63-478a-ace1-0bf61abbfddd",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two kinds of repair: the \\\"half hour\\\" kind and the \\\"half a shift\\\" kind. The most recent Line 2 filler jam came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jammed\",\"precision\":\"range\",\"rationale\":\"Two recognised repair kinds bracket the duration; the recent instance fell between them.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jammed",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "An event that befalls the line mid-run and forces the switch-or-wait decision.",
+          "assertion": {
+            "value": "The line's filler stops mid-run with an unknown ETA, putting the order on it at risk and forcing a decision to wait out the repair or move the order to the other line."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-5548a18b-9f79-4475-a9ab-83a74c750721",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line's filler stops mid-run with an unknown ETA, putting the order on it at risk and forcing a decision to wait out the repair or move the order to the other line.\"},\"kind\":\"activity\",\"node\":\"filler jammed\",\"precision\":\"spelled out\",\"rationale\":\"An event that befalls the line mid-run and forces the switch-or-wait decision.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "who can absorb the slip",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The practiced rule for choosing which order gets bumped when two cannot both be on time.",
+          "assertion": {
+            "value": "Protect the non-negotiable order's due date; for anything bumped, judge by how far it slips and who the customer is — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first. No formula; judgment on who can absorb the slip."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I use judgment on who can absorb the slip.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-1ee7c206-0c56-4d6b-b091-5861f9c40438",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Protect the non-negotiable order's due date; for anything bumped, judge by how far it slips and who the customer is — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first. No formula; judgment on who can absorb the slip.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The practiced rule for choosing which order gets bumped when two cannot both be on time.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "who can absorb the slip",
+          "slot": "what overrides it",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "The on-time line is crossed only when there is truly no way through."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "that's a line I won't cross unless there's truly no way through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-4b706f60-c02f-4973-aa58-2d3ded113c39",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The on-time line is crossed only when there is truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "constraint",
+          "node": "small holding tanks",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Consequence is stated (upstream stage waits); the numeric capacity is not held by the expert.",
+          "assertion": {
+            "value": "The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait; overlap is only possible if the tank ahead has space. Suspected to cost more than people admit, never proven."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "how often it's blocked because a tank's full and mixing has to wait",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-97ea5a05-d89c-4a7d-a136-f90526beaa27",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait; overlap is only possible if the tank ahead has space. Suspected to cost more than people admit, never proven.\"},\"kind\":\"constraint\",\"node\":\"small holding tanks\",\"precision\":\"spelled out\",\"rationale\":\"Consequence is stated (upstream stage waits); the numeric capacity is not held by the expert.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"how often it's blocked because a tank's full and mixing has to wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "constraint",
+          "node": "small holding tanks",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "named",
+          "assertion": {
+            "absence": "deferred",
+            "pointer": "engineering drawings — tank sizes obtainable from engineering, not carried in the scheduler's head"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings — tank sizes obtainable from engineering, not carried in the scheduler's head\"},\"kind\":\"constraint\",\"node\":\"small holding tanks\",\"precision\":\"named\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "data-binding",
+          "node": "stage-by-stage rates from the historian",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "rationale": "Stage-level durations are needed for the separate-stage model and exist only in the historian.",
+          "assertion": {
+            "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the plant historian; never pulled apart, not known to the scheduler."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-46d37104-fb87-4105-95d5-4448aade81ac",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the plant historian; never pulled apart, not known to the scheduler.\"},\"kind\":\"data-binding\",\"node\":\"stage-by-stage rates from the historian\",\"precision\":\"named\",\"rationale\":\"Stage-level durations are needed for the separate-stage model and exist only in the historian.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "validation-criterion",
+          "node": "the sheet's end-to-end batch times",
+          "slot": "how the expert would know the model is right",
+          "precision": "named",
+          "rationale": "The only figures the expert holds first-hand are sheet-level end-to-end times per SKU per line; engineering's counter-claim is that the line rate is what it is regardless of the tanks.",
+          "assertion": {
+            "value": "The model's end-to-end batch time for a given SKU on each line should match what the scheduler's sheet shows; and it would have to speak to engineering's claim that \"the line rate is what it is regardless\"."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "engineering tells me the line rate is what it is regardless",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-0cdda695-1dfa-43ef-971c-b9db09403a07",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The model's end-to-end batch time for a given SKU on each line should match what the scheduler's sheet shows; and it would have to speak to engineering's claim that \\\"the line rate is what it is regardless\\\".\"},\"kind\":\"validation-criterion\",\"node\":\"the sheet's end-to-end batch times\",\"precision\":\"named\",\"rationale\":\"The only figures the expert holds first-hand are sheet-level end-to-end times per SKU per line; engineering's counter-claim is that the line rate is what it is regardless of the tanks.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"engineering tells me the line rate is what it is regardless\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option actually loses less",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The expert's stated use: type in a disruption state and be told which of switch-or-wait loses less.",
+          "assertion": {
+            "value": "Given a disruption like \"filler's down, ETA unknown\", tell me which option actually loses less — shift the order to the other line or wait out the repair — instead of doing gut math at the huddle."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a5926e2a-88e8-459e-a296-282b16d499a8",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given a disruption like \\\"filler's down, ETA unknown\\\", tell me which option actually loses less — shift the order to the other line or wait out the repair — instead of doing gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"The expert's stated use: type in a disruption state and be told which of switch-or-wait loses less.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option actually loses less",
+          "slot": "what \"better\" means, and trade-off weights",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Hard constraint plus unweighted secondary terms; the expert explicitly denies having a formula.",
+          "assertion": {
+            "value": "First number: days late on Meridian, anything above zero is bad — on-time is non-negotiable, a line not crossed unless there's truly no way through. Underneath that: washdown hours (crew time, line taken out of anything else for that window) and whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-ea1779b0-9a83-42aa-92d1-746e73de43cc",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First number: days late on Meridian, anything above zero is bad — on-time is non-negotiable, a line not crossed unless there's truly no way through. Underneath that: washdown hours (crew time, line taken out of anything else for that window) and whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint plus unweighted secondary terms; the expert explicitly denies having a formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "which option actually loses less",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "The scorecard terms name the run, the jam, the washdown, the order type and the flow.",
+          "assertion": {
+            "value": [
+              "activity:run it through mix/mill/tint/fill",
+              "activity:filler jam",
+              "activity:tint-to-white washdown",
+              "entity-type:order (line item in the demand book)",
+              "entity-type:Line 1 and Line 2",
+              "ordering/flow:allocate → run → QA hold → release and ship",
+              "policy:who can absorb the slip"
+            ]
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-1288a3df-c7fd-4319-8d4e-a228572ba0b0",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:run it through mix/mill/tint/fill\",\"activity:filler jam\",\"activity:tint-to-white washdown\",\"entity-type:order (line item in the demand book)\",\"entity-type:Line 1 and Line 2\",\"ordering/flow:allocate → run → QA hold → release and ship\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard terms name the run, the jam, the washdown, the order type and the flow.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "where Line 1 loses its time",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "rationale": "Second in-scope question: whether the small tank between mill and fill on Line 1 is actually costing time.",
+          "assertion": {
+            "value": "Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill on Line 1 is costing more than the published line rate admits, so it can be taken to engineering as something other than a hunch."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill on Line 1 is costing more than the published line rate admits, so it can be taken to engineering as something other than a hunch.\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"spelled out\",\"rationale\":\"Second in-scope question: whether the small tank between mill and fill on Line 1 is actually costing time.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "where Line 1 loses its time",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "The tank question depends on the stage kit and the holding-tank constraint.",
+          "assertion": {
+            "value": [
+              "entity-type:mix, mill, tint, fill stages",
+              "constraint:small holding tanks between stages",
+              "activity:run it through mix/mill/tint/fill",
+              "entity-type:Line 1 and Line 2"
+            ]
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So yes — build it as separate stages if that's what it takes.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-bb291ebf-9fe0-4a6e-9840-e7d7fac44033",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:mix, mill, tint, fill stages\",\"constraint:small holding tanks between stages\",\"activity:run it through mix/mill/tint/fill\",\"entity-type:Line 1 and Line 2\"]},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"named\",\"rationale\":\"The tank question depends on the stage kit and the holding-tank constraint.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So yes — build it as separate stages if that's what it takes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order (line item in the demand book)",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "rationale": "Whites vs tints differ in the tint stage and in run time by line; customer identity differs in slip tolerance.",
+          "assertion": {
+            "value": "Orders are line items with quantity, due date and SKU. Treated apart: whites (tint stage barely there, more of a pass-through than a real letdown step) vs tints (real letdown); and by customer — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-edfaf81c-c276-4b57-a88c-914953b1c6be",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders are line items with quantity, due date and SKU. Treated apart: whites (tint stage barely there, more of a pass-through than a real letdown step) vs tints (real letdown); and by customer — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem.\"},\"kind\":\"entity-type\",\"node\":\"order (line item in the demand book)\",\"precision\":\"spelled out\",\"rationale\":\"Whites vs tints differ in the tint stage and in run time by line; customer identity differs in slip tolerance.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order (line item in the demand book)",
+          "slot": "state that rides along with each instance",
+          "precision": "spelled out",
+          "rationale": "Quantity, due date, SKU come from ERP; customer type is used in the slip judgement; line allocation is set at step one.",
+          "assertion": {
+            "value": "Quantity, due date, SKU; the customer (distributor / small account / awkward account); which line and week-slot it has been allocated to; whether it has gone late and by how many days."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-13339551-ff3a-414f-8260-e1296530d8ec",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; the customer (distributor / small account / awkward account); which line and week-slot it has been allocated to; whether it has gone late and by how many days.\"},\"kind\":\"entity-type\",\"node\":\"order (line item in the demand book)\",\"precision\":\"spelled out\",\"rationale\":\"Quantity, due date, SKU come from ERP; customer type is used in the slip judgement; line allocation is set at step one.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "Line 1 and Line 2",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "rationale": "The two lines differ on whites but not on tints — load-bearing for switch-or-wait.",
+          "assertion": {
+            "value": "Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to Line 2's figures (\"Line 2 is twice as fast\", though that's really a whites number). On tints they run at nearly the same speed."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-535749ea-ba99-4d11-84c0-8203fd058329",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to Line 2's figures (\\\"Line 2 is twice as fast\\\", though that's really a whites number). On tints they run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"rationale\":\"The two lines differ on whites but not on tints — load-bearing for switch-or-wait.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "mix, mill, tint, fill stages",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The floor's account: four separately contended pieces of kit per line, buffered by small holding tanks.",
+          "assertion": {
+            "value": "Mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can be starting the next order's batch while the fill head is still finishing the last one, if the holding tank between mix and mill, or mill and fill, has room."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-79eccb7f-a787-40d4-a2fa-e95bfda82d18",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can be starting the next order's batch while the fill head is still finishing the last one, if the holding tank between mix and mill, or mill and fill, has room.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill stages\",\"precision\":\"spelled out\",\"rationale\":\"The floor's account: four separately contended pieces of kit per line, buffered by small holding tanks.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "mix, mill, tint, fill stages",
+          "slot": "how many there are, or the population's shape",
+          "precision": "named",
+          "rationale": "Stage counts per line and tank sizes not carried by the expert; source named.",
+          "assertion": {
+            "absence": "deferred",
+            "pointer": "engineering drawings (tank sizes) — expert does not carry them in his head"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I don't have clean numbers for tank sizes or stage-by-stage rates.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-3c6b3e85-7fd3-4831-9201-6e3ef525e7cf",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings (tank sizes) — expert does not carry them in his head\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill stages\",\"precision\":\"named\",\"rationale\":\"Stage counts per line and tank sizes not carried by the expert; source named.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have clean numbers for tank sizes or stage-by-stage rates.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "boundary-condition",
+          "node": "demand book from ERP",
+          "slot": "the starting state",
+          "precision": "spelled out",
+          "rationale": "Orders enter the scheduler's world as ERP-generated demand-book line items.",
+          "assertion": {
+            "value": "Orders arrive as line items in the demand book once ERP spits that out, carrying quantity, due date and SKU."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders arrive as line items in the demand book once ERP spits that out, carrying quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"spelled out\",\"rationale\":\"Orders enter the scheduler's world as ERP-generated demand-book line items.\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Allocation fixes line and week-slot on the sheet.",
+          "assertion": {
+            "value": "The order is slotted onto a line and a slot in the week on the sheet."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-823c9593-db42-45eb-9515-937e6b90bd33",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Allocation fixes line and week-slot on the sheet.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "The expert himself, as master scheduler, does the slotting on the sheet.",
+          "assertion": {
+            "value": "The master scheduler, on the sheet"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I'm the master scheduler at a coatings plant.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 1,
+            "entryEnd": 1
+          },
+          "source": "user"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-f7e12936-7567-4b38-be19-a45fb5dc6274",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler, on the sheet\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"named\",\"rationale\":\"The expert himself, as master scheduler, does the slotting on the sheet.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm the master scheduler at a coatings plant.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":1,\\\"entryStart\\\":1,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "rationale": "Allocation follows the ERP demand-book line item existing.",
+          "assertion": {
+            "value": "A line item in the demand book from ERP, with quantity, due date and SKU."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book from ERP, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Allocation follows the ERP demand-book line item existing.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "allocate → run → QA hold → release and ship",
+          "slot": "the order things happen in",
+          "precision": "spelled out",
+          "rationale": "The expert's own end-to-end sequence for one order.",
+          "assertion": {
+            "value": "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (mix, mill, tint, fill and pack) → QA hold in the lab's queue → release, warehouse, and ship against the due date."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (mix, mill, tint, fill and pack) → QA hold in the lab's queue → release, warehouse, and ship against the due date.\"},\"kind\":\"ordering/flow\",\"node\":\"allocate → run → QA hold → release and ship\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own end-to-end sequence for one order.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "rationale": "A run needs the order allocated to a line and that line's kit available.",
+          "assertion": {
+            "value": "The order must have been allocated onto a line and a slot in the week, and the line's kit (mix, mill, tint, fill) available."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-afd366c9-1ea6-4b73-b2c0-ed97c9af0c79",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order must have been allocated onto a line and a slot in the week, and the line's kit (mix, mill, tint, fill) available.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"A run needs the order allocated to a line and that line's kit available.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Output is finished, packed product that comes off the fill line into QA hold.",
+          "assertion": {
+            "value": "The order is produced through mix, mill, tint, fill and pack; it comes off the fill line as packed product ready for QA hold."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-86fd1cfb-379b-42f7-bdbb-8586dae7f755",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is produced through mix, mill, tint, fill and pack; it comes off the fill line as packed product ready for QA hold.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"Output is finished, packed product that comes off the fill line into QA hold.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "The run is performed by whichever line the order is allocated to, with its crew.",
+          "assertion": {
+            "value": "entity-type:Line 1 and Line 2 — the line the order is slotted onto, plus its crew"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "On Line 1, same order — slower machine",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-90d36431-4341-4f9e-8bf6-8b5354b2fedd",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:Line 1 and Line 2 — the line the order is slotted onto, plus its crew\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"The run is performed by whichever line the order is allocated to, with its crew.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "how long it takes",
+          "precision": "spread",
+          "sourceRegime": "practiced",
+          "rationale": "First-pass spread for a Meridian-sized white on Line 2, mix-to-last-pack, with breakdowns folded in loosely; superseded by the clean-run capture.",
+          "assertion": {
+            "value": "White, Meridian-sized order, Line 2, mix-to-last-pack (includes fill-up time plus throughput): typical eight to nine hours; one in ten worse than twelve to thirteen hours (breakdowns folded in loosely); one in ten better than about six hours."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more \"the filler hiccupped twice\" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-7ef3368b-e678-4c58-b7f9-137d1607d8ec",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, Meridian-sized order, Line 2, mix-to-last-pack (includes fill-up time plus throughput): typical eight to nine hours; one in ten worse than twelve to thirteen hours (breakdowns folded in loosely); one in ten better than about six hours.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"First-pass spread for a Meridian-sized white on Line 2, mix-to-last-pack, with breakdowns folded in loosely; superseded by the clean-run capture.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more \\\\\\\"the filler hiccupped twice\\\\\\\" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "how long it takes",
+          "precision": "spread",
+          "sourceRegime": "practiced",
+          "rationale": "Superseding capture: breakdown time stripped out so filler jams are not double-counted; clean-run variability is small.",
+          "assertion": {
+            "value": "Clean run (nothing breaks — no jam, no QA holdup), white on Line 2: typical eight or nine hours; one in ten worse than nine to ten hours (normal slack, someone slow changing a roll of packaging film); one in ten better than about six hours. The twelve-to-thirteen-hour days are breakdowns showing up inside the run, not the run being slow."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-10d88b79-af70-4a14-90c1-da56ad526d36",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Clean run (nothing breaks — no jam, no QA holdup), white on Line 2: typical eight or nine hours; one in ten worse than nine to ten hours (normal slack, someone slow changing a roll of packaging film); one in ten better than about six hours. The twelve-to-thirteen-hour days are breakdowns showing up inside the run, not the run being slow.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"Superseding capture: breakdown time stripped out so filler jams are not double-counted; clean-run variability is small.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "whether its quantities vary by type",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "P07: run duration varies both by product type and by line, and the two interact.",
+          "assertion": {
+            "value": "Yes. White on Line 1: add maybe fifty, sixty percent to the Line 2 figures — typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten (this is where \"Line 2 is twice as fast\" comes from, and that's really a whites number). Tints: Line 1 and Line 2 run them at nearly the same speed — eight to ten hours typical on either line. No good reason known for why; it's what the sheet has always shown."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-921611c3-21b5-4ab2-8e56-9b8cdaa2eba2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes. White on Line 1: add maybe fifty, sixty percent to the Line 2 figures — typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten (this is where \\\"Line 2 is twice as fast\\\" comes from, and that's really a whites number). Tints: Line 1 and Line 2 run them at nearly the same speed — eight to ten hours typical on either line. No good reason known for why; it's what the sheet has always shown.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"P07: run duration varies both by product type and by line, and the two interact.\",\"slot\":\"whether its quantities vary by type\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "how long it takes",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Expert gave two named repair kinds and one recent instance; no quantiles yet, so range not spread.",
+          "assertion": {
+            "value": "Either the \"half hour\" kind or the \"half a shift\" kind of repair; the recent Line 2 instance came back in about two hours."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I went with waiting, it came back in about two hours, we just scraped the Thursday due date.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-6cf8c229-ab84-4448-abc6-3e7f4a76bb4c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Either the \\\"half hour\\\" kind or the \\\"half a shift\\\" kind of repair; the recent Line 2 instance came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Expert gave two named repair kinds and one recent instance; no quantiles yet, so range not spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours, we just scraped the Thursday due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The jam halts the line's fill stage and forces the switch-or-wait decision.",
+          "assertion": {
+            "value": "The filler stops and the run stalls — the line loses time (half a shift lost in the recent case), the in-progress order's finish is pushed out, and the scheduler must decide whether to shift the order to the other line or wait out the repair."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-ce789325-dd40-4b21-a936-73485ccb90b9",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The filler stops and the run stalls — the line loses time (half a shift lost in the recent case), the in-progress order's finish is pushed out, and the scheduler must decide whether to shift the order to the other line or wait out the repair.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"The jam halts the line's fill stage and forces the switch-or-wait decision.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what is lost when it changes the system's mode",
+          "precision": "number",
+          "sourceRegime": "practiced",
+          "rationale": "P02: named transition (tint to white) with a stated loss; a single figure, not a spread.",
+          "assertion": {
+            "value": "Three hours of washdown — crew time, and it takes the line out of anything else for that window."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-1ba32034-be19-432b-a012-326b682fd357",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of washdown — crew time, and it takes the line out of anything else for that window.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"P02: named transition (tint to white) with a stated loss; a single figure, not a spread.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "rationale": "Triggered by pulling a line off a tint run to run a white.",
+          "assertion": {
+            "value": "A line that is mid-run or last-run on a tint being pulled onto a white — the changeover from tint to white."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line that is mid-run or last-run on a tint being pulled onto a white — the changeover from tint to white.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Triggered by pulling a line off a tint run to run a white.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "how long it takes",
+          "precision": "named",
+          "sourceRegime": "practiced",
+          "rationale": "Vague quantifier — \"usually a few hours\" for a white — not yet quantiles; specialty products wait longer.",
+          "assertion": {
+            "value": "Usually a few hours for a white; \"nothing like the specialty wait\" — specialty products wait longer (amount not given)."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; \\\"nothing like the specialty wait\\\" — specialty products wait longer (amount not given).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Vague quantifier — \\\"usually a few hours\\\" for a white — not yet quantiles; specialty products wait longer.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "QA check gates release to warehouse and shipping.",
+          "assertion": {
+            "value": "The batch is checked and then released, goes to the warehouse, and ships against the due date."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-e28ed067-b6a4-40d8-935a-3598e2401cc1",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The batch is checked and then released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"QA check gates release to warehouse and shipping.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "The lab holds the queue and does the check.",
+          "assertion": {
+            "value": "The lab"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"The lab holds the queue and does the check.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "a line is occupied for the whole run",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "prescribed",
+          "rationale": "P08: the scheduling sheet's rule, which the expert says lies to him a bit.",
+          "assertion": {
+            "value": "On the sheet, a line is one row: the order occupies that line for its whole run, mix through fill, and nothing else is scheduled on it till it's done."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet, a line is one row: the order occupies that line for its whole run, mix through fill, and nothing else is scheduled on it till it's done.\"},\"kind\":\"policy\",\"node\":\"a line is occupied for the whole run\",\"precision\":\"spelled out\",\"rationale\":\"P08: the scheduling sheet's rule, which the expert says lies to him a bit.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "a line is occupied for the whole run",
+          "slot": "what overrides it",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "P08 divergence: floor practice overlaps stages when buffer space allows.",
+          "assertion": {
+            "value": "On the floor the crew will get a head start on mixing the next batch if the tank ahead of it has space — the mixer can start the next order while the fill head finishes the last one. How much overlap happens, and how often it is blocked because a tank is full, is not tracked."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-cfe5bf57-8879-4592-a938-1527d73c8bac",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the floor the crew will get a head start on mixing the next batch if the tank ahead of it has space — the mixer can start the next order while the fill head finishes the last one. How much overlap happens, and how often it is blocked because a tank is full, is not tracked.\"},\"kind\":\"policy\",\"node\":\"a line is occupied for the whole run\",\"precision\":\"spelled out\",\"rationale\":\"P08 divergence: floor practice overlaps stages when buffer space allows.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "who can absorb the slip",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The practiced rule for choosing which order to bump; explicitly judgement, not formula.",
+          "assertion": {
+            "value": "Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem. No formula — \"how bad is bad\" for the second-order stuff."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I use judgment on who can absorb the slip",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem. No formula — \\\"how bad is bad\\\" for the second-order stuff.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The practiced rule for choosing which order to bump; explicitly judgement, not formula.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "who can absorb the slip",
+          "slot": "what overrides it",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The hard on-time line overrides the slip-absorption weighing.",
+          "assertion": {
+            "value": "The Meridian-style on-time line overrides everything: that order shipping on time is non-negotiable unless there's truly no way through."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The Meridian-style on-time line overrides everything: that order shipping on time is non-negotiable unless there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The hard on-time line overrides the slip-absorption weighing.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "constraint",
+          "node": "small holding tanks between stages",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "named",
+          "sourceRegime": "practiced",
+          "rationale": "Consequence named (mixing has to wait when the tank ahead is full) but the capacities themselves are not held by the expert; source named.",
+          "assertion": {
+            "absence": "deferred",
+            "pointer": "engineering drawings — tank sizes; consequence as stated: the tanks are small, especially the one between mill and fill on Line 1, and when a tank is full mixing has to wait"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-23c5706e-37c1-481e-9438-8fae70973c13",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings — tank sizes; consequence as stated: the tanks are small, especially the one between mill and fill on Line 1, and when a tank is full mixing has to wait\"},\"kind\":\"constraint\",\"node\":\"small holding tanks between stages\",\"precision\":\"named\",\"rationale\":\"Consequence named (mixing has to wait when the tank ahead is full) but the capacities themselves are not held by the expert; source named.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "data-binding",
+          "node": "stage-by-stage durations from the historian",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "rationale": "Stage-level rates exist as data but not in the expert's head; feed named.",
+          "assertion": {
+            "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) per SKU and line — feed: the historian. Never pulled apart; only end-to-end batch time per SKU per line is on the scheduling sheet."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-00863ee1-f99c-48b2-b680-bf4eb71e6a57",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) per SKU and line — feed: the historian. Never pulled apart; only end-to-end batch time per SKU per line is on the scheduling sheet.\"},\"kind\":\"data-binding\",\"node\":\"stage-by-stage durations from the historian\",\"precision\":\"named\",\"rationale\":\"Stage-level rates exist as data but not in the expert's head; feed named.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "validation-criterion",
+          "node": "stage rates must come from data, not gut-feel",
+          "slot": "how the expert would know the model is right",
+          "precision": "spelled out",
+          "rationale": "Expert explicitly bounds what his own testimony can support.",
+          "assertion": {
+            "value": "Stage-level rates and tank sizes must not be taken from the expert's gut-feel — he can supply gut-feel and known bottleneck stories, but real numbers must come from the historian and engineering drawings."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-196b8447-3958-444f-9860-8de7330299ec",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-level rates and tank sizes must not be taken from the expert's gut-feel — he can supply gut-feel and known bottleneck stories, but real numbers must come from the historian and engineering drawings.\"},\"kind\":\"validation-criterion\",\"node\":\"stage rates must come from data, not gut-feel\",\"precision\":\"spelled out\",\"rationale\":\"Expert explicitly bounds what his own testimony can support.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "switch or wait when Line 2 goes down",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "rationale": "The expert wrote the question as he would type it into the tool.",
+          "assertion": {
+            "value": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\""
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-b58883f3-43e2-4626-bc59-a9c091f1d1b5",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\"\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down\",\"precision\":\"spelled out\",\"rationale\":\"The expert wrote the question as he would type it into the tool.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "switch or wait when Line 2 goes down",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "The expert listed what the answer hangs on: the protected run and its due date, the state of Line 1, the changeover and its direction, the jam duration, and whose order gets bumped.",
+          "assertion": {
+            "value": [
+              "entity-type:order",
+              "entity-type:line",
+              "activity:run it through mix/mill/tint/fill",
+              "activity:tint-to-white washdown",
+              "activity:filler jam",
+              "policy:who can absorb the slip"
+            ]
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the bumped order's identity matters, not just \"an order got delayed.\"",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-3aa3764b-8dd5-495a-bf3e-b32cbc89ba61",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:line\",\"activity:run it through mix/mill/tint/fill\",\"activity:tint-to-white washdown\",\"activity:filler jam\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down\",\"precision\":\"named\",\"rationale\":\"The expert listed what the answer hangs on: the protected run and its due date, the state of Line 1, the changeover and its direction, the jam duration, and whose order gets bumped.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the bumped order's identity matters, not just \\\\\\\"an order got delayed.\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "switch or wait when Line 2 goes down",
+          "slot": "what \"better\" means, and trade-off weights",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Expert gave a lexicographic hard constraint plus unweighted second-order criteria, explicitly denying a formula.",
+          "assertion": {
+            "value": "Hard line: days late on Meridian, anything above zero is bad news. Underneath that, weighed by judgment with no formula: washdown hours, and whether the bumped order goes late and by how much and for which customer."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-57ad71c3-f423-4d91-a9f8-d3ce31f1fca1",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Hard line: days late on Meridian, anything above zero is bad news. Underneath that, weighed by judgment with no formula: washdown hours, and whether the bumped order goes late and by how much and for which customer.\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down\",\"precision\":\"spelled out\",\"rationale\":\"Expert gave a lexicographic hard constraint plus unweighted second-order criteria, explicitly denying a formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "is the mill-to-fill tank on Line 1 slowing the line down",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "rationale": "Second question the expert wrote out as he would type it.",
+          "assertion": {
+            "value": "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\""
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-1a3325b9-15b6-436a-8e7f-feff95d98036",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\"\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"rationale\":\"Second question the expert wrote out as he would type it.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "is the mill-to-fill tank on Line 1 slowing the line down",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "Expert named stage-level rates on Line 1, the tank size between mill and fill, and per-SKU stage differences.",
+          "assertion": {
+            "value": [
+              "entity-type:the four stages — mix, mill, tint, fill",
+              "constraint:small holding tank between mill and fill on Line 1",
+              "entity-type:order",
+              "entity-type:line"
+            ]
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-0e28490a-6b4b-4996-9b6f-3d9249a7d2dc",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:the four stages — mix, mill, tint, fill\",\"constraint:small holding tank between mill and fill on Line 1\",\"entity-type:order\",\"entity-type:line\"]},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"named\",\"rationale\":\"Expert named stage-level rates on Line 1, the tank size between mill and fill, and per-SKU stage differences.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "state that rides along with each instance",
+          "precision": "spelled out",
+          "rationale": "Expert named the fields the order carries from the demand book and the state he consults mid-disruption.",
+          "assertion": {
+            "value": "Quantity, due date, SKU; remaining quantity as it runs; the customer it belongs to; how far through it is; which line and slot it is allocated to."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "whose order was it — that's the \"who can absorb it\" judgment call again",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-43c5ef42-68ce-478f-89b0-c552111d807a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; remaining quantity as it runs; the customer it belongs to; how far through it is; which line and slot it is allocated to.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Expert named the fields the order carries from the demand book and the state he consults mid-disruption.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whose order was it — that's the \\\\\\\"who can absorb it\\\\\\\" judgment call again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "rationale": "The process treats whites and tints differently at the tint stage and in run times; customer type changes how a slip is judged.",
+          "assertion": {
+            "value": "Whites versus tints (for a white the tint stage is barely there, a pass-through); and by customer type — distributor, small account, or an awkward account that gets prickly."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-ccc2d7eb-8a3f-4684-8f1c-a21a51049550",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints (for a white the tint stage is barely there, a pass-through); and by customer type — distributor, small account, or an awkward account that gets prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The process treats whites and tints differently at the tint stage and in run times; customer type changes how a slip is judged.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "line",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "sourceRegime": "prescribed",
+          "rationale": "The sheet's representation of a line, which the expert says 'lies to me a bit'.",
+          "assertion": {
+            "value": "On the scheduling sheet a line is one row and one resource: an order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the scheduling sheet a line is one row and one resource: an order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"spelled out\",\"rationale\":\"The sheet's representation of a line, which the expert says 'lies to me a bit'.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "the four stages — mix, mill, tint, fill",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The floor's version of the line: four contended stages with buffers, not one resource.",
+          "assertion": {
+            "value": "Physically mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head finishes the last one if the tank ahead has space."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the crew will get a head start on mixing the next batch if the tank ahead of it has space",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a158a5da-be3a-461f-87c0-69c38cac1a72",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head finishes the last one if the tank ahead has space.\"},\"kind\":\"entity-type\",\"node\":\"the four stages — mix, mill, tint, fill\",\"precision\":\"spelled out\",\"rationale\":\"The floor's version of the line: four contended stages with buffers, not one resource.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the crew will get a head start on mixing the next batch if the tank ahead of it has space\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "the four stages — mix, mill, tint, fill",
+          "slot": "how many there are, or the population's shape",
+          "precision": "named",
+          "rationale": "Count of stages is stated; occupancy/blocking frequency is explicitly untracked.",
+          "assertion": {
+            "value": "Four stages in series per line — mix, mill, tint, fill — with small holding tanks between them; how often blocking occurs is not tracked."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Four stages in series per line — mix, mill, tint, fill — with small holding tanks between them; how often blocking occurs is not tracked.\"},\"kind\":\"entity-type\",\"node\":\"the four stages — mix, mill, tint, fill\",\"precision\":\"named\",\"rationale\":\"Count of stages is stated; occupancy/blocking frequency is explicitly untracked.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Expert's step one.",
+          "assertion": {
+            "value": "The order is slotted onto a line and a slot in the week on the sheet."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-4043a577-c1b4-44c3-91f3-2194def82bd9",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Expert's step one.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "rationale": "Precondition named in the walkthrough.",
+          "assertion": {
+            "value": "A line item in the demand book, produced by ERP, carrying quantity, due date and SKU."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book, produced by ERP, carrying quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Precondition named in the walkthrough.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "boundary-condition",
+          "node": "demand book from ERP",
+          "slot": "the starting state",
+          "precision": "spelled out",
+          "rationale": "External source of work into the scheduling process.",
+          "assertion": {
+            "value": "Orders exist as line items in the demand book, each with quantity, due date and SKU, once ERP produces it."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders exist as line items in the demand book, each with quantity, due date and SKU, once ERP produces it.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"spelled out\",\"rationale\":\"External source of work into the scheduling process.\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "how long it takes",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Expert corrected his first spread to strip out jams, so the clean-run figure supersedes; no one-in-ten-better figure was given for the clean run.",
+          "assertion": {
+            "value": "Meridian-sized white on Line 2, clean run (nothing breaks): typically eight to nine hours mix-to-last-pack; a bad-but-clean day nine to ten hours. Clean-run variability is small; the twelve-to-thirteen-hour bad days are breakdowns showing up inside the run and are modelled separately."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-72d414e6-f6a2-420e-8407-667f41535411",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian-sized white on Line 2, clean run (nothing breaks): typically eight to nine hours mix-to-last-pack; a bad-but-clean day nine to ten hours. Clean-run variability is small; the twelve-to-thirteen-hour bad days are breakdowns showing up inside the run and are modelled separately.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"range\",\"rationale\":\"Expert corrected his first spread to strip out jams, so the clean-run figure supersedes; no one-in-ten-better figure was given for the clean run.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
+          "rationale": "Durations vary by line and by white-versus-tint; the Line 1 figures were given before the clean-run/breakdown split and may still fold in stoppages.",
+          "assertion": {
+            "value": "Yes. Same white order on Line 1 is about fifty to sixty percent longer than Line 2 — typical thirteen to fourteen hours, worse days eighteen-plus, best day about ten. Tints run at nearly the same speed on either line, about eight to ten hours typical, with no big gap; the 'Line 2 is twice as fast' rule is really a whites number."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes. Same white order on Line 1 is about fifty to sixty percent longer than Line 2 — typical thirteen to fourteen hours, worse days eighteen-plus, best day about ten. Tints run at nearly the same speed on either line, about eight to ten hours typical, with no big gap; the 'Line 2 is twice as fast' rule is really a whites number.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Durations vary by line and by white-versus-tint; the Line 1 figures were given before the clean-run/breakdown split and may still fold in stoppages.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "run it through mix/mill/tint/fill",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "Runs are performed on a named line; the expert compares Line 1 and Line 2 as the performing kit.",
+          "assertion": {
+            "value": "One of the two production lines (Line 1 or Line 2) with its crew."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-53f9387d-f037-4d0f-999b-f89a8f113f46",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One of the two production lines (Line 1 or Line 2) with its crew.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Runs are performed on a named line; the expert compares Line 1 and Line 2 as the performing kit.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "Named performer in the walkthrough.",
+          "assertion": {
+            "value": "The lab."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Named performer in the walkthrough.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "how long it takes",
+          "precision": "named",
+          "rationale": "Only a vague 'few hours' was given; not yet a range or spread.",
+          "assertion": {
+            "value": "Usually a few hours for a white; explicitly longer for specialty ('nothing like the specialty wait'), figure not given."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-38e0effa-0fb7-48ff-907c-2fc9f3e64211",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; explicitly longer for specialty ('nothing like the specialty wait'), figure not given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Only a vague 'few hours' was given; not yet a range or spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "release and ship",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Final step of the walkthrough.",
+          "assertion": {
+            "value": "The order is released, goes to the warehouse, and ships against its due date."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against its due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"rationale\":\"Final step of the walkthrough.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "order life on the floor",
+          "slot": "the order things happen in",
+          "precision": "spelled out",
+          "rationale": "Expert's own summary of the end-to-end sequence.",
+          "assertion": {
+            "value": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-314d8187-81ba-478c-8f71-1c9e5826965b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\"},\"kind\":\"ordering/flow\",\"node\":\"order life on the floor\",\"precision\":\"spelled out\",\"rationale\":\"Expert's own summary of the end-to-end sequence.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "how long it takes",
+          "precision": "number",
+          "rationale": "Single figure given for the tint-to-white washdown; no spread elicited.",
+          "assertion": {
+            "value": "Three hours"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-345fbb5a-c0c1-4e3a-9015-33b3ad727831",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Single figure given for the tint-to-white washdown; no spread elicited.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "rationale": "Changeover is directional and triggered by the family of what was running versus what is coming.",
+          "assertion": {
+            "value": "A changeover between product families on the same line; the direction decides the cost — tint-to-white is the expensive one, not the other way."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "the direction of the changeover matters as much as the fact of it",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-60f6f8c8-f52e-443a-adee-6818339f3b35",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A changeover between product families on the same line; the direction decides the cost — tint-to-white is the expensive one, not the other way.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Changeover is directional and triggered by the family of what was running versus what is coming.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the direction of the changeover matters as much as the fact of it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Stated consequence of the washdown.",
+          "assertion": {
+            "value": "The line is cleaned from tint to white and is taken out of anything else for that window; it costs crew time."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it takes Line 1 out of anything else for that window",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-be556841-bf14-4fe0-8c23-ffc773896b2b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line is cleaned from tint to white and is taken out of anything else for that window; it costs crew time.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Stated consequence of the washdown.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what is lost when it changes the system's mode",
+          "rationale": "Loss is named and affirmed as material but no quantity is held by the expert.",
+          "assertion": {
+            "absence": "unknown-to-user",
+            "pointer": "ramp scrap after the washdown — real product lost on top of the hours; expert has no good numbers"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-26d3ac6c-4b27-4765-baa3-8437f06fe8ca",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"ramp scrap after the washdown — real product lost on top of the hours; expert has no good numbers\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"rationale\":\"Loss is named and affirmed as material but no quantity is held by the expert.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "how long it takes",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "rationale": "Expert gave two named kinds of repair plus one observed instance; no typical or decile figures yet.",
+          "assertion": {
+            "value": "Between the 'half hour' kind and the 'half a shift' kind; the recent Line 2 case came back in about two hours."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I went with waiting, it came back in about two hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-da6d10a4-e0f2-4b1d-8e78-4d58cadeb8f2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Between the 'half hour' kind and the 'half a shift' kind; the recent Line 2 case came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Expert gave two named kinds of repair plus one observed instance; no typical or decile figures yet.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "rationale": "Event-shaped activity that befalls the line, distinct from the run itself.",
+          "assertion": {
+            "value": "The filler stops mid-run and the line is down for the repair; the run in progress stretches (the twelve-to-thirteen-hour bad days), and the scheduler must decide to wait or shift the order to the other line."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-68f9db28-a002-406d-912a-4cc410e5b380",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The filler stops mid-run and the line is down for the repair; the run in progress stretches (the twelve-to-thirteen-hour bad days), and the scheduler must decide to wait or shift the order to the other line.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"Event-shaped activity that befalls the line, distinct from the run itself.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "how often it occurs, if it is an event rather than a step",
+          "rationale": "No rate was stated; recording the gap rather than inferring one from the single incident.",
+          "assertion": {
+            "absence": "unknown-to-user",
+            "pointer": "frequency of filler jams was not given; expert spoke only to duration uncertainty at the time of the jam"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of \"could be quick, could be long\" rather than one number",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-0a06d184-bf72-42c4-95b3-7ad88ea4e059",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"frequency of filler jams was not given; expert spoke only to duration uncertainty at the time of the jam\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"rationale\":\"No rate was stated; recording the gap rather than inferring one from the single incident.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of \\\\\\\"could be quick, could be long\\\\\\\" rather than one number\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "who can absorb the slip",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "The tacit rule for choosing which order to bump; no formula, judged on customer identity and size of slip.",
+          "assertion": {
+            "value": "Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first, so it is protected."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I use judgment on who can absorb the slip",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first, so it is protected.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The tacit rule for choosing which order to bump; no formula, judged on customer identity and size of slip.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "who can absorb the slip",
+          "slot": "what overrides it",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "rationale": "Hard constraint sitting above the absorb-the-slip judgment.",
+          "assertion": {
+            "value": "The protected order's on-time ship date overrides: shipping Meridian on time is a line he won't cross unless there's truly no way through."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The protected order's on-time ship date overrides: shipping Meridian on time is a line he won't cross unless there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint sitting above the absorb-the-slip judgment.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "constraint",
+          "node": "small holding tank between mill and fill on Line 1",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "rationale": "Qualitative blocking rule stated; the numeric capacity is not available from the expert.",
+          "assertion": {
+            "value": "Holding tanks between stages are small — especially the one between mill and fill on Line 1. When there is room, the upstream stage can start the next order's batch; when the tank is full, the upstream stage is blocked and mixing has to wait. Actual tank capacity is not held by the expert; engineering's position is that the line rate is what it is regardless."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-7111ab55-5d90-44f6-a1d2-4aa1b48da4bb",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tanks between stages are small — especially the one between mill and fill on Line 1. When there is room, the upstream stage can start the next order's batch; when the tank is full, the upstream stage is blocked and mixing has to wait. Actual tank capacity is not held by the expert; engineering's position is that the line rate is what it is regardless.\"},\"kind\":\"constraint\",\"node\":\"small holding tank between mill and fill on Line 1\",\"precision\":\"spelled out\",\"rationale\":\"Qualitative blocking rule stated; the numeric capacity is not available from the expert.\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "data-binding",
+          "node": "stage-level rates",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "rationale": "Expert named the system where the missing stage-level numbers live.",
+          "assertion": {
+            "value": "Stage-by-stage durations/rates (how long mixing takes, how long milling takes, mill speed versus fill speed on Line 1) — feed: the historian."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations/rates (how long mixing takes, how long milling takes, mill speed versus fill speed on Line 1) — feed: the historian.\"},\"kind\":\"data-binding\",\"node\":\"stage-level rates\",\"precision\":\"named\",\"rationale\":\"Expert named the system where the missing stage-level numbers live.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "data-binding",
+          "node": "tank sizes",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "rationale": "Named source for a value the expert cannot give.",
+          "assertion": {
+            "value": "Holding tank capacities between stages — feed: engineering drawings, obtainable but not carried by the expert."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tank capacities between stages — feed: engineering drawings, obtainable but not carried by the expert.\"},\"kind\":\"data-binding\",\"node\":\"tank sizes\",\"precision\":\"named\",\"rationale\":\"Named source for a value the expert cannot give.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "switch or wait when Line 2 goes down mid-run",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "rationale": "The expert wrote the question as they would type it into the tool.",
+          "assertion": {
+            "value": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\""
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-1a240192-8179-4339-815e-3775a062e986",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\"\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down mid-run\",\"precision\":\"spelled out\",\"rationale\":\"The expert wrote the question as they would type it into the tool.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "switch or wait when Line 2 goes down mid-run",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "rationale": "The expert listed what the answer hangs on.",
+          "assertion": {
+            "value": [
+              "entity-type:order",
+              "entity-type:Line 1 and Line 2",
+              "activity:the run (mix, mill, tint, fill)",
+              "activity:filler jam",
+              "activity:tint-to-white washdown",
+              "policy:who can absorb the slip",
+              "constraint:Meridian ships on time"
+            ]
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "It hangs on the jam itself — how long is this repair *actually* going to take",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "And it hangs on the ramp scrap after the washdown",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the \"who can absorb it\" judgment call again.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-85062afa-e82d-46ce-b609-f7ed16f8b093",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:Line 1 and Line 2\",\"activity:the run (mix, mill, tint, fill)\",\"activity:filler jam\",\"activity:tint-to-white washdown\",\"policy:who can absorb the slip\",\"constraint:Meridian ships on time\"]},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down mid-run\",\"precision\":\"named\",\"rationale\":\"The expert listed what the answer hangs on.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And it hangs on the ramp scrap after the washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the \\\\\\\"who can absorb it\\\\\\\" judgment call again.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It hangs on the jam itself — how long is this repair *actually* going to take\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "switch or wait when Line 2 goes down mid-run",
+          "slot": "what \"better\" means, and trade-off weights",
+          "precision": "spelled out",
+          "rationale": "Hard constraint plus unweighted secondary measures; the expert explicitly denied having a formula.",
+          "assertion": {
+            "value": "Meridian on time is non-negotiable (days late on Meridian, anything above zero is bad news); underneath that, washdown hours and whether the bumped order goes late and by how much are weighed by judgment — \"I don't have a formula for it.\""
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I don't have a formula for it.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "days late on Meridian, and anything above zero is bad news I have to go explain",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-2c3fa15f-551b-4380-a3b3-8dbc6334a9bb",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian on time is non-negotiable (days late on Meridian, anything above zero is bad news); underneath that, washdown hours and whether the bumped order goes late and by how much are weighed by judgment — \\\"I don't have a formula for it.\\\"\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down mid-run\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint plus unweighted secondary measures; the expert explicitly denied having a formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"days late on Meridian, and anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "is the mill-to-fill tank on Line 1 slowing the line down",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\""
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-41269bfb-9040-4d54-a113-a94c09f6f2f0",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\"\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "is the mill-to-fill tank on Line 1 slowing the line down",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "assertion": {
+            "value": [
+              "entity-type:mix, mill, tint, fill kit and holding tanks",
+              "entity-type:Line 1 and Line 2",
+              "entity-type:order",
+              "ordering/flow:stage overlap on a line"
+            ]
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "It also probably depends on the product, since I now realize different SKUs are slow at different stages",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-f7ea7c88-4d40-48e7-84e5-2b12ebc5ea8e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:mix, mill, tint, fill kit and holding tanks\",\"entity-type:Line 1 and Line 2\",\"entity-type:order\",\"ordering/flow:stage overlap on a line\"]},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"named\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It also probably depends on the product, since I now realize different SKUs are slow at different stages\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "is the mill-to-fill tank on Line 1 slowing the line down",
+          "slot": "what \"better\" means, and trade-off weights",
+          "precision": "spelled out",
+          "rationale": "Qualitative: showing where Line 1 loses its time, in a form usable with engineering.",
+          "assertion": {
+            "value": "The model showing \"here's where Line 1 loses its time\" — something to take to engineering other than a hunch; no numeric weighting given."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The model showing \\\"here's where Line 1 loses its time\\\" — something to take to engineering other than a hunch; no numeric weighting given.\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"rationale\":\"Qualitative: showing where Line 1 loses its time, in a form usable with engineering.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "Whites versus tints (family decides run speed by line and washdown direction; for a white the tint stage is a pass-through); and customer identity — distributor, small account, or an awkward account that gets prickly."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the bumped order's identity matters, not just \"an order got delayed.\"",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-0e8d50b2-4222-4129-a619-09c5612c05c5",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints (family decides run speed by line and washdown direction; for a white the tint stage is a pass-through); and customer identity — distributor, small account, or an awkward account that gets prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the bumped order's identity matters, not just \\\\\\\"an order got delayed.\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "state that rides along with each instance",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "Quantity, due date, SKU; family (white/tint); customer; remaining quantity and how far through the run it is."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-117f9832-aaba-473a-9411-6fd4022388f2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; family (white/tint); customer; remaining quantity and how far through the run it is.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order",
+          "slot": "how many there are, or the population's shape",
+          "precision": "named",
+          "rationale": "The expert described orders arriving as line items in the demand book but gave no counts or arrival volumes.",
+          "assertion": {
+            "absence": "unknown-to-user",
+            "pointer": "demand book / ERP"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-e10d4081-78ed-42da-bb26-857f1118224c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"demand book / ERP\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"named\",\"rationale\":\"The expert described orders arriving as line items in the demand book but gave no counts or arrival volumes.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "Line 1 and Line 2",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "Two lines: Line 2 is the faster machine on whites (roughly twice as fast, \"really a whites number\"); Line 1 is the slower machine, add fifty to sixty percent on a white. On tints the two run at nearly the same speed."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-875ed21b-d257-48fe-867b-6785abf6abb7",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two lines: Line 2 is the faster machine on whites (roughly twice as fast, \\\"really a whites number\\\"); Line 1 is the slower machine, add fifty to sixty percent on a white. On tints the two run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "Line 1 and Line 2",
+          "slot": "state that rides along with each instance",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "What order is on it, how far through that order is, and what family (tint or white) it is currently running — the last decides washdown cost and direction."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-06d48b41-86fb-48c0-b3e0-59012ba81960",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"What order is on it, how far through that order is, and what family (tint or white) it is currently running — the last decides washdown cost and direction.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "Line 1 and Line 2",
+          "slot": "how many there are, or the population's shape",
+          "precision": "number",
+          "rationale": "The expert speaks only of Line 1 and Line 2 throughout.",
+          "assertion": {
+            "value": "Two lines — Line 1 and Line 2."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On the sheet, \"Line 2\" is one row",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Line 1 was mid-run on a tint.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-428e3931-676d-4af5-a30c-d7a31ea0d8ad",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two lines — Line 1 and Line 2.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"number\",\"rationale\":\"The expert speaks only of Line 1 and Line 2 throughout.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "mix, mill, tint, fill kit and holding tanks",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "assertion": {
+            "value": "Mix, mill, tint and fill are separate tanks and separate kit strung together, with small holding tanks between them."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-ecd3c093-8f6b-4a48-a1fc-d2775d4dbc1f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Mix, mill, tint and fill are separate tanks and separate kit strung together, with small holding tanks between them.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill kit and holding tanks\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "mix, mill, tint, fill kit and holding tanks",
+          "slot": "how many there are, or the population's shape",
+          "precision": "named",
+          "rationale": "Qualitative \"small\" only; sizes deferred to engineering drawings.",
+          "assertion": {
+            "absence": "deferred",
+            "pointer": "engineering drawings"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-c6339dee-036e-47cb-9dcf-42fc22d38aae",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill kit and holding tanks\",\"precision\":\"named\",\"rationale\":\"Qualitative \\\"small\\\" only; sizes deferred to engineering drawings.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "constraint",
+          "node": "holding tank capacity between stages",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "rationale": "Blocking consequence stated; frequency and size not tracked.",
+          "assertion": {
+            "value": "A stage can only get a head start if there's room in the holding tank ahead of it; when a tank's full, mixing has to wait. How often that blocking happens is not tracked by the expert."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "if there's room in the holding tank between mix and mill, or mill and fill, to buffer it",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-2bc071c4-2919-4ff3-910a-92d872eeaef2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A stage can only get a head start if there's room in the holding tank ahead of it; when a tank's full, mixing has to wait. How often that blocking happens is not tracked by the expert.\"},\"kind\":\"constraint\",\"node\":\"holding tank capacity between stages\",\"precision\":\"spelled out\",\"rationale\":\"Blocking consequence stated; frequency and size not tracked.\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if there's room in the holding tank between mix and mill, or mill and fill, to buffer it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "order lifecycle: allocate, run, QA hold, release and ship",
+          "slot": "the order things happen in",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-6ec49aac-c165-4e2b-a937-bed3c8c51c2c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\"},\"kind\":\"ordering/flow\",\"node\":\"order lifecycle: allocate, run, QA hold, release and ship\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "order lifecycle: allocate, run, QA hold, release and ship",
+          "slot": "how a branch or merge is decided",
+          "precision": "spelled out",
+          "rationale": "The line choice is made by the scheduler at allocation and can be revisited on disruption.",
+          "assertion": {
+            "value": "The scheduler slots the order onto a line on the sheet at allocation; on a disruption the choice is re-decided — shift it to the other line or wait out the repair."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I had to decide right then whether to shift it to Line 1 or just wait out the repair",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-c3f03d77-6760-4b3b-99e5-b78d119a352f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The scheduler slots the order onto a line on the sheet at allocation; on a disruption the choice is re-decided — shift it to the other line or wait out the repair.\"},\"kind\":\"ordering/flow\",\"node\":\"order lifecycle: allocate, run, QA hold, release and ship\",\"precision\":\"spelled out\",\"rationale\":\"The line choice is made by the scheduler at allocation and can be revisited on disruption.\",\"slot\":\"how a branch or merge is decided\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had to decide right then whether to shift it to Line 1 or just wait out the repair\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "stage overlap on a line",
+          "slot": "the order things happen in",
+          "precision": "spelled out",
+          "sourceRegime": "prescribed",
+          "assertion": {
+            "value": "On the sheet the line is one row: the order occupies the line for its whole run, mix through fill, and nothing else is scheduled on it until it's done."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet the line is one row: the order occupies the line for its whole run, mix through fill, and nothing else is scheduled on it until it's done.\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "stage overlap on a line",
+          "slot": "the order things happen in",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "assertion": {
+            "value": "The mixer can start the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill; the crew get a head start on mixing when the tank ahead has space."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-83e1381a-f2df-4713-a2f6-f11d034c2fd4",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The mixer can start the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill; the crew get a head start on mixing when the tank ahead has space.\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "the run (mix, mill, tint, fill)",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "The order allocated onto a line and a slot in the week (\"I slot it onto Line 2 on the sheet, that's step one, allocation\")."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-95cbfe20-605f-4218-9076-0f4816ebadfa",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order allocated onto a line and a slot in the week (\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\").\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "the run (mix, mill, tint, fill)",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "Filled and packed product coming off the fill line, which then goes into QA hold."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-1a5a8343-7367-416e-b760-c7e8f587fe25",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Filled and packed product coming off the fill line, which then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "the run (mix, mill, tint, fill)",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "assertion": {
+            "value": "The line (Line 1 or Line 2) — its mix, mill, tint and fill kit — worked by the crew."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "mix, mill, tint, fill are separate tanks and separate kit strung together",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "maybe six hours if everything's clean and the crew doesn't have to stop for anything",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-bf2e57a3-bda7-4090-92ca-af63e0c7a248",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line (Line 1 or Line 2) — its mix, mill, tint and fill kit — worked by the crew.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maybe six hours if everything's clean and the crew doesn't have to stop for anything\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill are separate tanks and separate kit strung together\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "the run (mix, mill, tint, fill)",
+          "slot": "how long it takes",
+          "precision": "spread",
+          "rationale": "First account of a white run on Line 2, mix-to-last-pack, including breakdowns folded in loosely.",
+          "assertion": {
+            "value": "White, Line 2, normal order size, mix-to-last-pack: typical eight to nine hours; one in ten worse twelve to thirteen hours; one in ten better about six hours. (Expert later said the twelve-thirteen folds in breakdowns.)"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-aec8ff27-3e3f-45d2-9142-b6dc2b5d88a3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, Line 2, normal order size, mix-to-last-pack: typical eight to nine hours; one in ten worse twelve to thirteen hours; one in ten better about six hours. (Expert later said the twelve-thirteen folds in breakdowns.)\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"rationale\":\"First account of a white run on Line 2, mix-to-last-pack, including breakdowns folded in loosely.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "the run (mix, mill, tint, fill)",
+          "slot": "how long it takes",
+          "precision": "spread",
+          "rationale": "Supersedes the earlier figure by stripping breakdowns out of the run duration; jams are modelled separately.",
+          "assertion": {
+            "value": "Clean run (nothing breaks), white on Line 2: typical eight or nine hours; bad-but-clean one in ten nine to ten hours; one in ten better about six hours. The twelve-thirteen hour bad day is a breakdown showing up inside the run, not the run itself being slow."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-9d59a385-a8ae-410a-a13d-a4bca3dde9a3",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Clean run (nothing breaks), white on Line 2: typical eight or nine hours; bad-but-clean one in ten nine to ten hours; one in ten better about six hours. The twelve-thirteen hour bad day is a breakdown showing up inside the run, not the run itself being slow.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"rationale\":\"Supersedes the earlier figure by stripping breakdowns out of the run duration; jams are modelled separately.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "the run (mix, mill, tint, fill)",
+          "slot": "how long it takes",
+          "precision": "spread",
+          "rationale": "Same white order on Line 1.",
+          "assertion": {
+            "value": "White on Line 1: typical thirteen to fourteen hours; worse days pushing eighteen-plus; best day maybe ten — roughly fifty to sixty percent more than Line 2."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-4b22a066-a97c-4329-8513-cbd85edd8d65",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White on Line 1: typical thirteen to fourteen hours; worse days pushing eighteen-plus; best day maybe ten — roughly fifty to sixty percent more than Line 2.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"rationale\":\"Same white order on Line 1.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "the run (mix, mill, tint, fill)",
+          "slot": "how long it takes",
+          "precision": "range",
+          "rationale": "Only a typical range was given for tints; no one-in-ten figures.",
+          "assertion": {
+            "value": "Tint run on either line: eight to ten hours typical; no big gap between the lines. One-in-ten worse/better not given."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-63fabb67-24c4-4bee-926f-17917300c8f4",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Tint run on either line: eight to ten hours typical; no big gap between the lines. One-in-ten worse/better not given.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"range\",\"rationale\":\"Only a typical range was given for tints; no one-in-ten figures.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "the run (mix, mill, tint, fill)",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
+          "assertion": {
+            "value": "Yes — run time varies by family and by line: whites are about twice as fast on Line 2 as Line 1, tints run at nearly the same speed on both; and different SKUs are slow at different stages."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "since I now realize different SKUs are slow at different stages",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-b1e5ded4-79d6-4ff4-bd0d-6386509efba9",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — run time varies by family and by line: whites are about twice as fast on Line 2 as Line 1, tints run at nearly the same speed on both; and different SKUs are slow at different stages.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"named\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"since I now realize different SKUs are slow at different stages\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "It stops the run on the line — \"Line 2 filler jammed at about nine in the morning, half a shift lost\" — forcing the wait-or-shift decision."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-147c2765-6bfb-4da0-9df9-b74a1c1049de",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"It stops the run on the line — \\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\" — forcing the wait-or-shift decision.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "how often it occurs, if it is an event rather than a step",
+          "precision": "range",
+          "rationale": "Line 2 filler, jams bad enough to stop the run.",
+          "assertion": {
+            "value": "Every week or two; low end once every three weeks, high end twice a week when temperamental. Not seasonal, but runs streaks of bad weeks."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "It's a \"every week or two\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-ec5740e7-5068-4222-ad24-8396f5975657",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Every week or two; low end once every three weeks, high end twice a week when temperamental. Not seasonal, but runs streaks of bad weeks.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Line 2 filler, jams bad enough to stop the run.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It's a \\\\\\\"every week or two\\\\\\\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "how long it takes",
+          "precision": "spread",
+          "assertion": {
+            "value": "Typical repair thirty to forty-five minutes; one-in-ten quick ten to fifteen minutes (a false alarm); one-in-ten bad four to five hours, occasionally eating the rest of the shift, when something's actually broken in the filler head."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-2884cc84-c616-4227-860a-d6b55a06c13d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Typical repair thirty to forty-five minutes; one-in-ten quick ten to fifteen minutes (a false alarm); one-in-ten bad four to five hours, occasionally eating the rest of the shift, when something's actually broken in the filler head.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "rationale": "Repair is done by a tech.",
+          "assertion": {
+            "value": "A tech — comes over, clears whatever's jammed, resets."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "tech comes over, clears whatever's jammed, resets, we're going again",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-0548a680-8da8-47e9-ad72-fb1e264fac80",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A tech — comes over, clears whatever's jammed, resets.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"named\",\"rationale\":\"Repair is done by a tech.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"tech comes over, clears whatever's jammed, resets, we're going again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "rationale": "At the time of the decision the repair length is unobservable to the scheduler.",
+          "assertion": {
+            "value": "Repair duration is not known at the time of the decision — \"which I never know at the time\"; only \"could be quick, could be long\"."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "how long is this repair *actually* going to take, which I never know at the time",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-8c6a716b-e09a-4977-94d9-f28ab74be7c4",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Repair duration is not known at the time of the decision — \\\"which I never know at the time\\\"; only \\\"could be quick, could be long\\\".\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"At the time of the decision the repair length is unobservable to the scheduler.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"how long is this repair *actually* going to take, which I never know at the time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "how long it takes",
+          "precision": "number",
+          "rationale": "Single figure given; no spread elicited.",
+          "assertion": {
+            "value": "Three hours for a tint-to-white washdown."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I eat a tint-to-white washdown — three hours",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a67683fd-0f34-4838-b48e-aa01f657a511",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours for a tint-to-white washdown.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Single figure given; no spread elicited.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "A changeover of family on the line; the direction matters as much as the fact of it — tint-to-white is the expensive one, not the other way."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "the direction of the changeover matters as much as the fact of it",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-1b632a29-f1de-48e5-8f96-a5ef908c4a56",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A changeover of family on the line; the direction matters as much as the fact of it — tint-to-white is the expensive one, not the other way.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the direction of the changeover matters as much as the fact of it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what is lost when it changes the system's mode",
+          "precision": "named",
+          "rationale": "Hours and crew time are known; ramp scrap is named but unquantified.",
+          "assertion": {
+            "absence": "unknown-to-user",
+            "pointer": "ramp scrap after the washdown — \"which I don't have good numbers for but shouldn't be ignored\"; three hours of line and crew time are known"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-9926552e-289f-4b4a-bc99-4cae34f1720a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"ramp scrap after the washdown — \\\"which I don't have good numbers for but shouldn't be ignored\\\"; three hours of line and crew time are known\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"named\",\"rationale\":\"Hours and crew time are known; ramp scrap is named but unquantified.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "assertion": {
+            "value": "The crew, on the line being changed over (Line 1 in the incident described)."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "the three-hour tint-to-white hit is real cost, crew time",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-06aac0a9-b270-4b13-a54f-37440769d685",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The crew, on the line being changed over (Line 1 in the incident described).\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "how long it takes",
+          "precision": "range",
+          "rationale": "\"a few hours for a white\" — no quantiles given, and the specialty wait is named but unquantified.",
+          "assertion": {
+            "value": "Usually a few hours for a white; \"nothing like the specialty wait\" — specialty duration not given."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-94948329-18e7-42fe-9538-a84fd72c225d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; \\\"nothing like the specialty wait\\\" — specialty duration not given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"range\",\"rationale\":\"\\\"a few hours for a white\\\" — no quantiles given, and the specialty wait is named but unquantified.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "assertion": {
+            "value": "The lab."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "sits in the lab's queue, gets checked",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-16b9c643-8b17-490e-bfe0-022a06efd914",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "The order is released, goes to the warehouse, and ships against the due date."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "who can absorb the slip",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "assertion": {
+            "value": "Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I use judgment on who can absorb the slip",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-821e00ef-6923-43b0-955b-3ed7d60ce127",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "who can absorb the slip",
+          "slot": "what overrides it",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "The hard on-time line for an order like Meridian overrides the weighing — it is not a trade-off, and is only crossed if there's truly no way through."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-6da3fa16-460b-4f07-aefc-f941d7118f76",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The hard on-time line for an order like Meridian overrides the weighing — it is not a trade-off, and is only crossed if there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "constraint",
+          "node": "Meridian ships on time",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "Meridian ships on time, full stop; days late above zero is bad news the scheduler has to go explain. Only crossed \"unless there's truly no way through\"."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "did Meridian ship on time or not, full stop",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "days late on Meridian, and anything above zero is bad news I have to go explain",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-731a5768-edc7-4858-ad42-50d2faf4b181",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian ships on time, full stop; days late above zero is bad news the scheduler has to go explain. Only crossed \\\"unless there's truly no way through\\\".\"},\"kind\":\"constraint\",\"node\":\"Meridian ships on time\",\"precision\":\"spelled out\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"days late on Meridian, and anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "boundary-condition",
+          "node": "demand book from ERP",
+          "slot": "the starting state",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "Orders start life as line items in the demand book once ERP spits it out, carrying quantity, due date and SKU."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-1bebb3ea-7788-477a-8127-593fe3fe6026",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders start life as line items in the demand book once ERP spits it out, carrying quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"spelled out\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "boundary-condition",
+          "node": "demand book from ERP",
+          "slot": "the arrival or availability pattern",
+          "precision": "named",
+          "rationale": "The expert named the demand book as the source but the arrival pattern was flagged as still open when the session ended.",
+          "assertion": {
+            "absence": "deferred",
+            "pointer": "how orders arrive into the demand book — named as still open at the close of the session"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "it starts life as a line item in the demand book once ERP spits that out",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-07cb7ca9-27c5-4395-bc9e-aaebc5811382",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"how orders arrive into the demand book — named as still open at the close of the session\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"named\",\"rationale\":\"The expert named the demand book as the source but the arrival pattern was flagged as still open when the session ended.\",\"slot\":\"the arrival or availability pattern\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "data-binding",
+          "node": "stage-level times in the historian",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "assertion": {
+            "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the historian; never pulled apart by the expert."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the historian; never pulled apart by the expert.\"},\"kind\":\"data-binding\",\"node\":\"stage-level times in the historian\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "data-binding",
+          "node": "tank sizes from engineering drawings",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "assertion": {
+            "value": "Holding tank sizes, especially mill-to-fill on Line 1 — feed: engineering drawings."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tank sizes, especially mill-to-fill on Line 1 — feed: engineering drawings.\"},\"kind\":\"data-binding\",\"node\":\"tank sizes from engineering drawings\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "data-binding",
+          "node": "filler repair work-order times in the CMMS",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "assertion": {
+            "value": "Actual filler repair durations — feed: maintenance work-order times in the CMMS; never pulled by the expert."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "maintenance would have the actual work-order times in the CMMS but I've never pulled them",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-a0429a34-1145-458d-bada-32d827d68959",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Actual filler repair durations — feed: maintenance work-order times in the CMMS; never pulled by the expert.\"},\"kind\":\"data-binding\",\"node\":\"filler repair work-order times in the CMMS\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maintenance would have the actual work-order times in the CMMS but I've never pulled them\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "wait or shift when Line 2 goes down",
+          "slot": "the question, in the expert's words",
+          "precision": "spelled out",
+          "rationale": "The expert wrote the question as he would type it into the tool.",
+          "assertion": {
+            "value": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\""
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-48033ee8-f7eb-4615-b21f-018837fc9c5e",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\"\"},\"kind\":\"objective\",\"node\":\"wait or shift when Line 2 goes down\",\"precision\":\"spelled out\",\"rationale\":\"The expert wrote the question as he would type it into the tool.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "wait or shift when Line 2 goes down",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "assertion": {
+            "value": "entity-type:order (demand book line item) — its due date and remaining quantity; entity-type:line (Line 1 / Line 2) — what is on Line 1 and how far through; entity-type:product family (white vs tint); activity:production run (mix, mill, tint, fill); activity:filler jam on Line 2 — repair length unknown at the time; activity:tint-to-white washdown — including its direction and ramp scrap; policy:who can absorb the slip — whose tint got bumped"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "What it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just \"an order got delayed.\"",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-88da9925-d922-48c3-8ea0-2c631df3ae3d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:order (demand book line item) — its due date and remaining quantity; entity-type:line (Line 1 / Line 2) — what is on Line 1 and how far through; entity-type:product family (white vs tint); activity:production run (mix, mill, tint, fill); activity:filler jam on Line 2 — repair length unknown at the time; activity:tint-to-white washdown — including its direction and ramp scrap; policy:who can absorb the slip — whose tint got bumped\"},\"kind\":\"objective\",\"node\":\"wait or shift when Line 2 goes down\",\"precision\":\"named\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just \\\\\\\"an order got delayed.\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "wait or shift when Line 2 goes down",
+          "slot": "what \"better\" means, and trade-off weights",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "assertion": {
+            "value": "Lexicographic: days late on Meridian first, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-f53d8f62-375e-4af6-9aaa-fb903839993c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lexicographic: days late on Meridian first, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"wait or shift when Line 2 goes down\",\"precision\":\"spelled out\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "objective",
+          "node": "is the mill-to-fill tank on Line 1 slowing the line down",
+          "slot": "the nodes it depends on",
+          "precision": "named",
+          "assertion": {
+            "value": "activity:production run (mix, mill, tint, fill) — stage-level mill speed versus fill speed on Line 1; constraint:small holding tanks between stages — the mill-to-fill tank size on Line 1; entity-type:product family (white vs tint) — different SKUs are slow at different stages"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-ac435640-eea2-4ad6-9695-8e5408b4d852",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"activity:production run (mix, mill, tint, fill) — stage-level mill speed versus fill speed on Line 1; constraint:small holding tanks between stages — the mill-to-fill tank size on Line 1; entity-type:product family (white vs tint) — different SKUs are slow at different stages\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"named\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "data-binding",
+          "node": "stage-level times from the historian and tank sizes from engineering drawings",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "assertion": {
+            "absence": "deferred",
+            "pointer": "the historian (stage-by-stage times) and engineering drawings (tank sizes)"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I don't have clean numbers for tank sizes or stage-by-stage rates.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 15,
+            "entryEnd": 15
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-f5a658db-c8ec-4ca0-8a87-3ad252dee56d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the historian (stage-by-stage times) and engineering drawings (tank sizes)\"},\"kind\":\"data-binding\",\"node\":\"stage-level times from the historian and tank sizes from engineering drawings\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have clean numbers for tank sizes or stage-by-stage rates.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "data-binding",
+          "node": "filler repair times from the CMMS",
+          "slot": "the variable and its feed",
+          "precision": "named",
+          "assertion": {
+            "absence": "deferred",
+            "pointer": "maintenance work-order times in the CMMS"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "maintenance would have the actual work-order times in the CMMS but I've never pulled them.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I'll ask maintenance for the CMMS numbers on the filler too while I'm at it.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 30,
+            "entryEnd": 30
+          },
+          "source": "user"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-618842bb-d23d-4371-ae57-73e5257ba215",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"maintenance work-order times in the CMMS\"},\"kind\":\"data-binding\",\"node\":\"filler repair times from the CMMS\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'll ask maintenance for the CMMS numbers on the filler too while I'm at it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":30,\\\"entryStart\\\":30,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user\\\"}\",\"{\\\"excerpt\\\":\\\"maintenance would have the actual work-order times in the CMMS but I've never pulled them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "boundary-condition",
+          "node": "demand book line items out of ERP",
+          "slot": "the starting state",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "An order starts life as a line item in the demand book once ERP spits that out, carrying quantity, due date and SKU."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-538fb022-2495-46bb-8661-8e1f38c802bf",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order starts life as a line item in the demand book once ERP spits that out, carrying quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book line items out of ERP\",\"precision\":\"spelled out\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order (demand book line item)",
+          "slot": "state that rides along with each instance",
+          "precision": "spelled out",
+          "rationale": "Quantity, due date and SKU are explicit; remaining quantity and customer identity are named later as things the answer hangs on.",
+          "assertion": {
+            "value": "Quantity, due date, SKU; plus remaining quantity and the customer's identity, which the expert weighs when an order slips."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; plus remaining quantity and the customer's identity, which the expert weighs when an order slips.\"},\"kind\":\"entity-type\",\"node\":\"order (demand book line item)\",\"precision\":\"spelled out\",\"rationale\":\"Quantity, due date and SKU are explicit; remaining quantity and customer identity are named later as things the answer hangs on.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "order (demand book line item)",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "assertion": {
+            "value": "Orders are treated apart by whose order it is: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-5d5f862f-c18c-4501-b544-76735d28e004",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders are treated apart by whose order it is: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem.\"},\"kind\":\"entity-type\",\"node\":\"order (demand book line item)\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "product family (white vs tint)",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step; tints run at nearly the same speed on both lines while whites do not; and the tint-to-white changeover direction is the expensive one."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-7f6b8be1-6336-465f-8e11-36a5277d51bd",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step; tints run at nearly the same speed on both lines while whites do not; and the tint-to-white changeover direction is the expensive one.\"},\"kind\":\"entity-type\",\"node\":\"product family (white vs tint)\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "line (Line 1 / Line 2)",
+          "slot": "the distinctions the process treats apart",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "Line 1 is the slower machine on whites (add maybe fifty, sixty percent to Line 2's times); on tints Line 1 and Line 2 run at nearly the same speed."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Line 1 and Line 2 run tints at nearly the same speed",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-1a83c9c6-a8f8-4ece-a5d4-53b81bf8cc9b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 is the slower machine on whites (add maybe fifty, sixty percent to Line 2's times); on tints Line 1 and Line 2 run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "entity-type",
+          "node": "line (Line 1 / Line 2)",
+          "slot": "how many there are, or the population's shape",
+          "precision": "number",
+          "rationale": "Only Line 1 and Line 2 are ever named; the count itself was never stated as a figure.",
+          "assertion": {
+            "value": "Two lines (Line 1 and Line 2), each comprising separate mix, mill, tint and fill kit with small holding tanks between."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "inferred",
+      "id": "capture-e6ae51ed-e1f6-45f3-aab1-c4bca2a979e8",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two lines (Line 1 and Line 2), each comprising separate mix, mill, tint and fill kit with small holding tanks between.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"number\",\"rationale\":\"Only Line 1 and Line 2 are ever named; the count itself was never stated as a figure.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "order flow from demand book to ship",
+          "slot": "the order things happen in",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship against the due date."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship against the due date.\"},\"kind\":\"ordering/flow\",\"node\":\"order flow from demand book to ship\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "line occupancy across the four stages",
+          "slot": "the order things happen in",
+          "precision": "spelled out",
+          "sourceRegime": "prescribed",
+          "assertion": {
+            "value": "On the sheet, Line 2 is one row: the order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet, Line 2 is one row: the order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done.\"},\"kind\":\"ordering/flow\",\"node\":\"line occupancy across the four stages\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "ordering/flow",
+          "node": "line occupancy across the four stages",
+          "slot": "the order things happen in",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "assertion": {
+            "value": "Physically the stages overlap: the mixer can start the next order's batch while the fill head is still finishing the last one, if there is room in the holding tank between mix and mill, or mill and fill; the crew will get a head start on mixing if the tank ahead has space."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-7f9ac97e-375b-4de3-bbcd-b65e5c7427a6",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically the stages overlap: the mixer can start the next order's batch while the fill head is still finishing the last one, if there is room in the holding tank between mix and mill, or mill and fill; the crew will get a head start on mixing if the tank ahead has space.\"},\"kind\":\"ordering/flow\",\"node\":\"line occupancy across the four stages\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "constraint",
+          "node": "small holding tanks between stages",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "The tanks are small — especially the one between mill and fill on Line 1 — and when a tank is full, mixing has to wait; how much overlap happens or how often it is blocked is not tracked."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 12,
+            "entryEnd": 12
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-66fbb371-91b7-41db-b437-5bd207d08aed",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The tanks are small — especially the one between mill and fill on Line 1 — and when a tank is full, mixing has to wait; how much overlap happens or how often it is blocked is not tracked.\"},\"kind\":\"constraint\",\"node\":\"small holding tanks between stages\",\"precision\":\"spelled out\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation onto a line and a slot in the week",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "assertion": {
+            "value": "The master scheduler, on the sheet."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-8da19d62-c082-41f6-ac55-f28afe266a8c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler, on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation onto a line and a slot in the week\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation onto a line and a slot in the week",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "A line item in the demand book out of ERP, with quantity, due date and SKU."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-995374a1-2d25-4690-8397-b342f46ebf02",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book out of ERP, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation onto a line and a slot in the week\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "allocation onto a line and a slot in the week",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "The order is placed onto a named line and a slot in the week."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "allocate it onto a line and a slot in the week",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-3cc84392-4ed4-4804-8a7c-db07d384a8b2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is placed onto a named line and a slot in the week.\"},\"kind\":\"activity\",\"node\":\"allocation onto a line and a slot in the week\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "production run (mix, mill, tint, fill)",
+          "slot": "what it needs before it can start",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "The order allocated to a line and a slot in the week; then it runs the same four stages every product goes through — mix, mill, tint, fill and pack."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-289ac648-e939-4e62-ad46-a17b112402d4",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order allocated to a line and a slot in the week; then it runs the same four stages every product goes through — mix, mill, tint, fill and pack.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "production run (mix, mill, tint, fill)",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "Packed product coming off the fill line, which then goes into QA hold."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-5376c084-3889-476f-adab-b09a038ded28",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Packed product coming off the fill line, which then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "production run (mix, mill, tint, fill)",
+          "slot": "how long it takes",
+          "precision": "spread",
+          "sourceRegime": "practiced",
+          "assertion": {
+            "value": "White, Meridian-sized, on Line 2, clean of breakdowns: typical eight to nine hours mix-to-last-pack; one in ten worse nine to ten hours; one in ten better maybe six hours."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-b9dfddf9-52d8-433e-81b8-5611e7356c34",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, Meridian-sized, on Line 2, clean of breakdowns: typical eight to nine hours mix-to-last-pack; one in ten worse nine to ten hours; one in ten better maybe six hours.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "production run (mix, mill, tint, fill)",
+          "slot": "how long it takes",
+          "precision": "spread",
+          "assertion": {
+            "value": "Same white order on Line 1: typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten — add maybe fifty, sixty percent to Line 2. (Stated before the breakdown/clean-run split was drawn, so the worse figure may still fold in jams.)"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-27ae8fdf-c227-4160-a1a5-e85530156938",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Same white order on Line 1: typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten — add maybe fifty, sixty percent to Line 2. (Stated before the breakdown/clean-run split was drawn, so the worse figure may still fold in jams.)\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "production run (mix, mill, tint, fill)",
+          "slot": "how long it takes",
+          "precision": "range",
+          "assertion": {
+            "value": "A tint run on either line: eight to ten hours typical, without the Line 1 / Line 2 gap."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "so a tint run on either line looks more like eight to ten hours typical, without that big gap",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-7bd393bf-3f05-4aa1-b15a-968c293b076f",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A tint run on either line: eight to ten hours typical, without the Line 1 / Line 2 gap.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"range\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"so a tint run on either line looks more like eight to ten hours typical, without that big gap\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "production run (mix, mill, tint, fill)",
+          "slot": "whether its quantities vary by type",
+          "precision": "named",
+          "assertion": {
+            "value": "Yes — run time varies by product family and line: whites are much slower on Line 1, tints are nearly the same speed on either line; the \"Line 2 is twice as fast\" figure is really a whites number. No explanation for the tint case; it is sheet-derived."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 18,
+            "entryEnd": 18
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-ef41e72f-3126-4003-82b2-686b5f8bfdfb",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — run time varies by product family and line: whites are much slower on Line 1, tints are nearly the same speed on either line; the \\\"Line 2 is twice as fast\\\" figure is really a whites number. No explanation for the tint case; it is sheet-derived.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"named\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam on Line 2",
+          "slot": "how often it occurs, if it is an event rather than a step",
+          "precision": "range",
+          "sourceRegime": "practiced",
+          "assertion": {
+            "value": "Every week or two; low end once every three weeks, high end twice a week. Not seasonal, but runs streaks of bad weeks."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "It's a \"every week or two\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-4fa34ba3-82e3-4a4a-ad28-362765a40046",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Every week or two; low end once every three weeks, high end twice a week. Not seasonal, but runs streaks of bad weeks.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"range\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It's a \\\\\\\"every week or two\\\\\\\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam on Line 2",
+          "slot": "how long it takes",
+          "precision": "spread",
+          "sourceRegime": "practiced",
+          "assertion": {
+            "value": "Repair: typical thirty to forty-five minutes; quick one-in-ten ten to fifteen minutes (basically a false alarm); bad one-in-ten four to five hours when something is actually broken in the filler head, occasionally eating the rest of the shift."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-2f670377-be1e-4275-9e46-24dd13316300",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Repair: typical thirty to forty-five minutes; quick one-in-ten ten to fifteen minutes (basically a false alarm); bad one-in-ten four to five hours when something is actually broken in the filler head, occasionally eating the rest of the shift.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam on Line 2",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "assertion": {
+            "value": "A tech comes over, clears whatever's jammed and resets."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "tech comes over, clears whatever's jammed, resets, we're going again",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 27,
+            "entryEnd": 27
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-9dc62989-7db7-4e58-baf1-b9ed0400d9a2",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A tech comes over, clears whatever's jammed and resets.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"tech comes over, clears whatever's jammed, resets, we're going again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "filler jam on Line 2",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "The run stops and time is lost inside the run — the big bad days (twelve to thirteen hours) are the breakdown showing up inside the run rather than the run being slow."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 21,
+            "entryEnd": 21
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-b92eccd9-e2ad-41a9-abce-bb1cf8b3c328",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The run stops and time is lost inside the run — the big bad days (twelve to thirteen hours) are the breakdown showing up inside the run rather than the run being slow.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "how long it takes",
+          "precision": "number",
+          "assertion": {
+            "value": "Three hours."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-55e95600-febe-4c98-8859-a56eb23ab156",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what is lost when it changes the system's mode",
+          "precision": "number",
+          "assertion": {
+            "value": "Three hours of crew time with Line 1 out of anything else for that window; direction matters — tint-to-white is the expensive one, not the other way."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-29c03a62-4be2-4dc2-852e-bfeab6770f1b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of crew time with Line 1 out of anything else for that window; direction matters — tint-to-white is the expensive one, not the other way.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "tint-to-white washdown",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "assertion": {
+            "absence": "unknown-to-user",
+            "pointer": "ramp scrap after the washdown — real product lost on top of the hours; no good numbers and no source named"
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 24,
+            "entryEnd": 24
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-9f708103-e43a-4766-bca4-cb3b7060fdcd",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"ramp scrap after the washdown — real product lost on top of the hours; no good numbers and no source named\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "release and ship",
+          "slot": "what it produces or changes",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "The order is released, goes to the warehouse, and ships against the due date."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "how long it takes",
+          "precision": "named",
+          "assertion": {
+            "value": "Usually a few hours for a white; nothing like the specialty wait (the specialty wait itself was never quantified)."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; nothing like the specialty wait (the specialty wait itself was never quantified).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "activity",
+          "node": "QA hold",
+          "slot": "who or what performs it",
+          "precision": "named",
+          "assertion": {
+            "value": "The lab — it sits in the lab's queue and gets checked."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 9,
+            "entryEnd": 9
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-12e575e7-b7a9-472d-b165-308334ae7513",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab — it sits in the lab's queue and gets checked.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "wait for the repair or shift the order to Line 1",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "assertion": {
+            "value": "Gut math at the huddle: weigh the gamble that the repair is the \"half hour\" kind against the tint-to-white washdown plus the bumped tint order going late. In the Meridian case he went with waiting; it came back in about two hours and just scraped the Thursday due date."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "I went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 3,
+            "entryEnd": 3
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-bc9d210e-beb9-4f7a-aa5d-243950605a2a",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Gut math at the huddle: weigh the gamble that the repair is the \\\"half hour\\\" kind against the tint-to-white washdown plus the bumped tint order going late. In the Meridian case he went with waiting; it came back in about two hours and just scraped the Thursday due date.\"},\"kind\":\"policy\",\"node\":\"wait for the repair or shift the order to Line 1\",\"precision\":\"spelled out\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "wait for the repair or shift the order to Line 1",
+          "slot": "what overrides it",
+          "precision": "spelled out",
+          "assertion": {
+            "value": "The Meridian-style on-time due date overrides the weighing — a line he won't cross unless there's truly no way through."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-90a38599-7f1b-46ed-9352-d3dd3566b338",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The Meridian-style on-time due date overrides the weighing — a line he won't cross unless there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"wait for the repair or shift the order to Line 1\",\"precision\":\"spelled out\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "hedged",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "policy",
+          "node": "who can absorb the slip",
+          "slot": "the rule as actually practiced",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "assertion": {
+            "value": "Judgment, not a formula: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-d889a88e-b7be-4055-9da1-e64f9fc858b0",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment, not a formula: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    },
+    {
+      "confidence": "firm",
+      "content": {
+        "value": {
+          "type": "slot-asserted",
+          "kind": "constraint",
+          "node": "Meridian-style due date is a line I won't cross",
+          "slot": "the limit and what happens when it is hit",
+          "precision": "spelled out",
+          "sourceRegime": "practiced",
+          "assertion": {
+            "value": "The protected order must ship on time; days late above zero is bad news the scheduler has to go explain. The line is crossed only if there's truly no way through."
+          }
+        }
+      },
+      "evidence": [
+        {
+          "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        },
+        {
+          "excerpt": "anything above zero is bad news I have to go explain",
+          "pointer": {
+            "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+            "entryStart": 6,
+            "entryEnd": 6
+          },
+          "source": "user-affordance-payload"
+        }
+      ],
+      "epistemicStatus": "explicit",
+      "id": "capture-173c6d39-090f-49a7-9e38-c8998003718b",
+      "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The protected order must ship on time; days late above zero is bad news the scheduler has to go explain. The line is crossed only if there's truly no way through.\"},\"kind\":\"constraint\",\"node\":\"Meridian-style due date is a line I won't cross\",\"precision\":\"spelled out\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+    }
+  ],
+  "issues": [],
+  "events": []
+}
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5-model.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5-model.md
new file mode 100644
index 00000000000..fbc00da3aed
--- /dev/null
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5-model.md
@@ -0,0 +1,444 @@
+# Condition 5 — the elicited model, folded from the capture store
+
+The harness's own deliverable: `foldElicitedModel` over the active captures, then
+`evaluateCompletion` against the sdcpn definition. Nothing here was written by the
+interviewer; every value is a capture the sweep extracted and the store admitted.
+
+- Plugin version: `sdcpn/2026-08-25.2`
+- Revision: `26a8219a17118558`
+- Active captures: 267
+- Complete: **no** — 46 unsatisfied, 53 node(s) outside every objective's slice, 0 unmapped capture(s)
+
+## Nodes
+
+### entity-type (12)
+
+#### `entity-type:line`
+- **how many there are, or the population's shape** — conflict — 2 readings
+- **state that rides along with each instance** — "What it is currently running — e.g. mid-run on a tint, which sets the colour it would have to be washed down from — and whether it is jammed/down awaiting repair." — spelled out, inferred, practiced — _A line is spoken of as carrying what it is currently running (its colour state) and whether it is down._
+- **the distinctions the process treats apart** — conflict — 2 readings
+
+#### `entity-type:line (Line 1 / Line 2)`
+- **how many there are, or the population's shape** — conflict — 2 readings
+- **the distinctions the process treats apart** — conflict — 3 readings
+
+#### `entity-type:Line 1 and Line 2`
+- **how many there are, or the population's shape** — "Two lines — Line 1 and Line 2." — number, explicit — _The expert speaks only of Line 1 and Line 2 throughout._
+- **state that rides along with each instance** — "What order is on it, how far through that order is, and what family (tint or white) it is currently running — the last decides washdown cost and direction." — spelled out, explicit
+- **the distinctions the process treats apart** — conflict — 3 readings
+
+#### `entity-type:mix, mill, tint, fill`
+- **how many there are, or the population's shape** — absence: unknown-to-user → how much overlap happens and how often mixing is blocked by a full tank is not tracked by the scheduler (explicit)
+- **the distinctions the process treats apart** — divergence — prescribed {"value":"On the sheet the line is one row treated as one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it is done."}; practiced {"value":"Physically four separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head is still finishing the last, if there is room in the holding tank — the crew will get a head start on mixing the next batch if the tank ahead of it has space."}
