diff --git a/.claude/blackboard.md b/.claude/blackboard.md
index f4e502aa..60c9de36 100644
--- a/.claude/blackboard.md
+++ b/.claude/blackboard.md
@@ -3,7 +3,52 @@
 > **Read this first.** The "Polyglot Notebook" architecture below is a
 > separate/older program, not the current epoch.
 
-## 2026-07-06 (latest) — F64 GEMM completed: FMA tier + register residency + native-engine swap
+## 2026-07-29 (latest) — blake3 dependency DROPPED: call sites swapped to the in-tree module
+
+Operator: "go ahead" on the rung-3a swap, with the measured cost table in
+hand. This closes the only rung of `the-simd-ladder.md` that carried a cargo
+cycle (`blake3 → ndarray::simd`).
+
+1. **15 call sites, 8 modules** (`seal`, `merkle_tree`, `plane`, `vsa`,
+   `spo_bundle`, `crystal_encoder`, `compression_curves`, `deepnsm`) now
+   reach `crate::hpc::blake3`. Implemented as one `use super::blake3;` per
+   module rather than rewriting each `blake3::` path — the in-tree API is
+   shape-compatible (`hash`, `Hasher::{new,new_keyed,new_derive_key,update,
+   finalize,finalize_xof}`, `Hash::as_bytes → &[u8;32]`), so the diff is 10
+   added lines, not 15 edited ones. `spo_bundle`'s use is inside
+   `#[cfg(test)]`, so it takes `use crate::hpc::blake3;` there instead of
+   leaning on the subtree's blanket `unused_imports` allow.
+2. **Dependency gone.** `dep:blake3` off the `std` feature; the ~55-line
+   Cargo.toml comment block replaced with a do-not-re-add note. `blake3`
+   **and** its transitive `constant_time_eq` are both absent from
+   `Cargo.lock`. nostd matrix untouched — every call site is under
+   `pub mod hpc`, itself `#[cfg(feature = "std")]`.
+3. **What this actually bought:** the second SIMD surface. Even at
+   `default-features = false, features = ["pure"]` the crate shipped its own
+   `rust_{sse2,sse41,avx2}.rs` intrinsics beside `ndarray::simd` — the exact
+   thing the matryoshka pattern exists to prevent. The old Cargo.toml comment
+   named this and said "Tracked, not done here."
+
+**Cost, accepted with numbers in hand [MEASURED, not re-measurable]:**
+1.25–1.39× across the input sizes this crate hashes (16 B 1.34–1.39×, 256 B
+1.25–1.29×, 2 KB 1.30×); 4.7–4.9× at 64 KB, which no call site here touches.
+The A/B bench needs both implementations present and is unbuildable from this
+commit forward, by its own design note.
+
+**Loose ends.**
+- `AdaWorldAPI/BLAKE3` (v1.8.5) exists and is an **unmodified upstream
+  mirror** — no ndarray wiring, all `ffi_*`/`rust_*` files intact. Master had
+  been pinning `blake3 = { version = "1" }` from **crates.io** while that fork
+  existed, i.e. the P0 fork rule was already broken. This change resolves it
+  by deletion; wiring the fork instead would have been the other resolution
+  and would NOT have closed the second-surface problem.
+- Verified `src/hpc/blake3_test_vectors.json` is **byte-identical** (31,922 B)
+  to that fork's `test_vectors.json`, so the correctness tests run against
+  genuine upstream vectors.
+- Rung 3b (`hash_many`) still absent; that is the whole 64 KB gap. Not worth
+  building for ndarray's own call sites — nothing here hashes bulk.
+
+## 2026-07-06 — F64 GEMM completed: FMA tier + register residency + native-engine swap
 
 Operator: "complete the F64 gemm… and pr". Three moves, all on the entry
 below's foundation:
diff --git a/.claude/knowledge/blake3-in-tree-measured.md b/.claude/knowledge/blake3-in-tree-measured.md
index 04b46217..ce8c798b 100644
--- a/.claude/knowledge/blake3-in-tree-measured.md
+++ b/.claude/knowledge/blake3-in-tree-measured.md
@@ -1,8 +1,22 @@
 # In-tree BLAKE3 — correct, and what it costs
 