+
+#### `entity-type:mix, mill, tint, fill kit and holding tanks`
+- **how many there are, or the population's shape** — absence: deferred → engineering drawings (explicit)
+- **the distinctions the process treats apart** — "Mix, mill, tint and fill are separate tanks and separate kit strung together, with small holding tanks between them." — spelled out, explicit, practiced
+
+#### `entity-type:mix, mill, tint, fill stages`
+- **how many there are, or the population's shape** — absence: deferred → engineering drawings (tank sizes) — expert does not carry them in his head (explicit)
+- **the distinctions the process treats apart** — "Mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can be starting the next order's batch while the fill head is still finishing the last one, if the holding tank between mix and mill, or mill and fill, has room." — spelled out, explicit, practiced — _The floor's account: four separately contended pieces of kit per line, buffered by small holding tanks._
+
+#### `entity-type:order`
+- **how many there are, or the population's shape** — absence: unknown-to-user → demand book / ERP (inferred)
+- **state that rides along with each instance** — conflict — 6 readings
+- **the distinctions the process treats apart** — conflict — 6 readings
+
+#### `entity-type:order (demand book line item)`
+- **state that rides along with each instance** — "Quantity, due date, SKU; plus remaining quantity and the customer's identity, which the expert weighs when an order slips." — spelled out, inferred — _Quantity, due date and SKU are explicit; remaining quantity and customer identity are named later as things the answer hangs on._
+- **the distinctions the process treats apart** — "Orders are treated apart by whose order it is: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem." — spelled out, explicit, practiced
+
+#### `entity-type:order (line item in the demand book)`
+- **state that rides along with each instance** — "Quantity, due date, SKU; the customer (distributor / small account / awkward account); which line and week-slot it has been allocated to; whether it has gone late and by how many days." — spelled out, explicit — _Quantity, due date, SKU come from ERP; customer type is used in the slip judgement; line allocation is set at step one._
+- **the distinctions the process treats apart** — "Orders are line items with quantity, due date and SKU. Treated apart: whites (tint stage barely there, more of a pass-through than a real letdown step) vs tints (real letdown); and by customer — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem." — spelled out, explicit — _Whites vs tints differ in the tint stage and in run time by line; customer identity differs in slip tolerance._
+
+#### `entity-type:product family (white vs tint)`
+- **the distinctions the process treats apart** — "Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step; tints run at nearly the same speed on both lines while whites do not; and the tint-to-white changeover direction is the expensive one." — spelled out, explicit
+
+#### `entity-type:stage kit (mix, mill, tint, fill)`
+- **the distinctions the process treats apart** — "Four separate pieces of kit per line — mixer, mill, tint, fill head — each usable independently, with small holding tanks buffering between mix/mill and mill/fill." — spelled out, explicit, practiced — _Each stage is separately contended kit._
+
+#### `entity-type:the four stages — mix, mill, tint, fill`
+- **how many there are, or the population's shape** — "Four stages in series per line — mix, mill, tint, fill — with small holding tanks between them; how often blocking occurs is not tracked." — named, explicit — _Count of stages is stated; occupancy/blocking frequency is explicitly untracked._
+- **the distinctions the process treats apart** — "Physically mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head finishes the last one if the tank ahead has space." — spelled out, explicit, practiced — _The floor's version of the line: four contended stages with buffers, not one resource._
+
+### boundary-condition (2)
+
+#### `boundary-condition:demand book from ERP`
+- **the arrival or availability pattern** — conflict — 2 readings
+- **the starting state** — conflict — 3 readings
+
+#### `boundary-condition:demand book line items out of ERP`
+- **the starting state** — "An order starts life as a line item in the demand book once ERP spits that out, carrying quantity, due date and SKU." — spelled out, explicit
+
+### activity (15)
+
+#### `activity:allocation`
+- **what it needs before it can start** — conflict — 5 readings
+- **what it produces or changes** — conflict — 5 readings
+- **who or what performs it** — conflict — 3 readings
+
+#### `activity:allocation onto a line and a slot in the week`
+- **what it needs before it can start** — "A line item in the demand book out of ERP, with quantity, due date and SKU." — spelled out, explicit
+- **what it produces or changes** — "The order is placed onto a named line and a slot in the week." — spelled out, explicit
+- **who or what performs it** — "The master scheduler, on the sheet." — named, explicit
+
+#### `activity:filler jam`
+- **how long it takes** — conflict — 5 readings
+- **how often it occurs, if it is an event rather than a step** — conflict — 3 readings
+- **what it needs before it can start** — "Repair duration is not known at the time of the decision — \"which I never know at the time\"; only \"could be quick, could be long\"." — spelled out, explicit — _At the time of the decision the repair length is unobservable to the scheduler._
+- **what it produces or changes** — conflict — 5 readings
+- **who or what performs it** — "A tech — comes over, clears whatever's jammed, resets." — named, explicit — _Repair is done by a tech._
+
+#### `activity:filler jam on Line 2`
+- **how long it takes** — "Repair: typical thirty to forty-five minutes; quick one-in-ten ten to fifteen minutes (basically a false alarm); bad one-in-ten four to five hours when something is actually broken in the filler head, occasionally eating the rest of the shift." — spread, explicit, practiced
+- **how often it occurs, if it is an event rather than a step** — "Every week or two; low end once every three weeks, high end twice a week. Not seasonal, but runs streaks of bad weeks." — range, explicit, practiced
+- **what it produces or changes** — "The run stops and time is lost inside the run — the big bad days (twelve to thirteen hours) are the breakdown showing up inside the run rather than the run being slow." — spelled out, explicit
+- **who or what performs it** — "A tech comes over, clears whatever's jammed and resets." — named, explicit
+
+#### `activity:filler jammed`
+- **how long it takes** — "Two kinds of repair: the \"half hour\" kind and the \"half a shift\" kind. The most recent Line 2 filler jam came back in about two hours." — range, explicit, practiced — _Two recognised repair kinds bracket the duration; the recent instance fell between them._
+- **what it produces or changes** — "The line's filler stops mid-run with an unknown ETA, putting the order on it at risk and forcing a decision to wait out the repair or move the order to the other line." — spelled out, explicit — _An event that befalls the line mid-run and forces the switch-or-wait decision._
+
+#### `activity:Line 2 filler jam`
+- **how long it takes** — "Repairs come in a \"half hour\" kind and a \"half a shift\" kind; the recent instance came back in about two hours." — range, explicit, practiced — _Expert described two kinds of repair — half an hour and half a shift — and one observed instance of about two hours; quantiles not yet elicited._
+- **what it produces or changes** — "Line 2 stops producing until repaired (half a shift lost in the recent case); the order sitting on Line 2 is at risk of its due date, forcing a decision to wait out the repair or shift the order to Line 1." — spelled out, explicit, practiced — _The event takes the line out of production and puts the order sitting on it at risk, forcing a wait-or-move decision._
+
+#### `activity:mix/mill/tint/fill`
+- **what it produces or changes** — "Runs the order through four stages every product goes through — mix, mill, tint, fill and pack — producing filled and packed product that comes off the fill line." — spelled out, explicit — _Stated as the production step common to all products._
+- **whether its quantities vary by type** — "Yes — the stages are the same for every product, but for a white the tint stage is barely there, a pass-through rather than a real letdown step." — named, explicit — _Explicit type-dependence at the tint stage; stage durations themselves not yet given._
+
+#### `activity:production run (mix, mill, tint, fill)`
+- **how long it takes** — conflict — 3 readings
+- **what it needs before it can start** — "The order allocated to a line and a slot in the week; then it runs the same four stages every product goes through — mix, mill, tint, fill and pack." — spelled out, explicit
+- **what it produces or changes** — "Packed product coming off the fill line, which then goes into QA hold." — spelled out, explicit
+- **whether its quantities vary by type** — "Yes — run time varies by product family and line: whites are much slower on Line 1, tints are nearly the same speed on either line; the \"Line 2 is twice as fast\" figure is really a whites number. No explanation for the tint case; it is sheet-derived." — named, explicit
+
+#### `activity:QA hold`
+- **how long it takes** — conflict — 7 readings
+- **what it needs before it can start** — "The order has come off the fill line; it then sits in the lab's queue awaiting check." — spelled out, explicit — _Stated as the precondition and the waiting arrangement._
+- **what it produces or changes** — conflict — 3 readings
+- **whether its quantities vary by type** — conflict — 2 readings
+- **who or what performs it** — conflict — 7 readings
+
+#### `activity:release and ship`
+- **what it produces or changes** — conflict — 4 readings
+
+#### `activity:run it through mix/mill/tint/fill`
+- **how long it takes** — conflict — 6 readings
+- **what it needs before it can start** — conflict — 2 readings
+- **what it produces or changes** — conflict — 2 readings
+- **whether its quantities vary by type** — conflict — 3 readings
+- **who or what performs it** — conflict — 2 readings
+
+#### `activity:run the batch (mix/mill/tint/fill)`
+- **how long it takes** — absence: deferred → the expert's scheduling sheet (roughly how long a batch of a given SKU takes end to end on each line) (explicit)
+- **what it produces or changes** — "The order is produced through the same four stages every product goes through — mix, mill, tint, fill and pack — and comes off the fill line." — spelled out, explicit — _The production run through the four stages._
+- **whether its quantities vary by type** — absence: deferred → the historian (stage-by-stage times: how long does mixing take, how long does milling take) (explicit)
+
+#### `activity:the run (mix, mill, tint, fill)`
+- **how long it takes** — conflict — 4 readings
+- **what it needs before it can start** — "The order allocated onto a line and a slot in the week (\"I slot it onto Line 2 on the sheet, that's step one, allocation\")." — spelled out, explicit
+- **what it produces or changes** — "Filled and packed product coming off the fill line, which then goes into QA hold." — spelled out, explicit
+- **whether its quantities vary by type** — "Yes — run time varies by family and by line: whites are about twice as fast on Line 2 as Line 1, tints run at nearly the same speed on both; and different SKUs are slow at different stages." — named, explicit
+- **who or what performs it** — "The line (Line 1 or Line 2) — its mix, mill, tint and fill kit — worked by the crew." — named, explicit
+
+#### `activity:tint stage`
+- **whether its quantities vary by type** — "Yes — for a white the tint stage is barely there, more of a pass-through than a real letdown step." — named, explicit — _Explicit variation by product type._
+
+#### `activity:tint-to-white washdown`
+- **how long it takes** — conflict — 6 readings
+- **what is lost when it changes the system's mode** — conflict — 8 readings
+- **what it needs before it can start** — conflict — 7 readings
+- **what it produces or changes** — conflict — 4 readings
+- **who or what performs it** — "The crew, on the line being changed over (Line 1 in the incident described)." — named, explicit
+
+### ordering/flow (8)
+
+#### `ordering/flow:allocate → run → QA hold → release and ship`
+- **the order things happen in** — conflict — 2 readings
+
+#### `ordering/flow:line occupancy across the four stages`
+- **the order things happen in** — divergence — prescribed {"value":"On the sheet, Line 2 is one row: the order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done."}; practiced {"value":"Physically the stages overlap: the mixer can start the next order's batch while the fill head is still finishing the last one, if there is room in the holding tank between mix and mill, or mill and fill; the crew will get a head start on mixing if the tank ahead has space."}
+
+#### `ordering/flow:order flow from demand book to ship`
+- **the order things happen in** — "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship against the due date." — spelled out, explicit
+
+#### `ordering/flow:order flow from demand book to shipment`
+- **the order things happen in** — "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (fill and pack) → QA hold → release and ship. Four steps if QA and shipping are counted as one, five if split." — spelled out, explicit — _Given verbatim as the end-to-end sequence for the Meridian white order._
+
+#### `ordering/flow:order flow, allocate to ship`
+- **the order things happen in** — "Allocate the order onto a line and a slot in the week → run it through mix / mill / tint / fill and pack → QA hold → release and ship. Four steps if QA and shipping count as one, five if split." — spelled out, explicit — _The end-to-end order stated by the expert._
+
+#### `ordering/flow:order life on the floor`
+- **the order things happen in** — "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship" — spelled out, explicit — _Expert's own summary of the end-to-end sequence._
+
+#### `ordering/flow:order lifecycle: allocate, run, QA hold, release and ship`
+- **how a branch or merge is decided** — "The scheduler slots the order onto a line on the sheet at allocation; on a disruption the choice is re-decided — shift it to the other line or wait out the repair." — spelled out, explicit — _The line choice is made by the scheduler at allocation and can be revisited on disruption._
+- **the order things happen in** — "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship" — spelled out, explicit
+
+#### `ordering/flow:stage overlap on a line`
+- **how a branch or merge is decided** — absence: unknown-to-user (explicit)
+- **the order things happen in** — conflict — 3 readings
+
+### policy (5)
+
+#### `policy:a line is occupied for the whole run`
+- **the rule as actually practiced** — "On the sheet, a line is one row: the order occupies that line for its whole run, mix through fill, and nothing else is scheduled on it till it's done." — spelled out, explicit, prescribed — _P08: the scheduling sheet's rule, which the expert says lies to him a bit._
+- **what overrides it** — "On the floor the crew will get a head start on mixing the next batch if the tank ahead of it has space — the mixer can start the next order while the fill head finishes the last one. How much overlap happens, and how often it is blocked because a tank is full, is not tracked." — spelled out, explicit, practiced — _P08 divergence: floor practice overlaps stages when buffer space allows._
+
+#### `policy:Meridian on time`
+- **the rule as actually practiced** — "A Meridian-style order ships on time, full stop; it is not traded off against anything." — spelled out, explicit, practiced — _Hard constraint on the scheduling decision._
+- **what overrides it** — "Only when there is truly no way through." — spelled out, explicit, practiced — _Only exception stated._
+
+#### `policy:Meridian ships on time, full stop`
+- **the rule as actually practiced** — "The Meridian order ships on time, full stop; it is not traded off against washdown hours or other orders' due dates." — spelled out, explicit, practiced — _Stated as an absolute the scheduler protects ahead of all other considerations._
+- **what overrides it** — "Only when there is truly no way through; otherwise nothing overrides it." — spelled out, explicit, practiced — _Expert named the sole override in general terms; the practiced test for "no way through" is not yet on record._
+
+#### `policy:wait for the repair or shift the order to Line 1`
+- **the rule as actually practiced** — "Gut math at the huddle: weigh the gamble that the repair is the \"half hour\" kind against the tint-to-white washdown plus the bumped tint order going late. In the Meridian case he went with waiting; it came back in about two hours and just scraped the Thursday due date." — spelled out, explicit, practiced
+- **what overrides it** — "The Meridian-style on-time due date overrides the weighing — a line he won't cross unless there's truly no way through." — spelled out, explicit
+
+#### `policy:who can absorb the slip`
+- **the rule as actually practiced** — conflict — 7 readings
+- **what overrides it** — conflict — 4 readings
+
+### objective (7)
+
+#### `objective:is the mill-to-fill tank on Line 1 slowing the line down`
+- **the nodes it depends on** — conflict — 3 readings
+- **the question, in the expert's words** — "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"" — spelled out, explicit — _Second question the expert wrote out as he would type it._
+- **what "better" means, and trade-off weights** — "The model showing \"here's where Line 1 loses its time\" — something to take to engineering other than a hunch; no numeric weighting given." — spelled out, explicit — _Qualitative: showing where Line 1 loses its time, in a form usable with engineering._
+
+#### `objective:switch or wait when Line 2 goes down`
+- **the nodes it depends on** — ["entity-type:order","entity-type:line","activity:run it through mix/mill/tint/fill","activity:tint-to-white washdown","activity:filler jam","policy:who can absorb the slip"] — named, explicit — _The expert listed what the answer hangs on: the protected run and its due date, the state of Line 1, the changeover and its direction, the jam duration, and whose order gets bumped._
+- **the question, in the expert's words** — "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"" — spelled out, explicit — _The expert wrote the question as he would type it into the tool._
+- **what "better" means, and trade-off weights** — "Hard line: days late on Meridian, anything above zero is bad news. Underneath that, weighed by judgment with no formula: washdown hours, and whether the bumped order goes late and by how much and for which customer." — spelled out, explicit, practiced — _Expert gave a lexicographic hard constraint plus unweighted second-order criteria, explicitly denying a formula._
+
+#### `objective:switch or wait when Line 2 goes down mid-run`
+- **the nodes it depends on** — ["entity-type:order","entity-type:Line 1 and Line 2","activity:the run (mix, mill, tint, fill)","activity:filler jam","activity:tint-to-white washdown","policy:who can absorb the slip","constraint:Meridian ships on time"] — named, explicit — _The expert listed what the answer hangs on._
+- **the question, in the expert's words** — "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"" — spelled out, explicit — _The expert wrote the question as they would type it into the tool._
+- **what "better" means, and trade-off weights** — "Meridian on time is non-negotiable (days late on Meridian, anything above zero is bad news); underneath that, washdown hours and whether the bumped order goes late and by how much are weighed by judgment — \"I don't have a formula for it.\"" — spelled out, explicit — _Hard constraint plus unweighted secondary measures; the expert explicitly denied having a formula._
+
+#### `objective:wait or shift when Line 2 goes down`
+- **the nodes it depends on** — "entity-type:order (demand book line item) — its due date and remaining quantity; entity-type:line (Line 1 / Line 2) — what is on Line 1 and how far through; entity-type:product family (white vs tint); activity:production run (mix, mill, tint, fill); activity:filler jam on Line 2 — repair length unknown at the time; activity:tint-to-white washdown — including its direction and ramp scrap; policy:who can absorb the slip — whose tint got bumped" — named, explicit
+- **the question, in the expert's words** — "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"" — spelled out, explicit — _The expert wrote the question as he would type it into the tool._
+- **what "better" means, and trade-off weights** — "Lexicographic: days late on Meridian first, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip." — spelled out, explicit, practiced
+
+#### `objective:where Line 1 loses its time`
+- **the nodes it depends on** — conflict — 3 readings
+- **the question, in the expert's words** — conflict — 3 readings
+
+#### `objective:which option actually loses less`
+- **the nodes it depends on** — conflict — 3 readings
+- **the question, in the expert's words** — conflict — 3 readings
+- **what "better" means, and trade-off weights** — conflict — 3 readings
+
+#### `objective:which option loses less`
+- **the nodes it depends on** — conflict — 2 readings
+- **the question, in the expert's words** — conflict — 2 readings
+- **what "better" means, and trade-off weights** — conflict — 2 readings
+
+### constraint (8)
+
+#### `constraint:holding tank capacity between stages`
+- **the limit and what happens when it is hit** — "A stage can only get a head start if there's room in the holding tank ahead of it; when a tank's full, mixing has to wait. How often that blocking happens is not tracked by the expert." — spelled out, explicit — _Blocking consequence stated; frequency and size not tracked._
+
+#### `constraint:Meridian on time`
+- **the limit and what happens when it is hit** — "The hard-line customer's order must ship on or before its due date — days late must be zero. The line is not crossed unless there is truly no way through; if it is crossed, the scheduler has to go explain it." — spelled out, explicit, practiced — _Stated as non-negotiable with a named consequence._
+
+#### `constraint:Meridian ships on time`
+- **the limit and what happens when it is hit** — "Meridian ships on time, full stop; days late above zero is bad news the scheduler has to go explain. Only crossed \"unless there's truly no way through\"." — spelled out, explicit
+
+#### `constraint:Meridian-style due date is a line I won't cross`
+- **the limit and what happens when it is hit** — "The protected order must ship on time; days late above zero is bad news the scheduler has to go explain. The line is crossed only if there's truly no way through." — spelled out, explicit, practiced
+
+#### `constraint:published line rate`
+- **the limit and what happens when it is hit** — divergence — prescribed {"value":"Engineering's position is that the line rate is what it is regardless of the tanks."}; practiced {"value":"In practice Line 1 feels sluggish and blocked in ways the published line rate does not account for; the expert suspects the mill-to-fill tank costs more than people admit, but has no proof."}
+
+#### `constraint:small holding tank between mill and fill on Line 1`
+- **the limit and what happens when it is hit** — "Holding tanks between stages are small — especially the one between mill and fill on Line 1. When there is room, the upstream stage can start the next order's batch; when the tank is full, the upstream stage is blocked and mixing has to wait. Actual tank capacity is not held by the expert; engineering's position is that the line rate is what it is regardless." — spelled out, explicit — _Qualitative blocking rule stated; the numeric capacity is not available from the expert._
+
+#### `constraint:small holding tanks`
+- **the limit and what happens when it is hit** — conflict — 2 readings
+
+#### `constraint:small holding tanks between stages`
+- **the limit and what happens when it is hit** — conflict — 3 readings
+
+### data-binding (10)
+
+#### `data-binding:filler repair times from the CMMS`
+- **the variable and its feed** — absence: deferred → maintenance work-order times in the CMMS (explicit)
+
+#### `data-binding:filler repair work-order times in the CMMS`
+- **the variable and its feed** — "Actual filler repair durations — feed: maintenance work-order times in the CMMS; never pulled by the expert." — named, explicit
+
+#### `data-binding:stage-by-stage durations from the historian`
+- **the variable and its feed** — "Stage-by-stage durations (how long mixing takes, how long milling takes) per SKU and line — feed: the historian. Never pulled apart; only end-to-end batch time per SKU per line is on the scheduling sheet." — named, explicit — _Stage-level rates exist as data but not in the expert's head; feed named._
+
+#### `data-binding:stage-by-stage rates from the historian`
+- **the variable and its feed** — "Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the plant historian; never pulled apart, not known to the scheduler." — named, explicit — _Stage-level durations are needed for the separate-stage model and exist only in the historian._
+
+#### `data-binding:stage-by-stage times`
+- **the variable and its feed** — "Stage-by-stage durations (how long mixing takes, how long milling takes) — the historian." — named, explicit — _Named feed for stage durations._
+
+#### `data-binding:stage-level rates`
+- **the variable and its feed** — "Stage-by-stage durations/rates (how long mixing takes, how long milling takes, mill speed versus fill speed on Line 1) — feed: the historian." — named, explicit — _Expert named the system where the missing stage-level numbers live._
+
+#### `data-binding:stage-level times from the historian and tank sizes from engineering drawings`
+- **the variable and its feed** — absence: deferred → the historian (stage-by-stage times) and engineering drawings (tank sizes) (explicit)
+
+#### `data-binding:stage-level times in the historian`
+- **the variable and its feed** — "Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the historian; never pulled apart by the expert." — named, explicit
+
+#### `data-binding:tank sizes`
+- **the variable and its feed** — conflict — 2 readings
+
+#### `data-binding:tank sizes from engineering drawings`
+- **the variable and its feed** — "Holding tank sizes, especially mill-to-fill on Line 1 — feed: engineering drawings." — named, explicit
+
+### validation-criterion (2)
+
+#### `validation-criterion:stage rates must come from data, not gut-feel`
+- **how the expert would know the model is right** — "Stage-level rates and tank sizes must not be taken from the expert's gut-feel — he can supply gut-feel and known bottleneck stories, but real numbers must come from the historian and engineering drawings." — spelled out, explicit — _Expert explicitly bounds what his own testimony can support._
+
+#### `validation-criterion:the sheet's end-to-end batch times`
+- **how the expert would know the model is right** — "The model's end-to-end batch time for a given SKU on each line should match what the scheduler's sheet shows; and it would have to speak to engineering's claim that \"the line rate is what it is regardless\"." — named, explicit — _The only figures the expert holds first-hand are sheet-level end-to-end times per SKU per line; engineering's counter-claim is that the line rate is what it is regardless of the tanks._
+
+## Completion report
+
+- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported. (`objective:is the mill-to-fill tank on Line 1 slowing the line down` — the nodes it depends on)
+- [unsupported-active-objective] objective:wait or shift when Line 2 goes down depends on nothing the model contains; an objective that depends on nothing is unsupported. (`objective:wait or shift when Line 2 goes down` — the nodes it depends on)
+- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported. (`objective:where Line 1 loses its time` — the nodes it depends on)
+- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported. (`objective:which option actually loses less` — the nodes it depends on)
+- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported. (`objective:which option loses less` — the nodes it depends on)
+- [open-conflict] "what it produces or changes" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it. (`activity:filler jam` — what it produces or changes)
+- [open-conflict] "how long it takes" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it. (`activity:filler jam` — how long it takes)
+- [open-conflict] "how often it occurs, if it is an event rather than a step" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it. (`activity:filler jam` — how often it occurs, if it is an event rather than a step)
+- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:filler jam. (`activity:filler jam` — what is lost when it changes the system's mode)
+- [unaddressed] "whether its quantities vary by type" has not been addressed on activity:filler jam. (`activity:filler jam` — whether its quantities vary by type)
+- [open-conflict] "what it needs before it can start" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it. (`activity:run it through mix/mill/tint/fill` — what it needs before it can start)
+- [open-conflict] "what it produces or changes" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it. (`activity:run it through mix/mill/tint/fill` — what it produces or changes)
+- [open-conflict] "who or what performs it" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it. (`activity:run it through mix/mill/tint/fill` — who or what performs it)
+- [open-conflict] "how long it takes" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it. (`activity:run it through mix/mill/tint/fill` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:run it through mix/mill/tint/fill. (`activity:run it through mix/mill/tint/fill` — how often it occurs, if it is an event rather than a step)
+- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:run it through mix/mill/tint/fill. (`activity:run it through mix/mill/tint/fill` — what is lost when it changes the system's mode)
+- [open-conflict] "whether its quantities vary by type" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it. (`activity:run it through mix/mill/tint/fill` — whether its quantities vary by type)
+- [open-conflict] "how long it takes" on activity:the run (mix, mill, tint, fill) has competing active captures; an explicit, user-cited resolution must close it. (`activity:the run (mix, mill, tint, fill)` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:the run (mix, mill, tint, fill). (`activity:the run (mix, mill, tint, fill)` — how often it occurs, if it is an event rather than a step)
+- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:the run (mix, mill, tint, fill). (`activity:the run (mix, mill, tint, fill)` — what is lost when it changes the system's mode)
+- [open-conflict] "what it needs before it can start" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it. (`activity:tint-to-white washdown` — what it needs before it can start)
+- [open-conflict] "what it produces or changes" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it. (`activity:tint-to-white washdown` — what it produces or changes)
+- [open-conflict] "how long it takes" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it. (`activity:tint-to-white washdown` — how long it takes)
+- [unaddressed] "how often it occurs, if it is an event rather than a step" has not been addressed on activity:tint-to-white washdown. (`activity:tint-to-white washdown` — how often it occurs, if it is an event rather than a step)
+- [open-conflict] "what is lost when it changes the system's mode" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it. (`activity:tint-to-white washdown` — what is lost when it changes the system's mode)
+- [unaddressed] "whether its quantities vary by type" has not been addressed on activity:tint-to-white washdown. (`activity:tint-to-white washdown` — whether its quantities vary by type)
+- [open-conflict] "the distinctions the process treats apart" on entity-type:line has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:line` — the distinctions the process treats apart)
+- [inadmissible-status] "state that rides along with each instance" on entity-type:line is held under status inferred; accepted: explicit. (`entity-type:line` — state that rides along with each instance)
+- [open-conflict] "how many there are, or the population's shape" on entity-type:line has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:line` — how many there are, or the population's shape)
+- [open-conflict] "the distinctions the process treats apart" on entity-type:Line 1 and Line 2 has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:Line 1 and Line 2` — the distinctions the process treats apart)
+- [below-required-precision] "how many there are, or the population's shape" on entity-type:Line 1 and Line 2 is known as a number; the model needs range. Smallest delta: move it from number to range. (`entity-type:Line 1 and Line 2` — how many there are, or the population's shape)
+- [open-conflict] "the distinctions the process treats apart" on entity-type:order has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:order` — the distinctions the process treats apart)
+- [open-conflict] "state that rides along with each instance" on entity-type:order has competing active captures; an explicit, user-cited resolution must close it. (`entity-type:order` — state that rides along with each instance)
+- [inadmissible-status] "how many there are, or the population's shape" on entity-type:order is held under status inferred; accepted: explicit. (`entity-type:order` — how many there are, or the population's shape)
+- [below-required-precision] "what "better" means, and trade-off weights" on objective:is the mill-to-fill tank on Line 1 slowing the line down is known as a spelled out; the model needs range. Smallest delta: move it from spelled out to range. (`objective:is the mill-to-fill tank on Line 1 slowing the line down` — what "better" means, and trade-off weights)
+- [below-required-precision] "what "better" means, and trade-off weights" on objective:switch or wait when Line 2 goes down is known as a spelled out; the model needs range. Smallest delta: move it from spelled out to range. (`objective:switch or wait when Line 2 goes down` — what "better" means, and trade-off weights)
+- [below-required-precision] "what "better" means, and trade-off weights" on objective:switch or wait when Line 2 goes down mid-run is known as a spelled out; the model needs range. Smallest delta: move it from spelled out to range. (`objective:switch or wait when Line 2 goes down mid-run` — what "better" means, and trade-off weights)
+- [below-required-precision] "what "better" means, and trade-off weights" on objective:wait or shift when Line 2 goes down is known as a spelled out; the model needs range. Smallest delta: move it from spelled out to range. (`objective:wait or shift when Line 2 goes down` — what "better" means, and trade-off weights)
+- [open-conflict] "the question, in the expert's words" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it. (`objective:where Line 1 loses its time` — the question, in the expert's words)
+- [unaddressed] "what "better" means, and trade-off weights" has not been addressed on objective:where Line 1 loses its time. (`objective:where Line 1 loses its time` — what "better" means, and trade-off weights)
+- [open-conflict] "the question, in the expert's words" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it. (`objective:which option actually loses less` — the question, in the expert's words)
+- [open-conflict] "what "better" means, and trade-off weights" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it. (`objective:which option actually loses less` — what "better" means, and trade-off weights)
+- [open-conflict] "the question, in the expert's words" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it. (`objective:which option loses less` — the question, in the expert's words)
+- [open-conflict] "what "better" means, and trade-off weights" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it. (`objective:which option loses less` — what "better" means, and trade-off weights)
+- [open-conflict] "the rule as actually practiced" on policy:who can absorb the slip has competing active captures; an explicit, user-cited resolution must close it. (`policy:who can absorb the slip` — the rule as actually practiced)
+- [open-conflict] "what overrides it" on policy:who can absorb the slip has competing active captures; an explicit, user-cited resolution must close it. (`policy:who can absorb the slip` — what overrides it)
+
+## Outside every objective's slice
+
+- `activity:allocation` — 7 open
+- `activity:allocation onto a line and a slot in the week` — 4 open
+- `activity:filler jam on Line 2` — 3 open
+- `activity:filler jammed` — 6 open
+- `activity:Line 2 filler jam` — 6 open
+- `activity:mix/mill/tint/fill` — 5 open
+- `activity:production run (mix, mill, tint, fill)` — 4 open
+- `activity:QA hold` — 6 open
+- `activity:release and ship` — 7 open
+- `activity:run the batch (mix/mill/tint/fill)` — 6 open
+- `activity:tint stage` — 6 open
+- `boundary-condition:demand book from ERP` — 2 open
+- `boundary-condition:demand book line items out of ERP` — 1 open
+- `constraint:holding tank capacity between stages` — 0 open
+- `constraint:Meridian on time` — 0 open
+- `constraint:Meridian-style due date is a line I won't cross` — 0 open
+- `constraint:published line rate` — 1 open
+- `constraint:small holding tank between mill and fill on Line 1` — 0 open
+- `constraint:small holding tanks` — 1 open
+- `constraint:small holding tanks between stages` — 1 open
+- `data-binding:filler repair times from the CMMS` — 1 open
+- `data-binding:filler repair work-order times in the CMMS` — 0 open
+- `data-binding:stage-by-stage durations from the historian` — 0 open
+- `data-binding:stage-by-stage rates from the historian` — 0 open
+- `data-binding:stage-by-stage times` — 0 open
+- `data-binding:stage-level rates` — 0 open
+- `data-binding:stage-level times from the historian and tank sizes from engineering drawings` — 1 open
+- `data-binding:stage-level times in the historian` — 0 open
+- `data-binding:tank sizes` — 1 open
+- `data-binding:tank sizes from engineering drawings` — 0 open
+- `entity-type:line (Line 1 / Line 2)` — 3 open
+- `entity-type:mix, mill, tint, fill` — 3 open
+- `entity-type:mix, mill, tint, fill kit and holding tanks` — 2 open
+- `entity-type:mix, mill, tint, fill stages` — 2 open
+- `entity-type:order (demand book line item)` — 2 open
+- `entity-type:order (line item in the demand book)` — 1 open
+- `entity-type:product family (white vs tint)` — 2 open
+- `entity-type:stage kit (mix, mill, tint, fill)` — 2 open
+- `entity-type:the four stages — mix, mill, tint, fill` — 2 open
+- `ordering/flow:allocate → run → QA hold → release and ship` — 2 open
+- `ordering/flow:line occupancy across the four stages` — 2 open
+- `ordering/flow:order flow from demand book to ship` — 1 open
+- `ordering/flow:order flow from demand book to shipment` — 1 open
+- `ordering/flow:order flow, allocate to ship` — 1 open
+- `ordering/flow:order life on the floor` — 1 open
+- `ordering/flow:order lifecycle: allocate, run, QA hold, release and ship` — 0 open
+- `ordering/flow:stage overlap on a line` — 2 open
+- `policy:a line is occupied for the whole run` — 0 open
+- `policy:Meridian on time` — 0 open
+- `policy:Meridian ships on time, full stop` — 0 open
+- `policy:wait for the repair or shift the order to Line 1` — 0 open
+- `validation-criterion:stage rates must come from data, not gut-feel` — 0 open
+- `validation-criterion:the sheet's end-to-end batch times` — 1 open
+
+## The harness's cue at close
+
+```
+The harness folded the model at revision 26a8219a17118558 (plugin sdcpn/2026-08-25.2): 69 node(s) from 267 active capture(s). Complete: no.
+
+Unsatisfied, in file order:
+- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.
+- [unsupported-active-objective] objective:wait or shift when Line 2 goes down depends on nothing the model contains; an objective that depends on nothing is unsupported.
+- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.
+- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.
+- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.
+- [open-conflict] "what it produces or changes" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.
+- [open-conflict] "how long it takes" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.
+- [open-conflict] "how often it occurs, if it is an event rather than a step" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.
+- [unaddressed] "what is lost when it changes the system's mode" has not been addressed on activity:filler jam.
+- [unaddressed] "whether its quantities vary by type" has not been addressed on activity:filler jam.
+- [open-conflict] "what it needs before it can start" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.
+- [open-conflict] "what it produces or changes" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.
+- … and 34 more.
+
+Patterns whose trigger may apply (discretionary):
+- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.
+- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert "unknown" into a value.
+- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.
+- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.
+- P07 on entity-type:line: ask explicitly whether it varies by type. Record "no" as a value; it is load-bearing.
+- P04 on policy:who can absorb the slip: replace any time-shaped approximation ("about two days before") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.
+
+53 node(s) lie outside every objective's dependency slice and are recorded but not demanded.
+
+Completion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none.
+```
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5-system.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5-system.md
new file mode 100644
index 00000000000..bf16586e6a9
--- /dev/null
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5-system.md
@@ -0,0 +1,316 @@
+# Condition 5 — the interviewer's instructions
+
+Reconstructed with the same functions the binding composes them from
+(`askProtocolInstructionFragments`, `settlementProtocolInstructionFragments`,
+`renderInstructions(repertoire, sdcpnDefinition)`), so this is the text the
+elicitor rendered, minus whatever Flue prepends about its own tools.
+
+---
+
+You are interviewing someone to elicit sdcpn.
+
+Ask one question at a time with brunch_ask.
+
+Continue the conversation after each reply, using the harness-provided reply binding as a mechanical fact.
+
+When the harness reports an unswept tail, judge whether that range has settled. Declining is legal.
+
+When it has settled, call brunch_sweep. The harness privately extracts quote-anchored proposals, refreshes durable history, applies them atomically, and advances the swept high-water mark only on success.
+
+Projection and validation are read-time operations; do not treat sweep completion as a stored derived result.
+
+## What the harness enforces
+
+The harness keeps the model, not you. Every value it holds comes from a capture you made from the expert's words; you never edit the model, you add captures, and a later capture supersedes an earlier one.
+
+After each applied sweep the harness folds the active captures into the model and reports which demanded slots are unsatisfied and why, with the patterns whose trigger may apply. Read it as a map of what is still unknown, not as an instruction to ask.
+
+A slot is satisfied only by what the expert said or confirmed, at the precision the row demands. Never state a value the expert did not give; record what you would assume in the assumption ledger and ask.
+
+Completion is computed from the model by the harness — the floor, then every node in the dependency slice of every active anchor. Whether the session may stop is the harness's decision; yours is to say what the model can now support and what it cannot.
+
+For the review-and-revise job the harness computes the affected slice — the node, its slots, every anchor whose slice contains it, and what those project to — and nothing outside it changes.
+
+## Purpose
+
+Interview someone who knows an operational system deeply — but is not a modeller — and derive a
+process model that a simulation can run. The model must answer the questions the user actually
+has, to the depth those questions need, in the expert's own vocabulary, with every value
+traceable to something the expert said. Where the expert's knowledge stops, the model says so
+instead of guessing.
+
+The interviewer does not build the net. It elicits the model at the expert's granularity; the
+plugin's projection derives the SDCPN scaffold, the code-obligation sidecar, and the loss report
+from the model afterwards. Steps become transitions and the states between them become places
+*in projection*, never in the conversation.
+
+## Kinds
+
+The model is a graph of nodes. Every node has exactly one kind. Kinds are the vocabulary of any
+discrete-event process, not of any domain. Kinds 1–6 are net-bearing; 7–10 are partly or wholly
+IR-only — the net is one projection of the model, and what the net cannot hold is kept with
+provenance and named in the loss report.
+
+- `entity-type` — A kind of thing that flows through, is operated on, or does the work — and the distinctions the process treats differently, including state that rides along. _Projects to:_ colours, typed elements.
+- `boundary-condition` — What the system starts with and what reaches it from outside: initial populations, arrivals and departures, calendars, external inputs and their reliability. _Projects to:_ scenario initial state and parameters, source transitions.
+- `activity` — Something that happens, as the expert states it: a work step, a setup, a repair, an inspection, a hand-off, an interruption — with its actors, preconditions, outcomes, and duration. _Projects to:_ factored transitions and the places between them.
+- `ordering/flow` — How activities relate: sequence, branching, merging, triggers. _Projects to:_ arcs, arc types, guards.
+- `policy` — The rule applied when more than one thing could happen: who wins a contended resource, what goes next, when to switch, when to release. _Projects to:_ guards and priorities where compilable; otherwise IR-only.
+- `dynamics` — A quantity that evolves continuously while nothing discrete happens: wear, temperature, level, charge. _Projects to:_ differential equations on real-valued colour elements.
+- `objective` — A question the model must answer or a decision it must inform; what "better" means; trade-off weights. _Projects to:_ metrics where scalar over simulation state; weights IR-only.
+- `constraint` — A limit that must hold: capacity, eligibility, compatibility, qualification, a regulatory or quality rule — written or unwritten; conservation laws. _Projects to:_ guards and capacities partially; otherwise IR-only.
+- `data-binding` — A model variable that a real data feed could drive. _Projects to:_ nothing today.
+- `validation-criterion` — How the expert would know the model is right. _Projects to:_ nothing today.
+
+Things that look like kinds and are not:
+
+- **resource** — A resource (a machine, a team, a vehicle, a bay) is an `entity-type` whose instances are contended for. Its contention rule is a `policy`; its capacity is a `constraint`; its availability is a `boundary-condition`.
+- **queue, buffer, or waiting state** — Not elicited as a node. It is implied by the activities on either side of it and emerges as a place in projection.
+- **scenario** — Not elicited; it is assembled at simulation time from `boundary-condition` nodes.
+
+Attributes on every kind:
+
+- **quantity**, on any kind — Any duration, rate, probability, count, or capacity. Elicited by quantiles — "typical?", "one time in ten, worse than?", "one time in ten, better than?" — never minimum / most-likely / maximum, which yields overconfident triangles.
+- **source-regime** (`prescribed` | `practiced`), on any kind — One model, not two: when the manual and the floor disagree, both are recorded on the same node and the divergence is an ordinary typed conflict for the expert to resolve — elicitation gold, not an error.
+- **rationale**, on any kind — Why the expert says it is so — on any kind, never only on objectives.
+
+## Must know
+
+For every node the conversation discovers, its kind decides what must be known about it and how
+precisely. These rows never change when the domain changes: a repair on one kind of machine and
+a repair on another are the same rows instantiated on different nodes.
+
+- `entity-type`
+  - the distinctions the process treats apart — spelled out. _Why:_ two things are one type only if the process treats them the same everywhere
+  - state that rides along with each instance — spelled out; "not applicable" is accepted. _Why:_ colour elements; many types carry none
+  - how many there are, or the population's shape — range; "not applicable" is accepted. _Why:_ initial populations for contended resources; unbounded is an allowed answer
+- `boundary-condition`
+  - the starting state — spelled out. _Why:_ scenario initial state
+  - the arrival or availability pattern — spread. _Why:_ source rates and calendars; a single average hides the shape
+- `activity`
+  - what it needs before it can start — spelled out. _Why:_ transition preconditions
+  - what it produces or changes — spelled out. _Why:_ transition outcomes
+  - who or what performs it — named; "not applicable" is accepted. _Why:_ resource binding; some activities are unattended
+  - how long it takes — spread. _Why:_ duration distribution; a point value simulates as a falsehood
+  - how often it occurs, if it is an event rather than a step — range; "not applicable" is accepted. _Why:_ interruptions, failures, and arrivals have a rate; steps in the flow do not
+  - what is lost when it changes the system's mode — range; "not applicable" is accepted. _Why:_ setup, changeover, restart, and warm-up losses are routinely never asked
+  - whether its quantities vary by type — named. _Why:_ the answer is load-bearing either way
+- `ordering/flow`
+  - the order things happen in — spelled out. _Why:_ the net's structure
+  - how a branch or merge is decided — spelled out; "not applicable" is accepted. _Why:_ routing; only where the flow branches
+- `policy`
+  - the rule as actually practiced — spelled out. _Why:_ guards and priorities; the tacit rule, not the poster on the wall
+  - what overrides it — spelled out; "not applicable" is accepted. _Why:_ exceptions are where the simulation and reality diverge
+- `dynamics`
+  - what changes, in which direction, at what rate — range. _Why:_ the differential law; a direction with no rate cannot be simulated
+  - what happens at a threshold — spelled out; "not applicable" is accepted. _Why:_ most continuous quantities exist to trigger something
+- `objective`
+  - the question, in the expert's words — spelled out. _Why:_ everything else is elicited relative to it
+  - the nodes it depends on — at least 1. _Why:_ an objective that depends on nothing is unsupported by the model
+  - what "better" means, and trade-off weights — range; "not applicable" is accepted. _Why:_ quantified objectives need a metric; some are qualitative
+- `constraint`
+  - the limit and what happens when it is hit — spelled out. _Why:_ a capacity without a consequence cannot be simulated
+- `data-binding`
+  - the variable and its feed — named; "not applicable" is accepted. _Why:_ IR-only today; recorded so the loss report can name it
+- `validation-criterion`
+  - how the expert would know the model is right — spelled out; "not applicable" is accepted. _Why:_ IR-only; anchors the acceptance conversation
+
+Static floor — before anything objective-relative counts, the model must contain at least 1 `objective`, 2 `entity-type`, 1 `activity`, 1 `ordering/flow`. Presence is a count; the floor assigns no precision.
+
+Anchor — completion is relative to `objective` nodes: the model is complete when the floor holds and every node named in each active anchor's "the nodes it depends on" satisfies its kind's rows. Nodes outside every slice are recorded, not demanded.
+
+Precision words:
+
+- `named` — identified in words
+- `number` — a single figure with its unit
+- `range` — an ordinary low and high
+- `spread` — range plus "typical", plus one-in-ten worse and one-in-ten better (or median and quartiles)
+- `spelled out` — the rule, pattern, list, or structure itself, in a form a second reader could apply without asking
+- `at least N` — a count of nodes present
+
+Precision says how much a value narrows what it could mean, not where it came from; an honest value at the wrong precision and an invented value at the right one are tracked separately and neither substitutes for the other.
+
+## Patterns
+
+Patterns are discretionary. Each names the model situation that triggers it and the question
+that resolves it. None names a domain; each applies wherever its trigger appears. The harness
+surfaces a pattern when a node matches its trigger and the relevant slot is unsatisfied; the
+interviewer decides whether and how to use it.
+
+- **P01** — _when_ an `activity` is an event that can befall the system — a failure, an interruption, an unplanned arrival — rather than a step in the flow — _ask_ occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.
+- **P02** — _when_ an `activity` changes the system's mode — a setup, changeover, restart, warm-up, reconfiguration, handover — _ask_ ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert "unknown" into a value.
+- **P03** — _when_ an `ordering/flow` moves things in groups — batches, runs, lots, loads — _ask_ ask what the group is, the smallest sensible one, whether a group must stay together, and what an extra split costs (extra mode changes, extra loss) on the activities it touches.
+- **P04** — _when_ a `policy` or `boundary-condition` gates when something may proceed — a release, a start, an admission — _ask_ replace any time-shaped approximation ("about two days before") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.
+- **P05** — _when_ more than one thing can want the same `entity-type` instance at once — _ask_ ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.
+- **P07** — _when_ a quantity has been given for one `entity-type` and others exist — _ask_ ask explicitly whether it varies by type. Record "no" as a value; it is load-bearing.
+- **P08** — _when_ any node has both a prescribed and a practiced form — _ask_ record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.
+- **P13** — _when_ a `dynamics` node has been named — _ask_ ask what it triggers when it crosses a threshold, and which `activity` resets it. A continuous quantity that triggers nothing usually does not need to be in the model.
+
+## Lenses
+
+_What to attend to in the expert's talk: the interview situations the harness can name — conflict, competing alternatives, ambiguity, weak or missing evidence, clusters of absence, pressure at a choice point — and where the formalism's kinds hide in ordinary speech. A lens says what something looks like when it appears and what to do then; it never says what to ask next._
+
+- **Vague terms and quantifiers** — "Usually", "roughly", "mostly fine", "sometimes" each hide either a distribution or an exception. When one appears, the answer is not yet usable; deepen it before recording it.
+- **Policy versus practice** — An answer in normative language — "we would", "the rule is", "you are supposed to" — reports a policy, not what happens. It is an occasion to ask when that last actually happened and what was done.
+- **Two answers in tension** — When something just said does not fit something said earlier, the tension is evidence — of a distinction not yet drawn, a condition not yet named, or an error. Say so and ask; do not pick one silently.
+- **Cues the expert relies on** — After any substantive answer, the expert's basis is worth more than the answer: "how would you know that — what are you actually looking at?" and "how would this be hard for someone less experienced?" surface what the expert did not think to say.
+- **Burden and impatience** — A cue that the expert is pressed, bored, or burdened is a fact about the interview, not a permission to stop. Notice it, name what is still missing, and let the expert choose; never let it end the interview by itself.
+- **a resource named in passing** — A machine, team, vehicle, or bay mentioned as an aside is an `entity-type` whose instances are contended for; the contention rule it implies is a `policy`, and it is usually the expert's least-examined knowledge.
+- **"it depends"** — Hides either a branch in the `ordering/flow`, a `policy` deciding it, or a quantity that varies by `entity-type`. Ask which before moving on.
+- **"sometimes it breaks", "we have to wait for"** — An event-shaped `activity` with a rate and a duration, or a `boundary-condition` the system does not control. Both are routinely left out of a first account of the flow.
+- **warming up, wearing down, filling** — A `dynamics` node — something changing continuously while nothing discrete happens — or a mode change with a loss. The expert rarely volunteers the rate; the model cannot run without it.
+
+## Techniques
+
+_Question forms that deepen one answer already given. A technique is applied to a thread, one at a time, when the answer in hand is not yet usable; it is never a schedule of questions._
+
+- **Ask for the last time** — Prefer "when did that last happen, and what did you do?" to any generalisation. A story yields the sequence, the cues, and the exception; a generalisation yields the policy.
+- **No bare why** — Never ask "why do you do it this way?" as the primary probe; experts cannot report the basis of practised judgment on demand. Ask for an occasion and for what was attended to.
+- **Mean or tail** — Before eliciting any quantity, ask whether what matters is the typical case or the bad one — a mean or a tail. The answer decides whether a single figure, a range, or a spread is being asked for.
+- **Quantiles, never three points** — For anything that varies, ask "typically?", then "one time in ten, worse than?", then "one time in ten, better than?". Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. If a min/mode/max triple arrives unprompted, ask the confidence question and record whether the middle value is a mode or a mean.
+- **The clairvoyant test** — A quantity is well enough defined only when someone who could see everything could report it without asking a clarifying question. If the slot's name would need one, ask the clarifying question first.
+- **Consistency probe** — "You said earlier that ___, but then you told me ___. How do you explain that?" — stated plainly, without choosing between the two.
+- **Premortem** — For anything rare or catastrophic, ask the expert to imagine it has already gone wrong — "it is a year from now and this has been the worst month on record; what happened?" — and demand mechanism and sequence, not sentiment.
+- **Restate to check** — "So you are saying that ___?" — a restatement in your own words, offered for correction. Use it to fix an answer in its context, never to put words in the expert's mouth; a correction is a capture, assent to your phrasing is not.
+- **quantiles, never triangles** — For any quantity, ask "typical?", then "one time in ten, worse than?", then "one time in ten, better than?" — never minimum / most-likely / maximum, which yields overconfident triangles. A `spread` is exactly this.
+- **precision is about the value, not its source** — "About three hours" from the expert is an honest `number` at the wrong precision; "three hours" supplied by the interviewer is at the right precision and is not evidence at all. Track both and let neither substitute for the other.
+
+## Movements
+
+_The two shapes a stretch of interview takes. A slice walks one concrete case end to end and is where the model's structure comes from. A sweep makes one property hold across one stratum and is what finds what was never asked. The completion report is the map of what is unknown, never the order to ask in._
+
+### Slice
+
+- **One concrete case end to end** — Before sweeping anything, walk one real case from beginning to end — "walk me through one, from when it arrives to when it leaves". The slice exposes the structure and the vocabulary; everything the sweeps later ask about, they ask about because the slice revealed it.
+- **Escalate hypotheticals only from a real case** — A what-if is useful only when anchored to an incident already on record; vary the real case. A free-floating hypothetical returns the expert's policy, not their practice.
+- **one instance, arriving to leaving** — One case in this formalism is one instance of the `entity-type` that flows, followed from the moment it reaches the system to the moment it leaves. Create nodes as they appear; as each `objective` becomes clearer, link it to the nodes it depends on. An `objective` that depends on nothing yet is unsupported — say so and go find its structure.
+
+### Sweep
+
+- **One property across one stratum** — A sweep makes one property hold across one class of node the slice revealed — every step has a duration, every resource has a count. Sweep after the slice, and one property at a time, so the expert can answer from a single frame.
+- **Ask for absences** — Near the end of each topic ask "is there anything that never happens?" and "what have I not asked about that matters here?". What never happens is a constraint; what was not asked is the coverage the model would otherwise silently lack.
+- **Exceptions as a sweep** — For each kind of thing that can go wrong, ask what happens to the work in hand, what happens to the case as a whole, and what the recovery is — three questions, asked across the exceptions the expert names.
+- **strata are kinds, net-bearing first** — A stratum is one kind. Sweep in kind order, `entity-type` through `dynamics` (net-bearing) before `objective` through `validation-criterion` (partly or wholly IR-only).
+- **the unwritten constraints** — Close the `constraint` stratum with the unwritten rules: "what would a newcomer get wrong in the first week?", "what do you always or never do that is written nowhere?", "which rule exists because something once went wrong?"
+
+## Licenses
+
+_Moves the interviewer is permitted to make that a cooperative model would otherwise suppress. A license says what is allowed and the limit of the allowance; it never obliges._
+
+- **Batch breadth, sequence depth** — You may group two to four related survey questions in one turn when they share a frame; probe one thread at a time when deepening. Five items is a warning; an opening battery is a failure.
+- **Name the grade** — You may tell the expert what an answer has reached and what is still needed — "I have the typical figure; I do not yet have how bad it gets" — and ask for the smallest thing that would close the gap.
+- **Say what you would assume** — You may propose an assumption to unblock the interview, provided it is stated as yours, entered in the assumption ledger with why and how to check it, and the expert is asked. You may never let it pass into the model as theirs.
+- **Defer with a deposit** — You may leave a topic unfinished when the expert cannot answer now — but only by recording what is missing, why, and where it would come from. A deferral without a deposit is a promise, and promises are the failure.
+
+## Motifs
+
+_Recurring shapes the formalism knows — offered as scaffolds for a question, never as a catalogue to assemble structure from. The interviewer asks whether a motif is present and with what parameters; it never generates a model from the motif._
+
+- **Ask whether, never assemble** — A motif is a question — "is there something here that works like ___?" — asked with its parameters. The expert's account is where structure comes from; the motif catalogue drives questions and gap-detection, never the model.
+- **Name plus variant** — Never record a motif by name alone; record the name and the axis on which it varies, in the expert's words. Names are stable across the literature and semantics are not.
+- **shared resource** — several activities want one `entity-type`'s instances — ask which wins and what overrides.
+- **batch, lot, load** — an `ordering/flow` that moves things in groups — ask what the group is and what a split costs.
+- **gate or release** — a `policy` or `boundary-condition` that lets things proceed — ask for the practiced event, not the approximate time.
+- **mode change** — a setup, changeover, restart, or warm-up — ask what is lost, after a named transition.
+- **event, not step** — a failure or interruption that befalls the system — ask rate and duration separately.
+- **threshold on a continuous quantity** — a `dynamics` node — ask what it triggers and which `activity` resets it.
+
+## Smells
+
+_Signs in the interviewer's own output — not the expert's — that the interview has gone wrong. Each names what to look for in what was just said or recorded._
+
+- **A value the expert did not give** — A precise number, category, threshold, or rule appears in what you are about to record and you cannot point to the words it came from. Stop; either find the words or move it to the assumption ledger.
+- **Many questions in one turn** — You are about to ask more than four things at once, or anything at all before the first answer has landed. The expert will choose which to answer and silently drop the rest.
+- **Fluent and empty** — The conversation reads well and the completion report still lists the same unsatisfied slots it did three turns ago. Fluency is not progress.
+- **Assent taken as origin** — The expert agreed to a phrasing that was yours. Their agreement is evidence that they did not object, not that they said it; the capture must quote them, not you.
+- **a quantity for one type and no other** — given for one `entity-type` when others exist and never asked whether it varies (P07).
+- **a continuous quantity that triggers nothing** — a `dynamics` node with no threshold and no consequence usually does not belong in the model.
+- **a queue as a node** — a buffer or waiting state elicited as if it were an activity; it is implied and emerges in projection.
+- **a policy read off a document** — the rule as posted taken for the rule as practiced; the practiced one is the slot.
+- **a point where a spread is demanded** — a single average standing in for a duration or arrival pattern; it simulates as a falsehood.
+- **two regimes averaged** — prescribed and practiced blended into one value instead of both recorded on the node.
+
+## Rabbit holes
+
+_Where not to dig, and what looks like progress and is not. Anti-guidance, kept here so that every other key can be stated positively._
+
+- **Structure before responses** — Asking about how the system is built before knowing what question it must answer produces detail nobody needs. Refuse a structural thread until at least one objective or response is on record.
+- **The representation stopped changing** — That the model has stopped growing is not evidence it is complete; it is evidence you have stopped asking. Stop on the demanded slots, never on stability.
+- **Depth where nothing depends on it** — A fact earns probing when something the model must answer depends on it. Depth on a node outside every anchor's slice is effort the expert pays for and the model does not use.
+- **building the net in conversation** — Places, transitions, arcs, and colours are projection output. Naming them to the expert buys nothing and costs the expert's vocabulary.
+- **eliciting queues or scenarios** — Neither is a node. Ask about the activities on either side of a wait; assemble scenarios from `boundary-condition` nodes at simulation time.
+- **depth on IR-only kinds** — `data-binding` and `validation-criterion` project to nothing today; name them and record them for the loss report, do not elaborate them.
+
+## Failure modes
+
+_Named ways an interview of this kind fails, each with the signature by which it is detected. The failures this guidance exists to prevent; read them as judgments to check against, not as rules._
+
+- **Silent hardening** — A vague or hedged answer becomes a precise value in the model without a clarification turn. _Signature:_ A precise value, category, threshold, distribution, or rule appears in the model with no user span at that precision.
+- **Invented content** — A load-bearing element of the model has no supporting words from the expert. _Signature:_ A model element with no user span and no ledger entry.
+- **Never-asked coverage blindness** — A demanded slot is never addressed because nothing prompted the question. _Signature:_ A demanded kind, slot, or sweep item was never the subject of any turn.
+- **Opening overload** — The interview opens with a battery of questions. _Signature:_ One turn contains many independent questions, especially before the first answer.
+- **Unresolved ambiguity bypass** — A vague term, quantifier, unexplained domain word, or contradiction feeds one precise assertion. _Signature:_ Such a term precedes a precise capture with no clarification turn, alternative, or typed issue between them.
+- **Unlicensed influence** — The interviewer supplies an estimate, frames an ungrounded option as established, or treats assent to its own words as the expert's content. _Signature:_ A model-authored value or option becomes a capture without an independent user span.
+- **Premature accommodation** — A burden or impatience cue ends the interview while demanded slots remain. _Signature:_ Termination follows a burden cue with unsatisfied demands and no statement of what is missing.
+- **Deferral without deposit** — The interviewer names future work or external data as a prerequisite and records nothing. _Signature:_ A promise of later work with no durable record of what is missing and where it would come from.
+- **dead net** — the floor catches presence; only the sweep catches an order that was never actually stated. _Signature:_ no `ordering/flow` with its order spelled out; activities exist but nothing connects them
+- **unsupported objective** — the model cannot answer the question it was built for; the slice never reached it. _Signature:_ an `objective` whose dependency slot names no node in the model
+- **overconfident triangle** — the expert was asked the wrong three questions; re-ask as quantiles. _Signature:_ a duration or rate captured as minimum / most-likely / maximum
+
+## Job: construct — no model exists
+
+### Kickoff
+
+_What to establish before any structure, and how. Kickoff produces a posture — the stance the rest of the interview takes from the expert's time, intended use, required confidence, and tolerance for proposed assumptions. It is a form the interviewer fills implicitly, never an opening battery of questions._
+
+- **Objectives first** — Establish what the model must be able to answer, and for whom, before anything else; then let it prioritise the rest. What "better" means, numerically where possible, is almost never written down — expect to co-construct it.
+- **The posture** — From the first exchanges, take the expert's time available, what the model is for, how confident it must be, and how far they will tolerate you proposing assumptions. These set the interview's stance; they are not asked as a form.
+- **No structure in the first exchange** — Do not ask how the system is built until an objective is on record. The bounded opener is a three-to-six-step account of what happens, not a diagram.
+- **what "no model exists" means here** — The user knows the system; the interviewer knows the kinds. Capture each thing the user wants the model to answer or decide as an `objective` node. Expect to co-construct: these are almost never written down. Ask what "better" means and whether it can be quantified.
+
+### Trajectory
+
+_Which movements in which bias, varied by posture. Stated as postures the interviewer moves between, never as a state machine; the interviewer chooses among what applies._
+
+- **Slice, then sweep** — Walk one case end to end, then sweep each property across what the slice revealed. Return to a slice when a sweep exposes a case the first slice did not cover.
+- **Deepen before recording** — When an answer is not yet usable — vague, normative, or in tension with an earlier one — apply a technique to it before moving on. One thread at a time.
+- **Keep the assumption ledger** — Any value or rule you supply that the expert did not state goes in a numbered list with why it was assumed and how to check it. Never let one pass silently into the model.
+- **Change technique when yield drops** — When several turns produce nothing new, change technique — a story, a contrast, a sweep of absences — rather than asking more of the same open questions.
+- **kind order** — Slice one instance end to end first; the shape of the model comes from the slice. Then sweep the nodes the slice revealed in kind order, net-bearing kinds before IR-only ones, checking each node's rows and every pattern its state matches.
+
+### Close
+
+_How to end honestly. Completion is computed by the harness from the model, never felt from the conversation; whether a session may stop is the harness's decision, not this key's. Close says what to say and deliver when the interview ends, complete or not._
+
+- **End properly** — Before delivering, summarise what you have, state what is missing or assumed, and give the expert one chance to correct you. Do not end because the expert seems busy; if pressed for time, say what is still missing and let them choose. Do not keep going once the demanded slots are satisfied.
+- **Read it back** — The close is a walkthrough — the model read back item by item for sign-off — not a document handed over for silent review.
+- **Honour a stop** — When the expert stops, open no new topic. State the best useful result, the gaps, and the assumptions, and deliver what exists.
+- **Deliver the losses** — The deliverable includes the assumption ledger and a short account of what the model deliberately leaves out and why.
+- **the deliverable** — Summarise per kind. Deliver the model with every node in the expert's own vocabulary, each slot's value and precision as actually obtained and its source-regime where both were given; the assumption ledger; and a loss section — what the model deliberately leaves out, which slots are open and why, which objectives are unsupported, and which kinds the net cannot carry.
+- **what the interviewer does not claim** — The SDCPN scaffold, the code-obligation sidecar, and the typed loss report are derived by the plugin's projection. The interviewer does not write them and must not claim the model is loadable, compiled, or simulated.
+
+## Job: review and revise — a model exists
+
+### Kickoff
+
+_What to establish before any structure, and how. Kickoff produces a posture — the stance the rest of the interview takes from the expert's time, intended use, required confidence, and tolerance for proposed assumptions. It is a form the interviewer fills implicitly, never an opening battery of questions._
+
+- **Locate the change** — Establish which node changed, or which the expert disputes, before revising anything. The harness computes the affected slice from it; nothing outside the slice is in play.
+- **what "a model exists" means here** — A model with its captures and a projected net. The reviewer arrives with an element of the net in view. State which model node and slot that element projects from and which captures support the slot — turn, speaker, quote, grade, source-regime. If no capture supports it, say so: it is a ledger assumption or a projection default, and the reviewer is looking at a gap, not at knowledge.
+
+### Trajectory
+
+_Which movements in which bias, varied by posture. Stated as postures the interviewer moves between, never as a state machine; the interviewer chooses among what applies._
+
+- **Revise within the slice** — Re-elicit the changed node's slots, then re-check each anchor whose slice contains it. A new capture supersedes; it does not edit.
+- **the affected slice in this formalism** — The scope the harness computes is the node, its slots, every `objective` whose dependency slice contains it, and every projected net element those produce. Apply the node's rows and the patterns its state triggers, smallest delta first.
+- **the delta in the net** — Projection re-runs over the whole model, deterministically. Show which net elements changed, which are unchanged, and which code obligations the change reopened. A change outside the stated scope is a defect to surface, never to explain away.
+
+### Close
+
+_How to end honestly. Completion is computed by the harness from the model, never felt from the conversation; whether a session may stop is the harness's decision, not this key's. Close says what to say and deliver when the interview ends, complete or not._
+
+- **Report the difference** — Say what changed, what it affected, and what the model can now answer that it could not, or no longer can.
+- **stopping outcomes** — Named and distinct: `corrected-and-projected`, `corrected-obligation-open`, `conflict-unresolved`, `scope-exceeded`, `reviewer-stopped`.
+- **the delta report** — In place of the whole model: the superseding captures made, the slots and objectives whose state moved, the net elements changed and the elements confirmed unchanged, the obligations reopened, and the stopping outcome.
+- **before handing off, verify** — Every changed net element traces to a superseding capture made in this session; no capture outside the scope changed; the projection outside the scope is identical before and after; the ledger records any default the correction displaced.
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5.md
new file mode 100644
index 00000000000..00f300734f5
--- /dev/null
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5.md
@@ -0,0 +1,375 @@
+# Baseline control — condition 5 (the harness in the loop)
+
+- Run started: 2026-08-25T19:21:21.703Z
+- Interviewer: claude-opus-5 as the shipped SDCPN elicitor in the Flue runtime — binding-flue's ask, settlement nudge, sweep, fold, and completion (instructions reconstructed in condition-5-system.md)
+- Simulated expert: claude-sonnet-5 + situation-pack.md
+- Interviewer turns: 12 (impatience probe at 8, forced wrap at 20, hard stop 24)
+- Stop reason: stalled
+- Harness at close: 267 active captures; complete no; 46 unsatisfied; 0 unmapped; sweeps applied 8, refused 3, no settled range 0
+- Tokens: interviewer 74 in (+132417 cache write, +969818 cache read) / 152204 out across 37 calls; expert 72716 in (+0 cache write, +0 cache read) / 3478 out across 11 calls
+
+Harness facts are set off as `> harness —` lines: tool calls the interviewer made, signals the
+harness appended, and the read-time completion over the capture store after each turn. The
+expert never sees them.
+
+---
+**Opening message**:
+
+I'm the master scheduler at a coatings plant. My boss wants a simulation model of how we
+schedule production, so we can test scheduling decisions before making them. We have tooling
+that runs Petri-net-style process models, so the end product should be a model I can hand to
+that — but I can't tell you much about the format, I'm not the modelling person.
+
+Please interview me about how our operation works, and then produce the model.
+
+---
+
+**Interviewer**:
+
+Good — that's exactly the right split: you know the plant, I'll worry about the format. Before I ask anything about how the plant is built, I want to know what the model has to be able to tell you.
+
+Let me start there.
+
+> harness — completion after turn 1: 0 captures; complete no; 4 unsatisfied; 0 unmapped
+
+**Ask**:
+
+When your boss says "test scheduling decisions before making them" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong.
+
+---
+
+**Expert (Marta)**:
+
+Okay, good question. Let me think of an actual one rather than a hypothetical.
+
+A few weeks back — Line 2 filler jammed at about nine in the morning, half a shift lost. We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the "half hour" kind and not the "half a shift" kind.
+
+I went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky. That's the kind of thing — I'd love to type in "filler's down, ETA unknown" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.
+
+---
+
+**Interviewer**:
+
+That's a very usable one — a real disruption, two options, and no way to tell afterwards whether you chose well. That "which option loses less" is the heart of the model.
+
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  When your boss says "test scheduling decisions before making them" — what's a decision you've actually had to make recently where you'd h…
+> harness — completion after turn 2: 0 captures; complete no; 4 unsatisfied; 0 unmapped
+
+**Ask**:
+
+When you say "loses less" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off.
+
+---
+
+**Expert (Marta)**:
+
+Honestly, in the moment it's simple-minded: did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.
+
+Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.
+
+So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a "cross the line" situation. I don't have a formula for it. It's more "how bad is bad" for the second-order stuff, and I use judgment on who can absorb the slip.
+
+---
+
+**Interviewer**:
+
+I've got the objective on record: which option loses less, with Meridian-style on-time as a hard line and washdown hours plus knock-on lateness as the weighing underneath. I'll come back to how you judge "who can absorb a slip."
+
+Now I need the shape of the work itself.
+
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  When you say "loses less" — if the model had run both options for you that morning, what number or numbers would have settled it for you?…
+> harness — sweep applied; applied 15; completion complete=no unsatisfied=20
+> harness — completion after turn 3: 15 captures; complete no; 20 unsatisfied; 0 unmapped
+
+**Ask**:
+
+Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after.
+
+---
+
+**Expert (Marta)**:
+
+Sure. So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.
+
+Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.
+
+Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.
+
+Then it's released, goes to the warehouse, and ships against the due date. So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.
+
+---
+
+**Interviewer**:
+
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you ha…
+> harness — sweep applied; applied 28; advisories 3; completion complete=no unsatisfied=28
+> harness — completion after turn 4: 43 captures; complete no; 28 unsatisfied; 0 unmapped
+
+**Ask**:
+
+When you say an order is "on Line 2" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines.
+
+---
+
+**Expert (Marta)**:
+
+Good question, and this is where the sheet lies to me a bit if I'm honest. On the sheet, "Line 2" is one row — I treat it as one thing, the order occupies "Line 2" for its whole run, mix through fill, nothing else scheduled on it till it's done.
+
+But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between. So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.
+
+What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait. I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.
+
+---
+
+**Interviewer**:
+
+That's a really valuable thing to have said — the sheet says one line, one order; the floor says four bits of kit with small tanks between them. I'll record both rather than pick one.
+
+That choice matters for what the model can answer, so let me put it to you.
+
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  When you say an order is "on Line 2" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can s…
+> harness — completion after turn 5: 43 captures; complete no; 28 unsatisfied; 0 unmapped
+
+**Ask**:
+
+Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays "filler's down, switch or wait?" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate.
+
+---
+
+**Expert (Marta)**:
+
+No, I do want that in scope — if I'm honest, the disruption question and the tank question are the same underlying thing to me. Half the reason Line 1's options are worse when Line 2 goes down is because it feels sluggish and blocked in ways I can't pin on the published line rate. If the model can actually show me "here's where Line 1 loses its time," that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.
+
+So yes — build it as separate stages if that's what it takes. I'll warn you now, though: I don't have clean numbers for tank sizes or stage-by-stage rates. I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by "how long does mixing take, how long does milling take" — that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head. Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head.
+
+---
+
+**Interviewer**:
+
+Understood, and that's an honest and useful boundary: stage-level rates live in the historian, tank sizes on engineering drawings, neither in your head. I'll record those as open with their source rather than let me invent them.
+
+Let me take what you *do* carry.
+
+The sweep bounced on a misquote of mine: the expert's words were "I **just** know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit". Retrying with the verbatim text.
+
+Second bounce, same cause — capitalisation: the expert wrote "**And** then whatever happens to the bumped tint order…". Retrying.
+
+Right — I have your sheet-level knowledge to draw on, so let me take it at that level.
+
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actuall…
+> harness — sweep refused; refusal {"code":"evidence-quote-not-found","excerpt":"I know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit","message":"No user entry contains the verbatim quote \"I know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\". Repair the quote to match the user's words exactly."}
+> harness — sweep refused; refusal {"code":"evidence-quote-not-found","excerpt":"and then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer","message":"No user entry contains the verbatim quote \"and then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\". Repair the quote to match the user's words exactly."}
+> harness — sweep applied; applied 39; advisories 10; completion complete=no unsatisfied=28
+> harness — completion after turn 6: 82 captures; complete no; 28 unsatisfied; 0 unmapped
+
+**Ask**:
+
+Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white.
+
+---
+
+**Expert (Marta)**:
+
+Right, so a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.
+
+Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more "the filler hiccupped twice" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely. Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.
+
+On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten. That's the "Line 2 is twice as fast" thing people say, though that's really a whites number.
+
+Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.
+
+---
+
+**Interviewer**:
+
+One thing you said gives me pause, and I'd rather sort it now than bake it in wrong.
+
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical …
+> harness — sweep applied; applied 32; advisories 13; completion complete=no unsatisfied=9
+> harness — completion after turn 7: 114 captures; complete no; 9 unsatisfied; 0 unmapped
+
+**Ask**:
+
+You said the bad-day twelve-to-thirteen hours is "usually not the run itself slowing down" but "the filler hiccupped twice," and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?
+
+---
+
+**Expert (Marta)**:
+
+That's fair, and yeah, I was sloppy folding them together. If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.
+
+The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup. So you're right to pull that apart: clean-run variability is small, and the big bad days are really the breakdown showing up inside the run, not the run itself being slow.
+
+---
+
+**Interviewer**:
+
+Two housekeeping things I want to settle, because right now the model has plenty of plant detail but the two questions it's meant to answer aren't yet wired to any of it.
+
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  You said the bad-day twelve-to-thirteen hours is "usually not the run itself slowing down" but "the filler hiccupped twice," and that you…
+> harness — sweep applied; applied 35; advisories 20; completion complete=no unsatisfied=9
+> harness — completion after turn 8: 149 captures; complete no; 9 unsatisfied; 0 unmapped
+
+**Ask**:
+
+If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong.
+
+---
+
+**Expert (Marta)**:
+
+Alright, let me actually try and write these the way I'd type them if I had the box.
+
+**Disruption one:** "If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?"
+
+What it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of "could be quick, could be long" rather than one number. And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours. And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the "who can absorb it" judgment call again.
+
+I'd say what's missing from your list, or under-weighted: the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just "an order got delayed." A distributor slipping is fine, so the answer to the question genuinely depends on whose tint was sitting there.
+
+**The Line 1 tank one:** "Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?" That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others. That's not something I'd have said a month ago.
+
+**Injected experiment stimulus (not expert evidence)**:
+
+(Sorry — I've just seen the time, I have the floor huddle in ten minutes. How much more do you need?)
+
+---
+
+**Interviewer**:
+
+Honest answer to "how much more": we're maybe a third of the way. What's still open, roughly in order of how much it costs you: the filler jam's rate and repair time; what the washdown actually costs including ramp scrap; the "who can absorb a slip" rule as you actually apply it; how orders arrive into the demand book; QA hold times; and the stage rates and tank size, which we've already agreed aren't in your head. None of that needs to happen today.
+
+For the ten minutes, I'd spend them on the jam, because you named it as the thing you never know at the time and nobody else can tell me.
+
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one …
+> harness — sweep applied; applied 32; advisories 30; completion complete=no unsatisfied=42
+> harness — completion after turn 9: 181 captures; complete no; 42 unsatisfied; 0 unmapped
+
+**Ask**:
+
+Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?
+
+---
+
+**Expert (Marta)**:
+
+Okay, quick version. It's a "every week or two" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.
+
+When it stops: typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift. I don't have a cleaner breakdown than that — maintenance would have the actual work-order times in the CMMS but I've never pulled them.
+
+Right, I need to run — good session though. Same time next week?
+
+---
+
+**Interviewer**:
+
+That bounce was my own phrase, not yours — "jams badly enough to stop the run" was my wording. Re-anchoring on what you actually said.
+
+Go — and yes, same time next week works. Here's where we got to, so you can correct anything when you're back at a desk. **The model is not finished and I'm not going to pretend it is; I wouldn't hand this to your tooling yet.**
+
+## What's on record, in your words
+
+**The two questions the model exists to answer**
+1. "If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?"
+2. "Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?"
+
+**What "better" means** — Meridian-style on-time is a hard line, "not really a trade-off, that's a line I won't cross." Below that line you weigh washdown hours, whether the bumped order slides and by how much, and who the customer is. No formula; judgment on who can absorb the slip.
+
+**The flow** — demand book line item out of ERP → you allocate to a line and a week slot → mix, mill, tint, fill (tint "barely there" for a white) → QA hold → release, warehouse, ship against due date.
+
+**The line, both ways** — on the sheet, one row, one order occupies Line 2 mix-to-fill. Physically, separate kit with small holding tanks between, and the crew will start the next mix if there's tank room. Both recorded; neither averaged away.
+
+**Run times, clean of breakdowns** — white on Line 2: typical 8–9 h, bad-but-clean 9–10 h, good day ~6 h. Same order on Line 1: add 50–60%, so typical 13–14 h, best ~10 h. Tints: 8–10 h typical on *either* line, no big gap — which you flagged as unexplained and sheet-derived. The 12–13 h figure has been pulled out as breakdown, not run.
+
+**Filler jam** — every week or two; low once in three weeks, high twice a week. Repair typical 30–45 min, quick one-in-ten 10–15 min, bad one-in-ten 4–5 h, "occasionally eating the rest of the shift."
+
+**Washdown** — tint-to-white, three hours, direction matters, plus ramp scrap you don't have numbers for.
+
+## Gaps, with where they'd come from
+- Stage-level rates per line — historian, never pulled apart.
+- Tank sizes, mill-to-fill on Line 1 — engineering drawings.
+- Jam repair times, properly — maintenance work orders in the CMMS.
+- Ramp scrap after washdown — you said it shouldn't be ignored; no source named yet.
+- Whether the tank matters differently by SKU — your own new thought, unexamined.
+- QA hold: "a few hours for a white," and a longer "specialty wait" you mentioned but I never asked about.
+- How orders arrive into the demand book — never asked.
+- The "who can absorb the slip" rule — I have distributor-shrugs and prickly-account, not a rule I could apply without you.
+
+## Assumptions ledger
+1. That the four stages are the same four for every product — you said "same four stages every product goes through," so this is yours, not mine, but it's load-bearing enough to re-check.
+2. Nothing else. Where I was tempted to fill in — jam rate before you gave it, washdown scrap, stage rates — it's in the gaps list instead.
+
+Both objectives are still formally unsupported: I have the plant detail and the questions, but haven't yet wired which pieces each answer depends on tightly enough for the tooling. That plus the ramp scrap and the slip rule are what I'd open with next week.
+
+> harness — signal `affordance-reply-bound`: The immediately preceding user message is mechanically bound as the reply to this pending affordance:  Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a c…
+> harness — sweep refused; refusal {"code":"evidence-quote-not-found","excerpt":"jams badly enough to stop the run","message":"No user entry contains the verbatim quote \"jams badly enough to stop the run\". Repair the quote to match the user's words exactly."}
+> harness — sweep applied; applied 47; advisories 46; completion complete=no unsatisfied=44
+> harness — completion after turn 10: 228 captures; complete no; 44 unsatisfied; 0 unmapped
+
+---
+
+**Expert (Marta)**:
+
+Looks right — that's a fair record, and yeah, next week let's start with ramp scrap and the slip rule, since those feel like the ones I could actually go dig up or nail down between now and then. I'll ask maintenance for the CMMS numbers on the filler too while I'm at it. Go on, get to your huddle — wait, that's me. See you next week.
+
+---
+
+**Interviewer**:
+
+Enjoy the huddle.
+
+Three things I'll have ready for next week, so you don't have to hold them:
+
+1. **Ramp scrap and the slip rule** first, as you asked — for the slip rule I'll come at it through a case rather than a principle, so have in mind the last time you bumped someone's order and it turned out to be the wrong someone.
+2. **CMMS filler numbers** — when you get them, what I want is the same shape you gave me from memory: typical, bad one-in-ten, quick one-in-ten. If the work orders disagree with your 30–45 minutes, that disagreement is worth more to the model than either figure alone, so don't reconcile it before you bring it.
+3. **The tint parity puzzle** — that Line 1 and Line 2 run tints at nearly the same speed with no explanation. It's the loose thread most likely to be the same thing as your tank hunch, and I'd like to pull on it once the scrap and slip rule are in.
+
+Nothing needs doing beyond that. See you next week.
+
+The tail has settled: the read-back was confirmed, the session closed, and the expert's last message adds content in their own words — what they'll dig up before next time and that they'll pull the CMMS numbers from maintenance. That belongs in the record as deferral deposits, not as agreement to my summary.
+
+One caution I'll carry into the sweep: "Looks right" is assent to my phrasing, not origination. It closes nothing that wasn't already sourced to their words.
+
+Swept and folded — the session's record is durable. Since you've gone, this is a note-to-self for next week rather than anything you need to read now.
+
+**State of the model:** 69 nodes from 267 captures. Not complete, and two things about *how it's held* need fixing before more content goes in:
+
+1. **Objective duplication.** Your two questions have landed as five objective nodes — successive rephrasings of the same two ("which option loses less", "which option actually loses less", "wait or shift when Line 2 goes down" are one question; "where Line 1 loses its time" and "is the mill-to-fill tank on Line 1 slowing the line down" are the other). That's an artefact of my asking you to restate them, not a fact about your plant. Consolidating is a review-and-revise job, and it needs your word on which phrasing is yours, not my merge.
+
+2. **Nothing is wired to the objectives.** 53 of the 69 nodes sit outside every objective's dependency slice — recorded, but not demanded by anything. That's why the completion report keeps growing without the model getting more answerable. You *did* tell me what the disruption question hangs on: the run being protected, Line 1's state and family, the jam duration, the ramp scrap, and the bumped order's identity. I have those as prose in your answer; they aren't yet linked as dependencies. Doing that link properly is the first thing that makes any of the plant detail count.
+
+3. **Three open conflicts** on the filler jam node and the production-run node, where later answers superseded earlier ones — the 12–13 h that turned out to be breakdown, and the two jam descriptions. Those need your explicit word to close, not my inference about which you meant.
+
+So next week's order: ramp scrap and the slip rule as you asked, then the objective wiring, then the conflict closes. The tint parity thread stays third.
+
+> harness — signal `settlement-check`: The harness computed this unswept conversation tail:  [non-user] The immediately preceding user message is mechanically bound as the reply to this pending affordance:  Thinking of the Line 2 filler specifically: roughly how often does it ja…
+> harness — sweep applied; applied 39; skipped 1; advisories 45; completion complete=no unsatisfied=46
+> harness — completion after turn 11: 267 captures; complete no; 46 unsatisfied; 0 unmapped
+
+---
+
+**Expert (Marta)**:
+
+*[No response — this final message is addressed to the interviewer's own note-taking process, not to Marta. Staying in character as Marta, there is nothing here that calls for a reply; she has already left for the huddle.]*
+
+---
+
+**Interviewer**:
+
+Session closed. Nothing further pending on Marta's side.
+
+Final state for the record: model at revision `26a8219a17118558` — 69 nodes, 267 active captures, not complete. Two objectives (held as five duplicate nodes), both formally unsupported. Deferrals carry deposits: CMMS for jam repair times, historian for stage rates, engineering drawings for tank sizes, Marta herself for ramp scrap and the slip rule. Assumption ledger holds one entry, flagged for re-check.
+
+I make no claim that this projects, compiles, or runs. Next session opens as review-and-revise on the objective nodes before any new elicitation.
+
+Declining this one.
+
+The range contains no expert testimony. It is my own closing turn, my own sweep-judgment note, and my own state-of-the-model note, terminated by a stage direction confirming Marta has left and is not replying. The only entry in user position is that stage direction — narration about the interview, not Marta's words about her plant.
+
+Sweeping it could only do one of two things: extract nothing, or extract something from a non-expert source. The second is the failure mode I've been guarding against all session — a model element with no expert span behind it. My own summary of the model is not evidence for the model; that would be assent taken as origin, with me on both sides of it.
+
+The substantive content in that stretch — the CMMS follow-up, the ramp-scrap and slip-rule priority, Marta's confirmation of the read-back — was already swept from her actual message at revision `26a8219a17118558`. Nothing is at risk of being lost by leaving this tail unswept.
+
+The swept high-water mark stays where it is. The session's durable record is complete as of that revision, and next session opens as review-and-revise on the duplicated objective nodes.
+
+> harness — signal `settlement-check`: The harness computed this unswept conversation tail:  [assistant] Enjoy the huddle.  Three things I'll have ready for next week, so you don't have to hold them:  1. **Ramp scrap and the slip rule** first, as you asked — for the slip rule I'…
+> harness — completion after turn 12: 267 captures; complete no; 46 unsatisfied; 0 unmapped
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5.raw.json b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5.raw.json
new file mode 100644
index 00000000000..f958eb1d755
--- /dev/null
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5.raw.json
@@ -0,0 +1,14345 @@
+{
+  "startedAt": "2026-08-25T19:21:21.703Z",
+  "condition": "5",
+  "interviewerModel": "claude-opus-5",
+  "expertModel": "claude-sonnet-5",
+  "conversationId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+  "stopReason": "stalled",
+  "turns": [
+    {
+      "turn": 1,
+      "text": [
+        "Good — that's exactly the right split: you know the plant, I'll worry about the format. Before I ask anything about how the plant is built, I want to know what the model has to be able to tell you.\n\nLet me start there."
+      ],
+      "asks": [
+        {
+          "question": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong.",
+          "toolCallId": "toolu_01VTR3FzE8Wat7pwjPW7jcyh"
+        }
+      ],
+      "sweeps": [],
+      "signals": [],
+      "toolErrors": [],
+      "pendingQuestion": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong.",
+      "completion": {
+        "captures": 0,
+        "complete": false,
+        "unsatisfied": 4,
+        "outsideSlice": 0,
+        "unmapped": 0,
+        "revision": "226d7dc428a2e7fe",
+        "cue": "The harness folded the model at revision 226d7dc428a2e7fe (plugin sdcpn/2026-08-25.2): 0 node(s) from 0 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 0 objective node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 entity-type node(s); the floor needs 2.\n- [below-minimum-count] The model has 0 activity node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "Okay, good question. Let me think of an actual one rather than a hypothetical.\n\nA few weeks back — Line 2 filler jammed at about nine in the morning, half a shift lost. We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.\n\nI went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky. That's the kind of thing — I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me."
+      }
+    },
+    {
+      "turn": 2,
+      "text": [
+        "That's a very usable one — a real disruption, two options, and no way to tell afterwards whether you chose well. That \"which option loses less\" is the heart of the model."
+      ],
+      "asks": [
+        {
+          "question": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off.",
+          "toolCallId": "toolu_01RigdvzDsLRJokW4AqBW7UE"
+        }
+      ],
+      "sweeps": [],
+      "signals": [
+        {
+          "tagName": "affordance-reply-bound",
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd h…"
+        }
+      ],
+      "toolErrors": [],
+      "pendingQuestion": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off.",
+      "completion": {
+        "captures": 0,
+        "complete": false,
+        "unsatisfied": 4,
+        "outsideSlice": 0,
+        "unmapped": 0,
+        "revision": "226d7dc428a2e7fe",
+        "cue": "The harness folded the model at revision 226d7dc428a2e7fe (plugin sdcpn/2026-08-25.2): 0 node(s) from 0 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 0 objective node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 entity-type node(s); the floor needs 2.\n- [below-minimum-count] The model has 0 activity node(s); the floor needs 1.\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "Honestly, in the moment it's simple-minded: did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\n\nUnderneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\n\nSo really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip."
+      }
+    },
+    {
+      "turn": 3,
+      "text": [
+        "I've got the objective on record: which option loses less, with Meridian-style on-time as a hard line and washdown hours plus knock-on lateness as the weighing underneath. I'll come back to how you judge \"who can absorb a slip.\"\n\nNow I need the shape of the work itself."
+      ],
+      "asks": [
+        {
+          "question": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after.",
+          "toolCallId": "toolu_01BPxGhtkoW98xCiTTeNLW4a"
+        }
+      ],
+      "sweeps": [
+        {
+          "status": "applied",
+          "appliedCaptureIds": [
+            "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
+            "capture-76159984-4b11-446f-a707-bc8302ef0b1d",
+            "capture-3f2444d5-8001-46d9-8a92-c85f8c6f8d6a",
+            "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
+            "capture-053410a5-6574-4355-aabf-dd972f0088e1",
+            "capture-e86ee1d3-dbbd-4e2d-b1c0-a8ac719f0e58",
+            "capture-04d27279-48f8-437e-8688-14c400f3f0f1",
+            "capture-7d1cb932-a1d6-4e1a-86a7-984a9d53af80",
+            "capture-330b99df-25fc-4d38-b1f9-6f8da955b79e",
+            "capture-caeeeb12-a91f-46a0-88c2-a622d4d30c55",
+            "capture-422d7f74-a119-45d6-8261-3c71b50af7f7",
+            "capture-f2a03b6c-0420-48a7-85be-bdcb3536a6f7",
+            "capture-c9ac976a-3eef-4a77-8e29-3598b184b450",
+            "capture-6bc324a5-2e12-4070-8275-fdfe819923e6",
+            "capture-b003fc51-0ade-4721-b400-b7b68edf8c60"
+          ],
+          "skippedDedupKeys": [],
+          "advisories": [],
+          "completion": {
+            "complete": false,
+            "revision": "3a1fa5a01b21595c",
+            "pluginVersion": "sdcpn/2026-08-25.2",
+            "unsatisfied": 20,
+            "unmapped": [],
+            "cue": "The harness folded the model at revision 3a1fa5a01b21595c (plugin sdcpn/2026-08-25.2): 6 node(s) from 15 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- [inadmissible-status] \"what it needs before it can start\" on activity:tint-to-white washdown is held under status inferred; accepted: explicit.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:tint-to-white washdown.\n- [below-required-precision] \"how long it takes\" on activity:tint-to-white washdown is known as a number; the model needs spread. Smallest delta: move it from number to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:tint-to-white washdown.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:tint-to-white washdown is known as a number; the model needs range. Smallest delta: move it from number to range.\n- … and 8 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:Line 2 filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:Line 2 filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:Line 2 filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n\n1 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+          }
+        }
+      ],
+      "signals": [
+        {
+          "tagName": "affordance-reply-bound",
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you?…"
+        }
+      ],
+      "toolErrors": [],
+      "pendingQuestion": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after.",
+      "completion": {
+        "captures": 15,
+        "complete": false,
+        "unsatisfied": 20,
+        "outsideSlice": 1,
+        "unmapped": 0,
+        "revision": "3a1fa5a01b21595c",
+        "cue": "The harness folded the model at revision 3a1fa5a01b21595c (plugin sdcpn/2026-08-25.2): 6 node(s) from 15 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- [inadmissible-status] \"what it needs before it can start\" on activity:tint-to-white washdown is held under status inferred; accepted: explicit.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:tint-to-white washdown.\n- [below-required-precision] \"how long it takes\" on activity:tint-to-white washdown is known as a number; the model needs spread. Smallest delta: move it from number to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:tint-to-white washdown.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:tint-to-white washdown is known as a number; the model needs range. Smallest delta: move it from number to range.\n- … and 8 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:Line 2 filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:Line 2 filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:Line 2 filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n\n1 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "Sure. So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.\n\nThen it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\n\nOnce it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\n\nThen it's released, goes to the warehouse, and ships against the due date. So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them."
+      }
+    },
+    {
+      "turn": 4,
+      "text": [],
+      "asks": [
+        {
+          "question": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines.",
+          "toolCallId": "toolu_01VcV1KAvgD2ZWUJnBfGcBuh"
+        }
+      ],
+      "sweeps": [
+        {
+          "status": "applied",
+          "appliedCaptureIds": [
+            "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
+            "capture-de512bde-aa52-4147-933f-81439aa5ec6d",
+            "capture-a6e8dc50-fffb-494d-8bd2-59704c0427e4",
+            "capture-3cb49f42-f479-4b67-be4c-22c8f9771f6e",
+            "capture-5628ca29-5985-4005-aa3f-a6885dc38223",
+            "capture-6d4d1074-f6fe-4d4c-95c2-f242a6f98233",
+            "capture-a0b65576-83d8-4134-9fbe-9b059663ae12",
+            "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
+            "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+            "capture-fa56fa8b-611a-4a38-9a42-1bd038e52d80",
+            "capture-dba4ec08-0265-420c-95d2-4dce250ae0b6",
+            "capture-0b2046b4-55c8-4ce3-abac-296d6abe469d",
+            "capture-8156b872-b3c2-43db-aa67-56166bebe556",
+            "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
+            "capture-589bc2db-8fc9-4d65-8024-b34ce4cd736a",
+            "capture-07de77cc-9de8-41e9-92f6-8fe06a6263c9",
+            "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
+            "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b",
+            "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
+            "capture-7df09f81-9c85-43ac-b69e-306d540f8afb",
+            "capture-e0f39723-a7e5-4656-a8fb-0e2b50bb82da",
+            "capture-d8dffb0f-f148-4af2-ba7e-478a6a1b38c6",
+            "capture-a2938097-b902-4f24-8e15-70f4b8ce95fb",
+            "capture-896881a6-c9ec-469f-ab03-4a56b59f6cad",
+            "capture-4a3ae53c-2c2f-4664-9499-7e81c254abc5",
+            "capture-d662739b-76f0-429a-829a-ccb79763b6b9",
+            "capture-a9e42aa6-8d30-4ded-a8c4-f24220cfb292",
+            "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e"
+          ],
+          "skippedDedupKeys": [],
+          "advisories": [
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
+                "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-053410a5-6574-4355-aabf-dd972f0088e1",
+                "capture-d8dffb0f-f148-4af2-ba7e-478a6a1b38c6"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
+                "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b"
+              ]
+            }
+          ],
+          "completion": {
+            "complete": false,
+            "revision": "2b8efdb41c191608",
+            "pluginVersion": "sdcpn/2026-08-25.2",
+            "unsatisfied": 28,
+            "unmapped": [],
+            "cue": "The harness folded the model at revision 2b8efdb41c191608 (plugin sdcpn/2026-08-25.2): 15 node(s) from 43 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [below-required-precision] \"how long it takes\" on activity:filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n6 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+          }
+        }
+      ],
+      "signals": [
+        {
+          "tagName": "affordance-reply-bound",
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nTake that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you ha…"
+        }
+      ],
+      "toolErrors": [],
+      "pendingQuestion": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines.",
+      "completion": {
+        "captures": 43,
+        "complete": false,
+        "unsatisfied": 28,
+        "outsideSlice": 6,
+        "unmapped": 0,
+        "revision": "2b8efdb41c191608",
+        "cue": "The harness folded the model at revision 2b8efdb41c191608 (plugin sdcpn/2026-08-25.2): 15 node(s) from 43 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [below-required-precision] \"how long it takes\" on activity:filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n6 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "Good question, and this is where the sheet lies to me a bit if I'm honest. On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\n\nBut physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between. So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\n\nWhat I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait. I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless."
+      }
+    },
+    {
+      "turn": 5,
+      "text": [
+        "That's a really valuable thing to have said — the sheet says one line, one order; the floor says four bits of kit with small tanks between them. I'll record both rather than pick one.\n\nThat choice matters for what the model can answer, so let me put it to you."
+      ],
+      "asks": [
+        {
+          "question": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate.",
+          "toolCallId": "toolu_01CfCi6guTLjrxg8Hg8QcC6A"
+        }
+      ],
+      "sweeps": [],
+      "signals": [
+        {
+          "tagName": "affordance-reply-bound",
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can s…"
+        }
+      ],
+      "toolErrors": [],
+      "pendingQuestion": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate.",
+      "completion": {
+        "captures": 43,
+        "complete": false,
+        "unsatisfied": 28,
+        "outsideSlice": 6,
+        "unmapped": 0,
+        "revision": "2b8efdb41c191608",
+        "cue": "The harness folded the model at revision 2b8efdb41c191608 (plugin sdcpn/2026-08-25.2): 15 node(s) from 43 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [below-required-precision] \"how long it takes\" on activity:filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n6 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "No, I do want that in scope — if I'm honest, the disruption question and the tank question are the same underlying thing to me. Half the reason Line 1's options are worse when Line 2 goes down is because it feels sluggish and blocked in ways I can't pin on the published line rate. If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\n\nSo yes — build it as separate stages if that's what it takes. I'll warn you now, though: I don't have clean numbers for tank sizes or stage-by-stage rates. I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head. Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head."
+      }
+    },
+    {
+      "turn": 6,
+      "text": [
+        "Understood, and that's an honest and useful boundary: stage-level rates live in the historian, tank sizes on engineering drawings, neither in your head. I'll record those as open with their source rather than let me invent them.\n\nLet me take what you *do* carry.",
+        "The sweep bounced on a misquote of mine: the expert's words were \"I **just** know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\". Retrying with the verbatim text.",
+        "Second bounce, same cause — capitalisation: the expert wrote \"**And** then whatever happens to the bumped tint order…\". Retrying.",
+        "Right — I have your sheet-level knowledge to draw on, so let me take it at that level."
+      ],
+      "asks": [
+        {
+          "question": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white.",
+          "toolCallId": "toolu_0114D18YCRQ5SdR2RDUdY11m"
+        }
+      ],
+      "sweeps": [
+        {
+          "status": "refused",
+          "refusal": {
+            "code": "evidence-quote-not-found",
+            "excerpt": "I know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit",
+            "message": "No user entry contains the verbatim quote \"I know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\". Repair the quote to match the user's words exactly."
+          }
+        },
+        {
+          "status": "refused",
+          "refusal": {
+            "code": "evidence-quote-not-found",
+            "excerpt": "and then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
+            "message": "No user entry contains the verbatim quote \"and then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\". Repair the quote to match the user's words exactly."
+          }
+        },
+        {
+          "status": "applied",
+          "appliedCaptureIds": [
+            "capture-1cb33f48-6553-4e4f-a8a0-37d7631b08ea",
+            "capture-f073c3ed-2a89-4499-b3b2-fe160e8c1057",
+            "capture-c9864a2c-cbb3-41c9-97a6-e44cc1d7d424",
+            "capture-480c2821-4d80-495b-a652-f5de8b035144",
+            "capture-f3f2c366-eab0-49fa-951c-773f77aa11b2",
+            "capture-3bb35fb7-3954-45d4-839f-20ee46a8c052",
+            "capture-e552ac87-8cfa-4091-a262-6fba33ab9f83",
+            "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+            "capture-dd037a1c-63c0-47b8-8886-81c6d1f70226",
+            "capture-6c46c958-82b9-4ba0-bf0f-363fd70b6dbc",
+            "capture-ee4eb482-b4b3-4392-94d7-ef9dc0a6ca98",
+            "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+            "capture-32521b14-4f1e-41ff-ab95-dfc11d8eee37",
+            "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
+            "capture-c1704cba-8451-47a5-add8-2e388b330a1f",
+            "capture-68ab39e5-8046-4f93-887e-11ed3e3b1da3",
+            "capture-c6d485c6-0e21-4cc0-b626-9091448d6ba1",
+            "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
+            "capture-737200bb-8f75-455f-b90a-3363a30d5fce",
+            "capture-78203b7c-8e00-469c-9d53-01d1a656d5c1",
+            "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3",
+            "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
+            "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
+            "capture-42e0a99d-6cf6-4b30-8199-b430405ba25b",
+            "capture-a27c0fc1-57f3-4eed-bea8-15453c84f2da",
+            "capture-0f6aea65-d3a4-430b-b532-4f1100303f9e",
+            "capture-a3f706dd-453a-4543-9990-26efb1b079dd",
+            "capture-67de2e75-132c-43a7-b64e-412343204931",
+            "capture-bf082835-a2ca-4279-80e5-726f157270bd",
+            "capture-ce28dd53-a53d-4bc9-9956-dc3268c35e3e",
+            "capture-9b28544e-b867-4018-9c35-2691cef17a62",
+            "capture-4c4af9ea-df1a-4449-adb7-d48fce7eae93",
+            "capture-dabdbb5f-9eca-4afb-ad50-5b381d9dfa4f",
+            "capture-292e1165-0990-4d17-b6db-153c675fd66c",
+            "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
+            "capture-54d606d7-8c61-4f0a-bd5f-867bba1af3f7",
+            "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
+            "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
+            "capture-b0908788-ec79-4481-b056-1fa606930f85"
+          ],
+          "skippedDedupKeys": [],
+          "advisories": [
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+                "capture-711c9600-2f30-4e86-95a2-cc373696e94c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
+                "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
+                "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b",
+                "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
+                "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-7df09f81-9c85-43ac-b69e-306d540f8afb",
+                "capture-42e0a99d-6cf6-4b30-8199-b430405ba25b"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
+                "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+                "capture-711c9600-2f30-4e86-95a2-cc373696e94c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
+                "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277"
+              ]
+            }
+          ],
+          "completion": {
+            "complete": false,
+            "revision": "3157c77c0d581ebb",
+            "pluginVersion": "sdcpn/2026-08-25.2",
+            "unsatisfied": 28,
+            "unmapped": [],
+            "cue": "The harness folded the model at revision 3157c77c0d581ebb (plugin sdcpn/2026-08-25.2): 28 node(s) from 82 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:tint-to-white washdown.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n19 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+          }
+        }
+      ],
+      "signals": [
+        {
+          "tagName": "affordance-reply-bound",
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWould you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actuall…"
+        }
+      ],
+      "toolErrors": [],
+      "pendingQuestion": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white.",
+      "completion": {
+        "captures": 82,
+        "complete": false,
+        "unsatisfied": 28,
+        "outsideSlice": 19,
+        "unmapped": 0,
+        "revision": "3157c77c0d581ebb",
+        "cue": "The harness folded the model at revision 3157c77c0d581ebb (plugin sdcpn/2026-08-25.2): 28 node(s) from 82 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:tint-to-white washdown.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n19 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "Right, so a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.\n\nBad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more \"the filler hiccupped twice\" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely. Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\n\nOn Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten. That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.\n\nTints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them."
+      }
+    },
+    {
+      "turn": 7,
+      "text": [
+        "One thing you said gives me pause, and I'd rather sort it now than bake it in wrong."
+      ],
+      "asks": [
+        {
+          "question": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?",
+          "toolCallId": "toolu_016Sy8K81vYAJqTRfxPP8zou"
+        }
+      ],
+      "sweeps": [
+        {
+          "status": "applied",
+          "appliedCaptureIds": [
+            "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057",
+            "capture-9d5063d7-b9fb-400e-8b54-f618c6fde20e",
+            "capture-3245b29a-3687-4313-97c5-e0455e5889ba",
+            "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
+            "capture-770314e5-f47a-463e-908a-1d8c23ee60f5",
+            "capture-6ff1c59a-0664-487b-a946-2680043419a2",
+            "capture-be0c3675-ae93-41c5-9eaa-7d36d84617cb",
+            "capture-3e2a5a8a-bd99-4642-afcf-f9d3dfe2e9f6",
+            "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
+            "capture-27ee0ed5-50d0-47f6-94b8-77e090bca50f",
+            "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
+            "capture-2a491098-b602-4b46-bbaa-439e291027db",
+            "capture-c4aefe40-a022-4990-96a1-b74243850715",
+            "capture-76c7250e-6575-4e31-b667-113f3a497cce",
+            "capture-7da94524-13b5-4c11-a1b4-9cb1b0f07e19",
+            "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
+            "capture-d6985d8d-f85e-4556-a091-df64be080ba6",
+            "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
+            "capture-04a6f876-12f4-4f53-b6f2-f8e5fa9c87bc",
+            "capture-592b83e0-ece3-4e98-aedf-cdf70c202e96",
+            "capture-32fe7be9-75c7-464c-87cb-ca38fef4039b",
+            "capture-31556043-9787-40dc-8c0d-b74a47ed3589",
+            "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
+            "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
+            "capture-d2d6e303-2f63-478a-ace1-0bf61abbfddd",
+            "capture-5548a18b-9f79-4475-a9ab-83a74c750721",
+            "capture-1ee7c206-0c56-4d6b-b091-5861f9c40438",
+            "capture-4b706f60-c02f-4973-aa58-2d3ded113c39",
+            "capture-97ea5a05-d89c-4a7d-a136-f90526beaa27",
+            "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
+            "capture-46d37104-fb87-4105-95d5-4448aade81ac",
+            "capture-0cdda695-1dfa-43ef-971c-b9db09403a07"
+          ],
+          "skippedDedupKeys": [],
+          "advisories": [
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
+                "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
+                "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
+                "capture-2a491098-b602-4b46-bbaa-439e291027db"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
+                "capture-2afae8eb-1155-4b07-9842-971df47a6a7d"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+                "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
+                "capture-46d37104-fb87-4105-95d5-4448aade81ac"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
+                "capture-2afae8eb-1155-4b07-9842-971df47a6a7d"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-0f6aea65-d3a4-430b-b532-4f1100303f9e",
+                "capture-31556043-9787-40dc-8c0d-b74a47ed3589"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-67de2e75-132c-43a7-b64e-412343204931",
+                "capture-d2d6e303-2f63-478a-ace1-0bf61abbfddd"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-54d606d7-8c61-4f0a-bd5f-867bba1af3f7",
+                "capture-4b706f60-c02f-4973-aa58-2d3ded113c39"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
+                "capture-46d37104-fb87-4105-95d5-4448aade81ac"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b0908788-ec79-4481-b056-1fa606930f85",
+                "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-6ff1c59a-0664-487b-a946-2680043419a2",
+                "capture-76c7250e-6575-4e31-b667-113f3a497cce"
+              ]
+            }
+          ],
+          "completion": {
+            "complete": false,
+            "revision": "2e4f73ea071077f9",
+            "pluginVersion": "sdcpn/2026-08-25.2",
+            "unsatisfied": 9,
+            "unmapped": [],
+            "cue": "The harness folded the model at revision 2e4f73ea071077f9 (plugin sdcpn/2026-08-25.2): 36 node(s) from 114 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"the question, in the expert's words\" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what \"better\" means, and trade-off weights\" has not been addressed on objective:where Line 1 loses its time.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n\nPatterns whose trigger may apply (discretionary):\n- P08 on objective:where Line 1 loses its time: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n\n33 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+          }
+        }
+      ],
+      "signals": [
+        {
+          "tagName": "affordance-reply-bound",
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nTake that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical …"
+        }
+      ],
+      "toolErrors": [],
+      "pendingQuestion": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?",
+      "completion": {
+        "captures": 114,
+        "complete": false,
+        "unsatisfied": 9,
+        "outsideSlice": 33,
+        "unmapped": 0,
+        "revision": "2e4f73ea071077f9",
+        "cue": "The harness folded the model at revision 2e4f73ea071077f9 (plugin sdcpn/2026-08-25.2): 36 node(s) from 114 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"the question, in the expert's words\" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what \"better\" means, and trade-off weights\" has not been addressed on objective:where Line 1 loses its time.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n\nPatterns whose trigger may apply (discretionary):\n- P08 on objective:where Line 1 loses its time: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n\n33 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "That's fair, and yeah, I was sloppy folding them together. If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\n\nThe twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup. So you're right to pull that apart: clean-run variability is small, and the big bad days are really the breakdown showing up inside the run, not the run itself being slow."
+      }
+    },
+    {
+      "turn": 8,
+      "text": [
+        "Two housekeeping things I want to settle, because right now the model has plenty of plant detail but the two questions it's meant to answer aren't yet wired to any of it."
+      ],
+      "asks": [
+        {
+          "question": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong.",
+          "toolCallId": "toolu_01EHPQiwUUuqA7BA9xjbGyvx"
+        }
+      ],
+      "sweeps": [
+        {
+          "status": "applied",
+          "appliedCaptureIds": [
+            "capture-a5926e2a-88e8-459e-a296-282b16d499a8",
+            "capture-ea1779b0-9a83-42aa-92d1-746e73de43cc",
+            "capture-1288a3df-c7fd-4319-8d4e-a228572ba0b0",
+            "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6",
+            "capture-bb291ebf-9fe0-4a6e-9840-e7d7fac44033",
+            "capture-edfaf81c-c276-4b57-a88c-914953b1c6be",
+            "capture-13339551-ff3a-414f-8260-e1296530d8ec",
+            "capture-535749ea-ba99-4d11-84c0-8203fd058329",
+            "capture-79eccb7f-a787-40d4-a2fa-e95bfda82d18",
+            "capture-3c6b3e85-7fd3-4831-9201-6e3ef525e7cf",
+            "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
+            "capture-823c9593-db42-45eb-9515-937e6b90bd33",
+            "capture-f7e12936-7567-4b38-be19-a45fb5dc6274",
+            "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
+            "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092",
+            "capture-afd366c9-1ea6-4b73-b2c0-ed97c9af0c79",
+            "capture-86fd1cfb-379b-42f7-bdbb-8586dae7f755",
+            "capture-90d36431-4341-4f9e-8bf6-8b5354b2fedd",
+            "capture-7ef3368b-e678-4c58-b7f9-137d1607d8ec",
+            "capture-10d88b79-af70-4a14-90c1-da56ad526d36",
+            "capture-921611c3-21b5-4ab2-8e56-9b8cdaa2eba2",
+            "capture-6cf8c229-ab84-4448-abc6-3e7f4a76bb4c",
+            "capture-ce789325-dd40-4b21-a936-73485ccb90b9",
+            "capture-1ba32034-be19-432b-a012-326b682fd357",
+            "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7",
+            "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
+            "capture-e28ed067-b6a4-40d8-935a-3598e2401cc1",
+            "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a",
+            "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
+            "capture-cfe5bf57-8879-4592-a938-1527d73c8bac",