-> **Status: MEASURED, 2026-07-29.** Correctness against the official vectors;
-> throughput against the external crate. Both numbers below are reproducible
-> with the instruments in this directory.
+> **Status: MEASURED, 2026-07-29 — and SWAPPED, 2026-07-29.** Correctness
+> against the official vectors; throughput against the external crate.
+>
+> **The open decision this document existed to inform has been taken:** the
+> operator authorised the swap, all 15 call sites now reach
+> `crate::hpc::blake3`, and the external dependency is gone. The cost below
+> was accepted with the numbers in hand, not discovered afterward.
+>
+> Two consequences for anyone reading this later:
+>
+> - The **correctness** numbers remain reproducible. The vectors file
+>   (`src/hpc/blake3_test_vectors.json`) is byte-identical to upstream's
+>   `test_vectors.json` — verified against `AdaWorldAPI/BLAKE3` v1.8.5.
+> - The **throughput** numbers are now historical and cannot be re-run. The
+>   A/B bench needs both implementations present; with the crate dropped there
+>   is nothing to compare against, exactly as its own header anticipated. To
+>   re-measure, you must temporarily re-add the dependency.
 
 ## READ BY:
 - Anyone about to drop the external `blake3` dependency
@@ -21,10 +35,16 @@ cycle — the only rung of the ladder that has one (`the-simd-ladder.md`).
 Cutting it means ndarray owning BLAKE3 rather than consuming the crate.
 
 Scoping finding that made this small: **ndarray's usage is entirely
-single-input.** 14 call sites across 8 files use only `hash`,
-`Hasher::{new, new_keyed, update, finalize, finalize_xof().fill()}`,
-`Hash::as_bytes`, and `Hash` as a signature type. **No `hash_many`.** So the
-serial core suffices, and it needs no SIMD at all.
+single-input.** 15 `blake3::` references across 8 files — 14 calls plus one
+type position (`merkle_tree::truncate_hash`'s `&blake3::Hash` parameter) —
+using only `hash`, `Hasher::{new, new_keyed, update, finalize,
+finalize_xof().fill()}`, `Hash::as_bytes`, and `Hash` as a signature type.
+**No `hash_many`.** So the serial core suffices, and it needs no SIMD at all.
+
+(An earlier revision said "14 call sites", counting calls but not the type
+position, while the swap record above counts all 15 references. Raised by
+CodeRabbit on #269; both numbers were describing different things, and the
+distinction is now explicit rather than a discrepancy.)
 
 ## Correctness — proven
 
@@ -135,9 +155,16 @@ hash small nodes, `deepnsm`/`compression_curves` small. So ndarray's real
 exposure is the **1.3–1.6× band**, not the 5× one — but 1.3× on a hot encoder
 path is a real cost, not a rounding error.
 
-**Not swapped here.** The module lands and is tested; the call sites still
-use the external crate. Flipping them is a decision with a measured price
-tag, and it is the operator's.
+**Not swapped in the commit this section was written for.** The module landed
+and was tested; the call sites still used the external crate. Flipping them
+was a decision with a measured price tag, and it was the operator's.
+
+**Taken 2026-07-29.** The operator authorised the flip with this table in
+hand. All 15 call sites across the eight modules named above now reach
+`crate::hpc::blake3` via a per-module `use super::blake3;`; `blake3` and its
+transitive `constant_time_eq` are gone from `Cargo.lock`. The accepted price
+is the 1.3× small-input band — the 4.8× 64 KB row was never on ndarray's
+curve, since no call site here hashes bulk input.
 
 ## One deliberate deviation from upstream, and one restored
 
diff --git a/Cargo.lock b/Cargo.lock
index 378af986..fa97f8dc 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -84,18 +84,6 @@ dependencies = [
  "password-hash",
 ]
 
-[[package]]
-name = "arrayref"
-version = "0.3.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "76a2e8124351fda1ef8aaaa3bbd7ebbcb486bbcd4225aca0aa0d84bb2db8fecb"
-
-[[package]]
-name = "arrayvec"
-version = "0.7.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"
-
 [[package]]
 name = "autocfg"
 version = "1.5.0"
@@ -150,20 +138,6 @@ dependencies = [
  "digest 0.10.7",
 ]
 
-[[package]]
-name = "blake3"
-version = "1.8.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4d2d5991425dfd0785aed03aedcf0b321d61975c9b5b3689c774a2610ae0b51e"
-dependencies = [
- "arrayref",
- "arrayvec",
- "cc",
- "cfg-if",
- "constant_time_eq",
- "cpufeatures 0.3.0",
-]
-
 [[package]]
 name = "blas-mock-tests"
 version = "0.1.0"
@@ -396,12 +370,6 @@ version = "0.10.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a6ef517f0926dd24a1582492c791b6a4818a4d94e789a334894aa15b0d12f55c"
 
-[[package]]
-name = "constant_time_eq"
-version = "0.4.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3d52eff69cd5e647efe296129160853a42795992097e8af39800e1060caeea9b"
-
 [[package]]
 name = "core-foundation"
 version = "0.10.1"
@@ -1318,7 +1286,6 @@ name = "ndarray"
 version = "0.17.2"
 dependencies = [
  "approx",
- "blake3",
  "cblas-sys",
  "cranelift-codegen",
  "cranelift-frontend",
diff --git a/Cargo.toml b/Cargo.toml
index a93181ae..1ab8a142 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -154,63 +154,48 @@ libc = { version = "0.2.82", optional = true }
 matrixmultiply = { version = "0.3.2", default-features = false, features=["cgemm"] }
 