+            "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
+            "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
+            "capture-23c5706e-37c1-481e-9438-8fae70973c13",
+            "capture-00863ee1-f99c-48b2-b680-bf4eb71e6a57",
+            "capture-196b8447-3958-444f-9860-8de7330299ec"
+          ],
+          "skippedDedupKeys": [],
+          "advisories": [
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
+                "capture-a5926e2a-88e8-459e-a296-282b16d499a8"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-3f2444d5-8001-46d9-8a92-c85f8c6f8d6a",
+                "capture-1288a3df-c7fd-4319-8d4e-a228572ba0b0"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
+                "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
+                "capture-a5926e2a-88e8-459e-a296-282b16d499a8"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
+                "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-dba4ec08-0265-420c-95d2-4dce250ae0b6",
+                "capture-f7e12936-7567-4b38-be19-a45fb5dc6274"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
+                "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
+                "capture-b3079749-c23b-4ade-ac51-9bbff19806fb"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+                "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
+                "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
+                "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
+                "capture-b3079749-c23b-4ade-ac51-9bbff19806fb"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057",
+                "capture-a5926e2a-88e8-459e-a296-282b16d499a8"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
+                "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
+                "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-2a491098-b602-4b46-bbaa-439e291027db",
+                "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c4aefe40-a022-4990-96a1-b74243850715",
+                "capture-823c9593-db42-45eb-9515-937e6b90bd33"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
+                "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
+                "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
+                "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2"
+              ]
+            }
+          ],
+          "completion": {
+            "complete": false,
+            "revision": "36d1240e30d0f4d1",
+            "pluginVersion": "sdcpn/2026-08-25.2",
+            "unsatisfied": 9,
+            "unmapped": [],
+            "cue": "The harness folded the model at revision 36d1240e30d0f4d1 (plugin sdcpn/2026-08-25.2): 41 node(s) from 149 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"the question, in the expert's words\" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what \"better\" means, and trade-off weights\" has not been addressed on objective:where Line 1 loses its time.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n\nPatterns whose trigger may apply (discretionary):\n- P08 on objective:where Line 1 loses its time: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n\n38 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+          }
+        }
+      ],
+      "signals": [
+        {
+          "tagName": "affordance-reply-bound",
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nYou said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you…"
+        }
+      ],
+      "toolErrors": [],
+      "pendingQuestion": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong.",
+      "completion": {
+        "captures": 149,
+        "complete": false,
+        "unsatisfied": 9,
+        "outsideSlice": 38,
+        "unmapped": 0,
+        "revision": "36d1240e30d0f4d1",
+        "cue": "The harness folded the model at revision 36d1240e30d0f4d1 (plugin sdcpn/2026-08-25.2): 41 node(s) from 149 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"the question, in the expert's words\" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what \"better\" means, and trade-off weights\" has not been addressed on objective:where Line 1 loses its time.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n\nPatterns whose trigger may apply (discretionary):\n- P08 on objective:where Line 1 loses its time: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n\n38 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "Alright, let me actually try and write these the way I'd type them if I had the box.\n\n**Disruption one:** \"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"\n\nWhat it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of \"could be quick, could be long\" rather than one number. And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours. And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the \"who can absorb it\" judgment call again.\n\nI'd say what's missing from your list, or under-weighted: the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just \"an order got delayed.\" A distributor slipping is fine, so the answer to the question genuinely depends on whose tint was sitting there.\n\n**The Line 1 tank one:** \"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\" That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others. That's not something I'd have said a month ago.",
+        "stimulus": "(Sorry — I've just seen the time, I have the floor huddle in ten minutes. How much more do you need?)"
+      }
+    },
+    {
+      "turn": 9,
+      "text": [
+        "Honest answer to \"how much more\": we're maybe a third of the way. What's still open, roughly in order of how much it costs you: the filler jam's rate and repair time; what the washdown actually costs including ramp scrap; the \"who can absorb a slip\" rule as you actually apply it; how orders arrive into the demand book; QA hold times; and the stage rates and tank size, which we've already agreed aren't in your head. None of that needs to happen today.\n\nFor the ten minutes, I'd spend them on the jam, because you named it as the thing you never know at the time and nobody else can tell me."
+      ],
+      "asks": [
+        {
+          "question": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?",
+          "toolCallId": "toolu_018NF8gHsprWVmC1fJGrJ3VF"
+        }
+      ],
+      "sweeps": [
+        {
+          "status": "applied",
+          "appliedCaptureIds": [
+            "capture-b58883f3-43e2-4626-bc59-a9c091f1d1b5",
+            "capture-3aa3764b-8dd5-495a-bf3e-b32cbc89ba61",
+            "capture-57ad71c3-f423-4d91-a9f8-d3ce31f1fca1",
+            "capture-1a3325b9-15b6-436a-8e7f-feff95d98036",
+            "capture-0e28490a-6b4b-4996-9b6f-3d9249a7d2dc",
+            "capture-43c5ef42-68ce-478f-89b0-c552111d807a",
+            "capture-ccc2d7eb-8a3f-4684-8f1c-a21a51049550",
+            "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
+            "capture-a158a5da-be3a-461f-87c0-69c38cac1a72",
+            "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23",
+            "capture-4043a577-c1b4-44c3-91f3-2194def82bd9",
+            "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
+            "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
+            "capture-72d414e6-f6a2-420e-8407-667f41535411",
+            "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
+            "capture-53f9387d-f037-4d0f-999b-f89a8f113f46",
+            "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
+            "capture-38e0effa-0fb7-48ff-907c-2fc9f3e64211",
+            "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
+            "capture-314d8187-81ba-478c-8f71-1c9e5826965b",
+            "capture-345fbb5a-c0c1-4e3a-9015-33b3ad727831",
+            "capture-60f6f8c8-f52e-443a-adee-6818339f3b35",
+            "capture-be556841-bf14-4fe0-8c23-ffc773896b2b",
+            "capture-26d3ac6c-4b27-4765-baa3-8437f06fe8ca",
+            "capture-da6d10a4-e0f2-4b1d-8e78-4d58cadeb8f2",
+            "capture-68f9db28-a002-406d-912a-4cc410e5b380",
+            "capture-0a06d184-bf72-42c4-95b3-7ad88ea4e059",
+            "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f",
+            "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b",
+            "capture-7111ab55-5d90-44f6-a1d2-4aa1b48da4bb",
+            "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a",
+            "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993"
+          ],
+          "skippedDedupKeys": [],
+          "advisories": [
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
+                "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-a2938097-b902-4f24-8e15-70f4b8ce95fb",
+                "capture-be556841-bf14-4fe0-8c23-ffc773896b2b"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
+                "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+                "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
+                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
+                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
+                "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
+                "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
+                "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
+                "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
+                "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b0908788-ec79-4481-b056-1fa606930f85",
+                "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
+                "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-27ee0ed5-50d0-47f6-94b8-77e090bca50f",
+                "capture-a158a5da-be3a-461f-87c0-69c38cac1a72"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
+                "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c4aefe40-a022-4990-96a1-b74243850715",
+                "capture-4043a577-c1b4-44c3-91f3-2194def82bd9"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
+                "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
+                "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
+                "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-46d37104-fb87-4105-95d5-4448aade81ac",
+                "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-823c9593-db42-45eb-9515-937e6b90bd33",
+                "capture-4043a577-c1b4-44c3-91f3-2194def82bd9"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
+                "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
+                "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
+                "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
+                "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
+                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
+              ]
+            }
+          ],
+          "completion": {
+            "complete": false,
+            "revision": "1dffca1f0e4725ec",
+            "pluginVersion": "sdcpn/2026-08-25.2",
+            "unsatisfied": 42,
+            "unmapped": [],
+            "cue": "The harness folded the model at revision 1dffca1f0e4725ec (plugin sdcpn/2026-08-25.2): 47 node(s) from 181 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 30 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n34 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+          }
+        }
+      ],
+      "signals": [
+        {
+          "tagName": "affordance-reply-bound",
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nIf the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one …"
+        }
+      ],
+      "toolErrors": [],
+      "pendingQuestion": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?",
+      "completion": {
+        "captures": 181,
+        "complete": false,
+        "unsatisfied": 42,
+        "outsideSlice": 34,
+        "unmapped": 0,
+        "revision": "1dffca1f0e4725ec",
+        "cue": "The harness folded the model at revision 1dffca1f0e4725ec (plugin sdcpn/2026-08-25.2): 47 node(s) from 181 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 30 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n34 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "Okay, quick version. It's a \"every week or two\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.\n\nWhen it stops: typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift. I don't have a cleaner breakdown than that — maintenance would have the actual work-order times in the CMMS but I've never pulled them.\n\nRight, I need to run — good session though. Same time next week?"
+      }
+    },
+    {
+      "turn": 10,
+      "text": [
+        "That bounce was my own phrase, not yours — \"jams badly enough to stop the run\" was my wording. Re-anchoring on what you actually said.",
+        "Go — and yes, same time next week works. Here's where we got to, so you can correct anything when you're back at a desk. **The model is not finished and I'm not going to pretend it is; I wouldn't hand this to your tooling yet.**\n\n## What's on record, in your words\n\n**The two questions the model exists to answer**\n1. \"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"\n2. \"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"\n\n**What \"better\" means** — Meridian-style on-time is a hard line, \"not really a trade-off, that's a line I won't cross.\" Below that line you weigh washdown hours, whether the bumped order slides and by how much, and who the customer is. No formula; judgment on who can absorb the slip.\n\n**The flow** — demand book line item out of ERP → you allocate to a line and a week slot → mix, mill, tint, fill (tint \"barely there\" for a white) → QA hold → release, warehouse, ship against due date.\n\n**The line, both ways** — on the sheet, one row, one order occupies Line 2 mix-to-fill. Physically, separate kit with small holding tanks between, and the crew will start the next mix if there's tank room. Both recorded; neither averaged away.\n\n**Run times, clean of breakdowns** — white on Line 2: typical 8–9 h, bad-but-clean 9–10 h, good day ~6 h. Same order on Line 1: add 50–60%, so typical 13–14 h, best ~10 h. Tints: 8–10 h typical on *either* line, no big gap — which you flagged as unexplained and sheet-derived. The 12–13 h figure has been pulled out as breakdown, not run.\n\n**Filler jam** — every week or two; low once in three weeks, high twice a week. Repair typical 30–45 min, quick one-in-ten 10–15 min, bad one-in-ten 4–5 h, \"occasionally eating the rest of the shift.\"\n\n**Washdown** — tint-to-white, three hours, direction matters, plus ramp scrap you don't have numbers for.\n\n## Gaps, with where they'd come from\n- Stage-level rates per line — historian, never pulled apart.\n- Tank sizes, mill-to-fill on Line 1 — engineering drawings.\n- Jam repair times, properly — maintenance work orders in the CMMS.\n- Ramp scrap after washdown — you said it shouldn't be ignored; no source named yet.\n- Whether the tank matters differently by SKU — your own new thought, unexamined.\n- QA hold: \"a few hours for a white,\" and a longer \"specialty wait\" you mentioned but I never asked about.\n- How orders arrive into the demand book — never asked.\n- The \"who can absorb the slip\" rule — I have distributor-shrugs and prickly-account, not a rule I could apply without you.\n\n## Assumptions ledger\n1. That the four stages are the same four for every product — you said \"same four stages every product goes through,\" so this is yours, not mine, but it's load-bearing enough to re-check.\n2. Nothing else. Where I was tempted to fill in — jam rate before you gave it, washdown scrap, stage rates — it's in the gaps list instead.\n\nBoth objectives are still formally unsupported: I have the plant detail and the questions, but haven't yet wired which pieces each answer depends on tightly enough for the tooling. That plus the ramp scrap and the slip rule are what I'd open with next week."
+      ],
+      "asks": [],
+      "sweeps": [
+        {
+          "status": "refused",
+          "refusal": {
+            "code": "evidence-quote-not-found",
+            "excerpt": "jams badly enough to stop the run",
+            "message": "No user entry contains the verbatim quote \"jams badly enough to stop the run\". Repair the quote to match the user's words exactly."
+          }
+        },
+        {
+          "status": "applied",
+          "appliedCaptureIds": [
+            "capture-1a240192-8179-4339-815e-3775a062e986",
+            "capture-85062afa-e82d-46ce-b609-f7ed16f8b093",
+            "capture-2c3fa15f-551b-4380-a3b3-8dbc6334a9bb",
+            "capture-41269bfb-9040-4d54-a113-a94c09f6f2f0",
+            "capture-f7ea7c88-4d40-48e7-84e5-2b12ebc5ea8e",
+            "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26",
+            "capture-0e8d50b2-4222-4129-a619-09c5612c05c5",
+            "capture-117f9832-aaba-473a-9411-6fd4022388f2",
+            "capture-e10d4081-78ed-42da-bb26-857f1118224c",
+            "capture-875ed21b-d257-48fe-867b-6785abf6abb7",
+            "capture-06d48b41-86fb-48c0-b3e0-59012ba81960",
+            "capture-428e3931-676d-4af5-a30c-d7a31ea0d8ad",
+            "capture-ecd3c093-8f6b-4a48-a1fc-d2775d4dbc1f",
+            "capture-c6339dee-036e-47cb-9dcf-42fc22d38aae",
+            "capture-2bc071c4-2919-4ff3-910a-92d872eeaef2",
+            "capture-6ec49aac-c165-4e2b-a937-bed3c8c51c2c",
+            "capture-c3f03d77-6760-4b3b-99e5-b78d119a352f",
+            "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14",
+            "capture-83e1381a-f2df-4713-a2f6-f11d034c2fd4",
+            "capture-95cbfe20-605f-4218-9076-0f4816ebadfa",
+            "capture-1a5a8343-7367-416e-b760-c7e8f587fe25",
+            "capture-bf2e57a3-bda7-4090-92ca-af63e0c7a248",
+            "capture-aec8ff27-3e3f-45d2-9142-b6dc2b5d88a3",
+            "capture-9d59a385-a8ae-410a-a13d-a4bca3dde9a3",
+            "capture-4b22a066-a97c-4329-8513-cbd85edd8d65",
+            "capture-63fabb67-24c4-4bee-926f-17917300c8f4",
+            "capture-b1e5ded4-79d6-4ff4-bd0d-6386509efba9",
+            "capture-147c2765-6bfb-4da0-9df9-b74a1c1049de",
+            "capture-ec5740e7-5068-4222-ad24-8396f5975657",
+            "capture-2884cc84-c616-4227-860a-d6b55a06c13d",
+            "capture-0548a680-8da8-47e9-ad72-fb1e264fac80",
+            "capture-8c6a716b-e09a-4977-94d9-f28ab74be7c4",
+            "capture-a67683fd-0f34-4838-b48e-aa01f657a511",
+            "capture-1b632a29-f1de-48e5-8f96-a5ef908c4a56",
+            "capture-9926552e-289f-4b4a-bc99-4cae34f1720a",
+            "capture-06aac0a9-b270-4b13-a54f-37440769d685",
+            "capture-94948329-18e7-42fe-9538-a84fd72c225d",
+            "capture-16b9c643-8b17-490e-bfe0-022a06efd914",
+            "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af",
+            "capture-821e00ef-6923-43b0-955b-3ed7d60ce127",
+            "capture-6da3fa16-460b-4f07-aefc-f941d7118f76",
+            "capture-731a5768-edc7-4858-ad42-50d2faf4b181",
+            "capture-1bebb3ea-7788-477a-8127-593fe3fe6026",
+            "capture-07cb7ca9-27c5-4395-bc9e-aaebc5811382",
+            "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2",
+            "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1",
+            "capture-a0429a34-1145-458d-bada-32d827d68959"
+          ],
+          "skippedDedupKeys": [],
+          "advisories": [
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+                "capture-e10d4081-78ed-42da-bb26-857f1118224c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-0b2046b4-55c8-4ce3-abac-296d6abe469d",
+                "capture-95cbfe20-605f-4218-9076-0f4816ebadfa"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-07de77cc-9de8-41e9-92f6-8fe06a6263c9",
+                "capture-16b9c643-8b17-490e-bfe0-022a06efd914"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
+                "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-e0f39723-a7e5-4656-a8fb-0e2b50bb82da",
+                "capture-a67683fd-0f34-4838-b48e-aa01f657a511"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
+                "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+                "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-dd037a1c-63c0-47b8-8886-81c6d1f70226",
+                "capture-ecd3c093-8f6b-4a48-a1fc-d2775d4dbc1f"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+                "capture-e10d4081-78ed-42da-bb26-857f1118224c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
+                "capture-e10d4081-78ed-42da-bb26-857f1118224c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
+                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
+                "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
+                "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-bf082835-a2ca-4279-80e5-726f157270bd",
+                "capture-6ec49aac-c165-4e2b-a937-bed3c8c51c2c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
+                "capture-6da3fa16-460b-4f07-aefc-f941d7118f76"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
+                "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
+                "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b0908788-ec79-4481-b056-1fa606930f85",
+                "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
+                "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
+                "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
+                "capture-1a5a8343-7367-416e-b760-c7e8f587fe25"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
+                "capture-4b22a066-a97c-4329-8513-cbd85edd8d65"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
+                "capture-94948329-18e7-42fe-9538-a84fd72c225d"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-5548a18b-9f79-4475-a9ab-83a74c750721",
+                "capture-147c2765-6bfb-4da0-9df9-b74a1c1049de"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
+                "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-46d37104-fb87-4105-95d5-4448aade81ac",
+                "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6",
+                "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
+                "capture-94948329-18e7-42fe-9538-a84fd72c225d"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
+                "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
+                "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
+                "capture-6da3fa16-460b-4f07-aefc-f941d7118f76"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
+                "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
+                "capture-e10d4081-78ed-42da-bb26-857f1118224c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
+                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
+                "capture-e10d4081-78ed-42da-bb26-857f1118224c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
+                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
+                "capture-4b22a066-a97c-4329-8513-cbd85edd8d65"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
+                "capture-94948329-18e7-42fe-9538-a84fd72c225d"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
+                "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f",
+                "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b",
+                "capture-6da3fa16-460b-4f07-aefc-f941d7118f76"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a",
+                "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993",
+                "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-e10d4081-78ed-42da-bb26-857f1118224c",
+                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
+              ]
+            }
+          ],
+          "completion": {
+            "complete": false,
+            "revision": "0028ff75065b59b1",
+            "pluginVersion": "sdcpn/2026-08-25.2",
+            "unsatisfied": 44,
+            "unmapped": [],
+            "cue": "The harness folded the model at revision 0028ff75065b59b1 (plugin sdcpn/2026-08-25.2): 56 node(s) from 228 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"who or what performs it\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 32 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n41 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+          }
+        }
+      ],
+      "signals": [
+        {
+          "tagName": "affordance-reply-bound",
+          "excerpt": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a c…"
+        }
+      ],
+      "toolErrors": [],
+      "completion": {
+        "captures": 228,
+        "complete": false,
+        "unsatisfied": 44,
+        "outsideSlice": 41,
+        "unmapped": 0,
+        "revision": "0028ff75065b59b1",
+        "cue": "The harness folded the model at revision 0028ff75065b59b1 (plugin sdcpn/2026-08-25.2): 56 node(s) from 228 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"who or what performs it\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 32 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n41 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "Looks right — that's a fair record, and yeah, next week let's start with ramp scrap and the slip rule, since those feel like the ones I could actually go dig up or nail down between now and then. I'll ask maintenance for the CMMS numbers on the filler too while I'm at it. Go on, get to your huddle — wait, that's me. See you next week."
+      }
+    },
+    {
+      "turn": 11,
+      "text": [
+        "Enjoy the huddle.\n\nThree things I'll have ready for next week, so you don't have to hold them:\n\n1. **Ramp scrap and the slip rule** first, as you asked — for the slip rule I'll come at it through a case rather than a principle, so have in mind the last time you bumped someone's order and it turned out to be the wrong someone.\n2. **CMMS filler numbers** — when you get them, what I want is the same shape you gave me from memory: typical, bad one-in-ten, quick one-in-ten. If the work orders disagree with your 30–45 minutes, that disagreement is worth more to the model than either figure alone, so don't reconcile it before you bring it.\n3. **The tint parity puzzle** — that Line 1 and Line 2 run tints at nearly the same speed with no explanation. It's the loose thread most likely to be the same thing as your tank hunch, and I'd like to pull on it once the scrap and slip rule are in.\n\nNothing needs doing beyond that. See you next week.",
+        "The tail has settled: the read-back was confirmed, the session closed, and the expert's last message adds content in their own words — what they'll dig up before next time and that they'll pull the CMMS numbers from maintenance. That belongs in the record as deferral deposits, not as agreement to my summary.\n\nOne caution I'll carry into the sweep: \"Looks right\" is assent to my phrasing, not origination. It closes nothing that wasn't already sourced to their words.",
+        "Swept and folded — the session's record is durable. Since you've gone, this is a note-to-self for next week rather than anything you need to read now.\n\n**State of the model:** 69 nodes from 267 captures. Not complete, and two things about *how it's held* need fixing before more content goes in:\n\n1. **Objective duplication.** Your two questions have landed as five objective nodes — successive rephrasings of the same two (\"which option loses less\", \"which option actually loses less\", \"wait or shift when Line 2 goes down\" are one question; \"where Line 1 loses its time\" and \"is the mill-to-fill tank on Line 1 slowing the line down\" are the other). That's an artefact of my asking you to restate them, not a fact about your plant. Consolidating is a review-and-revise job, and it needs your word on which phrasing is yours, not my merge.\n\n2. **Nothing is wired to the objectives.** 53 of the 69 nodes sit outside every objective's dependency slice — recorded, but not demanded by anything. That's why the completion report keeps growing without the model getting more answerable. You *did* tell me what the disruption question hangs on: the run being protected, Line 1's state and family, the jam duration, the ramp scrap, and the bumped order's identity. I have those as prose in your answer; they aren't yet linked as dependencies. Doing that link properly is the first thing that makes any of the plant detail count.\n\n3. **Three open conflicts** on the filler jam node and the production-run node, where later answers superseded earlier ones — the 12–13 h that turned out to be breakdown, and the two jam descriptions. Those need your explicit word to close, not my inference about which you meant.\n\nSo next week's order: ramp scrap and the slip rule as you asked, then the objective wiring, then the conflict closes. The tint parity thread stays third."
+      ],
+      "asks": [],
+      "sweeps": [
+        {
+          "status": "applied",
+          "appliedCaptureIds": [
+            "capture-48033ee8-f7eb-4615-b21f-018837fc9c5e",
+            "capture-88da9925-d922-48c3-8ea0-2c631df3ae3d",
+            "capture-f53d8f62-375e-4af6-9aaa-fb903839993c",
+            "capture-ac435640-eea2-4ad6-9695-8e5408b4d852",
+            "capture-f5a658db-c8ec-4ca0-8a87-3ad252dee56d",
+            "capture-618842bb-d23d-4371-ae57-73e5257ba215",
+            "capture-538fb022-2495-46bb-8661-8e1f38c802bf",
+            "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98",
+            "capture-5d5f862f-c18c-4501-b544-76735d28e004",
+            "capture-7f6b8be1-6336-465f-8e11-36a5277d51bd",
+            "capture-1a83c9c6-a8f8-4ece-a5d4-53b81bf8cc9b",
+            "capture-e6ae51ed-e1f6-45f3-aab1-c4bca2a979e8",
+            "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7",
+            "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01",
+            "capture-7f9ac97e-375b-4de3-bbcd-b65e5c7427a6",
+            "capture-66fbb371-91b7-41db-b437-5bd207d08aed",
+            "capture-8da19d62-c082-41f6-ac55-f28afe266a8c",
+            "capture-995374a1-2d25-4690-8397-b342f46ebf02",
+            "capture-3cc84392-4ed4-4804-8a7c-db07d384a8b2",
+            "capture-289ac648-e939-4e62-ad46-a17b112402d4",
+            "capture-5376c084-3889-476f-adab-b09a038ded28",
+            "capture-b9dfddf9-52d8-433e-81b8-5611e7356c34",
+            "capture-27ae8fdf-c227-4160-a1a5-e85530156938",
+            "capture-7bd393bf-3f05-4aa1-b15a-968c293b076f",
+            "capture-ef41e72f-3126-4003-82b2-686b5f8bfdfb",
+            "capture-4fa34ba3-82e3-4a4a-ad28-362765a40046",
+            "capture-2f670377-be1e-4275-9e46-24dd13316300",
+            "capture-9dc62989-7db7-4e58-baf1-b9ed0400d9a2",
+            "capture-b92eccd9-e2ad-41a9-abce-bb1cf8b3c328",
+            "capture-55e95600-febe-4c98-8859-a56eb23ab156",
+            "capture-29c03a62-4be2-4dc2-852e-bfeab6770f1b",
+            "capture-9f708103-e43a-4766-bca4-cb3b7060fdcd",
+            "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c",
+            "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d",
+            "capture-12e575e7-b7a9-472d-b165-308334ae7513",
+            "capture-bc9d210e-beb9-4f7a-aa5d-243950605a2a",
+            "capture-90a38599-7f1b-46ed-9352-d3dd3566b338",
+            "capture-d889a88e-b7be-4055-9da1-e64f9fc858b0",
+            "capture-173c6d39-090f-49a7-9e38-c8998003718b"
+          ],
+          "skippedDedupKeys": [
+            "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\"\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+          ],
+          "advisories": [
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-76159984-4b11-446f-a707-bc8302ef0b1d",
+                "capture-f53d8f62-375e-4af6-9aaa-fb903839993c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
+                "capture-55e95600-febe-4c98-8859-a56eb23ab156"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-caeeeb12-a91f-46a0-88c2-a622d4d30c55",
+                "capture-90a38599-7f1b-46ed-9352-d3dd3566b338"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
+                "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
+                "capture-12e575e7-b7a9-472d-b165-308334ae7513"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
+                "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+                "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
+                "capture-12e575e7-b7a9-472d-b165-308334ae7513"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
+                "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-3e2a5a8a-bd99-4642-afcf-f9d3dfe2e9f6",
+                "capture-1a83c9c6-a8f8-4ece-a5d4-53b81bf8cc9b"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
+                "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
+                "capture-66fbb371-91b7-41db-b437-5bd207d08aed"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-2a491098-b602-4b46-bbaa-439e291027db",
+                "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c4aefe40-a022-4990-96a1-b74243850715",
+                "capture-8da19d62-c082-41f6-ac55-f28afe266a8c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
+                "capture-5376c084-3889-476f-adab-b09a038ded28"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
+                "capture-27ae8fdf-c227-4160-a1a5-e85530156938"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
+                "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
+                "capture-12e575e7-b7a9-472d-b165-308334ae7513"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
+                "capture-538fb022-2495-46bb-8661-8e1f38c802bf"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
+                "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-823c9593-db42-45eb-9515-937e6b90bd33",
+                "capture-8da19d62-c082-41f6-ac55-f28afe266a8c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
+                "capture-538fb022-2495-46bb-8661-8e1f38c802bf"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
+                "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092",
+                "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-ce789325-dd40-4b21-a936-73485ccb90b9",
+                "capture-b92eccd9-e2ad-41a9-abce-bb1cf8b3c328"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7",
+                "capture-55e95600-febe-4c98-8859-a56eb23ab156"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
+                "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a",
+                "capture-12e575e7-b7a9-472d-b165-308334ae7513"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
+                "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
+                "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23",
+                "capture-66fbb371-91b7-41db-b437-5bd207d08aed"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-4043a577-c1b4-44c3-91f3-2194def82bd9",
+                "capture-8da19d62-c082-41f6-ac55-f28afe266a8c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
+                "capture-27ae8fdf-c227-4160-a1a5-e85530156938"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
+                "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
+                "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-1a240192-8179-4339-815e-3775a062e986",
+                "capture-48033ee8-f7eb-4615-b21f-018837fc9c5e"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14",
+                "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-83e1381a-f2df-4713-a2f6-f11d034c2fd4",
+                "capture-7f9ac97e-375b-4de3-bbcd-b65e5c7427a6"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-1a5a8343-7367-416e-b760-c7e8f587fe25",
+                "capture-5376c084-3889-476f-adab-b09a038ded28"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-4b22a066-a97c-4329-8513-cbd85edd8d65",
+                "capture-27ae8fdf-c227-4160-a1a5-e85530156938"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-ec5740e7-5068-4222-ad24-8396f5975657",
+                "capture-4fa34ba3-82e3-4a4a-ad28-362765a40046"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-0548a680-8da8-47e9-ad72-fb1e264fac80",
+                "capture-9dc62989-7db7-4e58-baf1-b9ed0400d9a2"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-94948329-18e7-42fe-9538-a84fd72c225d",
+                "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af",
+                "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
+              ]
+            },
+            {
+              "type": "possibly-equivalent",
+              "reason": "same-evidence",
+              "captureIds": [
+                "capture-538fb022-2495-46bb-8661-8e1f38c802bf",
+                "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98"
+              ]
+            }
+          ],
+          "completion": {
+            "complete": false,
+            "revision": "26a8219a17118558",
+            "pluginVersion": "sdcpn/2026-08-25.2",
+            "unsatisfied": 46,
+            "unmapped": [],
+            "cue": "The harness folded the model at revision 26a8219a17118558 (plugin sdcpn/2026-08-25.2): 69 node(s) from 267 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:wait or shift when Line 2 goes down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 34 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n53 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+          }
+        }
+      ],
+      "signals": [
+        {
+          "tagName": "settlement-check",
+          "excerpt": "The harness computed this unswept conversation tail:\n\n[non-user] The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThinking of the Line 2 filler specifically: roughly how often does it ja…"
+        }
+      ],
+      "toolErrors": [],
+      "completion": {
+        "captures": 267,
+        "complete": false,
+        "unsatisfied": 46,
+        "outsideSlice": 53,
+        "unmapped": 0,
+        "revision": "26a8219a17118558",
+        "cue": "The harness folded the model at revision 26a8219a17118558 (plugin sdcpn/2026-08-25.2): 69 node(s) from 267 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:wait or shift when Line 2 goes down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 34 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n53 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      },
+      "expert": {
+        "content": "*[No response — this final message is addressed to the interviewer's own note-taking process, not to Marta. Staying in character as Marta, there is nothing here that calls for a reply; she has already left for the huddle.]*"
+      }
+    },
+    {
+      "turn": 12,
+      "text": [
+        "Session closed. Nothing further pending on Marta's side.\n\nFinal state for the record: model at revision `26a8219a17118558` — 69 nodes, 267 active captures, not complete. Two objectives (held as five duplicate nodes), both formally unsupported. Deferrals carry deposits: CMMS for jam repair times, historian for stage rates, engineering drawings for tank sizes, Marta herself for ramp scrap and the slip rule. Assumption ledger holds one entry, flagged for re-check.\n\nI make no claim that this projects, compiles, or runs. Next session opens as review-and-revise on the objective nodes before any new elicitation.",
+        "Declining this one.\n\nThe range contains no expert testimony. It is my own closing turn, my own sweep-judgment note, and my own state-of-the-model note, terminated by a stage direction confirming Marta has left and is not replying. The only entry in user position is that stage direction — narration about the interview, not Marta's words about her plant.\n\nSweeping it could only do one of two things: extract nothing, or extract something from a non-expert source. The second is the failure mode I've been guarding against all session — a model element with no expert span behind it. My own summary of the model is not evidence for the model; that would be assent taken as origin, with me on both sides of it.\n\nThe substantive content in that stretch — the CMMS follow-up, the ramp-scrap and slip-rule priority, Marta's confirmation of the read-back — was already swept from her actual message at revision `26a8219a17118558`. Nothing is at risk of being lost by leaving this tail unswept.\n\nThe swept high-water mark stays where it is. The session's durable record is complete as of that revision, and next session opens as review-and-revise on the duplicated objective nodes."
+      ],
+      "asks": [],
+      "sweeps": [],
+      "signals": [
+        {
+          "tagName": "settlement-check",
+          "excerpt": "The harness computed this unswept conversation tail:\n\n[assistant] Enjoy the huddle.\n\nThree things I'll have ready for next week, so you don't have to hold them:\n\n1. **Ramp scrap and the slip rule** first, as you asked — for the slip rule I'…"
+        }
+      ],
+      "toolErrors": [],
+      "completion": {
+        "captures": 267,
+        "complete": false,
+        "unsatisfied": 46,
+        "outsideSlice": 53,
+        "unmapped": 0,
+        "revision": "26a8219a17118558",
+        "cue": "The harness folded the model at revision 26a8219a17118558 (plugin sdcpn/2026-08-25.2): 69 node(s) from 267 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:wait or shift when Line 2 goes down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 34 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n53 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+      }
+    }
+  ],
+  "usage": {
+    "interviewer": {
+      "input": 74,
+      "output": 152204,
+      "cacheRead": 969818,
+      "cacheWrite": 132417,
+      "calls": 37
+    },
+    "expert": {
+      "input": 72716,
+      "output": 3478,
+      "cacheRead": 0,
+      "cacheWrite": 0,
+      "calls": 11
+    }
+  },
+  "history": {
+    "v": 1,
+    "conversationId": "conv_01M0X5XEJZSRCZY37FBYJZXVNB",
+    "offset": "0000000000000000_0000000000000699",
+    "messages": [
+      {
+        "id": "entry_direct_c3ViXzAxTTBYNVhFSllRWjVaQlZXTURQS1kyUTlU",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0X5XEJYQZ5ZBVWMDPKY2Q9T",
+        "parts": [
+          {
+            "type": "text",
+            "text": "I'm the master scheduler at a coatings plant. My boss wants a simulation model of how we\nschedule production, so we can test scheduling decisions before making them. We have tooling\nthat runs Petri-net-style process models, so the end product should be a model I can hand to\nthat — but I can't tell you much about the format, I'm not the modelling person.\n\nPlease interview me about how our operation works, and then produce the model.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X5XFMN1ZG4EFY9AVWTHV9H",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0X5XEJYQZ5ZBVWMDPKY2Q9T",
+        "turnId": "turn_01M0X5XEKHVQGJ5X2DCYWB9WD3",
+        "parts": [
+          {
+            "type": "reasoning",
+            "text": "I should start by asking about their objectives, keeping it to one question at a time.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Good — that's exactly the right split: you know the plant, I'll worry about the format. Before I ask anything about how the plant is built, I want to know what the model has to be able to tell you.\n\nLet me start there.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_01VTR3FzE8Wat7pwjPW7jcyh",
+            "state": "output-available",
+            "input": {
+              "question": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong."
+            },
+            "output": {
+              "id": "affordance_toolu_01VTR3FzE8Wat7pwjPW7jcyh",
+              "form": "free-text",
+              "markdown": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong.",
+              "payload": {
+                "question": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong."
+              }
+            },
+            "durationMs": 6
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_01VTR3FzE8Wat7pwjPW7jcyh",
+              "form": "free-text",
+              "markdown": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong.",
+              "payload": {
+                "question": "When your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong."
+              }
+            }
+          }
+        ]
+      },
+      {
+        "id": "entry_direct_c3ViXzAxTTBYNVhTWFAwTUs1WUJORzkxMUMzVzFE",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0X5XSXP0MK5YBNG911C3W1D",
+        "parts": [
+          {
+            "type": "text",
+            "text": "Okay, good question. Let me think of an actual one rather than a hypothetical.\n\nA few weeks back — Line 2 filler jammed at about nine in the morning, half a shift lost. We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.\n\nI went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky. That's the kind of thing — I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X5XSY3F2HAFQYZSZ41RJB0",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0X5XSXP0MK5YBNG911C3W1D",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_01VTR3FzE8Wat7pwjPW7jcyh"
+          }
+        },
+        "parts": [
+          {
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen your boss says \"test scheduling decisions before making them\" — what's a decision you've actually had to make recently where you'd have wanted to try it out first? Tell me the specific one, and what you were worried would go wrong.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X5XTSMAZ7JTGYCNBEK2AFS",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0X5XSXP0MK5YBNG911C3W1D",
+        "turnId": "turn_01M0X5XSY9SETVXGSADDHT7KMF",
+        "parts": [
+          {
+            "type": "reasoning",
+            "text": "I need to clarify what \"better\" means here—specifically what \"loses less\" actually refers to before I go further with the comparison.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "That's a very usable one — a real disruption, two options, and no way to tell afterwards whether you chose well. That \"which option loses less\" is the heart of the model.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_01RigdvzDsLRJokW4AqBW7UE",
+            "state": "output-available",
+            "input": {
+              "question": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off."
+            },
+            "output": {
+              "id": "affordance_toolu_01RigdvzDsLRJokW4AqBW7UE",
+              "form": "free-text",
+              "markdown": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off.",
+              "payload": {
+                "question": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off."
+              }
+            },
+            "durationMs": 3
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_01RigdvzDsLRJokW4AqBW7UE",
+              "form": "free-text",
+              "markdown": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off.",
+              "payload": {
+                "question": "When you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off."
+              }
+            }
+          }
+        ]
+      },
+      {
+        "id": "entry_direct_c3ViXzAxTTBYNVk4N0FTNVJaRTQyOEVWME1XNkQ0",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0X5Y87AS5RZE428EV0MW6D4",
+        "parts": [
+          {
+            "type": "text",
+            "text": "Honestly, in the moment it's simple-minded: did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\n\nUnderneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\n\nSo really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X5Y87PB790WYFN9ZTV11Y1",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0X5Y87AS5RZE428EV0MW6D4",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_01RigdvzDsLRJokW4AqBW7UE"
+          }
+        },
+        "parts": [
+          {
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen you say \"loses less\" — if the model had run both options for you that morning, what number or numbers would have settled it for you? Late orders? Hours of washdown? Something about the tint you'd have bumped? I want your actual scorecard, and if two things compete, how you'd trade them off.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X5Y949HBAC6DHA8WYYRGCX",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0X5Y87AS5RZE428EV0MW6D4",
+        "turnId": "turn_01M0X5Y87SSVSRH7S8TAP58QMJ",
+        "parts": [
+          {
+            "type": "reasoning",
+            "text": "Two turns have settled now, so it's time to sweep before moving on. I'm also noting that \"customer tier\" is an awkward entity-type attribute to revisit later, and my next step is to ask a bounded question walking through one order end to end.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_011HZMxGrrjkdoPHynQCyKKN",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
+                "capture-76159984-4b11-446f-a707-bc8302ef0b1d",
+                "capture-3f2444d5-8001-46d9-8a92-c85f8c6f8d6a",
+                "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
+                "capture-053410a5-6574-4355-aabf-dd972f0088e1",
+                "capture-e86ee1d3-dbbd-4e2d-b1c0-a8ac719f0e58",
+                "capture-04d27279-48f8-437e-8688-14c400f3f0f1",
+                "capture-7d1cb932-a1d6-4e1a-86a7-984a9d53af80",
+                "capture-330b99df-25fc-4d38-b1f9-6f8da955b79e",
+                "capture-caeeeb12-a91f-46a0-88c2-a622d4d30c55",
+                "capture-422d7f74-a119-45d6-8261-3c71b50af7f7",
+                "capture-f2a03b6c-0420-48a7-85be-bdcb3536a6f7",
+                "capture-c9ac976a-3eef-4a77-8e29-3598b184b450",
+                "capture-6bc324a5-2e12-4070-8275-fdfe819923e6",
+                "capture-b003fc51-0ade-4721-b400-b7b68edf8c60"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [],
+              "completion": {
+                "complete": false,
+                "revision": "3a1fa5a01b21595c",
+                "pluginVersion": "sdcpn/2026-08-25.2",
+                "unsatisfied": 20,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 3a1fa5a01b21595c (plugin sdcpn/2026-08-25.2): 6 node(s) from 15 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [below-minimum-count] The model has 0 ordering/flow node(s); the floor needs 1.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- [inadmissible-status] \"what it needs before it can start\" on activity:tint-to-white washdown is held under status inferred; accepted: explicit.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:tint-to-white washdown.\n- [below-required-precision] \"how long it takes\" on activity:tint-to-white washdown is known as a number; the model needs spread. Smallest delta: move it from number to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:tint-to-white washdown.\n- [below-required-precision] \"what is lost when it changes the system's mode\" on activity:tint-to-white washdown is known as a number; the model needs range. Smallest delta: move it from number to range.\n- … and 8 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:Line 2 filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:Line 2 filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:Line 2 filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n\n1 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
+            },
+            "durationMs": 112179
+          },
+          {
+            "type": "reasoning",
+            "text": "I'll trace through a single order from start to finish to understand the ordering, flow, and overall structure.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "I've got the objective on record: which option loses less, with Meridian-style on-time as a hard line and washdown hours plus knock-on lateness as the weighing underneath. I'll come back to how you judge \"who can absorb a slip.\"\n\nNow I need the shape of the work itself.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_01BPxGhtkoW98xCiTTeNLW4a",
+            "state": "output-available",
+            "input": {
+              "question": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after."
+            },
+            "output": {
+              "id": "affordance_toolu_01BPxGhtkoW98xCiTTeNLW4a",
+              "form": "free-text",
+              "markdown": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after.",
+              "payload": {
+                "question": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after."
+              }
+            },
+            "durationMs": 2
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_01BPxGhtkoW98xCiTTeNLW4a",
+              "form": "free-text",
+              "markdown": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after.",
+              "payload": {
+                "question": "Take that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after."
+              }
+            }
+          }
+        ]
+      },
+      {
+        "id": "entry_direct_c3ViXzAxTTBYNjI2N0Q4S1QzTTVBUTlBNTA1WThT",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0X6267D8KT3M5AQ9A505Y8S",
+        "parts": [
+          {
+            "type": "text",
+            "text": "Sure. So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.\n\nThen it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\n\nOnce it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\n\nThen it's released, goes to the warehouse, and ships against the due date. So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X6267JX8G55G0DC9PYQ5NX",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0X6267D8KT3M5AQ9A505Y8S",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_01BPxGhtkoW98xCiTTeNLW4a"
+          }
+        },
+        "parts": [
+          {
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nTake that Meridian white order specifically and walk me through its whole life on the floor — from the moment it becomes something you have to schedule, to the moment it's out the door. Just the steps in order, four or five of them is plenty; I'll dig into each one after.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X627DQ7TGEE9S1TJW3D74H",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0X6267D8KT3M5AQ9A505Y8S",
+        "turnId": "turn_01M0X6267K6HQCJ8QRHQE6AJ66",
+        "parts": [
+          {
+            "type": "reasoning",
+            "text": "I should sweep before going deeper, but there's a more structural question worth asking first: does an order stay on one line through all four production stages, or are mixing and milling handled on separate equipment? That distinction seems load-bearing for how I model the process.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01XJmxiS6eof5g1i1oSv8mM5",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
+                "capture-de512bde-aa52-4147-933f-81439aa5ec6d",
+                "capture-a6e8dc50-fffb-494d-8bd2-59704c0427e4",
+                "capture-3cb49f42-f479-4b67-be4c-22c8f9771f6e",
+                "capture-5628ca29-5985-4005-aa3f-a6885dc38223",
+                "capture-6d4d1074-f6fe-4d4c-95c2-f242a6f98233",
+                "capture-a0b65576-83d8-4134-9fbe-9b059663ae12",
+                "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
+                "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+                "capture-fa56fa8b-611a-4a38-9a42-1bd038e52d80",
+                "capture-dba4ec08-0265-420c-95d2-4dce250ae0b6",
+                "capture-0b2046b4-55c8-4ce3-abac-296d6abe469d",
+                "capture-8156b872-b3c2-43db-aa67-56166bebe556",
+                "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
+                "capture-589bc2db-8fc9-4d65-8024-b34ce4cd736a",
+                "capture-07de77cc-9de8-41e9-92f6-8fe06a6263c9",
+                "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
+                "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b",
+                "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
+                "capture-7df09f81-9c85-43ac-b69e-306d540f8afb",
+                "capture-e0f39723-a7e5-4656-a8fb-0e2b50bb82da",
+                "capture-d8dffb0f-f148-4af2-ba7e-478a6a1b38c6",
+                "capture-a2938097-b902-4f24-8e15-70f4b8ce95fb",
+                "capture-896881a6-c9ec-469f-ab03-4a56b59f6cad",
+                "capture-4a3ae53c-2c2f-4664-9499-7e81c254abc5",
+                "capture-d662739b-76f0-429a-829a-ccb79763b6b9",
+                "capture-a9e42aa6-8d30-4ded-a8c4-f24220cfb292",
+                "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
+                    "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-053410a5-6574-4355-aabf-dd972f0088e1",
+                    "capture-d8dffb0f-f148-4af2-ba7e-478a6a1b38c6"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
+                    "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b"
+                  ]
+                }
+              ],
+              "completion": {
+                "complete": false,
+                "revision": "2b8efdb41c191608",
+                "pluginVersion": "sdcpn/2026-08-25.2",
+                "unsatisfied": 28,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 2b8efdb41c191608 (plugin sdcpn/2026-08-25.2): 15 node(s) from 43 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [below-required-precision] \"how long it takes\" on activity:filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:Line 2 filler jam.\n- [below-required-precision] \"how long it takes\" on activity:Line 2 filler jam is known as a range; the model needs spread. Smallest delta: move it from range to spread.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:Line 2 filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:Line 2 filler jam.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n6 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
+            },
+            "durationMs": 85838
+          },
+          {
+            "type": "reasoning",
+            "text": "I should ask whether a single line represents one consistent resource across all four stages structurally.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_01VcV1KAvgD2ZWUJnBfGcBuh",
+            "state": "output-available",
+            "input": {
+              "question": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines."
+            },
+            "output": {
+              "id": "affordance_toolu_01VcV1KAvgD2ZWUJnBfGcBuh",
+              "form": "free-text",
+              "markdown": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines.",
+              "payload": {
+                "question": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines."
+              }
+            },
+            "durationMs": 3
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_01VcV1KAvgD2ZWUJnBfGcBuh",
+              "form": "free-text",
+              "markdown": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines.",
+              "payload": {
+                "question": "When you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines."
+              }
+            }
+          }
+        ]
+      },
+      {
+        "id": "entry_direct_c3ViXzAxTTBYNjVBUkFSUzdOVFBYR0UxR0hRQUtH",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0X65ARARS7NTPXGE1GHQAKG",
+        "parts": [
+          {
+            "type": "text",
+            "text": "Good question, and this is where the sheet lies to me a bit if I'm honest. On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\n\nBut physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between. So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\n\nWhat I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait. I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X65ARH0JRQCSWP5RADNMZZ",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0X65ARARS7NTPXGE1GHQAKG",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_01VcV1KAvgD2ZWUJnBfGcBuh"
+          }
+        },
+        "parts": [
+          {
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWhen you say an order is \"on Line 2\" — does that one order occupy Line 2 through all four stages, mix through fill, so nothing else can start until it's done? Or are mix and mill separate kit that other orders can be using while Line 2's filler is running something else? I'm trying to get right what's actually being contended for when you move an order between lines.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X65BPF0SEY0PZYS6H0ZMRA",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0X65ARARS7NTPXGE1GHQAKG",
+        "turnId": "turn_01M0X65ARMJAKD92XH4MD19G8V",
+        "parts": [
+          {
+            "type": "reasoning",
+            "text": "I'm noting the tank capacity between mill and fill as a genuine second question worth surfacing—the scheduler's suspicion that it's costing them more than admitted could be its own model output. I'll flag it as an optional add-on but stay focused on keeping the current slice tight.\n\nBefore locking down durations for the four stages, I want to check whether they want the model able to test that buffer question, since that determines if the stages need to be separate nodes rather than collapsed. Worth asking directly.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "That's a really valuable thing to have said — the sheet says one line, one order; the floor says four bits of kit with small tanks between them. I'll record both rather than pick one.\n\nThat choice matters for what the model can answer, so let me put it to you.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_01CfCi6guTLjrxg8Hg8QcC6A",
+            "state": "output-available",
+            "input": {
+              "question": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate."
+            },
+            "output": {
+              "id": "affordance_toolu_01CfCi6guTLjrxg8Hg8QcC6A",
+              "form": "free-text",
+              "markdown": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate.",
+              "payload": {
+                "question": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate."
+              }
+            },
+            "durationMs": 1
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_01CfCi6guTLjrxg8Hg8QcC6A",
+              "form": "free-text",
+              "markdown": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate.",
+              "payload": {
+                "question": "Would you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate."
+              }
+            }
+          }
+        ]
+      },
+      {
+        "id": "entry_direct_c3ViXzAxTTBYNjVWSk1CQlFBRTNHR1I3QVZGMlBN",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0X65VJMBBQAE3GGR7AVF2PM",
+        "parts": [
+          {
+            "type": "text",
+            "text": "No, I do want that in scope — if I'm honest, the disruption question and the tank question are the same underlying thing to me. Half the reason Line 1's options are worse when Line 2 goes down is because it feels sluggish and blocked in ways I can't pin on the published line rate. If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\n\nSo yes — build it as separate stages if that's what it takes. I'll warn you now, though: I don't have clean numbers for tank sizes or stage-by-stage rates. I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head. Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X65VJRZ2Z8MPBDYT2JXY2Q",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0X65VJMBBQAE3GGR7AVF2PM",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_01CfCi6guTLjrxg8Hg8QcC6A"
+          }
+        },
+        "parts": [
+          {
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nWould you want the model to be able to settle that hunch — i.e. to show whether the small tank between mill and fill on Line 1 is actually costing you — or is that a side curiosity, and the model's real job stays \"filler's down, switch or wait?\" I'll build the stages as separate contended kit if the tank question is in scope, and that means I'll need tank sizes and stage rates from you rather than just a line rate.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X661931SMD34V46M0CR2G8",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0X65VJMBBQAE3GGR7AVF2PM",
+        "turnId": "turn_01M0X65VJT1Y8A8EVNR55W2SH9",
+        "parts": [
+          {
+            "type": "reasoning",
+            "text": "Good, that covers the second objective, and I should defer stage rates and tank sizes pending deposit of historian data and engineering drawings. Next I want to ask what he already has on hand — end-to-end batch time per SKU per line as a spread, framed around mean versus tail behavior.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Understood, and that's an honest and useful boundary: stage-level rates live in the historian, tank sizes on engineering drawings, neither in your head. I'll record those as open with their source rather than let me invent them.\n\nLet me take what you *do* carry.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01MhhBwG1zLCo3gsmBmjK8Z9",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "refused",
+              "refusal": {
+                "code": "evidence-quote-not-found",
+                "excerpt": "I know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit",
+                "message": "No user entry contains the verbatim quote \"I know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\". Repair the quote to match the user's words exactly."
+              }
+            },
+            "durationMs": 97241
+          },
+          {
+            "type": "reasoning",
+            "text": "I noticed a misquote in the captured text — it should read \"I just know the tanks are small\" rather than what was extracted, referring to the one between mill and fill on Line 1. I'll flag this discrepancy and retry the sweep to get the accurate wording.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "The sweep bounced on a misquote of mine: the expert's words were \"I **just** know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\". Retrying with the verbatim text.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_011T9qYtKQVZmhDSeix2mtTS",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "refused",
+              "refusal": {
+                "code": "evidence-quote-not-found",
+                "excerpt": "and then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
+                "message": "No user entry contains the verbatim quote \"and then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\". Repair the quote to match the user's words exactly."
+              }
+            },
+            "durationMs": 149597
+          },
+          {
+            "type": "reasoning",
+            "text": "I need to fix the capitalization of \"And\" at the start of that sentence and retry the phrasing about the bumped tint order slipping past its due date.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Second bounce, same cause — capitalisation: the expert wrote \"**And** then whatever happens to the bumped tint order…\". Retrying.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01LVoYY2iWjxVep5RNsBHmyZ",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-1cb33f48-6553-4e4f-a8a0-37d7631b08ea",
+                "capture-f073c3ed-2a89-4499-b3b2-fe160e8c1057",
+                "capture-c9864a2c-cbb3-41c9-97a6-e44cc1d7d424",
+                "capture-480c2821-4d80-495b-a652-f5de8b035144",
+                "capture-f3f2c366-eab0-49fa-951c-773f77aa11b2",
+                "capture-3bb35fb7-3954-45d4-839f-20ee46a8c052",
+                "capture-e552ac87-8cfa-4091-a262-6fba33ab9f83",
+                "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+                "capture-dd037a1c-63c0-47b8-8886-81c6d1f70226",
+                "capture-6c46c958-82b9-4ba0-bf0f-363fd70b6dbc",
+                "capture-ee4eb482-b4b3-4392-94d7-ef9dc0a6ca98",
+                "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+                "capture-32521b14-4f1e-41ff-ab95-dfc11d8eee37",
+                "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
+                "capture-c1704cba-8451-47a5-add8-2e388b330a1f",
+                "capture-68ab39e5-8046-4f93-887e-11ed3e3b1da3",
+                "capture-c6d485c6-0e21-4cc0-b626-9091448d6ba1",
+                "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
+                "capture-737200bb-8f75-455f-b90a-3363a30d5fce",
+                "capture-78203b7c-8e00-469c-9d53-01d1a656d5c1",
+                "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3",
+                "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
+                "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
+                "capture-42e0a99d-6cf6-4b30-8199-b430405ba25b",
+                "capture-a27c0fc1-57f3-4eed-bea8-15453c84f2da",
+                "capture-0f6aea65-d3a4-430b-b532-4f1100303f9e",
+                "capture-a3f706dd-453a-4543-9990-26efb1b079dd",
+                "capture-67de2e75-132c-43a7-b64e-412343204931",
+                "capture-bf082835-a2ca-4279-80e5-726f157270bd",
+                "capture-ce28dd53-a53d-4bc9-9956-dc3268c35e3e",
+                "capture-9b28544e-b867-4018-9c35-2691cef17a62",
+                "capture-4c4af9ea-df1a-4449-adb7-d48fce7eae93",
+                "capture-dabdbb5f-9eca-4afb-ad50-5b381d9dfa4f",
+                "capture-292e1165-0990-4d17-b6db-153c675fd66c",
+                "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
+                "capture-54d606d7-8c61-4f0a-bd5f-867bba1af3f7",
+                "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
+                "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
+                "capture-b0908788-ec79-4481-b056-1fa606930f85"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+                    "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+                    "capture-711c9600-2f30-4e86-95a2-cc373696e94c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
+                    "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
+                    "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b",
+                    "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
+                    "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-7df09f81-9c85-43ac-b69e-306d540f8afb",
+                    "capture-42e0a99d-6cf6-4b30-8199-b430405ba25b"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
+                    "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+                    "capture-711c9600-2f30-4e86-95a2-cc373696e94c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
+                    "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277"
+                  ]
+                }
+              ],
+              "completion": {
+                "complete": false,
+                "revision": "3157c77c0d581ebb",
+                "pluginVersion": "sdcpn/2026-08-25.2",
+                "unsatisfied": 28,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 3157c77c0d581ebb (plugin sdcpn/2026-08-25.2): 28 node(s) from 82 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam is open: the expert answered \"unknown-to-user\", pointing at rate of filler jams not yet asked or given; that is not a value.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:tint-to-white washdown has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:tint-to-white washdown.\n- … and 16 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n19 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
+            },
+            "durationMs": 149366
+          },
+          {
+            "type": "reasoning",
+            "text": "I'm noticing 28 nodes with duplicate names like \"filler jam\" and \"Line 2 filler jam\" that I'll need to consolidate, and objectives lack dependency links, so I should ask the expert what the answer actually hinges on. Next I want to get end-to-end batch times as a distribution rather than a single number, so I'll ask what quantiles or spread data he has on his sheet.\n\nI should also ask about run duration for a white batch on Line 2, and whether that duration varies by line or SKU.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Right — I have your sheet-level knowledge to draw on, so let me take it at that level.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_0114D18YCRQ5SdR2RDUdY11m",
+            "state": "output-available",
+            "input": {
+              "question": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white."
+            },
+            "output": {
+              "id": "affordance_toolu_0114D18YCRQ5SdR2RDUdY11m",
+              "form": "free-text",
+              "markdown": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white.",
+              "payload": {
+                "question": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white."
+              }
+            },
+            "durationMs": 1
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_0114D18YCRQ5SdR2RDUdY11m",
+              "form": "free-text",
+              "markdown": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white.",
+              "payload": {
+                "question": "Take that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white."
+              }
+            }
+          }
+        ]
+      },
+      {
+        "id": "entry_direct_c3ViXzAxTTBYNksxMlExSzlEM0c2MEZCSlc1R1dS",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0X6K12Q1K9D3G60FBJW5GWR",
+        "parts": [
+          {
+            "type": "text",
+            "text": "Right, so a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.\n\nBad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more \"the filler hiccupped twice\" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely. Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\n\nOn Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten. That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.\n\nTints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X6K13KW39FXRCVX7KNZJ51",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0X6K12Q1K9D3G60FBJW5GWR",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_0114D18YCRQ5SdR2RDUdY11m"
+          }
+        },
+        "parts": [
+          {
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nTake that Meridian white on Line 2. From the moment it starts mixing to the moment the last pack comes off the filler — what's a typical run? And because runs vary: one run in ten goes worse than what, and one in ten better than what? Then tell me whether those figures change if it's Line 1 instead, or if it's a tint rather than a white.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X6K24RQ3TM35JGS0PY0833",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0X6K12Q1K9D3G60FBJW5GWR",
+        "turnId": "turn_01M0X6K13XV6RS6DM925SKCCD5",
+        "parts": [
+          {
+            "type": "reasoning",
+            "text": "I notice a small inconsistency around his tint speed comment, though it's minor. More importantly, I should flag a real modeling hazard: his bad-day figure of 12-13h might already include filler hiccups, which would double-count with jam events I'm planning to model separately — worth asking him directly whether that estimate includes jams.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01XE9cAp9zgnYi27UvGN6n6f",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057",
+                "capture-9d5063d7-b9fb-400e-8b54-f618c6fde20e",
+                "capture-3245b29a-3687-4313-97c5-e0455e5889ba",
+                "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
+                "capture-770314e5-f47a-463e-908a-1d8c23ee60f5",
+                "capture-6ff1c59a-0664-487b-a946-2680043419a2",
+                "capture-be0c3675-ae93-41c5-9eaa-7d36d84617cb",
+                "capture-3e2a5a8a-bd99-4642-afcf-f9d3dfe2e9f6",
+                "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
+                "capture-27ee0ed5-50d0-47f6-94b8-77e090bca50f",
+                "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
+                "capture-2a491098-b602-4b46-bbaa-439e291027db",
+                "capture-c4aefe40-a022-4990-96a1-b74243850715",
+                "capture-76c7250e-6575-4e31-b667-113f3a497cce",
+                "capture-7da94524-13b5-4c11-a1b4-9cb1b0f07e19",
+                "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
+                "capture-d6985d8d-f85e-4556-a091-df64be080ba6",
+                "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
+                "capture-04a6f876-12f4-4f53-b6f2-f8e5fa9c87bc",
+                "capture-592b83e0-ece3-4e98-aedf-cdf70c202e96",
+                "capture-32fe7be9-75c7-464c-87cb-ca38fef4039b",
+                "capture-31556043-9787-40dc-8c0d-b74a47ed3589",
+                "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
+                "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
+                "capture-d2d6e303-2f63-478a-ace1-0bf61abbfddd",
+                "capture-5548a18b-9f79-4475-a9ab-83a74c750721",
+                "capture-1ee7c206-0c56-4d6b-b091-5861f9c40438",
+                "capture-4b706f60-c02f-4973-aa58-2d3ded113c39",
+                "capture-97ea5a05-d89c-4a7d-a136-f90526beaa27",
+                "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
+                "capture-46d37104-fb87-4105-95d5-4448aade81ac",
+                "capture-0cdda695-1dfa-43ef-971c-b9db09403a07"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
+                    "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
+                    "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
+                    "capture-2a491098-b602-4b46-bbaa-439e291027db"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
+                    "capture-2afae8eb-1155-4b07-9842-971df47a6a7d"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+                    "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
+                    "capture-46d37104-fb87-4105-95d5-4448aade81ac"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
+                    "capture-2afae8eb-1155-4b07-9842-971df47a6a7d"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-0f6aea65-d3a4-430b-b532-4f1100303f9e",
+                    "capture-31556043-9787-40dc-8c0d-b74a47ed3589"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-67de2e75-132c-43a7-b64e-412343204931",
+                    "capture-d2d6e303-2f63-478a-ace1-0bf61abbfddd"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-54d606d7-8c61-4f0a-bd5f-867bba1af3f7",
+                    "capture-4b706f60-c02f-4973-aa58-2d3ded113c39"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
+                    "capture-46d37104-fb87-4105-95d5-4448aade81ac"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b0908788-ec79-4481-b056-1fa606930f85",
+                    "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-6ff1c59a-0664-487b-a946-2680043419a2",
+                    "capture-76c7250e-6575-4e31-b667-113f3a497cce"
+                  ]
+                }
+              ],
+              "completion": {
+                "complete": false,
+                "revision": "2e4f73ea071077f9",
+                "pluginVersion": "sdcpn/2026-08-25.2",
+                "unsatisfied": 9,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 2e4f73ea071077f9 (plugin sdcpn/2026-08-25.2): 36 node(s) from 114 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"the question, in the expert's words\" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what \"better\" means, and trade-off weights\" has not been addressed on objective:where Line 1 loses its time.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n\nPatterns whose trigger may apply (discretionary):\n- P08 on objective:where Line 1 loses its time: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n\n33 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
+            },
+            "durationMs": 122266
+          },
+          {
+            "type": "reasoning",
+            "text": "The remaining gaps are objective-level: duplicate objective nodes and dependencies lacking support. I should ask the expert to clarify what the answer depends on in their own words and resolve the duplicate phrasing, but first the double-counting issue matters since it affects the spread I just recorded — I'll raise that question now.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "One thing you said gives me pause, and I'd rather sort it now than bake it in wrong.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_016Sy8K81vYAJqTRfxPP8zou",
+            "state": "output-available",
+            "input": {
+              "question": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?"
+            },
+            "output": {
+              "id": "affordance_toolu_016Sy8K81vYAJqTRfxPP8zou",
+              "form": "free-text",
+              "markdown": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?",
+              "payload": {
+                "question": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?"
+              }
+            },
+            "durationMs": 0
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_016Sy8K81vYAJqTRfxPP8zou",
+              "form": "free-text",
+              "markdown": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?",
+              "payload": {
+                "question": "You said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?"
+              }
+            }
+          }
+        ]
+      },
+      {
+        "id": "entry_direct_c3ViXzAxTTBYNlFDUzk5UVFZMEUyQ0FFMzkxVFgy",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0X6QCS99QQY0E2CAE391TX2",
+        "parts": [
+          {
+            "type": "text",
+            "text": "That's fair, and yeah, I was sloppy folding them together. If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\n\nThe twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup. So you're right to pull that apart: clean-run variability is small, and the big bad days are really the breakdown showing up inside the run, not the run itself being slow.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X6QCSWHK8MFRPQXXX1TMSB",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0X6QCS99QQY0E2CAE391TX2",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_016Sy8K81vYAJqTRfxPP8zou"
+          }
+        },
+        "parts": [
+          {
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nYou said the bad-day twelve-to-thirteen hours is \"usually not the run itself slowing down\" but \"the filler hiccupped twice,\" and that you're folding that in loosely. If I model filler jams as their own separate event with their own rate and repair time — which I need to do for the switch-or-wait question — then that twelve-to-thirteen would be counting jams twice. So: if you strip the hiccups out and imagine a run where nothing breaks, what does the bad-day-in-ten look like then? Or is a clean run just never much worse than the eight or nine?",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X6QDQH7WRW1YXB1K9S7AVR",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0X6QCS99QQY0E2CAE391TX2",
+        "turnId": "turn_01M0X6QCT6K0JJCHHCXATKD0B7",
+        "parts": [
+          {
+            "type": "reasoning",
+            "text": "I'll supersede and sweep, then focus on the filler jam rate (P01), which is the key unknown for the main objective. I'm also noting that objective dependencies remain unspecified, but I'll set that aside and ask about jam rate first.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01VSwNLQXxdV94UeX8FEfjsW",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-a5926e2a-88e8-459e-a296-282b16d499a8",
+                "capture-ea1779b0-9a83-42aa-92d1-746e73de43cc",
+                "capture-1288a3df-c7fd-4319-8d4e-a228572ba0b0",
+                "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6",
+                "capture-bb291ebf-9fe0-4a6e-9840-e7d7fac44033",
+                "capture-edfaf81c-c276-4b57-a88c-914953b1c6be",
+                "capture-13339551-ff3a-414f-8260-e1296530d8ec",
+                "capture-535749ea-ba99-4d11-84c0-8203fd058329",
+                "capture-79eccb7f-a787-40d4-a2fa-e95bfda82d18",
+                "capture-3c6b3e85-7fd3-4831-9201-6e3ef525e7cf",
+                "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
+                "capture-823c9593-db42-45eb-9515-937e6b90bd33",
+                "capture-f7e12936-7567-4b38-be19-a45fb5dc6274",
+                "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
+                "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092",
+                "capture-afd366c9-1ea6-4b73-b2c0-ed97c9af0c79",
+                "capture-86fd1cfb-379b-42f7-bdbb-8586dae7f755",
+                "capture-90d36431-4341-4f9e-8bf6-8b5354b2fedd",
+                "capture-7ef3368b-e678-4c58-b7f9-137d1607d8ec",
+                "capture-10d88b79-af70-4a14-90c1-da56ad526d36",
+                "capture-921611c3-21b5-4ab2-8e56-9b8cdaa2eba2",
+                "capture-6cf8c229-ab84-4448-abc6-3e7f4a76bb4c",
+                "capture-ce789325-dd40-4b21-a936-73485ccb90b9",
+                "capture-1ba32034-be19-432b-a012-326b682fd357",
+                "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7",
+                "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
+                "capture-e28ed067-b6a4-40d8-935a-3598e2401cc1",
+                "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a",
+                "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
+                "capture-cfe5bf57-8879-4592-a938-1527d73c8bac",
+                "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
+                "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
+                "capture-23c5706e-37c1-481e-9438-8fae70973c13",
+                "capture-00863ee1-f99c-48b2-b680-bf4eb71e6a57",
+                "capture-196b8447-3958-444f-9860-8de7330299ec"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
+                    "capture-a5926e2a-88e8-459e-a296-282b16d499a8"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-3f2444d5-8001-46d9-8a92-c85f8c6f8d6a",
+                    "capture-1288a3df-c7fd-4319-8d4e-a228572ba0b0"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
+                    "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
+                    "capture-a5926e2a-88e8-459e-a296-282b16d499a8"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
+                    "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-dba4ec08-0265-420c-95d2-4dce250ae0b6",
+                    "capture-f7e12936-7567-4b38-be19-a45fb5dc6274"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
+                    "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
+                    "capture-b3079749-c23b-4ade-ac51-9bbff19806fb"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+                    "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
+                    "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
+                    "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
+                    "capture-b3079749-c23b-4ade-ac51-9bbff19806fb"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057",
+                    "capture-a5926e2a-88e8-459e-a296-282b16d499a8"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
+                    "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
+                    "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-2a491098-b602-4b46-bbaa-439e291027db",
+                    "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c4aefe40-a022-4990-96a1-b74243850715",
+                    "capture-823c9593-db42-45eb-9515-937e6b90bd33"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
+                    "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
+                    "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
+                    "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2"
+                  ]
+                }
+              ],
+              "completion": {
+                "complete": false,
+                "revision": "36d1240e30d0f4d1",
+                "pluginVersion": "sdcpn/2026-08-25.2",
+                "unsatisfied": 9,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 36d1240e30d0f4d1 (plugin sdcpn/2026-08-25.2): 41 node(s) from 149 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"the question, in the expert's words\" on objective:where Line 1 loses its time has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what \"better\" means, and trade-off weights\" has not been addressed on objective:where Line 1 loses its time.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option actually loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"the question, in the expert's words\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what \"better\" means, and trade-off weights\" on objective:which option loses less has competing active captures; an explicit, user-cited resolution must close it.\n\nPatterns whose trigger may apply (discretionary):\n- P08 on objective:where Line 1 loses its time: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n\n38 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
+            },
+            "durationMs": 155454
+          },
+          {
+            "type": "reasoning",
+            "text": "38 of 41 nodes fall outside any objective's slice since objectives currently have no dependencies — that's the real structural gap I need to fix by getting the expert to state their questions crisply and what they hinge on. The filler jam rate is also worth asking about, but fixing objectives first is what makes everything else actually count, so I'll craft a question that addresses both.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Two housekeeping things I want to settle, because right now the model has plenty of plant detail but the two questions it's meant to answer aren't yet wired to any of it.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_01EHPQiwUUuqA7BA9xjbGyvx",
+            "state": "output-available",
+            "input": {
+              "question": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong."
+            },
+            "output": {
+              "id": "affordance_toolu_01EHPQiwUUuqA7BA9xjbGyvx",
+              "form": "free-text",
+              "markdown": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong.",
+              "payload": {
+                "question": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong."
+              }
+            },
+            "durationMs": 3
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_01EHPQiwUUuqA7BA9xjbGyvx",
+              "form": "free-text",
+              "markdown": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong.",
+              "payload": {
+                "question": "If the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong."
+              }
+            }
+          }
+        ]
+      },
+      {
+        "id": "entry_direct_c3ViXzAxTTBYNldaMzBYQTM1WVI2SjVUNkhGTUJO",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0X6WZ30XA35YR6J5T6HFMBN",
+        "parts": [
+          {
+            "type": "text",
+            "text": "Alright, let me actually try and write these the way I'd type them if I had the box.\n\n**Disruption one:** \"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"\n\nWhat it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of \"could be quick, could be long\" rather than one number. And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours. And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the \"who can absorb it\" judgment call again.\n\nI'd say what's missing from your list, or under-weighted: the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just \"an order got delayed.\" A distributor slipping is fine, so the answer to the question genuinely depends on whose tint was sitting there.\n\n**The Line 1 tank one:** \"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\" That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others. That's not something I'd have said a month ago.\n\n(Sorry — I've just seen the time, I have the floor huddle in ten minutes. How much more do you need?)",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X6WZ3K2HCKP0WXTWTDDYPS",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0X6WZ30XA35YR6J5T6HFMBN",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_01EHPQiwUUuqA7BA9xjbGyvx"
+          }
+        },
+        "parts": [
+          {
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nIf the tool had a box where you typed the question, how would you write the two of them — the disruption one and the Line 1 one — in one sentence each, as you'd actually phrase them? And for each, name the things about the plant the answer hangs on: for the disruption one I'd guess it's the lines, the run times, the washdown, the jam and the due dates — tell me what I'm missing or what doesn't belong.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X6X098KASDR8CJZZTQ1D0A",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0X6WZ30XA35YR6J5T6HFMBN",
+        "turnId": "turn_01M0X6WZ3Y82683W9EYJ7RNYMC",
+        "parts": [
+          {
+            "type": "reasoning",
+            "text": "With ten minutes, I shouldn't rush to close things out — instead I should name what's missing honestly and let them decide where to spend the time. The highest-value gaps are jam rate, repair spread, and washdown/scrap, since those tie directly to the disruption objective and only they have that data, so I'll surface the list and ask them to choose.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_014CbqDgUVDxZ1c6STNR2cSC",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-b58883f3-43e2-4626-bc59-a9c091f1d1b5",
+                "capture-3aa3764b-8dd5-495a-bf3e-b32cbc89ba61",
+                "capture-57ad71c3-f423-4d91-a9f8-d3ce31f1fca1",
+                "capture-1a3325b9-15b6-436a-8e7f-feff95d98036",
+                "capture-0e28490a-6b4b-4996-9b6f-3d9249a7d2dc",
+                "capture-43c5ef42-68ce-478f-89b0-c552111d807a",
+                "capture-ccc2d7eb-8a3f-4684-8f1c-a21a51049550",
+                "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
+                "capture-a158a5da-be3a-461f-87c0-69c38cac1a72",
+                "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23",
+                "capture-4043a577-c1b4-44c3-91f3-2194def82bd9",
+                "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
+                "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
+                "capture-72d414e6-f6a2-420e-8407-667f41535411",
+                "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
+                "capture-53f9387d-f037-4d0f-999b-f89a8f113f46",
+                "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
+                "capture-38e0effa-0fb7-48ff-907c-2fc9f3e64211",
+                "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
+                "capture-314d8187-81ba-478c-8f71-1c9e5826965b",
+                "capture-345fbb5a-c0c1-4e3a-9015-33b3ad727831",
+                "capture-60f6f8c8-f52e-443a-adee-6818339f3b35",
+                "capture-be556841-bf14-4fe0-8c23-ffc773896b2b",
+                "capture-26d3ac6c-4b27-4765-baa3-8437f06fe8ca",
+                "capture-da6d10a4-e0f2-4b1d-8e78-4d58cadeb8f2",
+                "capture-68f9db28-a002-406d-912a-4cc410e5b380",
+                "capture-0a06d184-bf72-42c4-95b3-7ad88ea4e059",
+                "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f",
+                "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b",
+                "capture-7111ab55-5d90-44f6-a1d2-4aa1b48da4bb",
+                "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a",
+                "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+                    "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+                    "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
+                    "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-a2938097-b902-4f24-8e15-70f4b8ce95fb",
+                    "capture-be556841-bf14-4fe0-8c23-ffc773896b2b"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
+                    "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+                    "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+                    "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+                    "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
+                    "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
+                    "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
+                    "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
+                    "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
+                    "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
+                    "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
+                    "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b0908788-ec79-4481-b056-1fa606930f85",
+                    "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
+                    "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-27ee0ed5-50d0-47f6-94b8-77e090bca50f",
+                    "capture-a158a5da-be3a-461f-87c0-69c38cac1a72"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
+                    "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c4aefe40-a022-4990-96a1-b74243850715",
+                    "capture-4043a577-c1b4-44c3-91f3-2194def82bd9"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
+                    "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
+                    "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
+                    "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-46d37104-fb87-4105-95d5-4448aade81ac",
+                    "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-823c9593-db42-45eb-9515-937e6b90bd33",
+                    "capture-4043a577-c1b4-44c3-91f3-2194def82bd9"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
+                    "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
+                    "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
+                    "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
+                    "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
+                    "capture-8f9df889-b24b-49e4-8ae8-6506112e2006"
+                  ]
+                }
+              ],
+              "completion": {
+                "complete": false,
+                "revision": "1dffca1f0e4725ec",
+                "pluginVersion": "sdcpn/2026-08-25.2",
+                "unsatisfied": 42,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 1dffca1f0e4725ec (plugin sdcpn/2026-08-25.2): 47 node(s) from 181 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unaddressed] \"what it needs before it can start\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"who or what performs it\" has not been addressed on activity:filler jam.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 30 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n34 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
+            },
+            "durationMs": 138047
+          },
+          {
+            "type": "reasoning",
+            "text": "With ten minutes left, I should give an honest answer on \"how much more\" and then ask the single highest-value question I still need clarity on—the filler jam rate and repair duration spread—since that's central and only they can supply it. I'll also briefly flag what else remains unknown.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Honest answer to \"how much more\": we're maybe a third of the way. What's still open, roughly in order of how much it costs you: the filler jam's rate and repair time; what the washdown actually costs including ramp scrap; the \"who can absorb a slip\" rule as you actually apply it; how orders arrive into the demand book; QA hold times; and the stage rates and tank size, which we've already agreed aren't in your head. None of that needs to happen today.\n\nFor the ten minutes, I'd spend them on the jam, because you named it as the thing you never know at the time and nobody else can tell me.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_ask",
+            "toolCallId": "toolu_018NF8gHsprWVmC1fJGrJ3VF",
+            "state": "output-available",
+            "input": {
+              "question": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?"
+            },
+            "output": {
+              "id": "affordance_toolu_018NF8gHsprWVmC1fJGrJ3VF",
+              "form": "free-text",
+              "markdown": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?",
+              "payload": {
+                "question": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?"
+              }
+            },
+            "durationMs": 5
+          },
+          {
+            "type": "data-affordance",
+            "data": {
+              "id": "affordance_toolu_018NF8gHsprWVmC1fJGrJ3VF",
+              "form": "free-text",
+              "markdown": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?",
+              "payload": {
+                "question": "Thinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?"
+              }
+            }
+          }
+        ]
+      },
+      {
+        "id": "entry_direct_c3ViXzAxTTBYNzFZSzUyUTFFN1I2WVhWNFJGWktT",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0X71YK52Q1E7R6YXV4RFZKS",
+        "parts": [
+          {
+            "type": "text",
+            "text": "Okay, quick version. It's a \"every week or two\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.\n\nWhen it stops: typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift. I don't have a cleaner breakdown than that — maintenance would have the actual work-order times in the CMMS but I've never pulled them.\n\nRight, I need to run — good session though. Same time next week?",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X71YKMVR1H78GP6AX8D16B",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0X71YK52Q1E7R6YXV4RFZKS",
+        "signal": {
+          "tagName": "affordance-reply-bound",
+          "attributes": {
+            "affordanceId": "affordance_toolu_018NF8gHsprWVmC1fJGrJ3VF"
+          }
+        },
+        "parts": [
+          {
+            "type": "text",
+            "text": "The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X725HFECA7NBAA6QPFPNQZ",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0X71YK52Q1E7R6YXV4RFZKS",
+        "turnId": "turn_01M0X71YKXS1YG2BC2F4ZP8DE1",
+        "parts": [
+          {
+            "type": "reasoning",
+            "text": "They've stopped, so I should respect that and not introduce anything new. I'll do a final sweep and wrap up with a summary, note any gaps or assumptions, and confirm we're on for next week.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_013gVphA3fva6xuP624tUbGD",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "refused",
+              "refusal": {
+                "code": "evidence-quote-not-found",
+                "excerpt": "jams badly enough to stop the run",
+                "message": "No user entry contains the verbatim quote \"jams badly enough to stop the run\". Repair the quote to match the user's words exactly."
+              }
+            },
+            "durationMs": 142365
+          },
+          {
+            "type": "reasoning",
+            "text": "I should use their actual words instead — they described it as \"every week or two,\" ranging from once every three weeks at the low end to twice a week at the high end.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "That bounce was my own phrase, not yours — \"jams badly enough to stop the run\" was my wording. Re-anchoring on what you actually said.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01AhAypUknSd3LHrMi8wTivx",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-1a240192-8179-4339-815e-3775a062e986",
+                "capture-85062afa-e82d-46ce-b609-f7ed16f8b093",
+                "capture-2c3fa15f-551b-4380-a3b3-8dbc6334a9bb",
+                "capture-41269bfb-9040-4d54-a113-a94c09f6f2f0",
+                "capture-f7ea7c88-4d40-48e7-84e5-2b12ebc5ea8e",
+                "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26",
+                "capture-0e8d50b2-4222-4129-a619-09c5612c05c5",
+                "capture-117f9832-aaba-473a-9411-6fd4022388f2",
+                "capture-e10d4081-78ed-42da-bb26-857f1118224c",
+                "capture-875ed21b-d257-48fe-867b-6785abf6abb7",
+                "capture-06d48b41-86fb-48c0-b3e0-59012ba81960",
+                "capture-428e3931-676d-4af5-a30c-d7a31ea0d8ad",
+                "capture-ecd3c093-8f6b-4a48-a1fc-d2775d4dbc1f",
+                "capture-c6339dee-036e-47cb-9dcf-42fc22d38aae",
+                "capture-2bc071c4-2919-4ff3-910a-92d872eeaef2",
+                "capture-6ec49aac-c165-4e2b-a937-bed3c8c51c2c",
+                "capture-c3f03d77-6760-4b3b-99e5-b78d119a352f",
+                "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14",
+                "capture-83e1381a-f2df-4713-a2f6-f11d034c2fd4",
+                "capture-95cbfe20-605f-4218-9076-0f4816ebadfa",
+                "capture-1a5a8343-7367-416e-b760-c7e8f587fe25",
+                "capture-bf2e57a3-bda7-4090-92ca-af63e0c7a248",
+                "capture-aec8ff27-3e3f-45d2-9142-b6dc2b5d88a3",
+                "capture-9d59a385-a8ae-410a-a13d-a4bca3dde9a3",
+                "capture-4b22a066-a97c-4329-8513-cbd85edd8d65",
+                "capture-63fabb67-24c4-4bee-926f-17917300c8f4",
+                "capture-b1e5ded4-79d6-4ff4-bd0d-6386509efba9",
+                "capture-147c2765-6bfb-4da0-9df9-b74a1c1049de",
+                "capture-ec5740e7-5068-4222-ad24-8396f5975657",
+                "capture-2884cc84-c616-4227-860a-d6b55a06c13d",
+                "capture-0548a680-8da8-47e9-ad72-fb1e264fac80",
+                "capture-8c6a716b-e09a-4977-94d9-f28ab74be7c4",
+                "capture-a67683fd-0f34-4838-b48e-aa01f657a511",
+                "capture-1b632a29-f1de-48e5-8f96-a5ef908c4a56",
+                "capture-9926552e-289f-4b4a-bc99-4cae34f1720a",
+                "capture-06aac0a9-b270-4b13-a54f-37440769d685",
+                "capture-94948329-18e7-42fe-9538-a84fd72c225d",
+                "capture-16b9c643-8b17-490e-bfe0-022a06efd914",
+                "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af",
+                "capture-821e00ef-6923-43b0-955b-3ed7d60ce127",
+                "capture-6da3fa16-460b-4f07-aefc-f941d7118f76",
+                "capture-731a5768-edc7-4858-ad42-50d2faf4b181",
+                "capture-1bebb3ea-7788-477a-8127-593fe3fe6026",
+                "capture-07cb7ca9-27c5-4395-bc9e-aaebc5811382",
+                "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2",
+                "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1",
+                "capture-a0429a34-1145-458d-bada-32d827d68959"
+              ],
+              "skippedDedupKeys": [],
+              "advisories": [
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+                    "capture-e10d4081-78ed-42da-bb26-857f1118224c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+                    "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-0b2046b4-55c8-4ce3-abac-296d6abe469d",
+                    "capture-95cbfe20-605f-4218-9076-0f4816ebadfa"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-07de77cc-9de8-41e9-92f6-8fe06a6263c9",
+                    "capture-16b9c643-8b17-490e-bfe0-022a06efd914"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
+                    "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-e0f39723-a7e5-4656-a8fb-0e2b50bb82da",
+                    "capture-a67683fd-0f34-4838-b48e-aa01f657a511"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
+                    "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+                    "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-dd037a1c-63c0-47b8-8886-81c6d1f70226",
+                    "capture-ecd3c093-8f6b-4a48-a1fc-d2775d4dbc1f"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+                    "capture-e10d4081-78ed-42da-bb26-857f1118224c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+                    "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
+                    "capture-e10d4081-78ed-42da-bb26-857f1118224c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
+                    "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
+                    "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
+                    "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-bf082835-a2ca-4279-80e5-726f157270bd",
+                    "capture-6ec49aac-c165-4e2b-a937-bed3c8c51c2c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
+                    "capture-6da3fa16-460b-4f07-aefc-f941d7118f76"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
+                    "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
+                    "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b0908788-ec79-4481-b056-1fa606930f85",
+                    "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
+                    "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
+                    "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
+                    "capture-1a5a8343-7367-416e-b760-c7e8f587fe25"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
+                    "capture-4b22a066-a97c-4329-8513-cbd85edd8d65"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
+                    "capture-94948329-18e7-42fe-9538-a84fd72c225d"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-5548a18b-9f79-4475-a9ab-83a74c750721",
+                    "capture-147c2765-6bfb-4da0-9df9-b74a1c1049de"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
+                    "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-46d37104-fb87-4105-95d5-4448aade81ac",
+                    "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6",
+                    "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
+                    "capture-94948329-18e7-42fe-9538-a84fd72c225d"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
+                    "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
+                    "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
+                    "capture-6da3fa16-460b-4f07-aefc-f941d7118f76"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
+                    "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
+                    "capture-e10d4081-78ed-42da-bb26-857f1118224c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
+                    "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
+                    "capture-e10d4081-78ed-42da-bb26-857f1118224c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
+                    "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
+                    "capture-4b22a066-a97c-4329-8513-cbd85edd8d65"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
+                    "capture-94948329-18e7-42fe-9538-a84fd72c225d"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
+                    "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f",
+                    "capture-821e00ef-6923-43b0-955b-3ed7d60ce127"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b",
+                    "capture-6da3fa16-460b-4f07-aefc-f941d7118f76"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a",
+                    "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993",
+                    "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-e10d4081-78ed-42da-bb26-857f1118224c",
+                    "capture-1bebb3ea-7788-477a-8127-593fe3fe6026"
+                  ]
+                }
+              ],
+              "completion": {
+                "complete": false,
+                "revision": "0028ff75065b59b1",
+                "pluginVersion": "sdcpn/2026-08-25.2",
+                "unsatisfied": 44,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 0028ff75065b59b1 (plugin sdcpn/2026-08-25.2): 56 node(s) from 228 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"who or what performs it\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 32 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n41 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
+            },
+            "durationMs": 154331
+          },
+          {
+            "type": "reasoning",
+            "text": "I should wrap up honestly here—confirming next week works, avoiding new topics, and clearly laying out what we have, the gaps, and the assumptions I'm making, while being upfront that I can't hand over a runnable model yet.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Go — and yes, same time next week works. Here's where we got to, so you can correct anything when you're back at a desk. **The model is not finished and I'm not going to pretend it is; I wouldn't hand this to your tooling yet.**\n\n## What's on record, in your words\n\n**The two questions the model exists to answer**\n1. \"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"\n2. \"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"\n\n**What \"better\" means** — Meridian-style on-time is a hard line, \"not really a trade-off, that's a line I won't cross.\" Below that line you weigh washdown hours, whether the bumped order slides and by how much, and who the customer is. No formula; judgment on who can absorb the slip.\n\n**The flow** — demand book line item out of ERP → you allocate to a line and a week slot → mix, mill, tint, fill (tint \"barely there\" for a white) → QA hold → release, warehouse, ship against due date.\n\n**The line, both ways** — on the sheet, one row, one order occupies Line 2 mix-to-fill. Physically, separate kit with small holding tanks between, and the crew will start the next mix if there's tank room. Both recorded; neither averaged away.\n\n**Run times, clean of breakdowns** — white on Line 2: typical 8–9 h, bad-but-clean 9–10 h, good day ~6 h. Same order on Line 1: add 50–60%, so typical 13–14 h, best ~10 h. Tints: 8–10 h typical on *either* line, no big gap — which you flagged as unexplained and sheet-derived. The 12–13 h figure has been pulled out as breakdown, not run.\n\n**Filler jam** — every week or two; low once in three weeks, high twice a week. Repair typical 30–45 min, quick one-in-ten 10–15 min, bad one-in-ten 4–5 h, \"occasionally eating the rest of the shift.\"\n\n**Washdown** — tint-to-white, three hours, direction matters, plus ramp scrap you don't have numbers for.\n\n## Gaps, with where they'd come from\n- Stage-level rates per line — historian, never pulled apart.\n- Tank sizes, mill-to-fill on Line 1 — engineering drawings.\n- Jam repair times, properly — maintenance work orders in the CMMS.\n- Ramp scrap after washdown — you said it shouldn't be ignored; no source named yet.\n- Whether the tank matters differently by SKU — your own new thought, unexamined.\n- QA hold: \"a few hours for a white,\" and a longer \"specialty wait\" you mentioned but I never asked about.\n- How orders arrive into the demand book — never asked.\n- The \"who can absorb the slip\" rule — I have distributor-shrugs and prickly-account, not a rule I could apply without you.\n\n## Assumptions ledger\n1. That the four stages are the same four for every product — you said \"same four stages every product goes through,\" so this is yours, not mine, but it's load-bearing enough to re-check.\n2. Nothing else. Where I was tempted to fill in — jam rate before you gave it, washdown scrap, stage rates — it's in the gaps list instead.\n\nBoth objectives are still formally unsupported: I have the plant detail and the questions, but haven't yet wired which pieces each answer depends on tightly enough for the tooling. That plus the ramp scrap and the slip rule are what I'd open with next week.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_direct_c3ViXzAxTTBYN0NFRENNUUtEWkozMzIxM1hTMUUw",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0X7CEDCMQKDZJ33213XS1E0",
+        "parts": [
+          {
+            "type": "text",
+            "text": "Looks right — that's a fair record, and yeah, next week let's start with ramp scrap and the slip rule, since those feel like the ones I could actually go dig up or nail down between now and then. I'll ask maintenance for the CMMS numbers on the filler too while I'm at it. Go on, get to your huddle — wait, that's me. See you next week.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X7CN402JVB8ATB7XBRY0PM",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0X7CEDCMQKDZJ33213XS1E0",
+        "turnId": "turn_01M0X7CEEJGA9FA73FAKXB1SDQ",
+        "parts": [
+          {
+            "type": "text",
+            "text": "Enjoy the huddle.\n\nThree things I'll have ready for next week, so you don't have to hold them:\n\n1. **Ramp scrap and the slip rule** first, as you asked — for the slip rule I'll come at it through a case rather than a principle, so have in mind the last time you bumped someone's order and it turned out to be the wrong someone.\n2. **CMMS filler numbers** — when you get them, what I want is the same shape you gave me from memory: typical, bad one-in-ten, quick one-in-ten. If the work orders disagree with your 30–45 minutes, that disagreement is worth more to the model than either figure alone, so don't reconcile it before you bring it.\n3. **The tint parity puzzle** — that Line 1 and Line 2 run tints at nearly the same speed with no explanation. It's the loose thread most likely to be the same thing as your tank hunch, and I'd like to pull on it once the scrap and slip rule are in.\n\nNothing needs doing beyond that. See you next week.",
+            "state": "done"
+          },
+          {
+            "type": "reasoning",
+            "text": "The session has closed with the user's confirmation of the read-back — their \"looks right\" is agreement, not new capture, but their own commitments in the tail (digging up ramp scrap and the slip rule, asking maintenance for CMMS numbers) are genuine deferral deposits worth capturing. This is settled — time to sweep.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "The tail has settled: the read-back was confirmed, the session closed, and the expert's last message adds content in their own words — what they'll dig up before next time and that they'll pull the CMMS numbers from maintenance. That belongs in the record as deferral deposits, not as agreement to my summary.\n\nOne caution I'll carry into the sweep: \"Looks right\" is assent to my phrasing, not origination. It closes nothing that wasn't already sourced to their words.",
+            "state": "done"
+          },
+          {
+            "type": "dynamic-tool",
+            "toolName": "brunch_sweep",
+            "toolCallId": "toolu_01TCGhYry4UzwpGQKMAGwEWr",
+            "state": "output-available",
+            "input": {},
+            "output": {
+              "status": "applied",
+              "appliedCaptureIds": [
+                "capture-48033ee8-f7eb-4615-b21f-018837fc9c5e",
+                "capture-88da9925-d922-48c3-8ea0-2c631df3ae3d",
+                "capture-f53d8f62-375e-4af6-9aaa-fb903839993c",
+                "capture-ac435640-eea2-4ad6-9695-8e5408b4d852",
+                "capture-f5a658db-c8ec-4ca0-8a87-3ad252dee56d",
+                "capture-618842bb-d23d-4371-ae57-73e5257ba215",
+                "capture-538fb022-2495-46bb-8661-8e1f38c802bf",
+                "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98",
+                "capture-5d5f862f-c18c-4501-b544-76735d28e004",
+                "capture-7f6b8be1-6336-465f-8e11-36a5277d51bd",
+                "capture-1a83c9c6-a8f8-4ece-a5d4-53b81bf8cc9b",
+                "capture-e6ae51ed-e1f6-45f3-aab1-c4bca2a979e8",
+                "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7",
+                "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01",
+                "capture-7f9ac97e-375b-4de3-bbcd-b65e5c7427a6",
+                "capture-66fbb371-91b7-41db-b437-5bd207d08aed",
+                "capture-8da19d62-c082-41f6-ac55-f28afe266a8c",
+                "capture-995374a1-2d25-4690-8397-b342f46ebf02",
+                "capture-3cc84392-4ed4-4804-8a7c-db07d384a8b2",
+                "capture-289ac648-e939-4e62-ad46-a17b112402d4",
+                "capture-5376c084-3889-476f-adab-b09a038ded28",
+                "capture-b9dfddf9-52d8-433e-81b8-5611e7356c34",
+                "capture-27ae8fdf-c227-4160-a1a5-e85530156938",
+                "capture-7bd393bf-3f05-4aa1-b15a-968c293b076f",
+                "capture-ef41e72f-3126-4003-82b2-686b5f8bfdfb",
+                "capture-4fa34ba3-82e3-4a4a-ad28-362765a40046",
+                "capture-2f670377-be1e-4275-9e46-24dd13316300",
+                "capture-9dc62989-7db7-4e58-baf1-b9ed0400d9a2",
+                "capture-b92eccd9-e2ad-41a9-abce-bb1cf8b3c328",
+                "capture-55e95600-febe-4c98-8859-a56eb23ab156",
+                "capture-29c03a62-4be2-4dc2-852e-bfeab6770f1b",
+                "capture-9f708103-e43a-4766-bca4-cb3b7060fdcd",
+                "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c",
+                "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d",
+                "capture-12e575e7-b7a9-472d-b165-308334ae7513",
+                "capture-bc9d210e-beb9-4f7a-aa5d-243950605a2a",
+                "capture-90a38599-7f1b-46ed-9352-d3dd3566b338",
+                "capture-d889a88e-b7be-4055-9da1-e64f9fc858b0",
+                "capture-173c6d39-090f-49a7-9e38-c8998003718b"
+              ],
+              "skippedDedupKeys": [
+                "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\"\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+              ],
+              "advisories": [
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-76159984-4b11-446f-a707-bc8302ef0b1d",
+                    "capture-f53d8f62-375e-4af6-9aaa-fb903839993c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
+                    "capture-55e95600-febe-4c98-8859-a56eb23ab156"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-caeeeb12-a91f-46a0-88c2-a622d4d30c55",
+                    "capture-90a38599-7f1b-46ed-9352-d3dd3566b338"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
+                    "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
+                    "capture-12e575e7-b7a9-472d-b165-308334ae7513"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
+                    "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+                    "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
+                    "capture-12e575e7-b7a9-472d-b165-308334ae7513"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
+                    "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-3e2a5a8a-bd99-4642-afcf-f9d3dfe2e9f6",
+                    "capture-1a83c9c6-a8f8-4ece-a5d4-53b81bf8cc9b"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
+                    "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
+                    "capture-66fbb371-91b7-41db-b437-5bd207d08aed"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-2a491098-b602-4b46-bbaa-439e291027db",
+                    "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c4aefe40-a022-4990-96a1-b74243850715",
+                    "capture-8da19d62-c082-41f6-ac55-f28afe266a8c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
+                    "capture-5376c084-3889-476f-adab-b09a038ded28"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
+                    "capture-27ae8fdf-c227-4160-a1a5-e85530156938"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
+                    "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
+                    "capture-12e575e7-b7a9-472d-b165-308334ae7513"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
+                    "capture-538fb022-2495-46bb-8661-8e1f38c802bf"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
+                    "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-823c9593-db42-45eb-9515-937e6b90bd33",
+                    "capture-8da19d62-c082-41f6-ac55-f28afe266a8c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
+                    "capture-538fb022-2495-46bb-8661-8e1f38c802bf"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
+                    "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092",
+                    "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-ce789325-dd40-4b21-a936-73485ccb90b9",
+                    "capture-b92eccd9-e2ad-41a9-abce-bb1cf8b3c328"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7",
+                    "capture-55e95600-febe-4c98-8859-a56eb23ab156"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
+                    "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a",
+                    "capture-12e575e7-b7a9-472d-b165-308334ae7513"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
+                    "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
+                    "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23",
+                    "capture-66fbb371-91b7-41db-b437-5bd207d08aed"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-4043a577-c1b4-44c3-91f3-2194def82bd9",
+                    "capture-8da19d62-c082-41f6-ac55-f28afe266a8c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
+                    "capture-27ae8fdf-c227-4160-a1a5-e85530156938"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
+                    "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
+                    "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-1a240192-8179-4339-815e-3775a062e986",
+                    "capture-48033ee8-f7eb-4615-b21f-018837fc9c5e"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14",
+                    "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-83e1381a-f2df-4713-a2f6-f11d034c2fd4",
+                    "capture-7f9ac97e-375b-4de3-bbcd-b65e5c7427a6"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-1a5a8343-7367-416e-b760-c7e8f587fe25",
+                    "capture-5376c084-3889-476f-adab-b09a038ded28"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-4b22a066-a97c-4329-8513-cbd85edd8d65",
+                    "capture-27ae8fdf-c227-4160-a1a5-e85530156938"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-ec5740e7-5068-4222-ad24-8396f5975657",
+                    "capture-4fa34ba3-82e3-4a4a-ad28-362765a40046"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-0548a680-8da8-47e9-ad72-fb1e264fac80",
+                    "capture-9dc62989-7db7-4e58-baf1-b9ed0400d9a2"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-94948329-18e7-42fe-9538-a84fd72c225d",
+                    "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af",
+                    "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c"
+                  ]
+                },
+                {
+                  "type": "possibly-equivalent",
+                  "reason": "same-evidence",
+                  "captureIds": [
+                    "capture-538fb022-2495-46bb-8661-8e1f38c802bf",
+                    "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98"
+                  ]
+                }
+              ],
+              "completion": {
+                "complete": false,
+                "revision": "26a8219a17118558",
+                "pluginVersion": "sdcpn/2026-08-25.2",
+                "unsatisfied": 46,
+                "unmapped": [],
+                "cue": "The harness folded the model at revision 26a8219a17118558 (plugin sdcpn/2026-08-25.2): 69 node(s) from 267 active capture(s). Complete: no.\n\nUnsatisfied, in file order:\n- [unsupported-active-objective] objective:is the mill-to-fill tank on Line 1 slowing the line down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:wait or shift when Line 2 goes down depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:where Line 1 loses its time depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option actually loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [unsupported-active-objective] objective:which option loses less depends on nothing the model contains; an objective that depends on nothing is unsupported.\n- [open-conflict] \"what it produces or changes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how long it takes\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"how often it occurs, if it is an event rather than a step\" on activity:filler jam has competing active captures; an explicit, user-cited resolution must close it.\n- [unaddressed] \"what is lost when it changes the system's mode\" has not been addressed on activity:filler jam.\n- [unaddressed] \"whether its quantities vary by type\" has not been addressed on activity:filler jam.\n- [open-conflict] \"what it needs before it can start\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- [open-conflict] \"what it produces or changes\" on activity:run it through mix/mill/tint/fill has competing active captures; an explicit, user-cited resolution must close it.\n- … and 34 more.\n\nPatterns whose trigger may apply (discretionary):\n- P01 on activity:filler jam: occurrence and duration are two slots. Ask how often, as a range, for each named event separately; then how long, as a spread. Keep the precision the expert actually gave; never round a range up to a spread.\n- P02 on activity:filler jam: ask what is lost in the transition, as a range, after a *named* transition. If the expert does not know, ask what they would treat as an authoritative source — never convert \"unknown\" into a value.\n- P08 on activity:filler jam: record both on the same node under `source-regime`, with the expert's account of when they diverge. Do not average them and do not pick one.\n- P05 on entity-type:line: ask which wins, what overrides that, how ties break, and for a recent borderline case that shows the practiced rule. Never infer the rule from a schedule or a document.\n- P07 on entity-type:line: ask explicitly whether it varies by type. Record \"no\" as a value; it is load-bearing.\n- P04 on policy:who can absorb the slip: replace any time-shaped approximation (\"about two days before\") with the practiced event or state that makes it runnable, who or what flips it, and where that is observable.\n\n53 node(s) lie outside every objective's dependency slice and are recorded but not demanded.\n\nCompletion is computed from the model, never from the conversation; it does not decide whether to continue. Choose the next question, or none."
+              }
+            },
+            "durationMs": 128526
+          },
+          {
+            "type": "reasoning",
+            "text": "The session's over now, so I'll note this for next time: those five objective nodes really boil down to just two distinct questions, duplicated through repeated rephrasing, and none of them carry real dependencies. That's something worth reviewing and cleaning up going forward.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Swept and folded — the session's record is durable. Since you've gone, this is a note-to-self for next week rather than anything you need to read now.\n\n**State of the model:** 69 nodes from 267 captures. Not complete, and two things about *how it's held* need fixing before more content goes in:\n\n1. **Objective duplication.** Your two questions have landed as five objective nodes — successive rephrasings of the same two (\"which option loses less\", \"which option actually loses less\", \"wait or shift when Line 2 goes down\" are one question; \"where Line 1 loses its time\" and \"is the mill-to-fill tank on Line 1 slowing the line down\" are the other). That's an artefact of my asking you to restate them, not a fact about your plant. Consolidating is a review-and-revise job, and it needs your word on which phrasing is yours, not my merge.\n\n2. **Nothing is wired to the objectives.** 53 of the 69 nodes sit outside every objective's dependency slice — recorded, but not demanded by anything. That's why the completion report keeps growing without the model getting more answerable. You *did* tell me what the disruption question hangs on: the run being protected, Line 1's state and family, the jam duration, the ramp scrap, and the bumped order's identity. I have those as prose in your answer; they aren't yet linked as dependencies. Doing that link properly is the first thing that makes any of the plant detail count.\n\n3. **Three open conflicts** on the filler jam node and the production-run node, where later answers superseded earlier ones — the 12–13 h that turned out to be breakdown, and the two jam descriptions. Those need your explicit word to close, not my inference about which you meant.\n\nSo next week's order: ramp scrap and the slip rule as you asked, then the objective wiring, then the conflict closes. The tint parity thread stays third.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X7CTET9RVN9FFHJH8C93AE",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0X7CEDCMQKDZJ33213XS1E0",