 # =====================================================================
-# blake3 — DEPENDENCY OF `std` FEATURE (NOT `hpc-extras`). READ BEFORE
-# TOUCHING.
+# blake3 — NO LONGER A DEPENDENCY. Do not re-add it.
 # =====================================================================
 #
-# blake3 is required by the cognitive substrate modules — plane, seal,
-# merkle_tree, vsa, spo_bundle, crystal_encoder, compression_curves,
-# deepnsm — which all live under `pub mod hpc;` (itself gated on
-# `feature = "std"` in lib.rs). Those modules `use blake3;` directly
-# and unconditionally; there is no #[cfg] dance inside them.
+# BLAKE3 now lives in-tree at `src/hpc/blake3.rs`, as a **portable-only
+# transcription of the BLAKE3 reference implementation -- no SIMD, no
+# unsafe**. See that module's own header. It is the serial path every
+# conformant implementation reduces to at `simd_degree() == 1`, which
+# suffices here because ndarray's usage is entirely single-input.
 #
-# Pinning blake3 to the `std` feature (rather than `hpc-extras`) means:
-#   * ANY consumer that enables `std` automatically gets blake3, with
-#     ZERO additional feature wiring. This is the default. Cargo's
-#     transitive feature resolution does the rest.
-#   * Consumers selecting `default-features = false, features = ["std"]`
-#     (e.g. burn-ndarray, which disables hpc-extras to shed p64/fractal)
-#     STILL get blake3 — no more "missing blake3" build errors that
-#     used to require chasing down hpc-extras.
-#   * Consumers selecting `default-features = false` (no std at all,
-#     e.g. the `thumbv6m-none-eabi` CI matrix entry) do NOT pull blake3
-#     and therefore do not pull `constant_time_eq`, whose lack of
-#     `#![no_std]` declaration would otherwise fail the nostd link with
-#     `error[E0463]: can't find crate for std`.
+# The external crate was removed because even with `default-features =
+# false, features = ["pure"]` it carried its own SSE2/SSE4.1/AVX2
+# intrinsics -- a second SIMD surface beside `ndarray::simd`, which is
+# exactly what the matryoshka pattern exists to prevent. The old comment
+# block here said "Tracked, not done here"; this is it being done.
 #
-# If you find yourself wanting to make blake3 unconditional (drop the
-# `optional = true`), check first: does it still pass
-# `cargo rustc -p ndarray --target=thumbv6m-none-eabi
-#  --no-default-features --features portable-atomic-critical-section`?
-# If not, leave the `optional = true` + `std`-feature pinning in place.
+# It also breaks a cycle. `ndarray -> blake3` meant blake3 could never be
+# built ON `ndarray::simd` without cargo seeing `ndarray -> blake3 ->
+# ndarray`. Dropping the dep is what makes an ndarray-backed BLAKE3
+# possible -- NOT here (this module is portable), but for a future
+# SIMD-backed implementation and for the AdaWorldAPI/BLAKE3 fork.
 #
-# =====================================================================
-# `default-features = false` + `pure`: NO C/ASM FFI. Operator directive
-# 2026-07-28 — "I don't want any ffi with c".
-#
-# blake3's default build runs `cc::Build` over `c/blake3_{sse2,sse41,avx2,
-# avx512}_x86-64_unix.S` and links them (measured before this change: 33 `.o`
-# files plus `libblake3_avx512_assembly.a` in target/, with `blake3_*_ffi`
-# cfgs set). The `pure` feature routes build.rs to
-# `build_sse2_sse41_avx2_rust_intrinsics()` — its own comment: "No C code to
-# compile here" — which only sets `blake3_{sse2,sse41,avx2}_rust` cfgs and
-# lets the normal cargo build compile the Rust intrinsics modules.
+# Separately: blake3 carried `cc` as an unconditional build-dependency, and
+# the `pure` feature existed only to stop that `cc` from compiling the
+# bundled C/ASM (operator directive 2026-07-28, "I don't want any ffi with
+# c"). In-tree there is no C to opt out of, and `cc` is no longer pulled on
+# blake3's account. Dropping blake3 also removed `constant_time_eq`,
+# `arrayref` and `arrayvec` from the lockfile.
 #
-# What `pure` costs (build.rs:344-371): the hand-tuned x86-64 assembly is
-# replaced by Rust intrinsics, the AVX-512 path is dropped entirely, and the
-# aarch64 NEON C intrinsics are dropped. What it removes: every byte of C.
+# Cost, measured: 1.25-1.39x across the input sizes this crate actually
+# hashes (16 B word 1.34-1.39x, 256 B 1.25-1.29x, 2 KB 1.30x), rising to
+# 4.7-4.9x at 64 KB where upstream's `hash_many` has no in-tree counterpart.
+# Every call site here sits in the small-input band, not the 64 KB one. Full
+# table, methodology and the attribution of the gap:
+# `.claude/knowledge/blake3-in-tree-measured.md`.
 #
-# `default-features = false` also drops blake3's own `std` (which only gates
-# `constant_time_eq/std`); this crate's `std` feature is what pulls blake3 in
-# at all, so nothing here needs blake3's.
+# The A/B bench under `.claude/knowledge/blake3-ab-bench/` compared the two
+# implementations and is, by its own design note, unbuildable from this commit
+# onward — there is no longer a second implementation to compare against.
 #
-# NOTE: `pure` still leaves blake3's Rust SSE2/SSE4.1/AVX2 intrinsics — a
-# second SIMD surface beside `ndarray::simd`, which the matryoshka pattern
-# exists to prevent. Closing that means implementing BLAKE3's compression on
-# `ndarray::simd::U32x16` (it is a ChaCha-derived u32 ARX kernel, and that
-# lane is proven at the AVX2 instruction floor — see
-# `.claude/knowledge/td-t22-asm-investigation.md`). Tracked, not done here.
-blake3 = { version = "1", optional = true, default-features = false, features = ["pure"] }
+# Call sites live under `pub mod hpc;` (gated on `feature = "std"` in lib.rs),
+# so the nostd matrix is untouched: `blake3` and its `constant_time_eq`
+# dependency are both gone from Cargo.lock entirely.
 
 # p64 + fractal — specialized convergence / manifold math. Gated behind
 # `hpc-extras` since they pull in a dep tree burn-ndarray doesn't need.
@@ -306,7 +291,7 @@ blas = ["dep:cblas-sys", "dep:libc"]
 
 serde = ["dep:serde"]
 
-std = ["num-traits/std", "matrixmultiply/std", "dep:blake3"]
+std = ["num-traits/std", "matrixmultiply/std"]
 rayon = ["dep:rayon", "std"]
 
 # Portable-SIMD backend (NIGHTLY ONLY). Routes `crate::simd::*` types
@@ -345,13 +330,9 @@ nightly-simd = ["std"]
 runtime-dispatch = ["std"]
 
 # HPC extras: p64 palette/NARS bridge + fractal manifold.
-# (blake3 was previously listed here; it is now part of `std` directly
-# because the cognitive substrate modules under hpc/ that import blake3
-# are themselves `std`-gated. See the blake3 comment in [dependencies].)
 # These pull in a non-trivial dependency tree; downstream crates such as
 # burn-ndarray that only need the core array layer can disable this with
-# `default-features = false` (and re-enable `std` explicitly if needed —
-# blake3 will come along with `std`).
+# `default-features = false` (and re-enable `std` explicitly if needed).
 hpc-extras = ["std", "dep:p64", "dep:fractal", "fractal/std"]
 
 matrixmultiply-threading = ["matrixmultiply/threading"]
diff --git a/README.md b/README.md
index 6c52d621..89d70c3d 100644
--- a/README.md
+++ b/README.md
@@ -210,20 +210,26 @@ cargo test
 
 ### Transitive dependencies of the `std` feature
 
-Enabling the `std` feature (the default) pulls in **`blake3`** as a hard
-transitive dependency. The cognitive substrate modules under `hpc/` —
-`plane`, `seal`, `merkle_tree`, `vsa`, `spo_bundle`, `crystal_encoder`,
-`compression_curves`, `deepnsm` — import `blake3` directly for integrity
-hashing and XOF expansion, and there is no separate feature to enable it.
-This was previously gated behind `hpc-extras`, which caused recurring
-"missing blake3" build errors for consumers (e.g. `burn-ndarray`) that
-selected `default-features = false, features = ["std"]` to shed the
-`p64` / `fractal` dependency tree. Pinning blake3 to `std` removes that
-footgun: any `std`-enabled build automatically gets blake3.
+**None for hashing.** BLAKE3 is in-tree.
+
+The cognitive substrate modules under `hpc/` — `plane`, `seal`,
+`merkle_tree`, `vsa`, `spo_bundle`, `crystal_encoder`, `compression_curves`,
+`deepnsm` — use `hpc::blake3` for integrity hashing and XOF expansion. That
+is a portable pure-Rust transcription of the BLAKE3 reference
+implementation, shipped in this crate: no SIMD, no `unsafe`, no C, and no
+build script.
+
+Earlier revisions pulled the external **`blake3`** crate here, first gated
+behind `hpc-extras` (which caused recurring "missing blake3" build errors
+for consumers such as `burn-ndarray` selecting
+`default-features = false, features = ["std"]`), then pinned to `std`.
+**Both are gone.** `blake3` and its transitive `constant_time_eq`,
+`arrayref` and `arrayvec` no longer appear in the dependency graph at any
+feature combination, so the footgun cannot recur.
 
 Consumers building `default-features = false` (no `std`, e.g. the
-`thumbv6m-none-eabi` nostd target) skip both the `hpc` module and the
-blake3 dep, so the nostd link is unaffected.
+`thumbv6m-none-eabi` nostd target) skip the `hpc` module and the BLAKE3
+code with it, so the nostd link is unaffected.
 
 ## Ecosystem
 
diff --git a/crates/burn/Cargo.lock b/crates/burn/Cargo.lock
index 968eaa00..e8488701 100644
--- a/crates/burn/Cargo.lock
+++ b/crates/burn/Cargo.lock
@@ -17,6 +17,19 @@ version = "2.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa"
 
+[[package]]
+name = "ahash"
+version = "0.8.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
+dependencies = [
+ "cfg-if",
+ "getrandom 0.3.4",
+ "once_cell",
+ "version_check",
+ "zerocopy",
+]
+
 [[package]]
 name = "aho-corasick"
 version = "1.1.4"
@@ -47,12 +60,6 @@ version = "1.0.102"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
 
-[[package]]
-name = "arrayref"
-version = "0.3.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "76a2e8124351fda1ef8aaaa3bbd7ebbcb486bbcd4225aca0aa0d84bb2db8fecb"
-
 [[package]]
 name = "arrayvec"
 version = "0.7.6"
@@ -119,16 +126,6 @@ version = "1.8.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2af50177e190e07a26ab74f8b1efbfe2ef87da2116221318cb1c2e82baf7de06"
 
-[[package]]
-name = "bincode"
-version = "2.0.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "36eaf5d7b090263e8150820482d5d93cd964a81e4019913c972f4edcc6edb740"
-dependencies = [
- "serde",
- "unty",
-]
-
 [[package]]
 name = "bit-set"
 version = "0.9.1"
@@ -153,20 +150,6 @@ dependencies = [
  "serde_core",
 ]
 