+        "signal": {
+          "tagName": "settlement-check"
+        },
+        "parts": [
+          {
+            "type": "text",
+            "text": "The harness computed this unswept conversation tail:\n\n[non-user] The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?\n[assistant] That bounce was my own phrase, not yours — \"jams badly enough to stop the run\" was my wording. Re-anchoring on what you actually said.Go — and yes, same time next week works. Here's where we got to, so you can correct anything when you're back at a desk. **The model is not finished and I'm not going to pretend it is; I wouldn't hand this to your tooling yet.**\n\n## What's on record, in your words\n\n**The two questions the model exists to answer**\n1. \"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"\n2. \"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"\n\n**What \"better\" means** — Meridian-style on-time is a hard line, \"not really a trade-off, that's a line I won't cross.\" Below that line you weigh washdown hours, whether the bumped order slides and by how much, and who the customer is. No formula; judgment on who can absorb the slip.\n\n**The flow** — demand book line item out of ERP → you allocate to a line and a week slot → mix, mill, tint, fill (tint \"barely there\" for a white) → QA hold → release, warehouse, ship against due date.\n\n**The line, both ways** — on the sheet, one row, one order occupies Line 2 mix-to-fill. Physically, separate kit with small holding tanks between, and the crew will start the next mix if there's tank room. Both recorded; neither averaged away.\n\n**Run times, clean of breakdowns** — white on Line 2: typical 8–9 h, bad-but-clean 9–10 h, good day ~6 h. Same order on Line 1: add 50–60%, so typical 13–14 h, best ~10 h. Tints: 8–10 h typical on *either* line, no big gap — which you flagged as unexplained and sheet-derived. The 12–13 h figure has been pulled out as breakdown, not run.\n\n**Filler jam** — every week or two; low once in three weeks, high twice a week. Repair typical 30–45 min, quick one-in-ten 10–15 min, bad one-in-ten 4–5 h, \"occasionally eating the rest of the shift.\"\n\n**Washdown** — tint-to-white, three hours, direction matters, plus ramp scrap you don't have numbers for.\n\n## Gaps, with where they'd come from\n- Stage-level rates per line — historian, never pulled apart.\n- Tank sizes, mill-to-fill on Line 1 — engineering drawings.\n- Jam repair times, properly — maintenance work orders in the CMMS.\n- Ramp scrap after washdown — you said it shouldn't be ignored; no source named yet.\n- Whether the tank matters differently by SKU — your own new thought, unexamined.\n- QA hold: \"a few hours for a white,\" and a longer \"specialty wait\" you mentioned but I never asked about.\n- How orders arrive into the demand book — never asked.\n- The \"who can absorb the slip\" rule — I have distributor-shrugs and prickly-account, not a rule I could apply without you.\n\n## Assumptions ledger\n1. That the four stages are the same four for every product — you said \"same four stages every product goes through,\" so this is yours, not mine, but it's load-bearing enough to re-check.\n2. Nothing else. Where I was tempted to fill in — jam rate before you gave it, washdown scrap, stage rates — it's in the gaps list instead.\n\nBoth objectives are still formally unsupported: I have the plant detail and the questions, but haven't yet wired which pieces each answer depends on tightly enough for the tooling. That plus the ramp scrap and the slip rule are what I'd open with next week.\n[user] Looks right — that's a fair record, and yeah, next week let's start with ramp scrap and the slip rule, since those feel like the ones I could actually go dig up or nail down between now and then. I'll ask maintenance for the CMMS numbers on the filler too while I'm at it. Go on, get to your huddle — wait, that's me. See you next week.\n\nJudge whether this range has settled. If it has, call brunch_sweep. Declining is legal; continue the interview when the topic is still open.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_direct_c3ViXzAxTTBYN0hSRzVCTlhCOERQMThGQlZaUFdR",
+        "role": "user",
+        "purpose": "user",
+        "display": "visible",
+        "submissionId": "sub_01M0X7HRG5BNXB8DP18FBVZPWQ",
+        "parts": [
+          {
+            "type": "text",
+            "text": "*[No response — this final message is addressed to the interviewer's own note-taking process, not to Marta. Staying in character as Marta, there is nothing here that calls for a reply; she has already left for the huddle.]*",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X7HYVCKNG7WPQ3SQTCKRNN",
+        "role": "assistant",
+        "purpose": "assistant",
+        "display": "visible",
+        "submissionId": "sub_01M0X7HRG5BNXB8DP18FBVZPWQ",
+        "turnId": "turn_01M0X7HRHNXMKH4B8VC1PGQNTZ",
+        "parts": [
+          {
+            "type": "reasoning",
+            "text": "No reply is needed here, so I'll just close things out simply without opening a new topic or asking anything.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Session closed. Nothing further pending on Marta's side.\n\nFinal state for the record: model at revision `26a8219a17118558` — 69 nodes, 267 active captures, not complete. Two objectives (held as five duplicate nodes), both formally unsupported. Deferrals carry deposits: CMMS for jam repair times, historian for stage rates, engineering drawings for tank sizes, Marta herself for ramp scrap and the slip rule. Assumption ledger holds one entry, flagged for re-check.\n\nI make no claim that this projects, compiles, or runs. Next session opens as review-and-revise on the objective nodes before any new elicitation.",
+            "state": "done"
+          },
+          {
+            "type": "reasoning",
+            "text": "This tail has no actual expert content to sweep — just a stage direction, not Marta's words about the plant. Declining seems right here; there's nothing capturable in this range anyway, so leaving it unswept is harmless.",
+            "state": "done"
+          },
+          {
+            "type": "text",
+            "text": "Declining this one.\n\nThe range contains no expert testimony. It is my own closing turn, my own sweep-judgment note, and my own state-of-the-model note, terminated by a stage direction confirming Marta has left and is not replying. The only entry in user position is that stage direction — narration about the interview, not Marta's words about her plant.\n\nSweeping it could only do one of two things: extract nothing, or extract something from a non-expert source. The second is the failure mode I've been guarding against all session — a model element with no expert span behind it. My own summary of the model is not evidence for the model; that would be assent taken as origin, with me on both sides of it.\n\nThe substantive content in that stretch — the CMMS follow-up, the ramp-scrap and slip-rule priority, Marta's confirmation of the read-back — was already swept from her actual message at revision `26a8219a17118558`. Nothing is at risk of being lost by leaving this tail unswept.\n\nThe swept high-water mark stays where it is. The session's durable record is complete as of that revision, and next session opens as review-and-revise on the duplicated objective nodes.",
+            "state": "done"
+          }
+        ]
+      },
+      {
+        "id": "entry_01M0X7J3K3R09V3EER3R7MQC0V",
+        "role": "system",
+        "purpose": "dispatch",
+        "display": "diagnostic",
+        "submissionId": "sub_01M0X7HRG5BNXB8DP18FBVZPWQ",
+        "signal": {
+          "tagName": "settlement-check"
+        },
+        "parts": [
+          {
+            "type": "text",
+            "text": "The harness computed this unswept conversation tail:\n\n[assistant] Enjoy the huddle.\n\nThree things I'll have ready for next week, so you don't have to hold them:\n\n1. **Ramp scrap and the slip rule** first, as you asked — for the slip rule I'll come at it through a case rather than a principle, so have in mind the last time you bumped someone's order and it turned out to be the wrong someone.\n2. **CMMS filler numbers** — when you get them, what I want is the same shape you gave me from memory: typical, bad one-in-ten, quick one-in-ten. If the work orders disagree with your 30–45 minutes, that disagreement is worth more to the model than either figure alone, so don't reconcile it before you bring it.\n3. **The tint parity puzzle** — that Line 1 and Line 2 run tints at nearly the same speed with no explanation. It's the loose thread most likely to be the same thing as your tank hunch, and I'd like to pull on it once the scrap and slip rule are in.\n\nNothing needs doing beyond that. See you next week.The tail has settled: the read-back was confirmed, the session closed, and the expert's last message adds content in their own words — what they'll dig up before next time and that they'll pull the CMMS numbers from maintenance. That belongs in the record as deferral deposits, not as agreement to my summary.\n\nOne caution I'll carry into the sweep: \"Looks right\" is assent to my phrasing, not origination. It closes nothing that wasn't already sourced to their words.Swept and folded — the session's record is durable. Since you've gone, this is a note-to-self for next week rather than anything you need to read now.\n\n**State of the model:** 69 nodes from 267 captures. Not complete, and two things about *how it's held* need fixing before more content goes in:\n\n1. **Objective duplication.** Your two questions have landed as five objective nodes — successive rephrasings of the same two (\"which option loses less\", \"which option actually loses less\", \"wait or shift when Line 2 goes down\" are one question; \"where Line 1 loses its time\" and \"is the mill-to-fill tank on Line 1 slowing the line down\" are the other). That's an artefact of my asking you to restate them, not a fact about your plant. Consolidating is a review-and-revise job, and it needs your word on which phrasing is yours, not my merge.\n\n2. **Nothing is wired to the objectives.** 53 of the 69 nodes sit outside every objective's dependency slice — recorded, but not demanded by anything. That's why the completion report keeps growing without the model getting more answerable. You *did* tell me what the disruption question hangs on: the run being protected, Line 1's state and family, the jam duration, the ramp scrap, and the bumped order's identity. I have those as prose in your answer; they aren't yet linked as dependencies. Doing that link properly is the first thing that makes any of the plant detail count.\n\n3. **Three open conflicts** on the filler jam node and the production-run node, where later answers superseded earlier ones — the 12–13 h that turned out to be breakdown, and the two jam descriptions. Those need your explicit word to close, not my inference about which you meant.\n\nSo next week's order: ramp scrap and the slip rule as you asked, then the objective wiring, then the conflict closes. The tint parity thread stays third.\n[non-user] The harness computed this unswept conversation tail:\n\n[non-user] The immediately preceding user message is mechanically bound as the reply to this pending affordance:\n\nThinking of the Line 2 filler specifically: roughly how often does it jam badly enough to stop the run — is that a once-a-week thing, a couple of times a month, once a quarter? Give me a low and high rather than one figure. And then, separately, when it does stop: how long is a typical repair, how long is the one-in-ten bad one, and how long is the one-in-ten quick one?\n[assistant] That bounce was my own phrase, not yours — \"jams badly enough to stop the run\" was my wording. Re-anchoring on what you actually said.Go — and yes, same time next week works. Here's where we got to, so you can correct anything when you're back at a desk. **The model is not finished and I'm not going to pretend it is; I wouldn't hand this to your tooling yet.**\n\n## What's on record, in your words\n\n**The two questions the model exists to answer**\n1. \"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"\n2. \"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"\n\n**What \"better\" means** — Meridian-style on-time is a hard line, \"not really a trade-off, that's a line I won't cross.\" Below that line you weigh washdown hours, whether the bumped order slides and by how much, and who the customer is. No formula; judgment on who can absorb the slip.\n\n**The flow** — demand book line item out of ERP → you allocate to a line and a week slot → mix, mill, tint, fill (tint \"barely there\" for a white) → QA hold → release, warehouse, ship against due date.\n\n**The line, both ways** — on the sheet, one row, one order occupies Line 2 mix-to-fill. Physically, separate kit with small holding tanks between, and the crew will start the next mix if there's tank room. Both recorded; neither averaged away.\n\n**Run times, clean of breakdowns** — white on Line 2: typical 8–9 h, bad-but-clean 9–10 h, good day ~6 h. Same order on Line 1: add 50–60%, so typical 13–14 h, best ~10 h. Tints: 8–10 h typical on *either* line, no big gap — which you flagged as unexplained and sheet-derived. The 12–13 h figure has been pulled out as breakdown, not run.\n\n**Filler jam** — every week or two; low once in three weeks, high twice a week. Repair typical 30–45 min, quick one-in-ten 10–15 min, bad one-in-ten 4–5 h, \"occasionally eating the rest of the shift.\"\n\n**Washdown** — tint-to-white, three hours, direction matters, plus ramp scrap you don't have numbers for.\n\n## Gaps, with where they'd come from\n- Stage-level rates per line — historian, never pulled apart.\n- Tank sizes, mill-to-fill on Line 1 — engineering drawings.\n- Jam repair times, properly — maintenance work orders in the CMMS.\n- Ramp scrap after washdown — you said it shouldn't be ignored; no source named yet.\n- Whether the tank matters differently by SKU — your own new thought, unexamined.\n- QA hold: \"a few hours for a white,\" and a longer \"specialty wait\" you mentioned but I never asked about.\n- How orders arrive into the demand book — never asked.\n- The \"who can absorb the slip\" rule — I have distributor-shrugs and prickly-account, not a rule I could apply without you.\n\n## Assumptions ledger\n1. That the four stages are the same four for every product — you said \"same four stages every product goes through,\" so this is yours, not mine, but it's load-bearing enough to re-check.\n2. Nothing else. Where I was tempted to fill in — jam rate before you gave it, washdown scrap, stage rates — it's in the gaps list instead.\n\nBoth objectives are still formally unsupported: I have the plant detail and the questions, but haven't yet wired which pieces each answer depends on tightly enough for the tooling. That plus the ramp scrap and the slip rule are what I'd open with next week.\n[user] Looks right — that's a fair record, and yeah, next week let's start with ramp scrap and the slip rule, since those feel like the ones I could actually go dig up or nail down between now and then. I'll ask maintenance for the CMMS numbers on the filler too while I'm at it. Go on, get to your huddle — wait, that's me. See you next week.\n\nJudge whether this range has settled. If it has, call brunch_sweep. Declining is legal; continue the interview when the topic is still open.\n[user] *[No response — this final message is addressed to the interviewer's own note-taking process, not to Marta. Staying in character as Marta, there is nothing here that calls for a reply; she has already left for the huddle.]*\n\nJudge whether this range has settled. If it has, call brunch_sweep. Declining is legal; continue the interview when the topic is still open.",
+            "state": "done"
+          }
+        ]
+      }
+    ],
+    "settlements": [
+      {
+        "submissionId": "sub_01M0X5XEJYQZ5ZBVWMDPKY2Q9T",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0X5XEJYQZ5ZBVWMDPKY2Q9T"
+      },
+      {
+        "submissionId": "sub_01M0X5XSXP0MK5YBNG911C3W1D",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0X5XSXP0MK5YBNG911C3W1D"
+      },
+      {
+        "submissionId": "sub_01M0X5Y87AS5RZE428EV0MW6D4",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0X5Y87AS5RZE428EV0MW6D4"
+      },
+      {
+        "submissionId": "sub_01M0X6267D8KT3M5AQ9A505Y8S",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0X6267D8KT3M5AQ9A505Y8S"
+      },
+      {
+        "submissionId": "sub_01M0X65ARARS7NTPXGE1GHQAKG",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0X65ARARS7NTPXGE1GHQAKG"
+      },
+      {
+        "submissionId": "sub_01M0X65VJMBBQAE3GGR7AVF2PM",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0X65VJMBBQAE3GGR7AVF2PM"
+      },
+      {
+        "submissionId": "sub_01M0X6K12Q1K9D3G60FBJW5GWR",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0X6K12Q1K9D3G60FBJW5GWR"
+      },
+      {
+        "submissionId": "sub_01M0X6QCS99QQY0E2CAE391TX2",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0X6QCS99QQY0E2CAE391TX2"
+      },
+      {
+        "submissionId": "sub_01M0X6WZ30XA35YR6J5T6HFMBN",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0X6WZ30XA35YR6J5T6HFMBN"
+      },
+      {
+        "submissionId": "sub_01M0X71YK52Q1E7R6YXV4RFZKS",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0X71YK52Q1E7R6YXV4RFZKS"
+      },
+      {
+        "submissionId": "sub_01M0X7CEDCMQKDZJ33213XS1E0",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0X7CEDCMQKDZJ33213XS1E0"
+      },
+      {
+        "submissionId": "sub_01M0X7HRG5BNXB8DP18FBVZPWQ",
+        "outcome": "completed",
+        "answeredBySubmissionId": "sub_01M0X7HRG5BNXB8DP18FBVZPWQ"
+      }
+    ],
+    "incarnation": "inc_01M0X5XEJYXDCKKMY6DCFTQ7AX"
+  },
+  "store": {
+    "captures": [
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option actually loses less",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Stated as the decision the model must settle: given a line-down event with unknown ETA, which of the available scheduling options loses less.",
+            "assertion": {
+              "value": "When a line goes down with ETA unknown, be able to enter that state and have the model say which option — wait out the repair, or move the order to the other line — actually loses less, instead of the scheduler doing gut math at the huddle."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a6ad400e-463a-4e08-80e5-1b5448355f62",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"When a line goes down with ETA unknown, be able to enter that state and have the model say which option — wait out the repair, or move the order to the other line — actually loses less, instead of the scheduler doing gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the decision the model must settle: given a line-down event with unknown ETA, which of the available scheduling options loses less.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option actually loses less",
+            "slot": "what \"better\" means, and trade-off weights",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Expert gave a lexicographic scorecard with an explicit refusal of a formula for the second tier.",
+            "assertion": {
+              "value": "First and non-negotiable: days late on the Meridian order, where anything above zero is bad. Below that, weighed together with no formula: washdown hours, and whether the bumped order goes late and by how much — with judgment applied to who the customer is and who can absorb the slip (a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem)."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-76159984-4b11-446f-a707-bc8302ef0b1d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First and non-negotiable: days late on the Meridian order, where anything above zero is bad. Below that, weighed together with no formula: washdown hours, and whether the bumped order goes late and by how much — with judgment applied to who the customer is and who can absorb the slip (a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem).\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Expert gave a lexicographic scorecard with an explicit refusal of a formula for the second tier.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option actually loses less",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "The scorecard names the washdown, the line-down event, and the orders with their due dates and customers as what the answer is computed from.",
+            "assertion": {
+              "value": [
+                "activity:tint-to-white washdown",
+                "activity:Line 2 filler jam",
+                "entity-type:order",
+                "entity-type:line"
+              ]
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-3f2444d5-8001-46d9-8a92-c85f8c6f8d6a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:tint-to-white washdown\",\"activity:Line 2 filler jam\",\"entity-type:order\",\"entity-type:line\"]},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard names the washdown, the line-down event, and the orders with their due dates and customers as what the answer is computed from.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "how long it takes",
+            "precision": "number",
+            "sourceRegime": "practiced",
+            "rationale": "Expert gave a single figure, not a spread; the low/high and typical are not yet on record.",
+            "assertion": {
+              "value": "three hours"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-b42a88f7-65b8-4f76-833d-18f39111ec49",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"three hours\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Expert gave a single figure, not a spread; the low/high and typical are not yet on record.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Expert stated the outcome as consuming crew time and blocking the line for the window.",
+            "assertion": {
+              "value": "Consumes crew time and takes Line 1 out of anything else for that window; afterwards the line is in white rather than tint."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-053410a5-6574-4355-aabf-dd972f0088e1",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Consumes crew time and takes Line 1 out of anything else for that window; afterwards the line is in white rather than tint.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Expert stated the outcome as consuming crew time and blocking the line for the window.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Stated as the consequence of pulling a line off a tint run to run a white order; the full precondition list was not elicited.",
+            "assertion": {
+              "value": "A line currently running a tint that is to be switched to a white order — pulling Line 1 off its tint run to cover Meridian white incurs the washdown."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-e86ee1d3-dbbd-4e2d-b1c0-a8ac719f0e58",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line currently running a tint that is to be switched to a white order — pulling Line 1 off its tint run to cover Meridian white incurs the washdown.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the consequence of pulling a line off a tint run to run a white order; the full precondition list was not elicited.\",\"slot\":\"what it needs before it can start\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what is lost when it changes the system's mode",
+            "precision": "number",
+            "sourceRegime": "practiced",
+            "rationale": "Loss named for the tint-to-white transition specifically, as a single figure plus crew time; other transitions were not yet asked about.",
+            "assertion": {
+              "value": "Three hours of the line plus crew time for the tint-to-white transition; the bumped order may itself go late as a knock-on."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-04d27279-48f8-437e-8688-14c400f3f0f1",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of the line plus crew time for the tint-to-white transition; the bumped order may itself go late as a knock-on.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Loss named for the tint-to-white transition specifically, as a single figure plus crew time; other transitions were not yet asked about.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "Line 2 filler jam",
+            "slot": "how long it takes",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Expert described two kinds of repair — half an hour and half a shift — and one observed instance of about two hours; quantiles not yet elicited.",
+            "assertion": {
+              "value": "Repairs come in a \"half hour\" kind and a \"half a shift\" kind; the recent instance came back in about two hours."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I went with waiting, it came back in about two hours, we just scraped the Thursday due date.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-7d1cb932-a1d6-4e1a-86a7-984a9d53af80",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Repairs come in a \\\"half hour\\\" kind and a \\\"half a shift\\\" kind; the recent instance came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"Line 2 filler jam\",\"precision\":\"range\",\"rationale\":\"Expert described two kinds of repair — half an hour and half a shift — and one observed instance of about two hours; quantiles not yet elicited.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours, we just scraped the Thursday due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "Line 2 filler jam",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The event takes the line out of production and puts the order sitting on it at risk, forcing a wait-or-move decision.",
+            "assertion": {
+              "value": "Line 2 stops producing until repaired (half a shift lost in the recent case); the order sitting on Line 2 is at risk of its due date, forcing a decision to wait out the repair or shift the order to Line 1."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-330b99df-25fc-4d38-b1f9-6f8da955b79e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 2 stops producing until repaired (half a shift lost in the recent case); the order sitting on Line 2 is at risk of its due date, forcing a decision to wait out the repair or shift the order to Line 1.\"},\"kind\":\"activity\",\"node\":\"Line 2 filler jam\",\"precision\":\"spelled out\",\"rationale\":\"The event takes the line out of production and puts the order sitting on it at risk, forcing a wait-or-move decision.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2, and I had to decide right then whether to shift it to Line 1 or just wait out the repair.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "Meridian ships on time, full stop",
+            "slot": "the rule as actually practiced",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Stated as an absolute the scheduler protects ahead of all other considerations.",
+            "assertion": {
+              "value": "The Meridian order ships on time, full stop; it is not traded off against washdown hours or other orders' due dates."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-caeeeb12-a91f-46a0-88c2-a622d4d30c55",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The Meridian order ships on time, full stop; it is not traded off against washdown hours or other orders' due dates.\"},\"kind\":\"policy\",\"node\":\"Meridian ships on time, full stop\",\"precision\":\"spelled out\",\"rationale\":\"Stated as an absolute the scheduler protects ahead of all other considerations.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "Meridian ships on time, full stop",
+            "slot": "what overrides it",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Expert named the sole override in general terms; the practiced test for \"no way through\" is not yet on record.",
+            "assertion": {
+              "value": "Only when there is truly no way through; otherwise nothing overrides it."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "that's a line I won't cross unless there's truly no way through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I use judgment on who can absorb the slip",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-422d7f74-a119-45d6-8261-3c71b50af7f7",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Only when there is truly no way through; otherwise nothing overrides it.\"},\"kind\":\"policy\",\"node\":\"Meridian ships on time, full stop\",\"precision\":\"spelled out\",\"rationale\":\"Expert named the sole override in general terms; the practiced test for \\\"no way through\\\" is not yet on record.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Orders are treated apart by colour class (white vs tint, which drives washdown) and by customer class (distributor / small account / awkward account that gets prickly).",
+            "assertion": {
+              "value": "Orders differ by colour class — white versus tint, which decides whether a washdown is incurred — and by customer, sorted into a distributor (sliding two days is a shrug), a small account (sliding a week is fine), and an awkward account that gets prickly."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "We had a Meridian white order due Thursday sitting on Line 2",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-f2a03b6c-0420-48a7-85be-bdcb3536a6f7",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders differ by colour class — white versus tint, which decides whether a washdown is incurred — and by customer, sorted into a distributor (sliding two days is a shrug), a small account (sliding a week is fine), and an awkward account that gets prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Orders are treated apart by colour class (white vs tint, which drives washdown) and by customer class (distributor / small account / awkward account that gets prickly).\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer, because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "state that rides along with each instance",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Each order is spoken of as carrying a due date, a customer, a colour, and the line it is sitting on.",
+            "assertion": {
+              "value": "Its due date (e.g. due Thursday), its customer (e.g. Meridian), its colour (white or tint), and which line it is sitting on."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "We had a Meridian white order due Thursday sitting on Line 2",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "does it slide past its own due date, and if so by how much and who's the customer",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-c9ac976a-3eef-4a77-8e29-3598b184b450",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Its due date (e.g. due Thursday), its customer (e.g. Meridian), its colour (white or tint), and which line it is sitting on.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Each order is spoken of as carrying a due date, a customer, a colour, and the line it is sitting on.\",\"slot\":\"state that rides along with each instance\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "line",
+            "slot": "how many there are, or the population's shape",
+            "precision": "named",
+            "sourceRegime": "practiced",
+            "rationale": "Line 1 and Line 2 named; whether these are the only lines has not been asked.",
+            "assertion": {
+              "value": "Line 1 and Line 2 named so far; total count not yet confirmed."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-6bc324a5-2e12-4070-8275-fdfe819923e6",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2 named so far; total count not yet confirmed.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"named\",\"rationale\":\"Line 1 and Line 2 named; whether these are the only lines has not been asked.\",\"slot\":\"how many there are, or the population's shape\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "line",
+            "slot": "state that rides along with each instance",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "A line is spoken of as carrying what it is currently running (its colour state) and whether it is down.",
+            "assertion": {
+              "value": "What it is currently running — e.g. mid-run on a tint, which sets the colour it would have to be washed down from — and whether it is jammed/down awaiting repair."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 1 was mid-run on a tint.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Line 2 filler jammed at about nine in the morning",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-b003fc51-0ade-4721-b400-b7b68edf8c60",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"What it is currently running — e.g. mid-run on a tint, which sets the colour it would have to be washed down from — and whether it is jammed/down awaiting repair.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"spelled out\",\"rationale\":\"A line is spoken of as carrying what it is currently running (its colour state) and whether it is down.\",\"slot\":\"state that rides along with each instance\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option loses less",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "rationale": "Stated as the concrete decision support the model must give, anchored to the Line 2 filler jam incident.",
+            "assertion": {
+              "value": "Given a disruption in progress (e.g. \"filler's down, ETA unknown\"), which of the available scheduling options — wait out the repair on the down line, or move the order to another line — actually loses less, decided in the moment instead of by gut math at the huddle."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a0a0bd7a-32fe-47e3-a2f4-8a452fe769bc",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given a disruption in progress (e.g. \\\"filler's down, ETA unknown\\\"), which of the available scheduling options — wait out the repair on the down line, or move the order to another line — actually loses less, decided in the moment instead of by gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the concrete decision support the model must give, anchored to the Line 2 filler jam incident.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option loses less",
+            "slot": "what \"better\" means, and trade-off weights",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Expert explicitly denies having a weighting formula; the ordering is stated, the weights are not.",
+            "assertion": {
+              "value": "Lexicographic: first, days late on the hard-line order (Meridian) — yes/no, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much, and who the customer is. No formula for the second-order trade-off — \"how bad is bad\", judged by who can absorb the slip."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-de512bde-aa52-4147-933f-81439aa5ec6d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lexicographic: first, days late on the hard-line order (Meridian) — yes/no, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much, and who the customer is. No formula for the second-order trade-off — \\\"how bad is bad\\\", judged by who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"Expert explicitly denies having a weighting formula; the ordering is stated, the weights are not.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option loses less",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "The scorecard names on-time delivery, washdown hours, lateness of the bumped order, and the repair outcome; the judgment of who can absorb a slip is the tiebreaker.",
+            "assertion": {
+              "value": [
+                "constraint:Meridian on time",
+                "activity:tint-to-white washdown",
+                "activity:filler jam",
+                "entity-type:order",
+                "entity-type:line",
+                "policy:who can absorb the slip"
+              ]
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a6e8dc50-fffb-494d-8bd2-59704c0427e4",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"constraint:Meridian on time\",\"activity:tint-to-white washdown\",\"activity:filler jam\",\"entity-type:order\",\"entity-type:line\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard names on-time delivery, washdown hours, lateness of the bumped order, and the repair outcome; the judgment of who can absorb a slip is the tiebreaker.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late. If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "rationale": "Colour class changes the process at the tint stage; customer type changes how lateness is weighed.",
+            "assertion": {
+              "value": "An order is a line item in the demand book from ERP. Treated apart by: product colour class — white (tint stage is barely there, a pass-through rather than a real letdown step) versus tint/specialty; and by customer type — distributor (a two-day slide is a shrug), small account (a week is fine), and awkward accounts that get prickly."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-3cb49f42-f479-4b67-be4c-22c8f9771f6e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order is a line item in the demand book from ERP. Treated apart by: product colour class — white (tint stage is barely there, a pass-through rather than a real letdown step) versus tint/specialty; and by customer type — distributor (a two-day slide is a shrug), small account (a week is fine), and awkward accounts that get prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Colour class changes the process at the tint stage; customer type changes how lateness is weighed.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"because a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "state that rides along with each instance",
+            "precision": "spelled out",
+            "rationale": "Named directly as what the demand-book line item carries, extended by the allocation step and the account-based lateness judgment.",
+            "assertion": {
+              "value": "Quantity, due date, SKU; plus the line and week-slot it has been allocated to on the sheet; plus the customer/account it belongs to."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-5628ca29-5985-4005-aa3f-a6885dc38223",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; plus the line and week-slot it has been allocated to on the sheet; plus the customer/account it belongs to.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Named directly as what the demand-book line item carries, extended by the allocation step and the account-based lateness judgment.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "line",
+            "slot": "the distinctions the process treats apart",
+            "precision": "named",
+            "rationale": "Lines are contended for between orders in the decision described.",
+            "assertion": {
+              "value": "Production lines, referred to individually as Line 1 and Line 2; an order is allocated to a specific line and a line can be mid-run on another order."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-6d4d1074-f6fe-4d4c-95c2-f242a6f98233",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Production lines, referred to individually as Line 1 and Line 2; an order is allocated to a specific line and a line can be mid-run on another order.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"named\",\"rationale\":\"Lines are contended for between orders in the decision described.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had to decide right then whether to shift it to Line 1 or just wait out the repair. Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "line",
+            "slot": "how many there are, or the population's shape",
+            "precision": "named",
+            "rationale": "Only the two lines involved in the incident were named; the plant's full line count was never asked.",
+            "assertion": {
+              "value": "At least two lines named: Line 1 and Line 2. Total line count not stated."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "whether to shift it to Line 1 or just wait out the repair",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "We had a Meridian white order due Thursday sitting on Line 2",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a0b65576-83d8-4134-9fbe-9b059663ae12",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"At least two lines named: Line 1 and Line 2. Total line count not stated.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"named\",\"rationale\":\"Only the two lines involved in the incident were named; the plant's full line count was never asked.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"We had a Meridian white order due Thursday sitting on Line 2\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whether to shift it to Line 1 or just wait out the repair\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "order flow from demand book to shipment",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "rationale": "Given verbatim as the end-to-end sequence for the Meridian white order.",
+            "assertion": {
+              "value": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (fill and pack) → QA hold → release and ship. Four steps if QA and shipping are counted as one, five if split."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-cbe1db57-3beb-4e48-9ef4-d81d638fa94a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (fill and pack) → QA hold → release and ship. Four steps if QA and shipping are counted as one, five if split.\"},\"kind\":\"ordering/flow\",\"node\":\"order flow from demand book to shipment\",\"precision\":\"spelled out\",\"rationale\":\"Given verbatim as the end-to-end sequence for the Meridian white order.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "Stated as the trigger for the order becoming something to schedule.",
+            "assertion": {
+              "value": "A line item in the demand book, produced by ERP, carrying quantity, due date and SKU."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-ee57e45e-a166-490d-ac0c-f5f2ea8c2ded",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book, produced by ERP, carrying quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the trigger for the order becoming something to schedule.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Directly stated as the outcome of step one.",
+            "assertion": {
+              "value": "The order is slotted onto a specific line and a slot in the week, on the sheet."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "allocate it onto a line and a slot in the week",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-fa56fa8b-611a-4a38-9a42-1bd038e52d80",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a specific line and a slot in the week, on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Directly stated as the outcome of step one.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "First person throughout; role stated at the outset.",
+            "assertion": {
+              "value": "The master scheduler (the expert), working on the sheet."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I'm the master scheduler at a coatings plant.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 1,
+              "entryEnd": 1
+            },
+            "source": "user"
+          },
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-dba4ec08-0265-420c-95d2-4dce250ae0b6",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler (the expert), working on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"named\",\"rationale\":\"First person throughout; role stated at the outset.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm the master scheduler at a coatings plant.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":1,\\\"entryStart\\\":1,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "mix/mill/tint/fill",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Stated as the production step common to all products.",
+            "assertion": {
+              "value": "Runs the order through four stages every product goes through — mix, mill, tint, fill and pack — producing filled and packed product that comes off the fill line."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-0b2046b4-55c8-4ce3-abac-296d6abe469d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Runs the order through four stages every product goes through — mix, mill, tint, fill and pack — producing filled and packed product that comes off the fill line.\"},\"kind\":\"activity\",\"node\":\"mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the production step common to all products.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "mix/mill/tint/fill",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "rationale": "Explicit type-dependence at the tint stage; stage durations themselves not yet given.",
+            "assertion": {
+              "value": "Yes — the stages are the same for every product, but for a white the tint stage is barely there, a pass-through rather than a real letdown step."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-8156b872-b3c2-43db-aa67-56166bebe556",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — the stages are the same for every product, but for a white the tint stage is barely there, a pass-through rather than a real letdown step.\"},\"kind\":\"activity\",\"node\":\"mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Explicit type-dependence at the tint stage; stage durations themselves not yet given.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "Stated as the precondition and the waiting arrangement.",
+            "assertion": {
+              "value": "The order has come off the fill line; it then sits in the lab's queue awaiting check."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-585f76f6-e841-4ef2-94df-036e711ebce8",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order has come off the fill line; it then sits in the lab's queue awaiting check.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Stated as the precondition and the waiting arrangement.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Release is the stated outcome of the QA hold.",
+            "assertion": {
+              "value": "The order is checked and then released, after which it goes to the warehouse and ships against the due date."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "sits in the lab's queue, gets checked",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-589bc2db-8fc9-4d65-8024-b34ce4cd736a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is checked and then released, after which it goes to the warehouse and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"Release is the stated outcome of the QA hold.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "Named as the owner of the queue and the check.",
+            "assertion": {
+              "value": "The lab."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "sits in the lab's queue, gets checked",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-07de77cc-9de8-41e9-92f6-8fe06a6263c9",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Named as the owner of the queue and the check.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "how long it takes",
+            "precision": "named",
+            "rationale": "Hedged quantifier only; not yet a usable spread.",
+            "assertion": {
+              "value": "Usually a few hours for a white; longer for specialty (\"nothing like the specialty wait\"). No figures for typical, one-in-ten worse or one-in-ten better yet."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-6ca0ba27-000e-4cbd-ae25-39dc7a1c679c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; longer for specialty (\\\"nothing like the specialty wait\\\"). No figures for typical, one-in-ten worse or one-in-ten better yet.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Hedged quantifier only; not yet a usable spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "rationale": "Type dependence stated explicitly in the same breath as the duration.",
+            "assertion": {
+              "value": "Yes — a white is usually a few hours, specialty waits are much longer."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-22890cbe-8720-408f-a3c9-fcbfe3826f2b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a white is usually a few hours, specialty waits are much longer.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Type dependence stated explicitly in the same breath as the duration.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "release and ship",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Final step of the walkthrough; due date is the reference for the objective's lateness metric.",
+            "assertion": {
+              "value": "The released order goes to the warehouse and ships against its due date; lateness is measured as days late against that due date."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-551ab6a6-2f47-4514-ad0b-f5995ef609b2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The released order goes to the warehouse and ships against its due date; lateness is measured as days late against that due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"rationale\":\"Final step of the walkthrough; due date is the reference for the objective's lateness metric.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "Named as the changeover that the tint→white switch forces.",
+            "assertion": {
+              "value": "A line changing over from a tint run to a white run; the line must be pulled off the tint it is mid-run on."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-7df09f81-9c85-43ac-b69e-306d540f8afb",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line changing over from a tint run to a white run; the line must be pulled off the tint it is mid-run on.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Named as the changeover that the tint→white switch forces.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "how long it takes",
+            "precision": "number",
+            "rationale": "A single figure was given, not a spread; recorded at the precision actually reached.",
+            "assertion": {
+              "value": "Three hours (tint-to-white)."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I eat a tint-to-white washdown — three hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-e0f39723-a7e5-4656-a8fb-0e2b50bb82da",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours (tint-to-white).\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"A single figure was given, not a spread; recorded at the precision actually reached.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what is lost when it changes the system's mode",
+            "precision": "number",
+            "rationale": "Loss named for a specific named transition (tint to white); only one figure given.",
+            "assertion": {
+              "value": "Three hours of the line's availability — real cost and crew time — during which the line is out of anything else."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-d8dffb0f-f148-4af2-ba7e-478a6a1b38c6",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of the line's availability — real cost and crew time — during which the line is out of anything else.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Loss named for a specific named transition (tint to white); only one figure given.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Effect on line availability stated directly.",
+            "assertion": {
+              "value": "Puts the line into a state able to run white; the line is unavailable for any other work for the duration."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it takes Line 1 out of anything else for that window",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a2938097-b902-4f24-8e15-70f4b8ce95fb",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Puts the line into a state able to run white; the line is unavailable for any other work for the duration.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Effect on line availability stated directly.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Described as the disruption that forces the scheduling decision.",
+            "assertion": {
+              "value": "The line's filler goes down, stopping the order sitting on that line until the repair completes; the scheduler must then decide to wait it out or shift the order to another line."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I went with waiting, it came back in about two hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-896881a6-c9ec-469f-ab03-4a56b59f6cad",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line's filler goes down, stopping the order sitting on that line until the repair completes; the scheduler must then decide to wait it out or shift the order to another line.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"Described as the disruption that forces the scheduling decision.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "how long it takes",
+            "precision": "range",
+            "rationale": "Two kinds named as the ends plus one observed instance; no typical or one-in-ten figures given, so this is a range, not a spread.",
+            "assertion": {
+              "value": "From about half an hour (\"the 'half hour' kind\") to about half a shift (\"the 'half a shift' kind\"); the recent instance came back in about two hours."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "it came back in about two hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-4a3ae53c-2c2f-4664-9499-7e81c254abc5",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"From about half an hour (\\\"the 'half hour' kind\\\") to about half a shift (\\\"the 'half a shift' kind\\\"); the recent instance came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Two kinds named as the ends plus one observed instance; no typical or one-in-ten figures given, so this is a range, not a spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "how often it occurs, if it is an event rather than a step",
+            "precision": "named",
+            "rationale": "One occurrence recounted; frequency never stated.",
+            "assertion": {
+              "absence": "unknown-to-user",
+              "pointer": "rate of filler jams not yet asked or given"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I'd love to type in \"filler's down, ETA unknown\"",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-d662739b-76f0-429a-829a-ccb79763b6b9",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"rate of filler jams not yet asked or given\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"named\",\"rationale\":\"One occurrence recounted; frequency never stated.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "constraint",
+            "node": "Meridian on time",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Stated as non-negotiable with a named consequence.",
+            "assertion": {
+              "value": "The hard-line customer's order must ship on or before its due date — days late must be zero. The line is not crossed unless there is truly no way through; if it is crossed, the scheduler has to go explain it."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "anything above zero is bad news I have to go explain",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a9e42aa6-8d30-4ded-a8c4-f24220cfb292",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The hard-line customer's order must ship on or before its due date — days late must be zero. The line is not crossed unless there is truly no way through; if it is crossed, the scheduler has to go explain it.\"},\"kind\":\"constraint\",\"node\":\"Meridian on time\",\"precision\":\"spelled out\",\"rationale\":\"Stated as non-negotiable with a named consequence.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "who can absorb the slip",
+            "slot": "the rule as actually practiced",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Given as the practiced basis for weighing knock-on lateness.",
+            "assertion": {
+              "value": "When deciding which order to bump, judge by who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem to solve the first. Applied by judgment, with no formula."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I use judgment on who can absorb the slip",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-b2c62684-e1ee-4d7f-b616-0ceb17a7282e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"When deciding which order to bump, judge by who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem to solve the first. Applied by judgment, with no formula.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"Given as the practiced basis for weighing knock-on lateness.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option actually loses less",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The expert states the model's job as evaluating a disruption response option set.",
+            "assertion": {
+              "value": "Given a disruption such as \"filler's down, ETA unknown\", tell me which option (switch the order to the other line, or wait out the repair) actually loses less — instead of gut math at the huddle."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-1cb33f48-6553-4e4f-a8a0-37d7631b08ea",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given a disruption such as \\\"filler's down, ETA unknown\\\", tell me which option (switch the order to the other line, or wait out the repair) actually loses less — instead of gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"The expert states the model's job as evaluating a disruption response option set.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option actually loses less",
+            "slot": "what \"better\" means, and trade-off weights",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Lexicographic scorecard given in words; the expert explicitly denies having numeric weights.",
+            "assertion": {
+              "value": "First and hard: days late on the Meridian-style order, anything above zero is bad. Underneath and traded off by judgement, not formula: washdown hours (crew time plus the line taken out of anything else), and whether the bumped order goes late and by how much and for which customer. No formula for the second-order weighting."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "days late on Meridian, and anything above zero is bad news",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I don't have a formula for it.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-f073c3ed-2a89-4499-b3b2-fe160e8c1057",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First and hard: days late on the Meridian-style order, anything above zero is bad. Underneath and traded off by judgement, not formula: washdown hours (crew time plus the line taken out of anything else), and whether the bumped order goes late and by how much and for which customer. No formula for the second-order weighting.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Lexicographic scorecard given in words; the expert explicitly denies having numeric weights.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"days late on Meridian, and anything above zero is bad news\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option actually loses less",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "The options the expert weighed name these nodes directly.",
+            "assertion": {
+              "value": "activity:filler jam; activity:tint-to-white washdown; entity-type:order; entity-type:line (Line 1 / Line 2); ordering/flow:order flow, allocate to ship; policy:Meridian on time; policy:who can absorb the slip"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-c9864a2c-cbb3-41c9-97a6-e44cc1d7d424",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"activity:filler jam; activity:tint-to-white washdown; entity-type:order; entity-type:line (Line 1 / Line 2); ordering/flow:order flow, allocate to ship; policy:Meridian on time; policy:who can absorb the slip\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"named\",\"rationale\":\"The options the expert weighed name these nodes directly.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "where Line 1 loses its time",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Second objective the expert put explicitly in scope.",
+            "assertion": {
+              "value": "Show where Line 1 loses its time — specifically whether the small tank between mill and fill is actually costing us — as evidence to take to engineering rather than a hunch."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I could take that to engineering with something other than a hunch",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-480c2821-4d80-495b-a652-f5de8b035144",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Show where Line 1 loses its time — specifically whether the small tank between mill and fill is actually costing us — as evidence to take to engineering rather than a hunch.\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"spelled out\",\"rationale\":\"Second objective the expert put explicitly in scope.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I could take that to engineering with something other than a hunch\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "where Line 1 loses its time",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "The tank hunch is about these nodes.",
+            "assertion": {
+              "value": "constraint:small holding tanks between stages; entity-type:stage kit (mix, mill, tint, fill); ordering/flow:stage overlap on a line; constraint:published line rate"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-f3f2c366-eab0-49fa-951c-773f77aa11b2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"constraint:small holding tanks between stages; entity-type:stage kit (mix, mill, tint, fill); ordering/flow:stage overlap on a line; constraint:published line rate\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"named\",\"rationale\":\"The tank hunch is about these nodes.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "rationale": "Distinctions the expert's process treats differently: product class (white vs tint vs specialty) and customer account type.",
+            "assertion": {
+              "value": "An order is a line item in the demand book (quantity, due date, SKU). Whites differ from tints (tint stage is a pass-through for a white; a tint-to-white change costs a washdown) and from specialties (QA wait much longer). Customers differ: distributor, small account, and \"awkward\" accounts that get prickly."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-3bb35fb7-3954-45d4-839f-20ee46a8c052",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order is a line item in the demand book (quantity, due date, SKU). Whites differ from tints (tint stage is a pass-through for a white; a tint-to-white change costs a washdown) and from specialties (QA wait much longer). Customers differ: distributor, small account, and \\\"awkward\\\" accounts that get prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Distinctions the expert's process treats differently: product class (white vs tint vs specialty) and customer account type.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "state that rides along with each instance",
+            "precision": "spelled out",
+            "rationale": "Attributes named on the order.",
+            "assertion": {
+              "value": "Quantity, due date, SKU; the line and slot in the week it is allocated to; the customer; and days late against its due date."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-e552ac87-8cfa-4091-a262-6fba33ab9f83",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; the line and slot in the week it is allocated to; the customer; and days late against its due date.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Attributes named on the order.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "line (Line 1 / Line 2)",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "sourceRegime": "prescribed",
+            "rationale": "The scheduling sheet's view of a line as a single indivisible resource.",
+            "assertion": {
+              "value": "On the sheet a line is one row, one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it's done."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-c74bc46d-649f-4e44-a48d-3a005dc44a7e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet a line is one row, one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it's done.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"spelled out\",\"rationale\":\"The scheduling sheet's view of a line as a single indivisible resource.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "line (Line 1 / Line 2)",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Physical reality diverges from the sheet; both recorded on the same node.",
+            "assertion": {
+              "value": "Physically a line is not one thing: mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-dd037a1c-63c0-47b8-8886-81c6d1f70226",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically a line is not one thing: mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"spelled out\",\"rationale\":\"Physical reality diverges from the sheet; both recorded on the same node.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "line (Line 1 / Line 2)",
+            "slot": "how many there are, or the population's shape",
+            "precision": "named",
+            "rationale": "Only Line 1 and Line 2 are named; no count was stated.",
+            "assertion": {
+              "value": "Line 1 and Line 2 are the lines named; no total count stated."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "whether to shift it to Line 1 or just wait out the repair",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "especially the one between mill and fill on Line 1",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-6c46c958-82b9-4ba0-bf0f-363fd70b6dbc",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2 are the lines named; no total count stated.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"named\",\"rationale\":\"Only Line 1 and Line 2 are named; no count was stated.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whether to shift it to Line 1 or just wait out the repair\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "stage kit (mix, mill, tint, fill)",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Each stage is separately contended kit.",
+            "assertion": {
+              "value": "Four separate pieces of kit per line — mixer, mill, tint, fill head — each usable independently, with small holding tanks buffering between mix/mill and mill/fill."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the mixer could be starting the next order's batch while the fill head is still finishing the last one",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-ee4eb482-b4b3-4392-94d7-ef9dc0a6ca98",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Four separate pieces of kit per line — mixer, mill, tint, fill head — each usable independently, with small holding tanks buffering between mix/mill and mill/fill.\"},\"kind\":\"entity-type\",\"node\":\"stage kit (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"rationale\":\"Each stage is separately contended kit.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the mixer could be starting the next order's batch while the fill head is still finishing the last one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "boundary-condition",
+            "node": "demand book from ERP",
+            "slot": "the arrival or availability pattern",
+            "precision": "named",
+            "rationale": "Arrival source named; no rate or shape given yet, so precision is only 'named'.",
+            "assertion": {
+              "value": "Orders arrive as line items in the demand book when ERP spits it out, each with quantity, due date and SKU."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-dd78828b-9d4f-47cd-bad8-90eae84bc4ae",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders arrive as line items in the demand book when ERP spits it out, each with quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"named\",\"rationale\":\"Arrival source named; no rate or shape given yet, so precision is only 'named'.\",\"slot\":\"the arrival or availability pattern\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Output of the allocation step.",
+            "assertion": {
+              "value": "The order is placed onto a line and a slot in the week on the sheet."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "allocate it onto a line and a slot in the week",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-32521b14-4f1e-41ff-ab95-dfc11d8eee37",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is placed onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Output of the allocation step.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "Precondition named.",
+            "assertion": {
+              "value": "A line item in the demand book from ERP, with quantity, due date and SKU."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-711c9600-2f30-4e86-95a2-cc373696e94c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book from ERP, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Precondition named.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "The expert performs it himself.",
+            "assertion": {
+              "value": "The master scheduler (the expert), on the sheet."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-c1704cba-8451-47a5-add8-2e388b330a1f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler (the expert), on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"named\",\"rationale\":\"The expert performs it himself.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run the batch (mix/mill/tint/fill)",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "The production run through the four stages.",
+            "assertion": {
+              "value": "The order is produced through the same four stages every product goes through — mix, mill, tint, fill and pack — and comes off the fill line."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-68ab39e5-8046-4f93-887e-11ed3e3b1da3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is produced through the same four stages every product goes through — mix, mill, tint, fill and pack — and comes off the fill line.\"},\"kind\":\"activity\",\"node\":\"run the batch (mix/mill/tint/fill)\",\"precision\":\"spelled out\",\"rationale\":\"The production run through the four stages.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run the batch (mix/mill/tint/fill)",
+            "slot": "how long it takes",
+            "rationale": "The expert says the end-to-end batch time per SKU per line exists on his sheet but gave no figures in this range.",
+            "assertion": {
+              "absence": "deferred",
+              "pointer": "the expert's scheduling sheet (roughly how long a batch of a given SKU takes end to end on each line)"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-c6d485c6-0e21-4cc0-b626-9091448d6ba1",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the expert's scheduling sheet (roughly how long a batch of a given SKU takes end to end on each line)\"},\"kind\":\"activity\",\"node\":\"run the batch (mix/mill/tint/fill)\",\"rationale\":\"The expert says the end-to-end batch time per SKU per line exists on his sheet but gave no figures in this range.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run the batch (mix/mill/tint/fill)",
+            "slot": "whether its quantities vary by type",
+            "rationale": "Stage-by-stage durations are not held by the expert; he names the historian as the source.",
+            "assertion": {
+              "absence": "deferred",
+              "pointer": "the historian (stage-by-stage times: how long does mixing take, how long does milling take)"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-663aaa9f-2bcb-4e01-937f-9d16ce860e80",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the historian (stage-by-stage times: how long does mixing take, how long does milling take)\"},\"kind\":\"activity\",\"node\":\"run the batch (mix/mill/tint/fill)\",\"rationale\":\"Stage-by-stage durations are not held by the expert; he names the historian as the source.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint stage",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "rationale": "Explicit variation by product type.",
+            "assertion": {
+              "value": "Yes — for a white the tint stage is barely there, more of a pass-through than a real letdown step."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-737200bb-8f75-455f-b90a-3363a30d5fce",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — for a white the tint stage is barely there, more of a pass-through than a real letdown step.\"},\"kind\":\"activity\",\"node\":\"tint stage\",\"precision\":\"named\",\"rationale\":\"Explicit variation by product type.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "how long it takes",
+            "precision": "named",
+            "rationale": "Vague quantity as given — 'usually a few hours for a white'; not yet a spread.",
+            "assertion": {
+              "value": "Usually a few hours for a white; the specialty wait is much longer (figure not given)."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-78203b7c-8e00-469c-9d53-01d1a656d5c1",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; the specialty wait is much longer (figure not given).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Vague quantity as given — 'usually a few hours for a white'; not yet a spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "rationale": "Explicit contrast between white and specialty.",
+            "assertion": {
+              "value": "Yes — a few hours for a white, nothing like the specialty wait."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "that's usually a few hours for a white, nothing like the specialty wait",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-86a1823e-ea26-45a4-b410-c9ecb6040ea3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — a few hours for a white, nothing like the specialty wait.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Explicit contrast between white and specialty.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "The lab performs the check.",
+            "assertion": {
+              "value": "The lab (the order sits in the lab's queue and gets checked)."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-ee79fe32-58f7-4a71-8c15-61f2fedc0a11",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab (the order sits in the lab's queue and gets checked).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"The lab performs the check.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "release and ship",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Terminal step.",
+            "assertion": {
+              "value": "The order is released, goes to the warehouse, and ships against the due date."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-addb8fe4-ac6f-4c59-a6be-12d60d197a53",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"rationale\":\"Terminal step.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "how long it takes",
+            "precision": "number",
+            "sourceRegime": "practiced",
+            "rationale": "A single figure given; not a spread.",
+            "assertion": {
+              "value": "Three hours."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-42e0a99d-6cf6-4b30-8199-b430405ba25b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"A single figure given; not a spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what is lost when it changes the system's mode",
+            "precision": "number",
+            "sourceRegime": "practiced",
+            "rationale": "Named mode change (tint to white) with its stated loss.",
+            "assertion": {
+              "value": "Three hours of crew time, and the line is out of anything else for that window."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a27c0fc1-57f3-4eed-bea8-15453c84f2da",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of crew time, and the line is out of anything else for that window.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Named mode change (tint to white) with its stated loss.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "Trigger condition for the changeover.",
+            "assertion": {
+              "value": "A line that has been running a tint being pulled onto a white."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-0f6aea65-d3a4-430b-b532-4f1100303f9e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line that has been running a tint being pulled onto a white.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Trigger condition for the changeover.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Event effect on the line and the order in hand.",
+            "assertion": {
+              "value": "The line's filler goes down mid-run with an unknown ETA; the order on it stalls and must either wait or be shifted to the other line."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the tint order I bumped now might itself be late",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a3f706dd-453a-4543-9990-26efb1b079dd",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line's filler goes down mid-run with an unknown ETA; the order on it stalls and must either wait or be shifted to the other line.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"Event effect on the line and the order in hand.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the tint order I bumped now might itself be late\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "how long it takes",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Two named repair kinds bound the range; the recent instance was about two hours. Not yet a spread.",
+            "assertion": {
+              "value": "From the \"half hour\" kind to the \"half a shift\" kind; the recent Line 2 jam came back in about two hours."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "it came back in about two hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-67de2e75-132c-43a7-b64e-412343204931",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"From the \\\"half hour\\\" kind to the \\\"half a shift\\\" kind; the recent Line 2 jam came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Two named repair kinds bound the range; the recent instance was about two hours. Not yet a spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "order flow, allocate to ship",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "rationale": "The end-to-end order stated by the expert.",
+            "assertion": {
+              "value": "Allocate the order onto a line and a slot in the week → run it through mix / mill / tint / fill and pack → QA hold → release and ship. Four steps if QA and shipping count as one, five if split."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-bf082835-a2ca-4279-80e5-726f157270bd",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate the order onto a line and a slot in the week → run it through mix / mill / tint / fill and pack → QA hold → release and ship. Four steps if QA and shipping count as one, five if split.\"},\"kind\":\"ordering/flow\",\"node\":\"order flow, allocate to ship\",\"precision\":\"spelled out\",\"rationale\":\"The end-to-end order stated by the expert.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "stage overlap on a line",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Overlap between consecutive orders on the same line, gated by tank space.",
+            "assertion": {
+              "value": "Stages can overlap between orders: the mixer may start the next order's batch while the fill head is still finishing the last one, provided the holding tank ahead (mix→mill or mill→fill) has space; the crew will take that head start when the tank ahead has room."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the crew will get a head start on mixing the next batch if the tank ahead of it has space",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-ce28dd53-a53d-4bc9-9956-dc3268c35e3e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stages can overlap between orders: the mixer may start the next order's batch while the fill head is still finishing the last one, provided the holding tank ahead (mix→mill or mill→fill) has space; the crew will take that head start when the tank ahead has room.\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"precision\":\"spelled out\",\"rationale\":\"Overlap between consecutive orders on the same line, gated by tank space.\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the crew will get a head start on mixing the next batch if the tank ahead of it has space\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "stage overlap on a line",
+            "slot": "how a branch or merge is decided",
+            "rationale": "The expert explicitly does not track how often overlap occurs or is blocked.",
+            "assertion": {
+              "absence": "unknown-to-user"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-9b28544e-b867-4018-9c35-2691cef17a62",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"rationale\":\"The expert explicitly does not track how often overlap occurs or is blocked.\",\"slot\":\"how a branch or merge is decided\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "constraint",
+            "node": "small holding tanks between stages",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Capacity and consequence stated qualitatively; the sizes themselves are not held by the expert.",
+            "assertion": {
+              "value": "The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait. Actual tank sizes not known to the expert; obtainable from engineering drawings."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "how often it's blocked because a tank's full and mixing has to wait",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-4c4af9ea-df1a-4449-adb7-d48fce7eae93",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait. Actual tank sizes not known to the expert; obtainable from engineering drawings.\"},\"kind\":\"constraint\",\"node\":\"small holding tanks between stages\",\"precision\":\"spelled out\",\"rationale\":\"Capacity and consequence stated qualitatively; the sizes themselves are not held by the expert.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"how often it's blocked because a tank's full and mixing has to wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "constraint",
+            "node": "published line rate",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "spelled out",
+            "sourceRegime": "prescribed",
+            "rationale": "Engineering's position, recorded as the prescribed reading.",
+            "assertion": {
+              "value": "Engineering's position is that the line rate is what it is regardless of the tanks."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "engineering tells me the line rate is what it is regardless",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-dabdbb5f-9eca-4afb-ad50-5b381d9dfa4f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Engineering's position is that the line rate is what it is regardless of the tanks.\"},\"kind\":\"constraint\",\"node\":\"published line rate\",\"precision\":\"spelled out\",\"rationale\":\"Engineering's position, recorded as the prescribed reading.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"engineering tells me the line rate is what it is regardless\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "constraint",
+            "node": "published line rate",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The expert's contrary practiced reading, recorded alongside engineering's.",
+            "assertion": {
+              "value": "In practice Line 1 feels sluggish and blocked in ways the published line rate does not account for; the expert suspects the mill-to-fill tank costs more than people admit, but has no proof."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it feels sluggish and blocked in ways I can't pin on the published line rate",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I've always suspected that one costs us more than people admit, but I've never had anything to prove it",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-292e1165-0990-4d17-b6db-153c675fd66c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"In practice Line 1 feels sluggish and blocked in ways the published line rate does not account for; the expert suspects the mill-to-fill tank costs more than people admit, but has no proof.\"},\"kind\":\"constraint\",\"node\":\"published line rate\",\"precision\":\"spelled out\",\"rationale\":\"The expert's contrary practiced reading, recorded alongside engineering's.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I've always suspected that one costs us more than people admit, but I've never had anything to prove it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it feels sluggish and blocked in ways I can't pin on the published line rate\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "Meridian on time",
+            "slot": "the rule as actually practiced",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Hard constraint on the scheduling decision.",
+            "assertion": {
+              "value": "A Meridian-style order ships on time, full stop; it is not traded off against anything."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-d509546d-b9bb-4b3b-b82d-a65b02b2f5dc",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A Meridian-style order ships on time, full stop; it is not traded off against anything.\"},\"kind\":\"policy\",\"node\":\"Meridian on time\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint on the scheduling decision.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "Meridian on time",
+            "slot": "what overrides it",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Only exception stated.",
+            "assertion": {
+              "value": "Only when there is truly no way through."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "that's a line I won't cross unless there's truly no way through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-54d606d7-8c61-4f0a-bd5f-867bba1af3f7",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Only when there is truly no way through.\"},\"kind\":\"policy\",\"node\":\"Meridian on time\",\"precision\":\"spelled out\",\"rationale\":\"Only exception stated.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "who can absorb the slip",
+            "slot": "the rule as actually practiced",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Practiced judgement about which customers can take lateness; examples given rather than a formula.",
+            "assertion": {
+              "value": "Judgement on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly counts as a second problem created to solve the first."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I use judgment on who can absorb the slip",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-b0a7a08e-c528-4592-ba81-e6026b3f356a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgement on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly counts as a second problem created to solve the first.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"Practiced judgement about which customers can take lateness; examples given rather than a formula.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "data-binding",
+            "node": "stage-by-stage times",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "rationale": "Named feed for stage durations.",
+            "assertion": {
+              "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) — the historian."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-9dfaeda1-b5ff-4581-9c8b-d487fe7b9277",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) — the historian.\"},\"kind\":\"data-binding\",\"node\":\"stage-by-stage times\",\"precision\":\"named\",\"rationale\":\"Named feed for stage durations.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "data-binding",
+            "node": "tank sizes",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "rationale": "Named source for the holding tank capacities.",
+            "assertion": {
+              "value": "Holding tank sizes — engineering drawings."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-b0908788-ec79-4481-b056-1fa606930f85",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tank sizes — engineering drawings.\"},\"kind\":\"data-binding\",\"node\":\"tank sizes\",\"precision\":\"named\",\"rationale\":\"Named source for the holding tank capacities.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option loses less",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "rationale": "The model's primary question, stated as a disruption decision: with the filler down and ETA unknown, whether to wait or switch lines.",
+            "assertion": {
+              "value": "Given \"filler's down, ETA unknown\", tell me which option actually loses less — wait out the repair, or move the order to the other line — instead of doing gut math at the huddle."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-d079be7f-20b9-4bb6-85e8-6ed631cb8057",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given \\\"filler's down, ETA unknown\\\", tell me which option actually loses less — wait out the repair, or move the order to the other line — instead of doing gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"The model's primary question, stated as a disruption decision: with the filler down and ETA unknown, whether to wait or switch lines.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option loses less",
+            "slot": "what \"better\" means, and trade-off weights",
+            "precision": "spelled out",
+            "rationale": "Lexicographic: on-time delivery for the protected order is a hard line; the remaining terms are weighed by judgment with no formula.",
+            "assertion": {
+              "value": "First: days late on Meridian, anything above zero is bad news — non-negotiable, a line not crossed unless there is truly no way through. Underneath: washdown hours (crew time plus the line taken out of anything else for that window), and whether the bumped order goes late and by how much, judged against who the customer is. No formula — \"how bad is bad\" and judgment on who can absorb the slip."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-9d5063d7-b9fb-400e-8b54-f618c6fde20e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First: days late on Meridian, anything above zero is bad news — non-negotiable, a line not crossed unless there is truly no way through. Underneath: washdown hours (crew time plus the line taken out of anything else for that window), and whether the bumped order goes late and by how much, judged against who the customer is. No formula — \\\"how bad is bad\\\" and judgment on who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"spelled out\",\"rationale\":\"Lexicographic: on-time delivery for the protected order is a hard line; the remaining terms are weighed by judgment with no formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option loses less",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "The scorecard terms the expert named map onto the washdown, the production run, the breakdown event and the order itself.",
+            "assertion": {
+              "value": [
+                "activity:tint-to-white washdown",
+                "activity:run it through mix/mill/tint/fill",
+                "activity:filler jammed",
+                "entity-type:order",
+                "policy:who can absorb the slip"
+              ]
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-3245b29a-3687-4313-97c5-e0455e5889ba",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:tint-to-white washdown\",\"activity:run it through mix/mill/tint/fill\",\"activity:filler jammed\",\"entity-type:order\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"which option loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard terms the expert named map onto the washdown, the production run, the breakdown event and the order itself.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window. And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "where Line 1 loses its time",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "rationale": "Second, explicitly in-scope objective: show whether the small tank between mill and fill on Line 1 is actually costing time, as evidence to take to engineering.",
+            "assertion": {
+              "value": "Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill is actually costing us — with something other than a hunch to take to engineering."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-225430d9-ae4d-4ef7-b439-6f9b1ccd50c5",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill is actually costing us — with something other than a hunch to take to engineering.\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"spelled out\",\"rationale\":\"Second, explicitly in-scope objective: show whether the small tank between mill and fill on Line 1 is actually costing time, as evidence to take to engineering.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "where Line 1 loses its time",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "The hunch is about blocking at the mill-to-fill tank, so it depends on the stage kit, the tank constraint and the run duration.",
+            "assertion": {
+              "value": [
+                "entity-type:mix, mill, tint, fill",
+                "constraint:small holding tanks",
+                "activity:run it through mix/mill/tint/fill",
+                "entity-type:Line 1 and Line 2"
+              ]
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "So yes — build it as separate stages if that's what it takes.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-770314e5-f47a-463e-908a-1d8c23ee60f5",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:mix, mill, tint, fill\",\"constraint:small holding tanks\",\"activity:run it through mix/mill/tint/fill\",\"entity-type:Line 1 and Line 2\"]},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"named\",\"rationale\":\"The hunch is about blocking at the mill-to-fill tank, so it depends on the stage kit, the tank constraint and the run duration.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"So yes — build it as separate stages if that's what it takes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "state that rides along with each instance",
+            "precision": "spelled out",
+            "rationale": "The attributes the scheduler works from on the sheet.",
+            "assertion": {
+              "value": "Quantity, due date, SKU; plus the line and week-slot it is allocated to, and the customer account."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-6ff1c59a-0664-487b-a946-2680043419a2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; plus the line and week-slot it is allocated to, and the customer account.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The attributes the scheduler works from on the sheet.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "rationale": "Whites versus tints differ in stage content and in run speed by line; customer type differs in how a slip is judged.",
+            "assertion": {
+              "value": "Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step, and whites run much faster on Line 2 than Line 1 while tints run at nearly the same speed on both. Customers are treated apart too: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-be0c3675-ae93-41c5-9eaa-7d36d84617cb",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step, and whites run much faster on Line 2 than Line 1 while tints run at nearly the same speed on both. Customers are treated apart too: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Whites versus tints differ in stage content and in run speed by line; customer type differs in how a slip is judged.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "Line 1 and Line 2",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "rationale": "The two lines are contended kit distinguished by speed, and the speed difference depends on product.",
+            "assertion": {
+              "value": "Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to a Line 2 run (\"Line 2 is twice as fast\", which is really a whites number); on tints the two lines run at nearly the same speed."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-3e2a5a8a-bd99-4642-afcf-f9d3dfe2e9f6",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to a Line 2 run (\\\"Line 2 is twice as fast\\\", which is really a whites number); on tints the two lines run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"rationale\":\"The two lines are contended kit distinguished by speed, and the speed difference depends on product.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "mix, mill, tint, fill",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "sourceRegime": "prescribed",
+            "rationale": "The scheduling sheet's view: the line is one indivisible resource.",
+            "assertion": {
+              "value": "On the sheet the line is one row treated as one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it is done."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-e9bb0ea0-9052-4006-96ad-c166a1d3a957",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet the line is one row treated as one thing: the order occupies it for its whole run, mix through fill, and nothing else is scheduled on it until it is done.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill\",\"precision\":\"spelled out\",\"rationale\":\"The scheduling sheet's view: the line is one indivisible resource.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "mix, mill, tint, fill",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The floor view: four separately contended pieces of kit with buffering between them, allowing overlap.",
+            "assertion": {
+              "value": "Physically four separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head is still finishing the last, if there is room in the holding tank — the crew will get a head start on mixing the next batch if the tank ahead of it has space."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the crew will get a head start on mixing the next batch if the tank ahead of it has space",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-27ee0ed5-50d0-47f6-94b8-77e090bca50f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically four separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head is still finishing the last, if there is room in the holding tank — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill\",\"precision\":\"spelled out\",\"rationale\":\"The floor view: four separately contended pieces of kit with buffering between them, allowing overlap.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the crew will get a head start on mixing the next batch if the tank ahead of it has space\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "mix, mill, tint, fill",
+            "slot": "how many there are, or the population's shape",
+            "precision": "named",
+            "assertion": {
+              "absence": "unknown-to-user",
+              "pointer": "how much overlap happens and how often mixing is blocked by a full tank is not tracked by the scheduler"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-f8e69ae7-6d72-4e37-9b53-b67b47115db5",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"how much overlap happens and how often mixing is blocked by a full tank is not tracked by the scheduler\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill\",\"precision\":\"named\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "allocate → run → QA hold → release and ship",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "rationale": "The order's life from demand-book line item to shipment, as walked end to end.",
+            "assertion": {
+              "value": "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (and pack) → QA hold in the lab's queue → release, go to the warehouse and ship against the due date."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-2a491098-b602-4b46-bbaa-439e291027db",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (and pack) → QA hold in the lab's queue → release, go to the warehouse and ship against the due date.\"},\"kind\":\"ordering/flow\",\"node\":\"allocate → run → QA hold → release and ship\",\"precision\":\"spelled out\",\"rationale\":\"The order's life from demand-book line item to shipment, as walked end to end.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Allocation binds the order to a line and a week slot, which is the scheduling decision under test.",
+            "assertion": {
+              "value": "The order is slotted onto a line and a slot in the week on the sheet."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-c4aefe40-a022-4990-96a1-b74243850715",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Allocation binds the order to a line and a week slot, which is the scheduling decision under test.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "The order exists as a line item in the demand book once ERP spits it out, with quantity, due date and SKU."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-76c7250e-6575-4e31-b667-113f3a497cce",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order exists as a line item in the demand book once ERP spits it out, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "The order must first be allocated onto a line and a slot in the week."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-7da94524-13b5-4c11-a1b4-9cb1b0f07e19",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order must first be allocated onto a line and a slot in the week.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "Filled and packed product coming off the fill line, which then goes into QA hold."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-c8f57cec-d8f5-42c0-9b99-29a1a71eab73",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Filled and packed product coming off the fill line, which then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "how long it takes",
+            "precision": "spread",
+            "sourceRegime": "practiced",
+            "rationale": "Sheet-level, mix-to-last-pack, for a Meridian-sized white on Line 2; includes fill-up time getting the line running plus actual throughput. The bad tail is loosely folded-in filler hiccups and QA-adjacent time.",
+            "assertion": {
+              "value": "White, normal/Meridian-sized order, Line 2, mix-to-last-pack: typical 8–9 hours; one run in ten worse than 12–13 hours; one run in ten better than about 6 hours."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-d6985d8d-f85e-4556-a091-df64be080ba6",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, normal/Meridian-sized order, Line 2, mix-to-last-pack: typical 8–9 hours; one run in ten worse than 12–13 hours; one run in ten better than about 6 hours.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"Sheet-level, mix-to-last-pack, for a Meridian-sized white on Line 2; includes fill-up time getting the line running plus actual throughput. The bad tail is loosely folded-in filler hiccups and QA-adjacent time.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "how long it takes",
+            "precision": "spread",
+            "sourceRegime": "practiced",
+            "rationale": "Same white order on the slower line.",
+            "assertion": {
+              "value": "White, same order, Line 1: typical 13–14 hours; worse days pushing 18-plus hours; best day maybe 10 hours — roughly fifty to sixty percent added to the Line 2 figures."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-97bc8f2b-2070-4c8a-8af4-7233caeef498",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, same order, Line 1: typical 13–14 hours; worse days pushing 18-plus hours; best day maybe 10 hours — roughly fifty to sixty percent added to the Line 2 figures.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"Same white order on the slower line.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "how long it takes",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Only a typical range was given for tints; no one-in-ten tails.",
+            "assertion": {
+              "value": "Tint run, either line: 8–10 hours typical. No one-in-ten worse/better figures given."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-04a6f876-12f4-4f53-b6f2-f8e5fa9c87bc",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Tint run, either line: 8–10 hours typical. No one-in-ten worse/better figures given.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"range\",\"rationale\":\"Only a typical range was given for tints; no one-in-ten tails.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "rationale": "Duration varies by product type and by line, and the two interact; the expert has no explanation for the tint parity.",
+            "assertion": {
+              "value": "Yes — duration varies both by product (white vs tint) and by line, and the two interact: whites are much slower on Line 1, tints run at nearly the same speed on both. \"I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\""
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-592b83e0-ece3-4e98-aedf-cdf70c202e96",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — duration varies both by product (white vs tint) and by line, and the two interact: whites are much slower on Line 1, tints run at nearly the same speed on both. \\\"I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\\\"\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Duration varies by product type and by line, and the two interact; the expert has no explanation for the tint parity.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what is lost when it changes the system's mode",
+            "precision": "number",
+            "rationale": "Named transition: tint to white on Line 1.",
+            "assertion": {
+              "value": "Three hours for a tint-to-white changeover — real cost in crew time, and it takes the line out of anything else for that window."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "it takes Line 1 out of anything else for that window",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-32fe7be9-75c7-464c-87cb-ca38fef4039b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours for a tint-to-white changeover — real cost in crew time, and it takes the line out of anything else for that window.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Named transition: tint to white on Line 1.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "A line coming off a tint run and being switched to a white — pulling Line 1 off its tint to cover a white order."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-31556043-9787-40dc-8c0d-b74a47ed3589",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line coming off a tint run and being switched to a white — pulling Line 1 off its tint to cover a white order.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint. If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "how long it takes",
+            "precision": "named",
+            "rationale": "Only a vague magnitude was given; no typical or tail figures, and the specialty case is named but unquantified.",
+            "assertion": {
+              "value": "Usually a few hours for a white; \"nothing like the specialty wait\". No typical/tail figures given."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-1f732daa-9626-420c-980f-5c2b88d9bff3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; \\\"nothing like the specialty wait\\\". No typical/tail figures given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Only a vague magnitude was given; no typical or tail figures, and the specialty case is named but unquantified.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "assertion": {
+              "value": "The lab — the order sits in the lab's queue and gets checked."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-2afae8eb-1155-4b07-9842-971df47a6a7d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab — the order sits in the lab's queue and gets checked.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jammed",
+            "slot": "how long it takes",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Two recognised repair kinds bracket the duration; the recent instance fell between them.",
+            "assertion": {
+              "value": "Two kinds of repair: the \"half hour\" kind and the \"half a shift\" kind. The most recent Line 2 filler jam came back in about two hours."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "it came back in about two hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-d2d6e303-2f63-478a-ace1-0bf61abbfddd",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two kinds of repair: the \\\"half hour\\\" kind and the \\\"half a shift\\\" kind. The most recent Line 2 filler jam came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jammed\",\"precision\":\"range\",\"rationale\":\"Two recognised repair kinds bracket the duration; the recent instance fell between them.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jammed",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "An event that befalls the line mid-run and forces the switch-or-wait decision.",
+            "assertion": {
+              "value": "The line's filler stops mid-run with an unknown ETA, putting the order on it at risk and forcing a decision to wait out the repair or move the order to the other line."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-5548a18b-9f79-4475-a9ab-83a74c750721",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line's filler stops mid-run with an unknown ETA, putting the order on it at risk and forcing a decision to wait out the repair or move the order to the other line.\"},\"kind\":\"activity\",\"node\":\"filler jammed\",\"precision\":\"spelled out\",\"rationale\":\"An event that befalls the line mid-run and forces the switch-or-wait decision.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "who can absorb the slip",
+            "slot": "the rule as actually practiced",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The practiced rule for choosing which order gets bumped when two cannot both be on time.",
+            "assertion": {
+              "value": "Protect the non-negotiable order's due date; for anything bumped, judge by how far it slips and who the customer is — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first. No formula; judgment on who can absorb the slip."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I use judgment on who can absorb the slip.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-1ee7c206-0c56-4d6b-b091-5861f9c40438",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Protect the non-negotiable order's due date; for anything bumped, judge by how far it slips and who the customer is — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first. No formula; judgment on who can absorb the slip.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The practiced rule for choosing which order gets bumped when two cannot both be on time.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "who can absorb the slip",
+            "slot": "what overrides it",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "The on-time line is crossed only when there is truly no way through."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "that's a line I won't cross unless there's truly no way through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-4b706f60-c02f-4973-aa58-2d3ded113c39",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The on-time line is crossed only when there is truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "constraint",
+            "node": "small holding tanks",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Consequence is stated (upstream stage waits); the numeric capacity is not held by the expert.",
+            "assertion": {
+              "value": "The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait; overlap is only possible if the tank ahead has space. Suspected to cost more than people admit, never proven."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "how often it's blocked because a tank's full and mixing has to wait",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-97ea5a05-d89c-4a7d-a136-f90526beaa27",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The holding tanks between stages are small — especially the one between mill and fill on Line 1. When a tank is full the upstream stage is blocked and mixing has to wait; overlap is only possible if the tank ahead has space. Suspected to cost more than people admit, never proven.\"},\"kind\":\"constraint\",\"node\":\"small holding tanks\",\"precision\":\"spelled out\",\"rationale\":\"Consequence is stated (upstream stage waits); the numeric capacity is not held by the expert.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"how often it's blocked because a tank's full and mixing has to wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "constraint",
+            "node": "small holding tanks",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "named",
+            "assertion": {
+              "absence": "deferred",
+              "pointer": "engineering drawings — tank sizes obtainable from engineering, not carried in the scheduler's head"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-6d66bc49-da1a-49e3-8d98-e5d732b6e4bb",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings — tank sizes obtainable from engineering, not carried in the scheduler's head\"},\"kind\":\"constraint\",\"node\":\"small holding tanks\",\"precision\":\"named\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "data-binding",
+            "node": "stage-by-stage rates from the historian",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "rationale": "Stage-level durations are needed for the separate-stage model and exist only in the historian.",
+            "assertion": {
+              "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the plant historian; never pulled apart, not known to the scheduler."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-46d37104-fb87-4105-95d5-4448aade81ac",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the plant historian; never pulled apart, not known to the scheduler.\"},\"kind\":\"data-binding\",\"node\":\"stage-by-stage rates from the historian\",\"precision\":\"named\",\"rationale\":\"Stage-level durations are needed for the separate-stage model and exist only in the historian.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "validation-criterion",
+            "node": "the sheet's end-to-end batch times",
+            "slot": "how the expert would know the model is right",
+            "precision": "named",
+            "rationale": "The only figures the expert holds first-hand are sheet-level end-to-end times per SKU per line; engineering's counter-claim is that the line rate is what it is regardless of the tanks.",
+            "assertion": {
+              "value": "The model's end-to-end batch time for a given SKU on each line should match what the scheduler's sheet shows; and it would have to speak to engineering's claim that \"the line rate is what it is regardless\"."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "engineering tells me the line rate is what it is regardless",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-0cdda695-1dfa-43ef-971c-b9db09403a07",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The model's end-to-end batch time for a given SKU on each line should match what the scheduler's sheet shows; and it would have to speak to engineering's claim that \\\"the line rate is what it is regardless\\\".\"},\"kind\":\"validation-criterion\",\"node\":\"the sheet's end-to-end batch times\",\"precision\":\"named\",\"rationale\":\"The only figures the expert holds first-hand are sheet-level end-to-end times per SKU per line; engineering's counter-claim is that the line rate is what it is regardless of the tanks.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"engineering tells me the line rate is what it is regardless\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option actually loses less",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The expert's stated use: type in a disruption state and be told which of switch-or-wait loses less.",
+            "assertion": {
+              "value": "Given a disruption like \"filler's down, ETA unknown\", tell me which option actually loses less — shift the order to the other line or wait out the repair — instead of doing gut math at the huddle."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I'd love to type in \"filler's down, ETA unknown\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a5926e2a-88e8-459e-a296-282b16d499a8",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Given a disruption like \\\"filler's down, ETA unknown\\\", tell me which option actually loses less — shift the order to the other line or wait out the repair — instead of doing gut math at the huddle.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"The expert's stated use: type in a disruption state and be told which of switch-or-wait loses less.\",\"slot\":\"the question, in the expert's words\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'd love to type in \\\\\\\"filler's down, ETA unknown\\\\\\\" and have something tell me which option actually loses less, instead of me doing gut math at the huddle with people staring at me.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option actually loses less",
+            "slot": "what \"better\" means, and trade-off weights",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Hard constraint plus unweighted secondary terms; the expert explicitly denies having a formula.",
+            "assertion": {
+              "value": "First number: days late on Meridian, anything above zero is bad — on-time is non-negotiable, a line not crossed unless there's truly no way through. Underneath that: washdown hours (crew time, line taken out of anything else for that window) and whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-ea1779b0-9a83-42aa-92d1-746e73de43cc",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"First number: days late on Meridian, anything above zero is bad — on-time is non-negotiable, a line not crossed unless there's truly no way through. Underneath that: washdown hours (crew time, line taken out of anything else for that window) and whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint plus unweighted secondary terms; the expert explicitly denies having a formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through. So the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "which option actually loses less",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "The scorecard terms name the run, the jam, the washdown, the order type and the flow.",
+            "assertion": {
+              "value": [
+                "activity:run it through mix/mill/tint/fill",
+                "activity:filler jam",
+                "activity:tint-to-white washdown",
+                "entity-type:order (line item in the demand book)",
+                "entity-type:Line 1 and Line 2",
+                "ordering/flow:allocate → run → QA hold → release and ship",
+                "policy:who can absorb the slip"
+              ]
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-1288a3df-c7fd-4319-8d4e-a228572ba0b0",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"activity:run it through mix/mill/tint/fill\",\"activity:filler jam\",\"activity:tint-to-white washdown\",\"entity-type:order (line item in the demand book)\",\"entity-type:Line 1 and Line 2\",\"ordering/flow:allocate → run → QA hold → release and ship\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"which option actually loses less\",\"precision\":\"named\",\"rationale\":\"The scorecard terms name the run, the jam, the washdown, the order type and the flow.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And then whatever happens to the bumped tint order — does it slide past its own due date, and if so by how much and who's the customer\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "where Line 1 loses its time",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "rationale": "Second in-scope question: whether the small tank between mill and fill on Line 1 is actually costing time.",
+            "assertion": {
+              "value": "Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill on Line 1 is costing more than the published line rate admits, so it can be taken to engineering as something other than a hunch."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-4be8c533-88e3-4f97-bcef-9b445cfeb3e6",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Show where Line 1 loses its time — in particular whether the small holding tank between mill and fill on Line 1 is costing more than the published line rate admits, so it can be taken to engineering as something other than a hunch.\"},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"spelled out\",\"rationale\":\"Second in-scope question: whether the small tank between mill and fill on Line 1 is actually costing time.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "where Line 1 loses its time",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "The tank question depends on the stage kit and the holding-tank constraint.",
+            "assertion": {
+              "value": [
+                "entity-type:mix, mill, tint, fill stages",
+                "constraint:small holding tanks between stages",
+                "activity:run it through mix/mill/tint/fill",
+                "entity-type:Line 1 and Line 2"
+              ]
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So yes — build it as separate stages if that's what it takes.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-bb291ebf-9fe0-4a6e-9840-e7d7fac44033",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:mix, mill, tint, fill stages\",\"constraint:small holding tanks between stages\",\"activity:run it through mix/mill/tint/fill\",\"entity-type:Line 1 and Line 2\"]},\"kind\":\"objective\",\"node\":\"where Line 1 loses its time\",\"precision\":\"named\",\"rationale\":\"The tank question depends on the stage kit and the holding-tank constraint.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So yes — build it as separate stages if that's what it takes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order (line item in the demand book)",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "rationale": "Whites vs tints differ in the tint stage and in run time by line; customer identity differs in slip tolerance.",
+            "assertion": {
+              "value": "Orders are line items with quantity, due date and SKU. Treated apart: whites (tint stage barely there, more of a pass-through than a real letdown step) vs tints (real letdown); and by customer — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-edfaf81c-c276-4b57-a88c-914953b1c6be",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders are line items with quantity, due date and SKU. Treated apart: whites (tint stage barely there, more of a pass-through than a real letdown step) vs tints (real letdown); and by customer — a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem.\"},\"kind\":\"entity-type\",\"node\":\"order (line item in the demand book)\",\"precision\":\"spelled out\",\"rationale\":\"Whites vs tints differ in the tint stage and in run time by line; customer identity differs in slip tolerance.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order (line item in the demand book)",
+            "slot": "state that rides along with each instance",
+            "precision": "spelled out",
+            "rationale": "Quantity, due date, SKU come from ERP; customer type is used in the slip judgement; line allocation is set at step one.",
+            "assertion": {
+              "value": "Quantity, due date, SKU; the customer (distributor / small account / awkward account); which line and week-slot it has been allocated to; whether it has gone late and by how many days."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-13339551-ff3a-414f-8260-e1296530d8ec",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; the customer (distributor / small account / awkward account); which line and week-slot it has been allocated to; whether it has gone late and by how many days.\"},\"kind\":\"entity-type\",\"node\":\"order (line item in the demand book)\",\"precision\":\"spelled out\",\"rationale\":\"Quantity, due date, SKU come from ERP; customer type is used in the slip judgement; line allocation is set at step one.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "Line 1 and Line 2",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "rationale": "The two lines differ on whites but not on tints — load-bearing for switch-or-wait.",
+            "assertion": {
+              "value": "Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to Line 2's figures (\"Line 2 is twice as fast\", though that's really a whites number). On tints they run at nearly the same speed."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-535749ea-ba99-4d11-84c0-8203fd058329",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 and Line 2. Line 1 is the slower machine on whites — add maybe fifty, sixty percent to Line 2's figures (\\\"Line 2 is twice as fast\\\", though that's really a whites number). On tints they run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"rationale\":\"The two lines differ on whites but not on tints — load-bearing for switch-or-wait.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "mix, mill, tint, fill stages",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The floor's account: four separately contended pieces of kit per line, buffered by small holding tanks.",
+            "assertion": {
+              "value": "Mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can be starting the next order's batch while the fill head is still finishing the last one, if the holding tank between mix and mill, or mill and fill, has room."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-79eccb7f-a787-40d4-a2fa-e95bfda82d18",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can be starting the next order's batch while the fill head is still finishing the last one, if the holding tank between mix and mill, or mill and fill, has room.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill stages\",\"precision\":\"spelled out\",\"rationale\":\"The floor's account: four separately contended pieces of kit per line, buffered by small holding tanks.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "mix, mill, tint, fill stages",
+            "slot": "how many there are, or the population's shape",
+            "precision": "named",
+            "rationale": "Stage counts per line and tank sizes not carried by the expert; source named.",
+            "assertion": {
+              "absence": "deferred",
+              "pointer": "engineering drawings (tank sizes) — expert does not carry them in his head"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I don't have clean numbers for tank sizes or stage-by-stage rates.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-3c6b3e85-7fd3-4831-9201-6e3ef525e7cf",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings (tank sizes) — expert does not carry them in his head\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill stages\",\"precision\":\"named\",\"rationale\":\"Stage counts per line and tank sizes not carried by the expert; source named.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have clean numbers for tank sizes or stage-by-stage rates.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "boundary-condition",
+            "node": "demand book from ERP",
+            "slot": "the starting state",
+            "precision": "spelled out",
+            "rationale": "Orders enter the scheduler's world as ERP-generated demand-book line items.",
+            "assertion": {
+              "value": "Orders arrive as line items in the demand book once ERP spits that out, carrying quantity, due date and SKU."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-f1eca8a3-a2c2-4d92-a428-763c67e7b02a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders arrive as line items in the demand book once ERP spits that out, carrying quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"spelled out\",\"rationale\":\"Orders enter the scheduler's world as ERP-generated demand-book line items.\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Allocation fixes line and week-slot on the sheet.",
+            "assertion": {
+              "value": "The order is slotted onto a line and a slot in the week on the sheet."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-823c9593-db42-45eb-9515-937e6b90bd33",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Allocation fixes line and week-slot on the sheet.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "The expert himself, as master scheduler, does the slotting on the sheet.",
+            "assertion": {
+              "value": "The master scheduler, on the sheet"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I'm the master scheduler at a coatings plant.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 1,
+              "entryEnd": 1
+            },
+            "source": "user"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-f7e12936-7567-4b38-be19-a45fb5dc6274",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler, on the sheet\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"named\",\"rationale\":\"The expert himself, as master scheduler, does the slotting on the sheet.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm the master scheduler at a coatings plant.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":1,\\\"entryStart\\\":1,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "Allocation follows the ERP demand-book line item existing.",
+            "assertion": {
+              "value": "A line item in the demand book from ERP, with quantity, due date and SKU."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-c27fb36e-eb7f-42be-b6ef-c5dd9e9283e2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book from ERP, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Allocation follows the ERP demand-book line item existing.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "allocate → run → QA hold → release and ship",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "rationale": "The expert's own end-to-end sequence for one order.",
+            "assertion": {
+              "value": "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (mix, mill, tint, fill and pack) → QA hold in the lab's queue → release, warehouse, and ship against the due date."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-5755b52c-e250-4fae-9c9b-ac6eba42d092",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill (mix, mill, tint, fill and pack) → QA hold in the lab's queue → release, warehouse, and ship against the due date.\"},\"kind\":\"ordering/flow\",\"node\":\"allocate → run → QA hold → release and ship\",\"precision\":\"spelled out\",\"rationale\":\"The expert's own end-to-end sequence for one order.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "A run needs the order allocated to a line and that line's kit available.",