-[[package]]
-name = "blake3"
-version = "1.8.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2468ef7d57b3fb7e16b576e8377cdbde2320c60e1491e961d11da40fc4f02a2d"
-dependencies = [
- "arrayref",
- "arrayvec",
- "cc",
- "cfg-if",
- "constant_time_eq",
- "cpufeatures 0.2.17",
-]
-
 [[package]]
 name = "blas-src"
 version = "0.10.0"
@@ -220,8 +203,8 @@ dependencies = [
 
 [[package]]
 name = "burn-backend"
-version = "0.21.0-pre.2"
-source = "git+https://github.com/tracel-ai/burn.git?rev=ed72d2b#ed72d2b125a364aff18aed2a53396c128e01cb42"
+version = "0.21.0-pre.4"
+source = "git+https://github.com/AdaWorldAPI/burn.git?rev=9b2b671#9b2b67127b0fbb5387021faf540b7b12b9c4e943"
 dependencies = [
  "burn-std",
  "bytemuck",
@@ -240,8 +223,8 @@ dependencies = [
 
 [[package]]
 name = "burn-ir"
-version = "0.21.0-pre.2"
-source = "git+https://github.com/tracel-ai/burn.git?rev=ed72d2b#ed72d2b125a364aff18aed2a53396c128e01cb42"
+version = "0.21.0-pre.4"
+source = "git+https://github.com/AdaWorldAPI/burn.git?rev=9b2b671#9b2b67127b0fbb5387021faf540b7b12b9c4e943"
 dependencies = [
  "burn-backend",
  "hashbrown 0.16.1",
@@ -250,8 +233,8 @@ dependencies = [
 
 [[package]]
 name = "burn-std"
-version = "0.21.0-pre.2"
-source = "git+https://github.com/tracel-ai/burn.git?rev=ed72d2b#ed72d2b125a364aff18aed2a53396c128e01cb42"
+version = "0.21.0-pre.4"
+source = "git+https://github.com/AdaWorldAPI/burn.git?rev=9b2b671#9b2b67127b0fbb5387021faf540b7b12b9c4e943"
 dependencies = [
  "bytemuck",
  "bytes",
@@ -261,6 +244,7 @@ dependencies = [
  "num-traits",
  "serde",
  "smallvec",
+ "spin",
 ]
 
 [[package]]
@@ -330,10 +314,37 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6f8d983286843e49675a4b7a2d174efe136dc93a18d69130dd18198a6c167601"
 dependencies = [
  "cfg-if",
- "cpufeatures 0.3.0",
+ "cpufeatures",
  "rand_core",
 ]
 
+[[package]]
+name = "ciborium"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42e69ffd6f0917f5c029256a24d0161db17cea3997d185db0d35926308770f0e"
+dependencies = [
+ "ciborium-io",
+ "ciborium-ll",
+ "serde",
+]
+
+[[package]]
+name = "ciborium-io"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "05afea1e0a06c9be33d539b876f1ce3692f4afea2cb41f740e7743225ed1c757"
+
+[[package]]
+name = "ciborium-ll"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "57663b653d948a338bfb3eeba9bb2fd5fcfaecb9e199e87e1eda4d9e8b240fd9"
+dependencies = [
+ "ciborium-io",
+ "half",
+]
+
 [[package]]
 name = "cmake"
 version = "0.1.58"
@@ -383,12 +394,6 @@ dependencies = [
  "tiny-keccak",
 ]
 
-[[package]]
-name = "constant_time_eq"
-version = "0.4.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3d52eff69cd5e647efe296129160853a42795992097e8af39800e1060caeea9b"
-
 [[package]]
 name = "convert_case"
 version = "0.10.0"
@@ -414,15 +419,6 @@ version = "0.8.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
 
-[[package]]
-name = "cpufeatures"
-version = "0.2.17"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280"
-dependencies = [
- "libc",
-]
-
 [[package]]
 name = "cpufeatures"
 version = "0.3.0"
@@ -489,8 +485,8 @@ checksum = "460fbee9c2c2f33933d720630a6a0bac33ba7053db5344fac858d4b8952d77d5"
 
 [[package]]
 name = "cubecl"
-version = "0.10.0-pre.2"
-source = "git+https://github.com/tracel-ai/cubecl?rev=5b831a3cfac3eca0065fe0dbf57cddf5946d1586#5b831a3cfac3eca0065fe0dbf57cddf5946d1586"
+version = "0.10.0-pre.4"
+source = "git+https://github.com/tracel-ai/cubecl?rev=f60142ccc35dcbede6db2c28a1315ae4cccabdd1#f60142ccc35dcbede6db2c28a1315ae4cccabdd1"
 dependencies = [
  "cubecl-core",
  "cubecl-cuda",
@@ -502,15 +498,15 @@ dependencies = [
 
 [[package]]
 name = "cubecl-common"
-version = "0.10.0-pre.2"
-source = "git+https://github.com/tracel-ai/cubecl?rev=5b831a3cfac3eca0065fe0dbf57cddf5946d1586#5b831a3cfac3eca0065fe0dbf57cddf5946d1586"
+version = "0.10.0-pre.4"
+source = "git+https://github.com/tracel-ai/cubecl?rev=f60142ccc35dcbede6db2c28a1315ae4cccabdd1#f60142ccc35dcbede6db2c28a1315ae4cccabdd1"
 dependencies = [
  "backtrace",
- "bincode",
  "bytemuck",
  "bytes",
  "cfg-if",
  "cfg_aliases",
+ "ciborium",
  "derive-new",
  "derive_more",
  "dirs",
@@ -533,6 +529,7 @@ dependencies = [
  "serde_bytes",
  "serde_json",
  "spin",
+ "toml",
  "tynm",
  "wasm-bindgen-futures",
  "web-time",
@@ -541,8 +538,8 @@ dependencies = [
 
 [[package]]
 name = "cubecl-core"
-version = "0.10.0-pre.2"
-source = "git+https://github.com/tracel-ai/cubecl?rev=5b831a3cfac3eca0065fe0dbf57cddf5946d1586#5b831a3cfac3eca0065fe0dbf57cddf5946d1586"
+version = "0.10.0-pre.4"
+source = "git+https://github.com/tracel-ai/cubecl?rev=f60142ccc35dcbede6db2c28a1315ae4cccabdd1#f60142ccc35dcbede6db2c28a1315ae4cccabdd1"
 dependencies = [
  "bitflags",
  "bytemuck",
@@ -567,8 +564,8 @@ dependencies = [
 
 [[package]]
 name = "cubecl-cpp"
-version = "0.10.0-pre.2"
-source = "git+https://github.com/tracel-ai/cubecl?rev=5b831a3cfac3eca0065fe0dbf57cddf5946d1586#5b831a3cfac3eca0065fe0dbf57cddf5946d1586"
+version = "0.10.0-pre.4"
+source = "git+https://github.com/tracel-ai/cubecl?rev=f60142ccc35dcbede6db2c28a1315ae4cccabdd1#f60142ccc35dcbede6db2c28a1315ae4cccabdd1"
 dependencies = [
  "bytemuck",
  "cubecl-common",
@@ -583,8 +580,8 @@ dependencies = [
 
 [[package]]
 name = "cubecl-cuda"
-version = "0.10.0-pre.2"
-source = "git+https://github.com/tracel-ai/cubecl?rev=5b831a3cfac3eca0065fe0dbf57cddf5946d1586#5b831a3cfac3eca0065fe0dbf57cddf5946d1586"
+version = "0.10.0-pre.4"
+source = "git+https://github.com/tracel-ai/cubecl?rev=f60142ccc35dcbede6db2c28a1315ae4cccabdd1#f60142ccc35dcbede6db2c28a1315ae4cccabdd1"
 dependencies = [
  "bytemuck",
  "cubecl-common",
@@ -600,8 +597,8 @@ dependencies = [
 
 [[package]]
 name = "cubecl-ir"
-version = "0.10.0-pre.2"
-source = "git+https://github.com/tracel-ai/cubecl?rev=5b831a3cfac3eca0065fe0dbf57cddf5946d1586#5b831a3cfac3eca0065fe0dbf57cddf5946d1586"
+version = "0.10.0-pre.4"
+source = "git+https://github.com/tracel-ai/cubecl?rev=f60142ccc35dcbede6db2c28a1315ae4cccabdd1#f60142ccc35dcbede6db2c28a1315ae4cccabdd1"
 dependencies = [
  "cubecl-common",
  "cubecl-macros-internal",
@@ -621,8 +618,8 @@ dependencies = [
 