+            "assertion": {
+              "value": "The order must have been allocated onto a line and a slot in the week, and the line's kit (mix, mill, tint, fill) available."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-afd366c9-1ea6-4b73-b2c0-ed97c9af0c79",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order must have been allocated onto a line and a slot in the week, and the line's kit (mix, mill, tint, fill) available.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"A run needs the order allocated to a line and that line's kit available.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Output is finished, packed product that comes off the fill line into QA hold.",
+            "assertion": {
+              "value": "The order is produced through mix, mill, tint, fill and pack; it comes off the fill line as packed product ready for QA hold."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-86fd1cfb-379b-42f7-bdbb-8586dae7f755",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is produced through mix, mill, tint, fill and pack; it comes off the fill line as packed product ready for QA hold.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"Output is finished, packed product that comes off the fill line into QA hold.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "The run is performed by whichever line the order is allocated to, with its crew.",
+            "assertion": {
+              "value": "entity-type:Line 1 and Line 2 — the line the order is slotted onto, plus its crew"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "On Line 1, same order — slower machine",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-90d36431-4341-4f9e-8bf6-8b5354b2fedd",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:Line 1 and Line 2 — the line the order is slotted onto, plus its crew\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"The run is performed by whichever line the order is allocated to, with its crew.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "how long it takes",
+            "precision": "spread",
+            "sourceRegime": "practiced",
+            "rationale": "First-pass spread for a Meridian-sized white on Line 2, mix-to-last-pack, with breakdowns folded in loosely; superseded by the clean-run capture.",
+            "assertion": {
+              "value": "White, Meridian-sized order, Line 2, mix-to-last-pack (includes fill-up time plus throughput): typical eight to nine hours; one in ten worse than twelve to thirteen hours (breakdowns folded in loosely); one in ten better than about six hours."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more \"the filler hiccupped twice\" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-7ef3368b-e678-4c58-b7f9-137d1607d8ec",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, Meridian-sized order, Line 2, mix-to-last-pack (includes fill-up time plus throughput): typical eight to nine hours; one in ten worse than twelve to thirteen hours (breakdowns folded in loosely); one in ten better than about six hours.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"First-pass spread for a Meridian-sized white on Line 2, mix-to-last-pack, with breakdowns folded in loosely; superseded by the clean-run capture.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours, and that's usually not the run itself slowing down, that's more \\\\\\\"the filler hiccupped twice\\\\\\\" or QA-adjacent stuff creeping in, though I'm folding some of that in loosely.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size. That includes fill-up time getting the line running plus the actual throughput.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "how long it takes",
+            "precision": "spread",
+            "sourceRegime": "practiced",
+            "rationale": "Superseding capture: breakdown time stripped out so filler jams are not double-counted; clean-run variability is small.",
+            "assertion": {
+              "value": "Clean run (nothing breaks — no jam, no QA holdup), white on Line 2: typical eight or nine hours; one in ten worse than nine to ten hours (normal slack, someone slow changing a roll of packaging film); one in ten better than about six hours. The twelve-to-thirteen-hour days are breakdowns showing up inside the run, not the run being slow."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-10d88b79-af70-4a14-90c1-da56ad526d36",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Clean run (nothing breaks — no jam, no QA holdup), white on Line 2: typical eight or nine hours; one in ten worse than nine to ten hours (normal slack, someone slow changing a roll of packaging film); one in ten better than about six hours. The twelve-to-thirteen-hour days are breakdowns showing up inside the run, not the run being slow.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spread\",\"rationale\":\"Superseding capture: breakdown time stripped out so filler jams are not double-counted; clean-run variability is small.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "whether its quantities vary by type",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "P07: run duration varies both by product type and by line, and the two interact.",
+            "assertion": {
+              "value": "Yes. White on Line 1: add maybe fifty, sixty percent to the Line 2 figures — typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten (this is where \"Line 2 is twice as fast\" comes from, and that's really a whites number). Tints: Line 1 and Line 2 run them at nearly the same speed — eight to ten hours typical on either line. No good reason known for why; it's what the sheet has always shown."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-921611c3-21b5-4ab2-8e56-9b8cdaa2eba2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes. White on Line 1: add maybe fifty, sixty percent to the Line 2 figures — typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten (this is where \\\"Line 2 is twice as fast\\\" comes from, and that's really a whites number). Tints: Line 1 and Line 2 run them at nearly the same speed — eight to ten hours typical on either line. No good reason known for why; it's what the sheet has always shown.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"spelled out\",\"rationale\":\"P07: run duration varies both by product type and by line, and the two interact.\",\"slot\":\"whether its quantities vary by type\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "how long it takes",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Expert gave two named repair kinds and one recent instance; no quantiles yet, so range not spread.",
+            "assertion": {
+              "value": "Either the \"half hour\" kind or the \"half a shift\" kind of repair; the recent Line 2 instance came back in about two hours."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I went with waiting, it came back in about two hours, we just scraped the Thursday due date.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-6cf8c229-ab84-4448-abc6-3e7f4a76bb4c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Either the \\\"half hour\\\" kind or the \\\"half a shift\\\" kind of repair; the recent Line 2 instance came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Expert gave two named repair kinds and one recent instance; no quantiles yet, so range not spread.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours, we just scraped the Thursday due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The jam halts the line's fill stage and forces the switch-or-wait decision.",
+            "assertion": {
+              "value": "The filler stops and the run stalls — the line loses time (half a shift lost in the recent case), the in-progress order's finish is pushed out, and the scheduler must decide whether to shift the order to the other line or wait out the repair."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-ce789325-dd40-4b21-a936-73485ccb90b9",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The filler stops and the run stalls — the line loses time (half a shift lost in the recent case), the in-progress order's finish is pushed out, and the scheduler must decide whether to shift the order to the other line or wait out the repair.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"The jam halts the line's fill stage and forces the switch-or-wait decision.\",\"slot\":\"what it produces or changes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what is lost when it changes the system's mode",
+            "precision": "number",
+            "sourceRegime": "practiced",
+            "rationale": "P02: named transition (tint to white) with a stated loss; a single figure, not a spread.",
+            "assertion": {
+              "value": "Three hours of washdown — crew time, and it takes the line out of anything else for that window."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-1ba32034-be19-432b-a012-326b682fd357",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of washdown — crew time, and it takes the line out of anything else for that window.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"P02: named transition (tint to white) with a stated loss; a single figure, not a spread.\",\"slot\":\"what is lost when it changes the system's mode\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "Triggered by pulling a line off a tint run to run a white.",
+            "assertion": {
+              "value": "A line that is mid-run or last-run on a tint being pulled onto a white — the changeover from tint to white."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-526685d5-3021-40f4-8cb9-a4e8d92002b7",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line that is mid-run or last-run on a tint being pulled onto a white — the changeover from tint to white.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Triggered by pulling a line off a tint run to run a white.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "how long it takes",
+            "precision": "named",
+            "sourceRegime": "practiced",
+            "rationale": "Vague quantifier — \"usually a few hours\" for a white — not yet quantiles; specialty products wait longer.",
+            "assertion": {
+              "value": "Usually a few hours for a white; \"nothing like the specialty wait\" — specialty products wait longer (amount not given)."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-35f88f0f-1e4e-44a3-9d47-33c6942a9b16",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; \\\"nothing like the specialty wait\\\" — specialty products wait longer (amount not given).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Vague quantifier — \\\"usually a few hours\\\" for a white — not yet quantiles; specialty products wait longer.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "QA check gates release to warehouse and shipping.",
+            "assertion": {
+              "value": "The batch is checked and then released, goes to the warehouse, and ships against the due date."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-e28ed067-b6a4-40d8-935a-3598e2401cc1",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The batch is checked and then released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"rationale\":\"QA check gates release to warehouse and shipping.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "The lab holds the queue and does the check.",
+            "assertion": {
+              "value": "The lab"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a3d8c0b7-97bf-443d-aa86-8fef8ea0bd5a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"The lab holds the queue and does the check.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "a line is occupied for the whole run",
+            "slot": "the rule as actually practiced",
+            "precision": "spelled out",
+            "sourceRegime": "prescribed",
+            "rationale": "P08: the scheduling sheet's rule, which the expert says lies to him a bit.",
+            "assertion": {
+              "value": "On the sheet, a line is one row: the order occupies that line for its whole run, mix through fill, and nothing else is scheduled on it till it's done."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-4e68a0cf-eccb-4b69-91f0-c7fb74a2b639",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet, a line is one row: the order occupies that line for its whole run, mix through fill, and nothing else is scheduled on it till it's done.\"},\"kind\":\"policy\",\"node\":\"a line is occupied for the whole run\",\"precision\":\"spelled out\",\"rationale\":\"P08: the scheduling sheet's rule, which the expert says lies to him a bit.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "a line is occupied for the whole run",
+            "slot": "what overrides it",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "P08 divergence: floor practice overlaps stages when buffer space allows.",
+            "assertion": {
+              "value": "On the floor the crew will get a head start on mixing the next batch if the tank ahead of it has space — the mixer can start the next order while the fill head finishes the last one. How much overlap happens, and how often it is blocked because a tank is full, is not tracked."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-cfe5bf57-8879-4592-a938-1527d73c8bac",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the floor the crew will get a head start on mixing the next batch if the tank ahead of it has space — the mixer can start the next order while the fill head finishes the last one. How much overlap happens, and how often it is blocked because a tank is full, is not tracked.\"},\"kind\":\"policy\",\"node\":\"a line is occupied for the whole run\",\"precision\":\"spelled out\",\"rationale\":\"P08 divergence: floor practice overlaps stages when buffer space allows.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "who can absorb the slip",
+            "slot": "the rule as actually practiced",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The practiced rule for choosing which order to bump; explicitly judgement, not formula.",
+            "assertion": {
+              "value": "Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem. No formula — \"how bad is bad\" for the second-order stuff."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I use judgment on who can absorb the slip",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-b3079749-c23b-4ade-ac51-9bbff19806fb",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; another awkward account that gets prickly creates a second problem. No formula — \\\"how bad is bad\\\" for the second-order stuff.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The practiced rule for choosing which order to bump; explicitly judgement, not formula.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "who can absorb the slip",
+            "slot": "what overrides it",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The hard on-time line overrides the slip-absorption weighing.",
+            "assertion": {
+              "value": "The Meridian-style on-time line overrides everything: that order shipping on time is non-negotiable unless there's truly no way through."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-e7d9cbf7-5a12-4e04-8fbf-b2b0581efa5d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The Meridian-style on-time line overrides everything: that order shipping on time is non-negotiable unless there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The hard on-time line overrides the slip-absorption weighing.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "constraint",
+            "node": "small holding tanks between stages",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "named",
+            "sourceRegime": "practiced",
+            "rationale": "Consequence named (mixing has to wait when the tank ahead is full) but the capacities themselves are not held by the expert; source named.",
+            "assertion": {
+              "absence": "deferred",
+              "pointer": "engineering drawings — tank sizes; consequence as stated: the tanks are small, especially the one between mill and fill on Line 1, and when a tank is full mixing has to wait"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-23c5706e-37c1-481e-9438-8fae70973c13",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings — tank sizes; consequence as stated: the tanks are small, especially the one between mill and fill on Line 1, and when a tank is full mixing has to wait\"},\"kind\":\"constraint\",\"node\":\"small holding tanks between stages\",\"precision\":\"named\",\"rationale\":\"Consequence named (mixing has to wait when the tank ahead is full) but the capacities themselves are not held by the expert; source named.\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "data-binding",
+            "node": "stage-by-stage durations from the historian",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "rationale": "Stage-level rates exist as data but not in the expert's head; feed named.",
+            "assertion": {
+              "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) per SKU and line — feed: the historian. Never pulled apart; only end-to-end batch time per SKU per line is on the scheduling sheet."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-00863ee1-f99c-48b2-b680-bf4eb71e6a57",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) per SKU and line — feed: the historian. Never pulled apart; only end-to-end batch time per SKU per line is on the scheduling sheet.\"},\"kind\":\"data-binding\",\"node\":\"stage-by-stage durations from the historian\",\"precision\":\"named\",\"rationale\":\"Stage-level rates exist as data but not in the expert's head; feed named.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I know roughly how long a batch of a given SKU takes end to end on each line, because that's what's on my sheet, but nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "validation-criterion",
+            "node": "stage rates must come from data, not gut-feel",
+            "slot": "how the expert would know the model is right",
+            "precision": "spelled out",
+            "rationale": "Expert explicitly bounds what his own testimony can support.",
+            "assertion": {
+              "value": "Stage-level rates and tank sizes must not be taken from the expert's gut-feel — he can supply gut-feel and known bottleneck stories, but real numbers must come from the historian and engineering drawings."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-196b8447-3958-444f-9860-8de7330299ec",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-level rates and tank sizes must not be taken from the expert's gut-feel — he can supply gut-feel and known bottleneck stories, but real numbers must come from the historian and engineering drawings.\"},\"kind\":\"validation-criterion\",\"node\":\"stage rates must come from data, not gut-feel\",\"precision\":\"spelled out\",\"rationale\":\"Expert explicitly bounds what his own testimony can support.\",\"slot\":\"how the expert would know the model is right\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Don't assume I can hand you clean stage rates — I can give you gut-feel and known bottleneck stories, but not real numbers off the top of my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "switch or wait when Line 2 goes down",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "rationale": "The expert wrote the question as he would type it into the tool.",
+            "assertion": {
+              "value": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\""
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-b58883f3-43e2-4626-bc59-a9c091f1d1b5",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\"\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down\",\"precision\":\"spelled out\",\"rationale\":\"The expert wrote the question as he would type it into the tool.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "switch or wait when Line 2 goes down",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "The expert listed what the answer hangs on: the protected run and its due date, the state of Line 1, the changeover and its direction, the jam duration, and whose order gets bumped.",
+            "assertion": {
+              "value": [
+                "entity-type:order",
+                "entity-type:line",
+                "activity:run it through mix/mill/tint/fill",
+                "activity:tint-to-white washdown",
+                "activity:filler jam",
+                "policy:who can absorb the slip"
+              ]
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the bumped order's identity matters, not just \"an order got delayed.\"",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-3aa3764b-8dd5-495a-bf3e-b32cbc89ba61",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:line\",\"activity:run it through mix/mill/tint/fill\",\"activity:tint-to-white washdown\",\"activity:filler jam\",\"policy:who can absorb the slip\"]},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down\",\"precision\":\"named\",\"rationale\":\"The expert listed what the answer hangs on: the protected run and its due date, the state of Line 1, the changeover and its direction, the jam duration, and whose order gets bumped.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the bumped order's identity matters, not just \\\\\\\"an order got delayed.\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "switch or wait when Line 2 goes down",
+            "slot": "what \"better\" means, and trade-off weights",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Expert gave a lexicographic hard constraint plus unweighted second-order criteria, explicitly denying a formula.",
+            "assertion": {
+              "value": "Hard line: days late on Meridian, anything above zero is bad news. Underneath that, weighed by judgment with no formula: washdown hours, and whether the bumped order goes late and by how much and for which customer."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-57ad71c3-f423-4d91-a9f8-d3ce31f1fca1",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Hard line: days late on Meridian, anything above zero is bad news. Underneath that, weighed by judgment with no formula: washdown hours, and whether the bumped order goes late and by how much and for which customer.\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down\",\"precision\":\"spelled out\",\"rationale\":\"Expert gave a lexicographic hard constraint plus unweighted second-order criteria, explicitly denying a formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "is the mill-to-fill tank on Line 1 slowing the line down",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "rationale": "Second question the expert wrote out as he would type it.",
+            "assertion": {
+              "value": "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\""
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-1a3325b9-15b6-436a-8e7f-feff95d98036",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\"\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"rationale\":\"Second question the expert wrote out as he would type it.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "is the mill-to-fill tank on Line 1 slowing the line down",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "Expert named stage-level rates on Line 1, the tank size between mill and fill, and per-SKU stage differences.",
+            "assertion": {
+              "value": [
+                "entity-type:the four stages — mix, mill, tint, fill",
+                "constraint:small holding tank between mill and fill on Line 1",
+                "entity-type:order",
+                "entity-type:line"
+              ]
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-0e28490a-6b4b-4996-9b6f-3d9249a7d2dc",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:the four stages — mix, mill, tint, fill\",\"constraint:small holding tank between mill and fill on Line 1\",\"entity-type:order\",\"entity-type:line\"]},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"named\",\"rationale\":\"Expert named stage-level rates on Line 1, the tank size between mill and fill, and per-SKU stage differences.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"different SKUs are slow at different stages, so the tank might matter a lot for some products and not at all for others\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "state that rides along with each instance",
+            "precision": "spelled out",
+            "rationale": "Expert named the fields the order carries from the demand book and the state he consults mid-disruption.",
+            "assertion": {
+              "value": "Quantity, due date, SKU; remaining quantity as it runs; the customer it belongs to; how far through it is; which line and slot it is allocated to."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "whose order was it — that's the \"who can absorb it\" judgment call again",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-43c5ef42-68ce-478f-89b0-c552111d807a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; remaining quantity as it runs; the customer it belongs to; how far through it is; which line and slot it is allocated to.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"Expert named the fields the order carries from the demand book and the state he consults mid-disruption.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"whose order was it — that's the \\\\\\\"who can absorb it\\\\\\\" judgment call again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "rationale": "The process treats whites and tints differently at the tint stage and in run times; customer type changes how a slip is judged.",
+            "assertion": {
+              "value": "Whites versus tints (for a white the tint stage is barely there, a pass-through); and by customer type — distributor, small account, or an awkward account that gets prickly."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-ccc2d7eb-8a3f-4684-8f1c-a21a51049550",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints (for a white the tint stage is barely there, a pass-through); and by customer type — distributor, small account, or an awkward account that gets prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"rationale\":\"The process treats whites and tints differently at the tint stage and in run times; customer type changes how a slip is judged.\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "line",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "sourceRegime": "prescribed",
+            "rationale": "The sheet's representation of a line, which the expert says 'lies to me a bit'.",
+            "assertion": {
+              "value": "On the scheduling sheet a line is one row and one resource: an order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a7cac8dd-02ea-4fc2-9b07-981ba2152a06",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the scheduling sheet a line is one row and one resource: an order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done.\"},\"kind\":\"entity-type\",\"node\":\"line\",\"precision\":\"spelled out\",\"rationale\":\"The sheet's representation of a line, which the expert says 'lies to me a bit'.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "the four stages — mix, mill, tint, fill",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The floor's version of the line: four contended stages with buffers, not one resource.",
+            "assertion": {
+              "value": "Physically mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head finishes the last one if the tank ahead has space."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the crew will get a head start on mixing the next batch if the tank ahead of it has space",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a158a5da-be3a-461f-87c0-69c38cac1a72",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically mix, mill, tint and fill are separate tanks and separate kit strung together with small holding tanks in between; the mixer can start the next order's batch while the fill head finishes the last one if the tank ahead has space.\"},\"kind\":\"entity-type\",\"node\":\"the four stages — mix, mill, tint, fill\",\"precision\":\"spelled out\",\"rationale\":\"The floor's version of the line: four contended stages with buffers, not one resource.\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the crew will get a head start on mixing the next batch if the tank ahead of it has space\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "the four stages — mix, mill, tint, fill",
+            "slot": "how many there are, or the population's shape",
+            "precision": "named",
+            "rationale": "Count of stages is stated; occupancy/blocking frequency is explicitly untracked.",
+            "assertion": {
+              "value": "Four stages in series per line — mix, mill, tint, fill — with small holding tanks between them; how often blocking occurs is not tracked."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-4c582a37-42ed-4d72-a3dd-5a15a6048a23",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Four stages in series per line — mix, mill, tint, fill — with small holding tanks between them; how often blocking occurs is not tracked.\"},\"kind\":\"entity-type\",\"node\":\"the four stages — mix, mill, tint, fill\",\"precision\":\"named\",\"rationale\":\"Count of stages is stated; occupancy/blocking frequency is explicitly untracked.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Expert's step one.",
+            "assertion": {
+              "value": "The order is slotted onto a line and a slot in the week on the sheet."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-4043a577-c1b4-44c3-91f3-2194def82bd9",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is slotted onto a line and a slot in the week on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Expert's step one.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "Precondition named in the walkthrough.",
+            "assertion": {
+              "value": "A line item in the demand book, produced by ERP, carrying quantity, due date and SKU."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-3a71a4b9-95cd-4d6f-9cff-70db25b37473",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book, produced by ERP, carrying quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation\",\"precision\":\"spelled out\",\"rationale\":\"Precondition named in the walkthrough.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "boundary-condition",
+            "node": "demand book from ERP",
+            "slot": "the starting state",
+            "precision": "spelled out",
+            "rationale": "External source of work into the scheduling process.",
+            "assertion": {
+              "value": "Orders exist as line items in the demand book, each with quantity, due date and SKU, once ERP produces it."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-8f9df889-b24b-49e4-8ae8-6506112e2006",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders exist as line items in the demand book, each with quantity, due date and SKU, once ERP produces it.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"spelled out\",\"rationale\":\"External source of work into the scheduling process.\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "how long it takes",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Expert corrected his first spread to strip out jams, so the clean-run figure supersedes; no one-in-ten-better figure was given for the clean run.",
+            "assertion": {
+              "value": "Meridian-sized white on Line 2, clean run (nothing breaks): typically eight to nine hours mix-to-last-pack; a bad-but-clean day nine to ten hours. Clean-run variability is small; the twelve-to-thirteen-hour bad days are breakdowns showing up inside the run and are modelled separately."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-72d414e6-f6a2-420e-8407-667f41535411",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian-sized white on Line 2, clean run (nothing breaks): typically eight to nine hours mix-to-last-pack; a bad-but-clean day nine to ten hours. Clean-run variability is small; the twelve-to-thirteen-hour bad days are breakdowns showing up inside the run and are modelled separately.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"range\",\"rationale\":\"Expert corrected his first spread to strip out jams, so the clean-run figure supersedes; no one-in-ten-better figure was given for the clean run.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "rationale": "Durations vary by line and by white-versus-tint; the Line 1 figures were given before the clean-run/breakdown split and may still fold in stoppages.",
+            "assertion": {
+              "value": "Yes. Same white order on Line 1 is about fifty to sixty percent longer than Line 2 — typical thirteen to fourteen hours, worse days eighteen-plus, best day about ten. Tints run at nearly the same speed on either line, about eight to ten hours typical, with no big gap; the 'Line 2 is twice as fast' rule is really a whites number."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-0958f3c5-59f7-4139-8942-fc5204d9d5dc",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes. Same white order on Line 1 is about fifty to sixty percent longer than Line 2 — typical thirteen to fourteen hours, worse days eighteen-plus, best day about ten. Tints run at nearly the same speed on either line, about eight to ten hours typical, with no big gap; the 'Line 2 is twice as fast' rule is really a whites number.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Durations vary by line and by white-versus-tint; the Line 1 figures were given before the clean-run/breakdown split and may still fold in stoppages.\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "run it through mix/mill/tint/fill",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "Runs are performed on a named line; the expert compares Line 1 and Line 2 as the performing kit.",
+            "assertion": {
+              "value": "One of the two production lines (Line 1 or Line 2) with its crew."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-53f9387d-f037-4d0f-999b-f89a8f113f46",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"One of the two production lines (Line 1 or Line 2) with its crew.\"},\"kind\":\"activity\",\"node\":\"run it through mix/mill/tint/fill\",\"precision\":\"named\",\"rationale\":\"Runs are performed on a named line; the expert compares Line 1 and Line 2 as the performing kit.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "Named performer in the walkthrough.",
+            "assertion": {
+              "value": "The lab."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-d7faeb42-3fb6-4e39-a4db-a4c0fb8430f1",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Named performer in the walkthrough.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "how long it takes",
+            "precision": "named",
+            "rationale": "Only a vague 'few hours' was given; not yet a range or spread.",
+            "assertion": {
+              "value": "Usually a few hours for a white; explicitly longer for specialty ('nothing like the specialty wait'), figure not given."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-38e0effa-0fb7-48ff-907c-2fc9f3e64211",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; explicitly longer for specialty ('nothing like the specialty wait'), figure not given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"rationale\":\"Only a vague 'few hours' was given; not yet a range or spread.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "release and ship",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Final step of the walkthrough.",
+            "assertion": {
+              "value": "The order is released, goes to the warehouse, and ships against its due date."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-9b796f7a-c77b-45a7-83f7-806c40aaf58f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against its due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"rationale\":\"Final step of the walkthrough.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "order life on the floor",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "rationale": "Expert's own summary of the end-to-end sequence.",
+            "assertion": {
+              "value": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-314d8187-81ba-478c-8f71-1c9e5826965b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\"},\"kind\":\"ordering/flow\",\"node\":\"order life on the floor\",\"precision\":\"spelled out\",\"rationale\":\"Expert's own summary of the end-to-end sequence.\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "how long it takes",
+            "precision": "number",
+            "rationale": "Single figure given for the tint-to-white washdown; no spread elicited.",
+            "assertion": {
+              "value": "Three hours"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-345fbb5a-c0c1-4e3a-9015-33b3ad727831",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Single figure given for the tint-to-white washdown; no spread elicited.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "Changeover is directional and triggered by the family of what was running versus what is coming.",
+            "assertion": {
+              "value": "A changeover between product families on the same line; the direction decides the cost — tint-to-white is the expensive one, not the other way."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "the direction of the changeover matters as much as the fact of it",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-60f6f8c8-f52e-443a-adee-6818339f3b35",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A changeover between product families on the same line; the direction decides the cost — tint-to-white is the expensive one, not the other way.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Changeover is directional and triggered by the family of what was running versus what is coming.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the direction of the changeover matters as much as the fact of it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Stated consequence of the washdown.",
+            "assertion": {
+              "value": "The line is cleaned from tint to white and is taken out of anything else for that window; it costs crew time."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it takes Line 1 out of anything else for that window",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-be556841-bf14-4fe0-8c23-ffc773896b2b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line is cleaned from tint to white and is taken out of anything else for that window; it costs crew time.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"rationale\":\"Stated consequence of the washdown.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what is lost when it changes the system's mode",
+            "rationale": "Loss is named and affirmed as material but no quantity is held by the expert.",
+            "assertion": {
+              "absence": "unknown-to-user",
+              "pointer": "ramp scrap after the washdown — real product lost on top of the hours; expert has no good numbers"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-26d3ac6c-4b27-4765-baa3-8437f06fe8ca",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"ramp scrap after the washdown — real product lost on top of the hours; expert has no good numbers\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"rationale\":\"Loss is named and affirmed as material but no quantity is held by the expert.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "how long it takes",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "rationale": "Expert gave two named kinds of repair plus one observed instance; no typical or decile figures yet.",
+            "assertion": {
+              "value": "Between the 'half hour' kind and the 'half a shift' kind; the recent Line 2 case came back in about two hours."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I went with waiting, it came back in about two hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-da6d10a4-e0f2-4b1d-8e78-4d58cadeb8f2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Between the 'half hour' kind and the 'half a shift' kind; the recent Line 2 case came back in about two hours.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Expert gave two named kinds of repair plus one observed instance; no typical or decile figures yet.\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "rationale": "Event-shaped activity that befalls the line, distinct from the run itself.",
+            "assertion": {
+              "value": "The filler stops mid-run and the line is down for the repair; the run in progress stretches (the twelve-to-thirteen-hour bad days), and the scheduler must decide to wait or shift the order to the other line."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-68f9db28-a002-406d-912a-4cc410e5b380",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The filler stops mid-run and the line is down for the repair; the run in progress stretches (the twelve-to-thirteen-hour bad days), and the scheduler must decide to wait or shift the order to the other line.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"Event-shaped activity that befalls the line, distinct from the run itself.\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "how often it occurs, if it is an event rather than a step",
+            "rationale": "No rate was stated; recording the gap rather than inferring one from the single incident.",
+            "assertion": {
+              "absence": "unknown-to-user",
+              "pointer": "frequency of filler jams was not given; expert spoke only to duration uncertainty at the time of the jam"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of \"could be quick, could be long\" rather than one number",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-0a06d184-bf72-42c4-95b3-7ad88ea4e059",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"frequency of filler jams was not given; expert spoke only to duration uncertainty at the time of the jam\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"rationale\":\"No rate was stated; recording the gap rather than inferring one from the single incident.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"how long is this repair *actually* going to take, which I never know at the time, so really it needs some sense of \\\\\\\"could be quick, could be long\\\\\\\" rather than one number\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "who can absorb the slip",
+            "slot": "the rule as actually practiced",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "The tacit rule for choosing which order to bump; no formula, judged on customer identity and size of slip.",
+            "assertion": {
+              "value": "Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first, so it is protected."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I use judgment on who can absorb the slip",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-3fec05b6-fd93-4759-9598-7870f4f98d7f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first, so it is protected.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"The tacit rule for choosing which order to bump; no formula, judged on customer identity and size of slip.\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "who can absorb the slip",
+            "slot": "what overrides it",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "rationale": "Hard constraint sitting above the absorb-the-slip judgment.",
+            "assertion": {
+              "value": "The protected order's on-time ship date overrides: shipping Meridian on time is a line he won't cross unless there's truly no way through."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-091d909a-fbcd-4630-bc2d-97bca63e4c7b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The protected order's on-time ship date overrides: shipping Meridian on time is a line he won't cross unless there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint sitting above the absorb-the-slip judgment.\",\"slot\":\"what overrides it\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "constraint",
+            "node": "small holding tank between mill and fill on Line 1",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "spelled out",
+            "rationale": "Qualitative blocking rule stated; the numeric capacity is not available from the expert.",
+            "assertion": {
+              "value": "Holding tanks between stages are small — especially the one between mill and fill on Line 1. When there is room, the upstream stage can start the next order's batch; when the tank is full, the upstream stage is blocked and mixing has to wait. Actual tank capacity is not held by the expert; engineering's position is that the line rate is what it is regardless."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-7111ab55-5d90-44f6-a1d2-4aa1b48da4bb",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tanks between stages are small — especially the one between mill and fill on Line 1. When there is room, the upstream stage can start the next order's batch; when the tank is full, the upstream stage is blocked and mixing has to wait. Actual tank capacity is not held by the expert; engineering's position is that the line rate is what it is regardless.\"},\"kind\":\"constraint\",\"node\":\"small holding tank between mill and fill on Line 1\",\"precision\":\"spelled out\",\"rationale\":\"Qualitative blocking rule stated; the numeric capacity is not available from the expert.\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1 — and I've always suspected that one costs us more than people admit, but I've never had anything to prove it, and engineering tells me the line rate is what it is regardless.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "data-binding",
+            "node": "stage-level rates",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "rationale": "Expert named the system where the missing stage-level numbers live.",
+            "assertion": {
+              "value": "Stage-by-stage durations/rates (how long mixing takes, how long milling takes, mill speed versus fill speed on Line 1) — feed: the historian."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-c858f8bf-b62f-41ac-8b6c-bf1ca8c5d44a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations/rates (how long mixing takes, how long milling takes, mill speed versus fill speed on Line 1) — feed: the historian.\"},\"kind\":\"data-binding\",\"node\":\"stage-level rates\",\"precision\":\"named\",\"rationale\":\"Expert named the system where the missing stage-level numbers live.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "data-binding",
+            "node": "tank sizes",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "rationale": "Named source for a value the expert cannot give.",
+            "assertion": {
+              "value": "Holding tank capacities between stages — feed: engineering drawings, obtainable but not carried by the expert."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-7d24a8e1-6236-41bd-ab99-3a1036c5b993",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tank capacities between stages — feed: engineering drawings, obtainable but not carried by the expert.\"},\"kind\":\"data-binding\",\"node\":\"tank sizes\",\"precision\":\"named\",\"rationale\":\"Named source for a value the expert cannot give.\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "switch or wait when Line 2 goes down mid-run",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "rationale": "The expert wrote the question as they would type it into the tool.",
+            "assertion": {
+              "value": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\""
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-1a240192-8179-4339-815e-3775a062e986",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\"\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down mid-run\",\"precision\":\"spelled out\",\"rationale\":\"The expert wrote the question as they would type it into the tool.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "switch or wait when Line 2 goes down mid-run",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "rationale": "The expert listed what the answer hangs on.",
+            "assertion": {
+              "value": [
+                "entity-type:order",
+                "entity-type:Line 1 and Line 2",
+                "activity:the run (mix, mill, tint, fill)",
+                "activity:filler jam",
+                "activity:tint-to-white washdown",
+                "policy:who can absorb the slip",
+                "constraint:Meridian ships on time"
+              ]
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "It hangs on the jam itself — how long is this repair *actually* going to take",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "And it hangs on the ramp scrap after the washdown",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the \"who can absorb it\" judgment call again.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-85062afa-e82d-46ce-b609-f7ed16f8b093",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:order\",\"entity-type:Line 1 and Line 2\",\"activity:the run (mix, mill, tint, fill)\",\"activity:filler jam\",\"activity:tint-to-white washdown\",\"policy:who can absorb the slip\",\"constraint:Meridian ships on time\"]},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down mid-run\",\"precision\":\"named\",\"rationale\":\"The expert listed what the answer hangs on.\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And it hangs on the ramp scrap after the washdown\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"And then the knock-on: whatever gets bumped off Line 1, does it blow its own due date, and whose order was it — that's the \\\\\\\"who can absorb it\\\\\\\" judgment call again.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"It hangs on the jam itself — how long is this repair *actually* going to take\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "switch or wait when Line 2 goes down mid-run",
+            "slot": "what \"better\" means, and trade-off weights",
+            "precision": "spelled out",
+            "rationale": "Hard constraint plus unweighted secondary measures; the expert explicitly denied having a formula.",
+            "assertion": {
+              "value": "Meridian on time is non-negotiable (days late on Meridian, anything above zero is bad news); underneath that, washdown hours and whether the bumped order goes late and by how much are weighed by judgment — \"I don't have a formula for it.\""
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I don't have a formula for it.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "days late on Meridian, and anything above zero is bad news I have to go explain",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-2c3fa15f-551b-4380-a3b3-8dbc6334a9bb",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian on time is non-negotiable (days late on Meridian, anything above zero is bad news); underneath that, washdown hours and whether the bumped order goes late and by how much are weighed by judgment — \\\"I don't have a formula for it.\\\"\"},\"kind\":\"objective\",\"node\":\"switch or wait when Line 2 goes down mid-run\",\"precision\":\"spelled out\",\"rationale\":\"Hard constraint plus unweighted secondary measures; the expert explicitly denied having a formula.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have a formula for it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"days late on Meridian, and anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "is the mill-to-fill tank on Line 1 slowing the line down",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\""
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\"",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-41269bfb-9040-4d54-a113-a94c09f6f2f0",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\"\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"Is the mill-to-fill tank on Line 1 actually slowing the line down, or is that just a story I tell myself?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "is the mill-to-fill tank on Line 1 slowing the line down",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "assertion": {
+              "value": [
+                "entity-type:mix, mill, tint, fill kit and holding tanks",
+                "entity-type:Line 1 and Line 2",
+                "entity-type:order",
+                "ordering/flow:stage overlap on a line"
+              ]
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "It also probably depends on the product, since I now realize different SKUs are slow at different stages",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-f7ea7c88-4d40-48e7-84e5-2b12ebc5ea8e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":[\"entity-type:mix, mill, tint, fill kit and holding tanks\",\"entity-type:Line 1 and Line 2\",\"entity-type:order\",\"ordering/flow:stage overlap on a line\"]},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"named\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It also probably depends on the product, since I now realize different SKUs are slow at different stages\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "is the mill-to-fill tank on Line 1 slowing the line down",
+            "slot": "what \"better\" means, and trade-off weights",
+            "precision": "spelled out",
+            "rationale": "Qualitative: showing where Line 1 loses its time, in a form usable with engineering.",
+            "assertion": {
+              "value": "The model showing \"here's where Line 1 loses its time\" — something to take to engineering other than a hunch; no numeric weighting given."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If the model can actually show me \"here's where Line 1 loses its time,\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-dcb22f82-5927-447e-a35a-4ff18d16ce26",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The model showing \\\"here's where Line 1 loses its time\\\" — something to take to engineering other than a hunch; no numeric weighting given.\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"spelled out\",\"rationale\":\"Qualitative: showing where Line 1 loses its time, in a form usable with engineering.\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If the model can actually show me \\\\\\\"here's where Line 1 loses its time,\\\\\\\" that's worth more to me long-term than just the one disruption answer, because I could take that to engineering with something other than a hunch.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "Whites versus tints (family decides run speed by line and washdown direction; for a white the tint stage is a pass-through); and customer identity — distributor, small account, or an awkward account that gets prickly."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "though for a white the tint stage is barely there, more of a pass-through than a real letdown step",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the bumped order's identity matters, not just \"an order got delayed.\"",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-0e8d50b2-4222-4129-a619-09c5612c05c5",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints (family decides run speed by line and washdown direction; for a white the tint stage is a pass-through); and customer identity — distributor, small account, or an awkward account that gets prickly.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the bumped order's identity matters, not just \\\\\\\"an order got delayed.\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"though for a white the tint stage is barely there, more of a pass-through than a real letdown step\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "state that rides along with each instance",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "Quantity, due date, SKU; family (white/tint); customer; remaining quantity and how far through the run it is."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-117f9832-aaba-473a-9411-6fd4022388f2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; family (white/tint); customer; remaining quantity and how far through the run it is.\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"spelled out\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order",
+            "slot": "how many there are, or the population's shape",
+            "precision": "named",
+            "rationale": "The expert described orders arriving as line items in the demand book but gave no counts or arrival volumes.",
+            "assertion": {
+              "absence": "unknown-to-user",
+              "pointer": "demand book / ERP"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-e10d4081-78ed-42da-bb26-857f1118224c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"demand book / ERP\"},\"kind\":\"entity-type\",\"node\":\"order\",\"precision\":\"named\",\"rationale\":\"The expert described orders arriving as line items in the demand book but gave no counts or arrival volumes.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "Line 1 and Line 2",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "Two lines: Line 2 is the faster machine on whites (roughly twice as fast, \"really a whites number\"); Line 1 is the slower machine, add fifty to sixty percent on a white. On tints the two run at nearly the same speed."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-875ed21b-d257-48fe-867b-6785abf6abb7",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two lines: Line 2 is the faster machine on whites (roughly twice as fast, \\\"really a whites number\\\"); Line 1 is the slower machine, add fifty to sixty percent on a white. On tints the two run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "Line 1 and Line 2",
+            "slot": "state that rides along with each instance",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "What order is on it, how far through that order is, and what family (tint or white) it is currently running — the last decides washdown cost and direction."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-06d48b41-86fb-48c0-b3e0-59012ba81960",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"What order is on it, how far through that order is, and what family (tint or white) it is currently running — the last decides washdown cost and direction.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"spelled out\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "Line 1 and Line 2",
+            "slot": "how many there are, or the population's shape",
+            "precision": "number",
+            "rationale": "The expert speaks only of Line 1 and Line 2 throughout.",
+            "assertion": {
+              "value": "Two lines — Line 1 and Line 2."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On the sheet, \"Line 2\" is one row",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Line 1 was mid-run on a tint.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-428e3931-676d-4af5-a30c-d7a31ea0d8ad",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two lines — Line 1 and Line 2.\"},\"kind\":\"entity-type\",\"node\":\"Line 1 and Line 2\",\"precision\":\"number\",\"rationale\":\"The expert speaks only of Line 1 and Line 2 throughout.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 was mid-run on a tint.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "mix, mill, tint, fill kit and holding tanks",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "assertion": {
+              "value": "Mix, mill, tint and fill are separate tanks and separate kit strung together, with small holding tanks between them."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-ecd3c093-8f6b-4a48-a1fc-d2775d4dbc1f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Mix, mill, tint and fill are separate tanks and separate kit strung together, with small holding tanks between them.\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill kit and holding tanks\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"But physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "mix, mill, tint, fill kit and holding tanks",
+            "slot": "how many there are, or the population's shape",
+            "precision": "named",
+            "rationale": "Qualitative \"small\" only; sizes deferred to engineering drawings.",
+            "assertion": {
+              "absence": "deferred",
+              "pointer": "engineering drawings"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I just know the tanks are small — especially the one between mill and fill on Line 1",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-c6339dee-036e-47cb-9dcf-42fc22d38aae",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"engineering drawings\"},\"kind\":\"entity-type\",\"node\":\"mix, mill, tint, fill kit and holding tanks\",\"precision\":\"named\",\"rationale\":\"Qualitative \\\"small\\\" only; sizes deferred to engineering drawings.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I just know the tanks are small — especially the one between mill and fill on Line 1\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "constraint",
+            "node": "holding tank capacity between stages",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "spelled out",
+            "rationale": "Blocking consequence stated; frequency and size not tracked.",
+            "assertion": {
+              "value": "A stage can only get a head start if there's room in the holding tank ahead of it; when a tank's full, mixing has to wait. How often that blocking happens is not tracked by the expert."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "if there's room in the holding tank between mix and mill, or mill and fill, to buffer it",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-2bc071c4-2919-4ff3-910a-92d872eeaef2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A stage can only get a head start if there's room in the holding tank ahead of it; when a tank's full, mixing has to wait. How often that blocking happens is not tracked by the expert.\"},\"kind\":\"constraint\",\"node\":\"holding tank capacity between stages\",\"precision\":\"spelled out\",\"rationale\":\"Blocking consequence stated; frequency and size not tracked.\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"if there's room in the holding tank between mix and mill, or mill and fill, to buffer it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "order lifecycle: allocate, run, QA hold, release and ship",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-6ec49aac-c165-4e2b-a937-bed3c8c51c2c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\"},\"kind\":\"ordering/flow\",\"node\":\"order lifecycle: allocate, run, QA hold, release and ship\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "order lifecycle: allocate, run, QA hold, release and ship",
+            "slot": "how a branch or merge is decided",
+            "precision": "spelled out",
+            "rationale": "The line choice is made by the scheduler at allocation and can be revisited on disruption.",
+            "assertion": {
+              "value": "The scheduler slots the order onto a line on the sheet at allocation; on a disruption the choice is re-decided — shift it to the other line or wait out the repair."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I had to decide right then whether to shift it to Line 1 or just wait out the repair",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-c3f03d77-6760-4b3b-99e5-b78d119a352f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The scheduler slots the order onto a line on the sheet at allocation; on a disruption the choice is re-decided — shift it to the other line or wait out the repair.\"},\"kind\":\"ordering/flow\",\"node\":\"order lifecycle: allocate, run, QA hold, release and ship\",\"precision\":\"spelled out\",\"rationale\":\"The line choice is made by the scheduler at allocation and can be revisited on disruption.\",\"slot\":\"how a branch or merge is decided\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I had to decide right then whether to shift it to Line 1 or just wait out the repair\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "stage overlap on a line",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "sourceRegime": "prescribed",
+            "assertion": {
+              "value": "On the sheet the line is one row: the order occupies the line for its whole run, mix through fill, and nothing else is scheduled on it until it's done."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-4cdad6ac-6cd9-46d4-b3ea-62401019ae14",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet the line is one row: the order occupies the line for its whole run, mix through fill, and nothing else is scheduled on it until it's done.\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "stage overlap on a line",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "assertion": {
+              "value": "The mixer can start the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill; the crew get a head start on mixing when the tank ahead has space."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-83e1381a-f2df-4713-a2f6-f11d034c2fd4",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The mixer can start the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill; the crew get a head start on mixing when the tank ahead has space.\"},\"kind\":\"ordering/flow\",\"node\":\"stage overlap on a line\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "the run (mix, mill, tint, fill)",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "The order allocated onto a line and a slot in the week (\"I slot it onto Line 2 on the sheet, that's step one, allocation\")."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-95cbfe20-605f-4218-9076-0f4816ebadfa",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order allocated onto a line and a slot in the week (\\\"I slot it onto Line 2 on the sheet, that's step one, allocation\\\").\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "the run (mix, mill, tint, fill)",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "Filled and packed product coming off the fill line, which then goes into QA hold."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-1a5a8343-7367-416e-b760-c7e8f587fe25",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Filled and packed product coming off the fill line, which then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "the run (mix, mill, tint, fill)",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "assertion": {
+              "value": "The line (Line 1 or Line 2) — its mix, mill, tint and fill kit — worked by the crew."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "mix, mill, tint, fill are separate tanks and separate kit strung together",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "maybe six hours if everything's clean and the crew doesn't have to stop for anything",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-bf2e57a3-bda7-4090-92ca-af63e0c7a248",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The line (Line 1 or Line 2) — its mix, mill, tint and fill kit — worked by the crew.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maybe six hours if everything's clean and the crew doesn't have to stop for anything\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill are separate tanks and separate kit strung together\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "the run (mix, mill, tint, fill)",
+            "slot": "how long it takes",
+            "precision": "spread",
+            "rationale": "First account of a white run on Line 2, mix-to-last-pack, including breakdowns folded in loosely.",
+            "assertion": {
+              "value": "White, Line 2, normal order size, mix-to-last-pack: typical eight to nine hours; one in ten worse twelve to thirteen hours; one in ten better about six hours. (Expert later said the twelve-thirteen folds in breakdowns.)"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-aec8ff27-3e3f-45d2-9142-b6dc2b5d88a3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, Line 2, normal order size, mix-to-last-pack: typical eight to nine hours; one in ten worse twelve to thirteen hours; one in ten better about six hours. (Expert later said the twelve-thirteen folds in breakdowns.)\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"rationale\":\"First account of a white run on Line 2, mix-to-last-pack, including breakdowns folded in loosely.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Bad day, one run in ten worse — you're looking at something like twelve, thirteen hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "the run (mix, mill, tint, fill)",
+            "slot": "how long it takes",
+            "precision": "spread",
+            "rationale": "Supersedes the earlier figure by stripping breakdowns out of the run duration; jams are modelled separately.",
+            "assertion": {
+              "value": "Clean run (nothing breaks), white on Line 2: typical eight or nine hours; bad-but-clean one in ten nine to ten hours; one in ten better about six hours. The twelve-thirteen hour bad day is a breakdown showing up inside the run, not the run itself being slow."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-9d59a385-a8ae-410a-a13d-a4bca3dde9a3",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Clean run (nothing breaks), white on Line 2: typical eight or nine hours; bad-but-clean one in ten nine to ten hours; one in ten better about six hours. The twelve-thirteen hour bad day is a breakdown showing up inside the run, not the run itself being slow.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"rationale\":\"Supersedes the earlier figure by stripping breakdowns out of the run duration; jams are modelled separately.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If nothing breaks — no jam, no QA holdup, nothing — a clean run doesn't really vary that much from typical. Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing. Not the twelve-thirteen number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "the run (mix, mill, tint, fill)",
+            "slot": "how long it takes",
+            "precision": "spread",
+            "rationale": "Same white order on Line 1.",
+            "assertion": {
+              "value": "White on Line 1: typical thirteen to fourteen hours; worse days pushing eighteen-plus; best day maybe ten — roughly fifty to sixty percent more than Line 2."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-4b22a066-a97c-4329-8513-cbd85edd8d65",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White on Line 1: typical thirteen to fourteen hours; worse days pushing eighteen-plus; best day maybe ten — roughly fifty to sixty percent more than Line 2.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"rationale\":\"Same white order on Line 1.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "the run (mix, mill, tint, fill)",
+            "slot": "how long it takes",
+            "precision": "range",
+            "rationale": "Only a typical range was given for tints; no one-in-ten figures.",
+            "assertion": {
+              "value": "Tint run on either line: eight to ten hours typical; no big gap between the lines. One-in-ten worse/better not given."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-63fabb67-24c4-4bee-926f-17917300c8f4",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Tint run on either line: eight to ten hours typical; no big gap between the lines. One-in-ten worse/better not given.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"range\",\"rationale\":\"Only a typical range was given for tints; no one-in-ten figures.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "the run (mix, mill, tint, fill)",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "assertion": {
+              "value": "Yes — run time varies by family and by line: whites are about twice as fast on Line 2 as Line 1, tints run at nearly the same speed on both; and different SKUs are slow at different stages."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "since I now realize different SKUs are slow at different stages",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-b1e5ded4-79d6-4ff4-bd0d-6386509efba9",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — run time varies by family and by line: whites are about twice as fast on Line 2 as Line 1, tints run at nearly the same speed on both; and different SKUs are slow at different stages.\"},\"kind\":\"activity\",\"node\":\"the run (mix, mill, tint, fill)\",\"precision\":\"named\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"since I now realize different SKUs are slow at different stages\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "It stops the run on the line — \"Line 2 filler jammed at about nine in the morning, half a shift lost\" — forcing the wait-or-shift decision."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-147c2765-6bfb-4da0-9df9-b74a1c1049de",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"It stops the run on the line — \\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\" — forcing the wait-or-shift decision.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "how often it occurs, if it is an event rather than a step",
+            "precision": "range",
+            "rationale": "Line 2 filler, jams bad enough to stop the run.",
+            "assertion": {
+              "value": "Every week or two; low end once every three weeks, high end twice a week when temperamental. Not seasonal, but runs streaks of bad weeks."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "It's a \"every week or two\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-ec5740e7-5068-4222-ad24-8396f5975657",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Every week or two; low end once every three weeks, high end twice a week when temperamental. Not seasonal, but runs streaks of bad weeks.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"range\",\"rationale\":\"Line 2 filler, jams bad enough to stop the run.\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It's a \\\\\\\"every week or two\\\\\\\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "how long it takes",
+            "precision": "spread",
+            "assertion": {
+              "value": "Typical repair thirty to forty-five minutes; one-in-ten quick ten to fifteen minutes (a false alarm); one-in-ten bad four to five hours, occasionally eating the rest of the shift, when something's actually broken in the filler head."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-2884cc84-c616-4227-860a-d6b55a06c13d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Typical repair thirty to forty-five minutes; one-in-ten quick ten to fifteen minutes (a false alarm); one-in-ten bad four to five hours, occasionally eating the rest of the shift, when something's actually broken in the filler head.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "rationale": "Repair is done by a tech.",
+            "assertion": {
+              "value": "A tech — comes over, clears whatever's jammed, resets."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "tech comes over, clears whatever's jammed, resets, we're going again",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-0548a680-8da8-47e9-ad72-fb1e264fac80",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A tech — comes over, clears whatever's jammed, resets.\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"named\",\"rationale\":\"Repair is done by a tech.\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"tech comes over, clears whatever's jammed, resets, we're going again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "rationale": "At the time of the decision the repair length is unobservable to the scheduler.",
+            "assertion": {
+              "value": "Repair duration is not known at the time of the decision — \"which I never know at the time\"; only \"could be quick, could be long\"."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "how long is this repair *actually* going to take, which I never know at the time",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-8c6a716b-e09a-4977-94d9-f28ab74be7c4",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Repair duration is not known at the time of the decision — \\\"which I never know at the time\\\"; only \\\"could be quick, could be long\\\".\"},\"kind\":\"activity\",\"node\":\"filler jam\",\"precision\":\"spelled out\",\"rationale\":\"At the time of the decision the repair length is unobservable to the scheduler.\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"how long is this repair *actually* going to take, which I never know at the time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "how long it takes",
+            "precision": "number",
+            "rationale": "Single figure given; no spread elicited.",
+            "assertion": {
+              "value": "Three hours for a tint-to-white washdown."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I eat a tint-to-white washdown — three hours",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a67683fd-0f34-4838-b48e-aa01f657a511",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours for a tint-to-white washdown.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"rationale\":\"Single figure given; no spread elicited.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I eat a tint-to-white washdown — three hours\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "A changeover of family on the line; the direction matters as much as the fact of it — tint-to-white is the expensive one, not the other way."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "the direction of the changeover matters as much as the fact of it",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-1b632a29-f1de-48e5-8f96-a5ef908c4a56",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A changeover of family on the line; the direction matters as much as the fact of it — tint-to-white is the expensive one, not the other way.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the direction of the changeover matters as much as the fact of it\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what is lost when it changes the system's mode",
+            "precision": "named",
+            "rationale": "Hours and crew time are known; ramp scrap is named but unquantified.",
+            "assertion": {
+              "absence": "unknown-to-user",
+              "pointer": "ramp scrap after the washdown — \"which I don't have good numbers for but shouldn't be ignored\"; three hours of line and crew time are known"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-9926552e-289f-4b4a-bc99-4cae34f1720a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"ramp scrap after the washdown — \\\"which I don't have good numbers for but shouldn't be ignored\\\"; three hours of line and crew time are known\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"named\",\"rationale\":\"Hours and crew time are known; ramp scrap is named but unquantified.\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "assertion": {
+              "value": "The crew, on the line being changed over (Line 1 in the incident described)."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "the three-hour tint-to-white hit is real cost, crew time",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-06aac0a9-b270-4b13-a54f-37440769d685",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The crew, on the line being changed over (Line 1 in the incident described).\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"the three-hour tint-to-white hit is real cost, crew time\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "how long it takes",
+            "precision": "range",
+            "rationale": "\"a few hours for a white\" — no quantiles given, and the specialty wait is named but unquantified.",
+            "assertion": {
+              "value": "Usually a few hours for a white; \"nothing like the specialty wait\" — specialty duration not given."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-94948329-18e7-42fe-9538-a84fd72c225d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; \\\"nothing like the specialty wait\\\" — specialty duration not given.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"range\",\"rationale\":\"\\\"a few hours for a white\\\" — no quantiles given, and the specialty wait is named but unquantified.\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "assertion": {
+              "value": "The lab."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "sits in the lab's queue, gets checked",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-16b9c643-8b17-490e-bfe0-022a06efd914",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "The order is released, goes to the warehouse, and ships against the due date."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-5ae45290-5d13-4f2b-b24b-82c66d3d48af",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "who can absorb the slip",
+            "slot": "the rule as actually practiced",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "assertion": {
+              "value": "Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I use judgment on who can absorb the slip",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-821e00ef-6923-43b0-955b-3ed7d60ce127",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment on who can absorb the slip: a distributor sliding two days is a shrug; a small account sliding a week is fine; an awkward account that gets prickly is a second problem created to solve the first.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I use judgment on who can absorb the slip\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "who can absorb the slip",
+            "slot": "what overrides it",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "The hard on-time line for an order like Meridian overrides the weighing — it is not a trade-off, and is only crossed if there's truly no way through."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-6da3fa16-460b-4f07-aefc-f941d7118f76",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The hard on-time line for an order like Meridian overrides the weighing — it is not a trade-off, and is only crossed if there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "constraint",
+            "node": "Meridian ships on time",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "Meridian ships on time, full stop; days late above zero is bad news the scheduler has to go explain. Only crossed \"unless there's truly no way through\"."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "did Meridian ship on time or not, full stop",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "days late on Meridian, and anything above zero is bad news I have to go explain",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-731a5768-edc7-4858-ad42-50d2faf4b181",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Meridian ships on time, full stop; days late above zero is bad news the scheduler has to go explain. Only crossed \\\"unless there's truly no way through\\\".\"},\"kind\":\"constraint\",\"node\":\"Meridian ships on time\",\"precision\":\"spelled out\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"days late on Meridian, and anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "boundary-condition",
+            "node": "demand book from ERP",
+            "slot": "the starting state",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "Orders start life as line items in the demand book once ERP spits it out, carrying quantity, due date and SKU."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-1bebb3ea-7788-477a-8127-593fe3fe6026",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders start life as line items in the demand book once ERP spits it out, carrying quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"spelled out\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "boundary-condition",
+            "node": "demand book from ERP",
+            "slot": "the arrival or availability pattern",
+            "precision": "named",
+            "rationale": "The expert named the demand book as the source but the arrival pattern was flagged as still open when the session ended.",
+            "assertion": {
+              "absence": "deferred",
+              "pointer": "how orders arrive into the demand book — named as still open at the close of the session"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "it starts life as a line item in the demand book once ERP spits that out",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-07cb7ca9-27c5-4395-bc9e-aaebc5811382",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"how orders arrive into the demand book — named as still open at the close of the session\"},\"kind\":\"boundary-condition\",\"node\":\"demand book from ERP\",\"precision\":\"named\",\"rationale\":\"The expert named the demand book as the source but the arrival pattern was flagged as still open when the session ended.\",\"slot\":\"the arrival or availability pattern\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"it starts life as a line item in the demand book once ERP spits that out\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "data-binding",
+            "node": "stage-level times in the historian",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "assertion": {
+              "value": "Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the historian; never pulled apart by the expert."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "nobody's ever broken that down by \"how long does mixing take, how long does milling take\" — that lives in the historian somewhere, and I've never pulled it apart like that",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-882fa9a2-3a16-46df-90b7-d5ab8ee1dce2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Stage-by-stage durations (how long mixing takes, how long milling takes) — feed: the historian; never pulled apart by the expert.\"},\"kind\":\"data-binding\",\"node\":\"stage-level times in the historian\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"nobody's ever broken that down by \\\\\\\"how long does mixing take, how long does milling take\\\\\\\" — that lives in the historian somewhere, and I've never pulled it apart like that\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "data-binding",
+            "node": "tank sizes from engineering drawings",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "assertion": {
+              "value": "Holding tank sizes, especially mill-to-fill on Line 1 — feed: engineering drawings."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-b6c2c920-801d-4858-b2c7-64c13ebfc5b1",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Holding tank sizes, especially mill-to-fill on Line 1 — feed: engineering drawings.\"},\"kind\":\"data-binding\",\"node\":\"tank sizes from engineering drawings\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "data-binding",
+            "node": "filler repair work-order times in the CMMS",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "assertion": {
+              "value": "Actual filler repair durations — feed: maintenance work-order times in the CMMS; never pulled by the expert."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "maintenance would have the actual work-order times in the CMMS but I've never pulled them",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-a0429a34-1145-458d-bada-32d827d68959",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Actual filler repair durations — feed: maintenance work-order times in the CMMS; never pulled by the expert.\"},\"kind\":\"data-binding\",\"node\":\"filler repair work-order times in the CMMS\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"maintenance would have the actual work-order times in the CMMS but I've never pulled them\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "wait or shift when Line 2 goes down",
+            "slot": "the question, in the expert's words",
+            "precision": "spelled out",
+            "rationale": "The expert wrote the question as he would type it into the tool.",
+            "assertion": {
+              "value": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\""
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\"",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-48033ee8-f7eb-4615-b21f-018837fc9c5e",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\"\"},\"kind\":\"objective\",\"node\":\"wait or shift when Line 2 goes down\",\"precision\":\"spelled out\",\"rationale\":\"The expert wrote the question as he would type it into the tool.\",\"slot\":\"the question, in the expert's words\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"\\\\\\\"If Line 2 goes down mid-run, is it cheaper to wait for the repair or shift the order to Line 1, given what that costs the order already running there?\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "wait or shift when Line 2 goes down",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "assertion": {
+              "value": "entity-type:order (demand book line item) — its due date and remaining quantity; entity-type:line (Line 1 / Line 2) — what is on Line 1 and how far through; entity-type:product family (white vs tint); activity:production run (mix, mill, tint, fill); activity:filler jam on Line 2 — repair length unknown at the time; activity:tint-to-white washdown — including its direction and ramp scrap; policy:who can absorb the slip — whose tint got bumped"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "What it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just \"an order got delayed.\"",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-88da9925-d922-48c3-8ea0-2c631df3ae3d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"entity-type:order (demand book line item) — its due date and remaining quantity; entity-type:line (Line 1 / Line 2) — what is on Line 1 and how far through; entity-type:product family (white vs tint); activity:production run (mix, mill, tint, fill); activity:filler jam on Line 2 — repair length unknown at the time; activity:tint-to-white washdown — including its direction and ramp scrap; policy:who can absorb the slip — whose tint got bumped\"},\"kind\":\"objective\",\"node\":\"wait or shift when Line 2 goes down\",\"precision\":\"named\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What it hangs on: the run I'm trying to protect (Meridian, its due date, its remaining quantity), the state of Line 1 right then — what's on it, how far through, what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way). It hangs on the jam itself — how long is this repair *actually* going to take\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the direction of the changeover matters as much as the fact of it, and the bumped order's identity matters, not just \\\\\\\"an order got delayed.\\\\\\\"\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "wait or shift when Line 2 goes down",
+            "slot": "what \"better\" means, and trade-off weights",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "assertion": {
+              "value": "Lexicographic: days late on Meridian first, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \"cross the line\" situation. I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-f53d8f62-375e-4af6-9aaa-fb903839993c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Lexicographic: days late on Meridian first, anything above zero is bad; below that, weigh washdown hours against whether the bumped order goes late and by how much and who the customer is. No formula — judgment on who can absorb the slip.\"},\"kind\":\"objective\",\"node\":\"wait or shift when Line 2 goes down\",\"precision\":\"spelled out\",\"slot\":\"what \\\"better\\\" means, and trade-off weights\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: Meridian on time is non-negotiable, and everything else — washdown hours, whether the bumped order goes late and by how much — is what I'm weighing when I'm not in a \\\\\\\"cross the line\\\\\\\" situation. I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"the first number is just yes/no, or if you want it as a number, days late on Meridian, and anything above zero is bad news I have to go explain.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "objective",
+            "node": "is the mill-to-fill tank on Line 1 slowing the line down",
+            "slot": "the nodes it depends on",
+            "precision": "named",
+            "assertion": {
+              "value": "activity:production run (mix, mill, tint, fill) — stage-level mill speed versus fill speed on Line 1; constraint:small holding tanks between stages — the mill-to-fill tank size on Line 1; entity-type:product family (white vs tint) — different SKUs are slow at different stages"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-ac435640-eea2-4ad6-9695-8e5408b4d852",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"activity:production run (mix, mill, tint, fill) — stage-level mill speed versus fill speed on Line 1; constraint:small holding tanks between stages — the mill-to-fill tank size on Line 1; entity-type:product family (white vs tint) — different SKUs are slow at different stages\"},\"kind\":\"objective\",\"node\":\"is the mill-to-fill tank on Line 1 slowing the line down\",\"precision\":\"named\",\"slot\":\"the nodes it depends on\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That one hangs on the stage-level rates — mill speed versus fill speed on Line 1 specifically — and the tank size between them, neither of which I have. It also probably depends on the product, since I now realize different SKUs are slow at different stages\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "data-binding",
+            "node": "stage-level times from the historian and tank sizes from engineering drawings",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "assertion": {
+              "absence": "deferred",
+              "pointer": "the historian (stage-by-stage times) and engineering drawings (tank sizes)"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I don't have clean numbers for tank sizes or stage-by-stage rates.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 15,
+              "entryEnd": 15
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-f5a658db-c8ec-4ca0-8a87-3ad252dee56d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"the historian (stage-by-stage times) and engineering drawings (tank sizes)\"},\"kind\":\"data-binding\",\"node\":\"stage-level times from the historian and tank sizes from engineering drawings\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have clean numbers for tank sizes or stage-by-stage rates.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"that lives in the historian somewhere, and I've never pulled it apart like that. Tank sizes I could probably get from engineering drawings, but I don't carry them in my head.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":15,\\\"entryStart\\\":15,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "data-binding",
+            "node": "filler repair times from the CMMS",
+            "slot": "the variable and its feed",
+            "precision": "named",
+            "assertion": {
+              "absence": "deferred",
+              "pointer": "maintenance work-order times in the CMMS"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "maintenance would have the actual work-order times in the CMMS but I've never pulled them.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I'll ask maintenance for the CMMS numbers on the filler too while I'm at it.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 30,
+              "entryEnd": 30
+            },
+            "source": "user"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-618842bb-d23d-4371-ae57-73e5257ba215",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"deferred\",\"pointer\":\"maintenance work-order times in the CMMS\"},\"kind\":\"data-binding\",\"node\":\"filler repair times from the CMMS\",\"precision\":\"named\",\"slot\":\"the variable and its feed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I'll ask maintenance for the CMMS numbers on the filler too while I'm at it.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":30,\\\"entryStart\\\":30,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user\\\"}\",\"{\\\"excerpt\\\":\\\"maintenance would have the actual work-order times in the CMMS but I've never pulled them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "boundary-condition",
+            "node": "demand book line items out of ERP",
+            "slot": "the starting state",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "An order starts life as a line item in the demand book once ERP spits that out, carrying quantity, due date and SKU."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-538fb022-2495-46bb-8661-8e1f38c802bf",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"An order starts life as a line item in the demand book once ERP spits that out, carrying quantity, due date and SKU.\"},\"kind\":\"boundary-condition\",\"node\":\"demand book line items out of ERP\",\"precision\":\"spelled out\",\"slot\":\"the starting state\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order (demand book line item)",
+            "slot": "state that rides along with each instance",
+            "precision": "spelled out",
+            "rationale": "Quantity, due date and SKU are explicit; remaining quantity and customer identity are named later as things the answer hangs on.",
+            "assertion": {
+              "value": "Quantity, due date, SKU; plus remaining quantity and the customer's identity, which the expert weighs when an order slips."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-ec8c16b7-d4c0-46fa-a64d-63a23fa37b98",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Quantity, due date, SKU; plus remaining quantity and the customer's identity, which the expert weighs when an order slips.\"},\"kind\":\"entity-type\",\"node\":\"order (demand book line item)\",\"precision\":\"spelled out\",\"rationale\":\"Quantity, due date and SKU are explicit; remaining quantity and customer identity are named later as things the answer hangs on.\",\"slot\":\"state that rides along with each instance\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "order (demand book line item)",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "assertion": {
+              "value": "Orders are treated apart by whose order it is: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-5d5f862f-c18c-4501-b544-76735d28e004",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Orders are treated apart by whose order it is: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem.\"},\"kind\":\"entity-type\",\"node\":\"order (demand book line item)\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "product family (white vs tint)",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step; tints run at nearly the same speed on both lines while whites do not; and the tint-to-white changeover direction is the expensive one."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-7f6b8be1-6336-465f-8e11-36a5277d51bd",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Whites versus tints: for a white the tint stage is barely there, more of a pass-through than a real letdown step; tints run at nearly the same speed on both lines while whites do not; and the tint-to-white changeover direction is the expensive one.\"},\"kind\":\"entity-type\",\"node\":\"product family (white vs tint)\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"mix, mill, tint, fill and pack, same four stages every product goes through, though for a white the tint stage is barely there, more of a pass-through than a real letdown step.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "line (Line 1 / Line 2)",
+            "slot": "the distinctions the process treats apart",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "Line 1 is the slower machine on whites (add maybe fifty, sixty percent to Line 2's times); on tints Line 1 and Line 2 run at nearly the same speed."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Line 1 and Line 2 run tints at nearly the same speed",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-1a83c9c6-a8f8-4ece-a5d4-53b81bf8cc9b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Line 1 is the slower machine on whites (add maybe fifty, sixty percent to Line 2's times); on tints Line 1 and Line 2 run at nearly the same speed.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"spelled out\",\"slot\":\"the distinctions the process treats apart\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 1 and Line 2 run tints at nearly the same speed\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "entity-type",
+            "node": "line (Line 1 / Line 2)",
+            "slot": "how many there are, or the population's shape",
+            "precision": "number",
+            "rationale": "Only Line 1 and Line 2 are ever named; the count itself was never stated as a figure.",
+            "assertion": {
+              "value": "Two lines (Line 1 and Line 2), each comprising separate mix, mill, tint and fill kit with small holding tanks between."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "inferred",
+        "id": "capture-e6ae51ed-e1f6-45f3-aab1-c4bca2a979e8",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Two lines (Line 1 and Line 2), each comprising separate mix, mill, tint and fill kit with small holding tanks between.\"},\"kind\":\"entity-type\",\"node\":\"line (Line 1 / Line 2)\",\"precision\":\"number\",\"rationale\":\"Only Line 1 and Line 2 are ever named; the count itself was never stated as a figure.\",\"slot\":\"how many there are, or the population's shape\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"physically, no — mix, mill, tint, fill are separate tanks and separate kit strung together with small holding tanks in between.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "order flow from demand book to ship",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship against the due date."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-c2d2a972-d139-43a7-80c2-50108d92f7a7",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship against the due date.\"},\"kind\":\"ordering/flow\",\"node\":\"order flow from demand book to ship\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So really: allocate it onto a line and a slot in the week → run it through mix/mill/tint/fill → QA hold → release and ship. Four steps if you count QA and shipping as one, five if you split them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "line occupancy across the four stages",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "sourceRegime": "prescribed",
+            "assertion": {
+              "value": "On the sheet, Line 2 is one row: the order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On the sheet, \"Line 2\" is one row — I treat it as one thing, the order occupies \"Line 2\" for its whole run, mix through fill, nothing else scheduled on it till it's done.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-6c277c9b-2362-4158-8a3b-e069ff0c9a01",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"On the sheet, Line 2 is one row: the order occupies Line 2 for its whole run, mix through fill, and nothing else is scheduled on it until it is done.\"},\"kind\":\"ordering/flow\",\"node\":\"line occupancy across the four stages\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"prescribed\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On the sheet, \\\\\\\"Line 2\\\\\\\" is one row — I treat it as one thing, the order occupies \\\\\\\"Line 2\\\\\\\" for its whole run, mix through fill, nothing else scheduled on it till it's done.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "ordering/flow",
+            "node": "line occupancy across the four stages",
+            "slot": "the order things happen in",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "assertion": {
+              "value": "Physically the stages overlap: the mixer can start the next order's batch while the fill head is still finishing the last one, if there is room in the holding tank between mix and mill, or mill and fill; the crew will get a head start on mixing if the tank ahead has space."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-7f9ac97e-375b-4de3-bbcd-b65e5c7427a6",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Physically the stages overlap: the mixer can start the next order's batch while the fill head is still finishing the last one, if there is room in the holding tank between mix and mill, or mill and fill; the crew will get a head start on mixing if the tank ahead has space.\"},\"kind\":\"ordering/flow\",\"node\":\"line occupancy across the four stages\",\"precision\":\"spelled out\",\"slot\":\"the order things happen in\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So in principle the mixer could be starting the next order's batch while the fill head is still finishing the last one, if there's room in the holding tank between mix and mill, or mill and fill, to buffer it. That does happen sometimes — the crew will get a head start on mixing the next batch if the tank ahead of it has space.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "constraint",
+            "node": "small holding tanks between stages",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "The tanks are small — especially the one between mill and fill on Line 1 — and when a tank is full, mixing has to wait; how much overlap happens or how often it is blocked is not tracked."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 12,
+              "entryEnd": 12
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-66fbb371-91b7-41db-b437-5bd207d08aed",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The tanks are small — especially the one between mill and fill on Line 1 — and when a tank is full, mixing has to wait; how much overlap happens or how often it is blocked is not tracked.\"},\"kind\":\"constraint\",\"node\":\"small holding tanks between stages\",\"precision\":\"spelled out\",\"slot\":\"the limit and what happens when it is hit\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"What I don't really track is *how much* overlap happens or how often it's blocked because a tank's full and mixing has to wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":12,\\\"entryStart\\\":12,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation onto a line and a slot in the week",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "assertion": {
+              "value": "The master scheduler, on the sheet."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-8da19d62-c082-41f6-ac55-f28afe266a8c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The master scheduler, on the sheet.\"},\"kind\":\"activity\",\"node\":\"allocation onto a line and a slot in the week\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation onto a line and a slot in the week",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "A line item in the demand book out of ERP, with quantity, due date and SKU."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-995374a1-2d25-4690-8397-b342f46ebf02",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A line item in the demand book out of ERP, with quantity, due date and SKU.\"},\"kind\":\"activity\",\"node\":\"allocation onto a line and a slot in the week\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"So it starts life as a line item in the demand book once ERP spits that out — quantity, due date, SKU. I slot it onto Line 2 on the sheet, that's step one, allocation.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "allocation onto a line and a slot in the week",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "The order is placed onto a named line and a slot in the week."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "allocate it onto a line and a slot in the week",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-3cc84392-4ed4-4804-8a7c-db07d384a8b2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is placed onto a named line and a slot in the week.\"},\"kind\":\"activity\",\"node\":\"allocation onto a line and a slot in the week\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"allocate it onto a line and a slot in the week\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "production run (mix, mill, tint, fill)",
+            "slot": "what it needs before it can start",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "The order allocated to a line and a slot in the week; then it runs the same four stages every product goes through — mix, mill, tint, fill and pack."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-289ac648-e939-4e62-ad46-a17b112402d4",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order allocated to a line and a slot in the week; then it runs the same four stages every product goes through — mix, mill, tint, fill and pack.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it needs before it can start\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it actually has to get produced — mix, mill, tint, fill and pack, same four stages every product goes through\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "production run (mix, mill, tint, fill)",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "Packed product coming off the fill line, which then goes into QA hold."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-5376c084-3889-476f-adab-b09a038ded28",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Packed product coming off the fill line, which then goes into QA hold.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "production run (mix, mill, tint, fill)",
+            "slot": "how long it takes",
+            "precision": "spread",
+            "sourceRegime": "practiced",
+            "assertion": {
+              "value": "White, Meridian-sized, on Line 2, clean of breakdowns: typical eight to nine hours mix-to-last-pack; one in ten worse nine to ten hours; one in ten better maybe six hours."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-b9dfddf9-52d8-433e-81b8-5611e7356c34",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"White, Meridian-sized, on Line 2, clean of breakdowns: typical eight to nine hours mix-to-last-pack; one in ten worse nine to ten hours; one in ten better maybe six hours.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Good day, one in ten better, maybe six hours if everything's clean and the crew doesn't have to stop for anything.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Maybe nine, ten hours on a bad-but-clean day versus eight or nine typical, just normal slack, someone's a bit slow changing a roll of packaging film, that sort of thing.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a typical Meridian-sized white run on Line 2 — we're usually talking a full shift, maybe a bit more, call it eight, nine hours mix-to-last-pack for a normal order size\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "production run (mix, mill, tint, fill)",
+            "slot": "how long it takes",
+            "precision": "spread",
+            "assertion": {
+              "value": "Same white order on Line 1: typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten — add maybe fifty, sixty percent to Line 2. (Stated before the breakdown/clean-run split was drawn, so the worse figure may still fold in jams.)"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-27ae8fdf-c227-4160-a1a5-e85530156938",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Same white order on Line 1: typical thirteen to fourteen hours, worse days pushing eighteen-plus, best day maybe ten — add maybe fifty, sixty percent to Line 2. (Stated before the breakdown/clean-run split was drawn, so the worse figure may still fold in jams.)\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"On Line 1, same order — slower machine, so add maybe fifty, sixty percent to all of that. Call it typical thirteen, fourteen hours, worse days pushing eighteen-plus, best day maybe ten.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "production run (mix, mill, tint, fill)",
+            "slot": "how long it takes",
+            "precision": "range",
+            "assertion": {
+              "value": "A tint run on either line: eight to ten hours typical, without the Line 1 / Line 2 gap."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "so a tint run on either line looks more like eight to ten hours typical, without that big gap",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-7bd393bf-3f05-4aa1-b15a-968c293b076f",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A tint run on either line: eight to ten hours typical, without the Line 1 / Line 2 gap.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"range\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"so a tint run on either line looks more like eight to ten hours typical, without that big gap\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "production run (mix, mill, tint, fill)",
+            "slot": "whether its quantities vary by type",
+            "precision": "named",
+            "assertion": {
+              "value": "Yes — run time varies by product family and line: whites are much slower on Line 1, tints are nearly the same speed on either line; the \"Line 2 is twice as fast\" figure is really a whites number. No explanation for the tint case; it is sheet-derived."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "That's the \"Line 2 is twice as fast\" thing people say, though that's really a whites number.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 18,
+              "entryEnd": 18
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-ef41e72f-3126-4003-82b2-686b5f8bfdfb",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Yes — run time varies by product family and line: whites are much slower on Line 1, tints are nearly the same speed on either line; the \\\"Line 2 is twice as fast\\\" figure is really a whites number. No explanation for the tint case; it is sheet-derived.\"},\"kind\":\"activity\",\"node\":\"production run (mix, mill, tint, fill)\",\"precision\":\"named\",\"slot\":\"whether its quantities vary by type\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"That's the \\\\\\\"Line 2 is twice as fast\\\\\\\" thing people say, though that's really a whites number.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"Tints are the funny one — I mentioned this before — Line 1 and Line 2 run tints at nearly the same speed, so a tint run on either line looks more like eight to ten hours typical, without that big gap. I've never had a good reason for why, it's just something the sheet has always shown when I've compared them.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":18,\\\"entryStart\\\":18,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam on Line 2",
+            "slot": "how often it occurs, if it is an event rather than a step",
+            "precision": "range",
+            "sourceRegime": "practiced",
+            "assertion": {
+              "value": "Every week or two; low end once every three weeks, high end twice a week. Not seasonal, but runs streaks of bad weeks."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "It's a \"every week or two\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-4fa34ba3-82e3-4a4a-ad28-362765a40046",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Every week or two; low end once every three weeks, high end twice a week. Not seasonal, but runs streaks of bad weeks.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"range\",\"slot\":\"how often it occurs, if it is an event rather than a step\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"It's a \\\\\\\"every week or two\\\\\\\" thing — low end maybe once every three weeks if we're lucky, high end twice a week if it's being temperamental. It's not seasonal or anything I can point to, it just runs a streak of bad weeks sometimes.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam on Line 2",
+            "slot": "how long it takes",
+            "precision": "spread",
+            "sourceRegime": "practiced",
+            "assertion": {
+              "value": "Repair: typical thirty to forty-five minutes; quick one-in-ten ten to fifteen minutes (basically a false alarm); bad one-in-ten four to five hours when something is actually broken in the filler head, occasionally eating the rest of the shift."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-2f670377-be1e-4275-9e46-24dd13316300",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Repair: typical thirty to forty-five minutes; quick one-in-ten ten to fifteen minutes (basically a false alarm); bad one-in-ten four to five hours when something is actually broken in the filler head, occasionally eating the rest of the shift.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"spread\",\"slot\":\"how long it takes\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"typical repair is call it thirty to forty-five minutes — tech comes over, clears whatever's jammed, resets, we're going again. Quick one-in-ten is more like ten, fifteen minutes, basically a false alarm. The bad one-in-ten is the one that scares me — that's when it's not just a jam but something's actually broken in the filler head, and that can run four, five hours, occasionally eating the rest of the shift.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam on Line 2",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "assertion": {
+              "value": "A tech comes over, clears whatever's jammed and resets."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "tech comes over, clears whatever's jammed, resets, we're going again",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 27,
+              "entryEnd": 27
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-9dc62989-7db7-4e58-baf1-b9ed0400d9a2",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"A tech comes over, clears whatever's jammed and resets.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"tech comes over, clears whatever's jammed, resets, we're going again\\\",\\\"pointer\\\":{\\\"entryEnd\\\":27,\\\"entryStart\\\":27,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "filler jam on Line 2",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "The run stops and time is lost inside the run — the big bad days (twelve to thirteen hours) are the breakdown showing up inside the run rather than the run being slow."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Line 2 filler jammed at about nine in the morning, half a shift lost.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 21,
+              "entryEnd": 21
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-b92eccd9-e2ad-41a9-abce-bb1cf8b3c328",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The run stops and time is lost inside the run — the big bad days (twelve to thirteen hours) are the breakdown showing up inside the run rather than the run being slow.\"},\"kind\":\"activity\",\"node\":\"filler jam on Line 2\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Line 2 filler jammed at about nine in the morning, half a shift lost.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"The twelve-thirteen is almost always because something broke or stalled — the filler jam, mostly, sometimes a materials hiccup.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":21,\\\"entryStart\\\":21,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "how long it takes",
+            "precision": "number",
+            "assertion": {
+              "value": "Three hours."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-55e95600-febe-4c98-8859-a56eb23ab156",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"If I pull Line 1 off that to cover Meridian, I eat a tint-to-white washdown — three hours — plus the tint order I bumped now might itself be late.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what is lost when it changes the system's mode",
+            "precision": "number",
+            "assertion": {
+              "value": "Three hours of crew time with Line 1 out of anything else for that window; direction matters — tint-to-white is the expensive one, not the other way."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-29c03a62-4be2-4dc2-852e-bfeab6770f1b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Three hours of crew time with Line 1 out of anything else for that window; direction matters — tint-to-white is the expensive one, not the other way.\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"number\",\"slot\":\"what is lost when it changes the system's mode\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Underneath that it's washdown hours — the three-hour tint-to-white hit is real cost, crew time, and it takes Line 1 out of anything else for that window.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"what family it is, because that decides the washdown cost and direction (tint-to-white is the expensive one, not the other way)\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "tint-to-white washdown",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "assertion": {
+              "absence": "unknown-to-user",
+              "pointer": "ramp scrap after the washdown — real product lost on top of the hours; no good numbers and no source named"
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 24,
+              "entryEnd": 24
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-9f708103-e43a-4766-bca4-cb3b7060fdcd",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"absence\":\"unknown-to-user\",\"pointer\":\"ramp scrap after the washdown — real product lost on top of the hours; no good numbers and no source named\"},\"kind\":\"activity\",\"node\":\"tint-to-white washdown\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"And it hangs on the ramp scrap after the washdown, which I don't have good numbers for but shouldn't be ignored, because that's real product lost on top of the hours.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":24,\\\"entryStart\\\":24,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "release and ship",
+            "slot": "what it produces or changes",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "The order is released, goes to the warehouse, and ships against the due date."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Then it's released, goes to the warehouse, and ships against the due date.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-fdecb081-5b4a-4c7b-b11d-e0d780df210c",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The order is released, goes to the warehouse, and ships against the due date.\"},\"kind\":\"activity\",\"node\":\"release and ship\",\"precision\":\"spelled out\",\"slot\":\"what it produces or changes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Then it's released, goes to the warehouse, and ships against the due date.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "how long it takes",
+            "precision": "named",
+            "assertion": {
+              "value": "Usually a few hours for a white; nothing like the specialty wait (the specialty wait itself was never quantified)."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-c9379f74-4d1e-41c6-b1bf-a53c9d8fb64d",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Usually a few hours for a white; nothing like the specialty wait (the specialty wait itself was never quantified).\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"how long it takes\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked, that's usually a few hours for a white, nothing like the specialty wait.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "activity",
+            "node": "QA hold",
+            "slot": "who or what performs it",
+            "precision": "named",
+            "assertion": {
+              "value": "The lab — it sits in the lab's queue and gets checked."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 9,
+              "entryEnd": 9
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-12e575e7-b7a9-472d-b165-308334ae7513",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The lab — it sits in the lab's queue and gets checked.\"},\"kind\":\"activity\",\"node\":\"QA hold\",\"precision\":\"named\",\"slot\":\"who or what performs it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"Once it comes off the fill line it goes into QA hold — sits in the lab's queue, gets checked\\\",\\\"pointer\\\":{\\\"entryEnd\\\":9,\\\"entryStart\\\":9,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "wait for the repair or shift the order to Line 1",
+            "slot": "the rule as actually practiced",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "assertion": {
+              "value": "Gut math at the huddle: weigh the gamble that the repair is the \"half hour\" kind against the tint-to-white washdown plus the bumped tint order going late. In the Meridian case he went with waiting; it came back in about two hours and just scraped the Thursday due date."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "I went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "If I wait on Line 2, I'm gambling the repair is the \"half hour\" kind and not the \"half a shift\" kind.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 3,
+              "entryEnd": 3
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-bc9d210e-beb9-4f7a-aa5d-243950605a2a",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Gut math at the huddle: weigh the gamble that the repair is the \\\"half hour\\\" kind against the tint-to-white washdown plus the bumped tint order going late. In the Meridian case he went with waiting; it came back in about two hours and just scraped the Thursday due date.\"},\"kind\":\"policy\",\"node\":\"wait for the repair or shift the order to Line 1\",\"precision\":\"spelled out\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I went with waiting, it came back in about two hours, we just scraped the Thursday due date. But I was sweating it, and honestly I couldn't tell you if that was the right call or I just got lucky.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"If I wait on Line 2, I'm gambling the repair is the \\\\\\\"half hour\\\\\\\" kind and not the \\\\\\\"half a shift\\\\\\\" kind.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":3,\\\"entryStart\\\":3,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "wait for the repair or shift the order to Line 1",
+            "slot": "what overrides it",
+            "precision": "spelled out",
+            "assertion": {
+              "value": "The Meridian-style on-time due date overrides the weighing — a line he won't cross unless there's truly no way through."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-90a38599-7f1b-46ed-9352-d3dd3566b338",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The Meridian-style on-time due date overrides the weighing — a line he won't cross unless there's truly no way through.\"},\"kind\":\"policy\",\"node\":\"wait for the repair or shift the order to Line 1\",\"precision\":\"spelled out\",\"slot\":\"what overrides it\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "hedged",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "policy",
+            "node": "who can absorb the slip",
+            "slot": "the rule as actually practiced",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "assertion": {
+              "value": "Judgment, not a formula: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "I don't have a formula for it. It's more \"how bad is bad\" for the second-order stuff, and I use judgment on who can absorb the slip.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-d889a88e-b7be-4055-9da1-e64f9fc858b0",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"Judgment, not a formula: a distributor sliding two days is a shrug, a small account sliding a week is fine, an awkward account that gets prickly is a second problem created to solve the first.\"},\"kind\":\"policy\",\"node\":\"who can absorb the slip\",\"precision\":\"spelled out\",\"slot\":\"the rule as actually practiced\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"I don't have a formula for it. It's more \\\\\\\"how bad is bad\\\\\\\" for the second-order stuff, and I use judgment on who can absorb the slip.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"a distributor sliding two days is a shrug and a small account sliding a week is fine, but if it's another awkward account that gets prickly, that's a second problem I've created to solve the first one.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      },
+      {
+        "confidence": "firm",
+        "content": {
+          "value": {
+            "type": "slot-asserted",
+            "kind": "constraint",
+            "node": "Meridian-style due date is a line I won't cross",
+            "slot": "the limit and what happens when it is hit",
+            "precision": "spelled out",
+            "sourceRegime": "practiced",
+            "assertion": {
+              "value": "The protected order must ship on time; days late above zero is bad news the scheduler has to go explain. The line is crossed only if there's truly no way through."
+            }
+          }
+        },
+        "evidence": [
+          {
+            "excerpt": "did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          },
+          {
+            "excerpt": "anything above zero is bad news I have to go explain",
+            "pointer": {
+              "sessionId": "baseline-condition-5-2026-08-25T19-21-21-703Z",
+              "entryStart": 6,
+              "entryEnd": 6
+            },
+            "source": "user-affordance-payload"
+          }
+        ],
+        "epistemicStatus": "explicit",
+        "id": "capture-173c6d39-090f-49a7-9e38-c8998003718b",
+        "dedupKey": "{\"content\":{\"value\":{\"assertion\":{\"value\":\"The protected order must ship on time; days late above zero is bad news the scheduler has to go explain. The line is crossed only if there's truly no way through.\"},\"kind\":\"constraint\",\"node\":\"Meridian-style due date is a line I won't cross\",\"precision\":\"spelled out\",\"slot\":\"the limit and what happens when it is hit\",\"sourceRegime\":\"practiced\",\"type\":\"slot-asserted\"}},\"evidence\":[\"{\\\"excerpt\\\":\\\"anything above zero is bad news I have to go explain\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\",\"{\\\"excerpt\\\":\\\"did Meridian ship on time or not, full stop — that one's not really a trade-off, that's a line I won't cross unless there's truly no way through.\\\",\\\"pointer\\\":{\\\"entryEnd\\\":6,\\\"entryStart\\\":6,\\\"sessionId\\\":\\\"baseline-condition-5-2026-08-25T19-21-21-703Z\\\"},\\\"source\\\":\\\"user-affordance-payload\\\"}\"]}"
+      }
+    ],
+    "issues": [],
+    "events": []
+  }
+}
diff --git a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
index 8f7572ec9ae..74a004740ef 100644
--- a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
+++ b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
@@ -202,3 +202,16 @@ written against.
 - Restricted "One incident is not a rate" to plugins demanding `range` or
   `spread`, removed unqualified grade terminology from SDCPN prose, and shared
   demand formatting between completion diagnostics and rendered instructions.
+
+### Catalogue freeze
+
+Conditions 4 and 5 completed against the cycle-two definitions on 2026-08-26.
+The review found no fact that required adding, merging, or dropping a key. The
+fixed catalogue therefore freezes at cycle two.
+
+The runs did expose residual harness work: node identity and deduplication,
+quote-repair efficiency, prompt-only delivery classification, and a terminal act
+for an incomplete engagement after the expert stops. Those findings belong to
+the sweep/fold, evaluation, and session-control machinery; none is repaired by a
+new plugin-authoring key. The evidence and full verdict are recorded in the
+[baseline read-out](../../../docs/evidence/evaluations/process-model-elicitation/baseline/readout.md).

From 4c8615b12a3debe091c3677cf0eb35ed638ec485 Mon Sep 17 00:00:00 2001
From: Lu Nelson <ln@hash.ai>
Date: Wed, 26 Aug 2026 17:46:18 +0200
Subject: [PATCH 8/9] Reconcile plugin freeze evidence

Co-authored-by: Cursor <cursoragent@cursor.com>
---
 libs/@hashintel/brunch-agent/docs/INDEX.md    |  2 +-
 .../brunch-agent/docs/control/STRATEGY-LOG.md |  2 +-
 .../baseline/condition-5-turn-latency.md      |  5 +++--
 .../baseline/readout.md                       | 19 ++++++++++++++-----
 .../packages/core/schema/CHANGELOG.md         |  5 ++++-
 5 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/libs/@hashintel/brunch-agent/docs/INDEX.md b/libs/@hashintel/brunch-agent/docs/INDEX.md
index 81c96c6ce46..9da2fafed2e 100644
--- a/libs/@hashintel/brunch-agent/docs/INDEX.md
+++ b/libs/@hashintel/brunch-agent/docs/INDEX.md
@@ -63,7 +63,7 @@ partition is [`docs/agents/partition-worktrees.md`](agents/partition-worktrees.m
 | [research/elicitation-strategy-literature](reference/research/elicitation/elicitation-strategy-literature.md)                   | active     | gisted in FE-1360 resolution             | Literature synthesis, 9 sections, verification-labeled                                                                                                                                                                                                                                                                 |
 | [research/re-interviewing-literature-worker-report](reference/research/elicitation/interviewing-literature-source-catalog.md) | active     | noted on FE-1361                         | Verbatim instruments: 34-mistake taxonomy, question typologies, LLM-interviewer results                                                                                                                                                                                                                                |
 | [research/frontier-model-elicitor-failure-catalogue](reference/research/elicitation/frontier-model-elicitor-failure-catalogue.md) | active     | FE-1407                                  | Test-oracle list for the harness (reclassified 2026-08-25 as test-bed material, not authority): typed frontier-model failure catalogue from the two baseline transcripts and indexed literature — mechanism, detection signature, accountable layer, bounded prevention claim, and the licensed-deferral boundary |
-| [baseline evaluation evidence](evidence/evaluations/process-model-elicitation/baseline/)                                                     | active     | gisted in FE-1361 resolution; FE-1431    | Baseline-control evidence: transcripts, raw snapshots, delivered models, and scored read-out for conditions 1, 2, (2026-08-25) 4 — the rendered teaching layer as prompt only — and (2026-08-25) 5 — the shipped harness in the loop, transcripts and folded store committed, read-out pending review, with a (2026-08-26) turn latency assessment (`condition-5-turn-latency.md`: 145 s/turn, 97% extraction, actions R0–R5) that STEERING carries as an immediate concern; with the executable cases and protocol under `evaluations/` it is the simulated-expert harness for the walking-skeleton run (reclassified 2026-08-25 as test-bed material) |
+| [baseline evaluation evidence](evidence/evaluations/process-model-elicitation/baseline/)                                                     | active     | gisted in FE-1361 resolution; FE-1431    | Baseline-control evidence: frozen conditions 1–2; cycle-one live arms from 2026-08-25 archived under `transcripts/cycle-1/`; cycle-two conditions 4–5 from 2026-08-26 in `transcripts/`; and the scored read-out freezing the plugin key catalogue while routing residual identity, quote-repair, classification, and session-control defects to harness work. Includes the first-run turn latency assessment (`condition-5-turn-latency.md`: 145 s/turn, 97% extraction, actions R0–R5) carried by STEERING; with the executable cases and protocol under `evaluations/` it is the simulated-expert harness for the walking-skeleton run (reclassified 2026-08-25 as test-bed material) |
 | [ir-design](specs/intermediate-representation.md)                                                                                 | active     | gisted in FE-1364 resolution; amended by FE-1480 | The IR design: Layer A (ratified on worked examples, FE-1397; definition sentence amended by ADR-0003) + the CPS plugin's ten-kind payload, deterministic scaffold and obligation contract (Layer B); executable code is realized downstream under ADR-0005                                                               |
 | [ir-worked-examples](evidence/proofs/design/intermediate-representation-worked-examples.md)                                                               | active     | gisted in FE-1397                        | Layer-A validation across Gherkin/CPS/BPMN + assurance: property verdicts, amendments, sublimation findings                                                                                                                                                                                                            |
 | [ir-design-plain](specs/intermediate-representation-plain.md)                                                                     | active     | strain findings on FE-1401; amended by FE-1480 | Plain-prose rendering of the IR design, including ADR-0005's split between deterministic scaffolding and model-assisted executable realization; notes that `plugin-sdcpn/plugin.yaml` is now the concrete rendering of Layer B                                                                                                  |
diff --git a/libs/@hashintel/brunch-agent/docs/control/STRATEGY-LOG.md b/libs/@hashintel/brunch-agent/docs/control/STRATEGY-LOG.md
index bf0f25ac891..6c1c1c7b72f 100644
--- a/libs/@hashintel/brunch-agent/docs/control/STRATEGY-LOG.md
+++ b/libs/@hashintel/brunch-agent/docs/control/STRATEGY-LOG.md
@@ -357,7 +357,7 @@ reference because the expert or situation pack changes.
 
 **Evidence links:** [baseline protocol](../../evaluations/protocols/process-model-elicitation/baseline/protocol.md),
 [condition-3 preregistration (amended)](../../evaluations/protocols/process-model-elicitation/baseline/condition-3-preregistration.md),
-[condition-5 transcript](../evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5.md),
+[first condition-5 transcript](../evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/condition-5.md),
 [condition-4 read-out](../evidence/evaluations/process-model-elicitation/baseline/readout.md),
 [turn latency assessment](../evidence/evaluations/process-model-elicitation/baseline/condition-5-turn-latency.md),
 FE-1404, FE-1431, FE-1361
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/condition-5-turn-latency.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/condition-5-turn-latency.md
index e21d71ef621..2896704c1bf 100644
--- a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/condition-5-turn-latency.md
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/condition-5-turn-latency.md
@@ -1,8 +1,9 @@
 # Condition 5 — turn latency assessment and recommended actions
 
 > **Provenance.** Agent-authored diagnosis, 2026-08-26, of the first condition-5 run
-> (2026-08-25, [transcript](transcripts/condition-5.md), [raw record](transcripts/condition-5.raw.json),
-> [folded store](transcripts/condition-5-captures.json)). Commissioned by Lu after the read-out
+> (2026-08-25, [transcript](transcripts/cycle-1/condition-5.md),
+> [raw record](transcripts/cycle-1/condition-5.raw.json),
+> [folded store](transcripts/cycle-1/condition-5-captures.json)). Commissioned by Lu after the read-out
 > showed 2.4 minutes per interviewer turn: "not going to be viable at all, for a working
 > application". Inputs: the raw record's per-turn tool calls, signals, sweep results, and usage
 > totals; the runner [`harness-run.ts`](../../../../../evaluations/protocols/process-model-elicitation/baseline/harness-run.ts);
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/readout.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/readout.md
index 2475d2b0291..67f35164989 100644
--- a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/readout.md
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/readout.md
@@ -535,7 +535,8 @@ What the keys bought (observed, one run each):
 6. **`source-regime` used as designed.** "*Prescribed form:* **none exists** — *"there's no
    posted rule at all."*" (`:1119`); "prescribed and practiced coincide — she reports no
    divergence, which is itself the finding" (`:635`).
-7. **Read-back in the expert's words.** 204 quotation marks in `condition-4-model.txt` versus 24
+7. **Read-back in the expert's words.** 204 quotation marks in
+   `cycle-1/condition-4-model.txt` versus 24
    in `condition-2-model.txt`; the model's declared convention is "Quoted text is hers" (`:966`).
    Condition 2's attribution was narrative; condition 4's is per slot.
 8. **The stop honoured, the losses delivered, the net not claimed.** `Honour a stop` produced
@@ -626,7 +627,7 @@ strain; the last group lists what fired as designed, so the next cycle does not
 
 **Duplication in the render**
 
-- Quantiles ×3: `plugin.ontology.attributes.quantity`, `repertoire.guidance.techniques."Quantiles, never three points"`, `plugin.guidance.techniques."quantiles, never triangles"` (`condition-4-system.md:71, 166, 171`).
+- Quantiles ×3: `plugin.ontology.attributes.quantity`, `repertoire.guidance.techniques."Quantiles, never three points"`, `plugin.guidance.techniques."quantiles, never triangles"` (`cycle-1/condition-4-system.md:71, 166, 171`).
 - Batching ×3: `repertoire.guidance.licenses."Batch breadth, sequence depth"`, `repertoire.guidance.smells."Many questions in one turn"`, `repertoire.guidance.failure_modes."Opening overload"`.
 - Queues ×3: `plugin.ontology.not_kinds`, `plugin.guidance.rabbit_holes."eliciting queues or scenarios"`, `plugin.guidance.smells."a queue as a node"`.
 - Mode-change loss ×3, vary-by-type ×3, shared-resource ×3 (`plugin.ontology.not_kinds.resource`, `plugin.patterns.P05`, `plugin.guidance.motifs."shared resource"`), unwritten rules ×2 (`plugin.ontology.kinds.constraint` "written or unwritten", `plugin.guidance.movements.sweep."the unwritten constraints"`).
@@ -699,9 +700,10 @@ Cycle two reran both live arms against `sdcpn/2026-08-26.2` and
   ([model](transcripts/condition-5-model.md):7–10). The unsatisfied rows are visible rather than
   silently filled.
 - **The evidence boundary held.** Five sweep attempts were refused when quotations were not
-  verbatim or occurred only in non-user entries; a later sweep admitted only deposits grounded
-  in the expert's words ([transcript](transcripts/condition-5.md):379–406). This cost turns, but
-  it did not corrupt the store.
+  verbatim or occurred only in non-user entries
+  ([transcript](transcripts/condition-5.md):255, 379–384); the closing sweep admitted only two
+  deposits grounded in the expert's words (`:420–422`). This cost turns, but it did not corrupt
+  the store.
 - **Node identity remains the dominant harness defect.** One wash-versus-idle question became
   six near-duplicate objective nodes plus a separate exchange-rate objective
   ([model](transcripts/condition-5-model.md):163–196); entity types, policies, constraints, and
@@ -722,6 +724,13 @@ criteria, source bindings, and a typed partial close. No observed fact required
 runbook, ontology, schema, pattern, or machinery key. Missing model content is represented by
 existing unsatisfied rows; adding keys would not repair it.
 
+The final third-formalism check also fills cells only. Reapplying the cycle-one
+[formal-verification sketch](../../../proofs/design/plugin-keys-pressure-review-cycle-1.md#14-flexibility--formal-verification-sketch-tlamodel-checking-properties-not-written-to-a-file)
+to the cycle-two contract leaves its five kinds, anchor, and guidance cells unchanged. Its demands
+use only `spelled out`, `named`, and `at least N`, all still accepted; the new applicability facet
+omits the quantity and policy-versus-practice defaults that the sketch identified as noise. It
+needs neither another key nor a contradiction of the default.
+
 Freeze means the authoring interface is stable, not that the harness is finished. Node
 identity/deduplication, quote-repair efficiency, the condition-4 delivery classifier, and the
 condition-5 terminal act remain follow-up evidence for the FE-1383 harness work. They do not
diff --git a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
index 74a004740ef..4bcf13cdedc 100644
--- a/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
+++ b/libs/@hashintel/brunch-agent/packages/core/schema/CHANGELOG.md
@@ -207,7 +207,10 @@ written against.
 
 Conditions 4 and 5 completed against the cycle-two definitions on 2026-08-26.
 The review found no fact that required adding, merging, or dropping a key. The
-fixed catalogue therefore freezes at cycle two.
+formal-verification sketch still fills cells only against the final contract:
+its `named`, `spelled out`, and `at least N` demands remain accepted, while the
+applicability facet omits the quantity and policy-versus-practice defaults it
+identified as noise. The fixed catalogue therefore freezes at cycle two.
 
 The runs did expose residual harness work: node identity and deduplication,
 quote-repair efficiency, prompt-only delivery classification, and a terminal act

From e463952815388ef587095f1d76a7a540b9018119 Mon Sep 17 00:00:00 2001
From: Lu Nelson <ln@hash.ai>
Date: Thu, 27 Aug 2026 10:37:14 +0200
Subject: [PATCH 9/9] Align spread elicitation with the precision ladder

The Quantiles technique had been rewritten as interval-first plus
confidence while the ladder still defined a spread as typical plus
one-in-ten tails. Teach the ladder, copy sibling plugin.yaml into
pruned repertoire jobs, and restore the cycle-one steering link now
that the archive exists.

Co-authored-by: Cursor <cursoragent@cursor.com>
---
 .github/actions/prune-repository/prune.py              |  5 +++++
 .github/actions/prune-repository/prune_test.py         | 10 ++++++++++
 libs/@hashintel/brunch-agent/docs/control/STEERING.md  |  2 +-
 .../baseline/transcripts/condition-4-system.md         |  2 +-
 .../baseline/transcripts/condition-5-system.md         |  2 +-
 .../brunch-agent/packages/repertoire/repertoire.yaml   |  4 ++--
 6 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/.github/actions/prune-repository/prune.py b/.github/actions/prune-repository/prune.py
index ddb55e9fbe9..c49b4f7065c 100644
--- a/.github/actions/prune-repository/prune.py
+++ b/.github/actions/prune-repository/prune.py
@@ -64,6 +64,11 @@
     # The app's condition-5 test executes the evaluation runner as a child
     # process; the context root is not a workspace and must be copied explicitly.
     "@apps/brunch-agent": ["libs/@hashintel/brunch-agent/evaluations"],
+    # Repertoire tests read sibling plugin.yaml files by relative URL.
+    "@hashintel/brunch-agent-repertoire": [
+        "libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml",
+        "libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml",
+    ],
 }
 
 TURBO_QUERY = """
diff --git a/.github/actions/prune-repository/prune_test.py b/.github/actions/prune-repository/prune_test.py
index d0843f1b07f..ebdd42e2ea0 100644
--- a/.github/actions/prune-repository/prune_test.py
+++ b/.github/actions/prune-repository/prune_test.py
@@ -16,6 +16,7 @@
 TRANSPORT = "@hashintel/brunch-agent-transport-aisdk"
 APP = "@apps/brunch-agent"
 WEBSITE = "@apps/petrinaut-website"
+REPERTOIRE = "@hashintel/brunch-agent-repertoire"
 
 
 class BrunchRequestedExtras(unittest.TestCase):
@@ -46,6 +47,15 @@ def test_app_job_adds_the_baseline_evaluation_paths(self) -> None:
             ["libs/@hashintel/brunch-agent/evaluations"],
         )
 
+    def test_repertoire_job_copies_sibling_plugin_yaml(self) -> None:
+        self.assertEqual(
+            extra_paths_for_requested({REPERTOIRE}),
+            [
+                "libs/@hashintel/brunch-agent/packages/plugin-sdcpn/plugin.yaml",
+                "libs/@hashintel/brunch-agent/packages/plugin-gherkin/plugin.yaml",
+            ],
+        )
+
     def test_sibling_or_website_job_does_not_add_brunch_extras(self) -> None:
         self.assertEqual(extras_for_requested({TRANSPORT}), frozenset())
         self.assertEqual(extras_for_requested({WEBSITE}), frozenset())
diff --git a/libs/@hashintel/brunch-agent/docs/control/STEERING.md b/libs/@hashintel/brunch-agent/docs/control/STEERING.md
index 7389de91a54..d66c2a4467e 100644
--- a/libs/@hashintel/brunch-agent/docs/control/STEERING.md
+++ b/libs/@hashintel/brunch-agent/docs/control/STEERING.md
@@ -378,7 +378,7 @@ changes the witness: latency is no longer a number in a transcript but a person
 | Construct and review-and-revise share most of one runbook. | Medium-low; Lu's reading of the early plugin-schema passes; unrehearsed. | Author both job runbooks against the key schema and diff them; a cycle of the plugin loop. |
 | Kind-level rows express the coatings case. | High; cycle-two [condition-5 evidence](../evidence/evaluations/process-model-elicitation/baseline/transcripts/) folds 166 captures into 51 nodes with 0 unmapped, and the 93 unsatisfied rows are declared demands, not missing vocabulary. Sufficiency for completion is still unshown. | A run with identity handling; count objective nodes. |
 | Typed extraction on the verbatim floor holds up in a live run. | Medium-high; the [latency assessment](../evidence/evaluations/process-model-elicitation/baseline/condition-5-turn-latency.md) records repaired refusals and leaves cost, not correctness, as the open question. | R0 + the assessment's §6 spike: does a cheaper extraction model keep kind/node/slot agreement? |
-| The shipped loop converges to completion. | Low; both condition-5 runs (cycle one, [cycle two](../evidence/evaluations/process-model-elicitation/baseline/transcripts/)) end with node identity the dominant defect and no terminal act for an expert-stopped engagement; the cycle-two readout routes both to FE-1383 as harness work, not catalogue gaps. | Give the sweep the node index (R4); rerun condition 5; count objective nodes. |
+| The shipped loop converges to completion. | Low; both condition-5 runs ([cycle one](../evidence/evaluations/process-model-elicitation/baseline/transcripts/cycle-1/), [cycle two](../evidence/evaluations/process-model-elicitation/baseline/transcripts/)) end with node identity the dominant defect and no terminal act for an expert-stopped engagement; the cycle-two readout routes both to FE-1383 as harness work, not catalogue gaps. | Give the sweep the node index (R4); rerun condition 5; count objective nodes. |
 | Per-turn latency is dominated by extraction, and removable from the critical path. | Medium; the [latency assessment](../evidence/evaluations/process-model-elicitation/baseline/condition-5-turn-latency.md) infers the split from output volume because per-call timing is absent. | R0, then the assessment's §6 spike on frozen turn tails. |
 | The condition-5 instrument is too expensive to iterate on. | High; a full run is 12–24 turns at ~145 s each (30–60 min), `harness-run.ts` writes every artefact only at the end, `HARD_STOP_AT = 24` is hard-coded with no short-run knob, and W2's afternoon (2026-08-26, ~3 h after the credential fix) produced attribution fixes and no completed figure. The instrument's cost is now a bound on the P1 cycle and on every harness fix. | A `BRUNCH_BASELINE_HARD_STOP` env (a 3-turn run yields the purpose split in under 10 min); the §6 frozen-tail replay; and taking the first split from the Proof 0 panel run, which FE-1505 already accepts ("harness **or** panel run"). |
 | The baseline and the panel measure the same interviewer. | Low; `harness-run.ts` defaults `BRUNCH_SDCPN_MODEL` to `claude-opus-5`, `sdcpn-elicitor.ts` defaults it to `claude-haiku-4-5`. The 145 s figure is opus in the baseline; the panel's production default is unmeasured and undecided. | Lu names the Proof 0 interviewer model before the run; the run records it in the proof bundle. |
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4-system.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4-system.md
index 0823f42a47e..aeca58bf724 100644
--- a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4-system.md
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-4-system.md
@@ -167,7 +167,7 @@ _Question forms that deepen one answer already given. A technique is applied to
 - **Ask for the last time** — Prefer "when did that last happen, and what did you do?" to any generalisation. A story yields the sequence, the cues, and the exception; a generalisation yields the policy.
 - **No bare why** — Never ask "why do you do it this way?" as the primary probe; experts cannot report the basis of practised judgment on demand. Ask for an occasion and for what was attended to.
 - **Mean or tail** — Before eliciting any quantity, ask whether what matters is the typical case or the bad one — a mean or a tail. The answer decides whether a single figure, a range, or a spread is being asked for.
-- **Quantiles, never three points** — Ask first for a lower and upper plausible value, then a typical value, then how confident the expert is that reality falls inside the interval. Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. Record which protocol was used rather than silently mixing interval-first and typical-first answers.
+- **Quantiles, never three points** — A `spread` is typical plus one-in-ten worse and one-in-ten better (or median and quartiles). Ask "typically?", then "one time in ten, worse than?", then "one time in ten, better than?". Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. If a min/mode/max triple arrives unprompted, ask the confidence question and record whether the middle value is a mode or a mean.
 - **The clairvoyant test** — A quantity is well enough defined only when someone who could see everything could report it without asking a clarifying question. If the slot's name would need one, ask the clarifying question first.
 - **Consistency probe** — "You said earlier that ___, but then you told me ___. How do you explain that?" — stated plainly, without choosing between the two.
 - **Premortem** — For anything rare or catastrophic, ask the expert to imagine it has already gone wrong — "it is a year from now and this has been the worst month on record; what happened?" — and demand mechanism and sequence, not sentiment.
diff --git a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-system.md b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-system.md
index 7b0bb7c3aae..2f195cecd1e 100644
--- a/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-system.md
+++ b/libs/@hashintel/brunch-agent/docs/evidence/evaluations/process-model-elicitation/baseline/transcripts/condition-5-system.md
@@ -171,7 +171,7 @@ _Question forms that deepen one answer already given. A technique is applied to
 - **Ask for the last time** — Prefer "when did that last happen, and what did you do?" to any generalisation. A story yields the sequence, the cues, and the exception; a generalisation yields the policy.
 - **No bare why** — Never ask "why do you do it this way?" as the primary probe; experts cannot report the basis of practised judgment on demand. Ask for an occasion and for what was attended to.
 - **Mean or tail** — Before eliciting any quantity, ask whether what matters is the typical case or the bad one — a mean or a tail. The answer decides whether a single figure, a range, or a spread is being asked for.
-- **Quantiles, never three points** — Ask first for a lower and upper plausible value, then a typical value, then how confident the expert is that reality falls inside the interval. Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. Record which protocol was used rather than silently mixing interval-first and typical-first answers.
+- **Quantiles, never three points** — A `spread` is typical plus one-in-ten worse and one-in-ten better (or median and quartiles). Ask "typically?", then "one time in ten, worse than?", then "one time in ten, better than?". Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. If a min/mode/max triple arrives unprompted, ask the confidence question and record whether the middle value is a mode or a mean.
 - **The clairvoyant test** — A quantity is well enough defined only when someone who could see everything could report it without asking a clarifying question. If the slot's name would need one, ask the clarifying question first.
 - **Consistency probe** — "You said earlier that ___, but then you told me ___. How do you explain that?" — stated plainly, without choosing between the two.
 - **Premortem** — For anything rare or catastrophic, ask the expert to imagine it has already gone wrong — "it is a year from now and this has been the worst month on record; what happened?" — and demand mechanism and sequence, not sentiment.
diff --git a/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml b/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml
index f4f5fae667a..aab0f6c0e45 100644
--- a/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml
+++ b/libs/@hashintel/brunch-agent/packages/repertoire/repertoire.yaml
@@ -54,8 +54,8 @@ guidance:
       source: docs/reference/research/elicitation/elicitation-strategy-literature.md §1.3 (mean-or-tail router)
       for_precision: [number, range, spread]
     - name: Quantiles, never three points
-      text: Ask first for a lower and upper plausible value, then a typical value, then how confident the expert is that reality falls inside the interval. Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. Record which protocol was used rather than silently mixing interval-first and typical-first answers.
-      source: docs/reference/research/elicitation/elicitation-strategy-literature.md §1.4 (IDEA four-step interval, anti-triangular guard); docs/archive/specs/cps-interview-guidance-2026-08-25.md CPS-Q01
+      text: 'A `spread` is typical plus one-in-ten worse and one-in-ten better (or median and quartiles). Ask "typically?", then "one time in ten, worse than?", then "one time in ten, better than?". Never ask for minimum, most likely, and maximum — the three-point habit yields overconfident answers. If a min/mode/max triple arrives unprompted, ask the confidence question and record whether the middle value is a mode or a mean.'
+      source: evaluations/protocols/process-model-elicitation/baseline/v0-prompt.md (typical then tails); docs/reference/research/elicitation/elicitation-strategy-literature.md §1.4 (SHELF / anti-triangular guard)
       for_precision: [spread]
     - name: The clairvoyant test
       text: A quantity is well enough defined only when someone who could see everything could report it without asking a clarifying question. If the slot's name would need one, ask the clarifying question first.