 [[package]]
 name = "cubecl-macros"
-version = "0.10.0-pre.2"
-source = "git+https://github.com/tracel-ai/cubecl?rev=5b831a3cfac3eca0065fe0dbf57cddf5946d1586#5b831a3cfac3eca0065fe0dbf57cddf5946d1586"
+version = "0.10.0-pre.4"
+source = "git+https://github.com/tracel-ai/cubecl?rev=f60142ccc35dcbede6db2c28a1315ae4cccabdd1#f60142ccc35dcbede6db2c28a1315ae4cccabdd1"
 dependencies = [
  "cubecl-common",
  "darling 0.23.0",
@@ -637,8 +634,8 @@ dependencies = [
 
 [[package]]
 name = "cubecl-macros-internal"
-version = "0.10.0-pre.2"
-source = "git+https://github.com/tracel-ai/cubecl?rev=5b831a3cfac3eca0065fe0dbf57cddf5946d1586#5b831a3cfac3eca0065fe0dbf57cddf5946d1586"
+version = "0.10.0-pre.4"
+source = "git+https://github.com/tracel-ai/cubecl?rev=f60142ccc35dcbede6db2c28a1315ae4cccabdd1#f60142ccc35dcbede6db2c28a1315ae4cccabdd1"
 dependencies = [
  "darling 0.23.0",
  "proc-macro2",
@@ -648,8 +645,8 @@ dependencies = [
 
 [[package]]
 name = "cubecl-opt"
-version = "0.10.0-pre.2"
-source = "git+https://github.com/tracel-ai/cubecl?rev=5b831a3cfac3eca0065fe0dbf57cddf5946d1586#5b831a3cfac3eca0065fe0dbf57cddf5946d1586"
+version = "0.10.0-pre.4"
+source = "git+https://github.com/tracel-ai/cubecl?rev=f60142ccc35dcbede6db2c28a1315ae4cccabdd1#f60142ccc35dcbede6db2c28a1315ae4cccabdd1"
 dependencies = [
  "cubecl-common",
  "cubecl-core",
@@ -665,9 +662,10 @@ dependencies = [
 
 [[package]]
 name = "cubecl-runtime"
-version = "0.10.0-pre.2"
-source = "git+https://github.com/tracel-ai/cubecl?rev=5b831a3cfac3eca0065fe0dbf57cddf5946d1586#5b831a3cfac3eca0065fe0dbf57cddf5946d1586"
+version = "0.10.0-pre.4"
+source = "git+https://github.com/tracel-ai/cubecl?rev=f60142ccc35dcbede6db2c28a1315ae4cccabdd1#f60142ccc35dcbede6db2c28a1315ae4cccabdd1"
 dependencies = [
+ "ahash",
  "async-channel",
  "bytemuck",
  "cfg-if",
@@ -687,15 +685,14 @@ dependencies = [
  "spin",
  "thiserror",
  "toml",
- "variadics_please",
  "wasm-bindgen-futures",
  "web-time",
 ]
 
 [[package]]
 name = "cubecl-wgpu"
-version = "0.10.0-pre.2"
-source = "git+https://github.com/tracel-ai/cubecl?rev=5b831a3cfac3eca0065fe0dbf57cddf5946d1586#5b831a3cfac3eca0065fe0dbf57cddf5946d1586"
+version = "0.10.0-pre.4"
+source = "git+https://github.com/tracel-ai/cubecl?rev=f60142ccc35dcbede6db2c28a1315ae4cccabdd1#f60142ccc35dcbede6db2c28a1315ae4cccabdd1"
 dependencies = [
  "async-channel",
  "bytemuck",
@@ -711,13 +708,14 @@ dependencies = [
  "hashbrown 0.16.1",
  "log",
  "sanitize-filename",
+ "wasm-bindgen-futures",
  "wgpu",
 ]
 
 [[package]]
 name = "cubecl-zspace"
-version = "0.10.0-pre.2"
-source = "git+https://github.com/tracel-ai/cubecl?rev=5b831a3cfac3eca0065fe0dbf57cddf5946d1586#5b831a3cfac3eca0065fe0dbf57cddf5946d1586"
+version = "0.10.0-pre.4"
+source = "git+https://github.com/tracel-ai/cubecl?rev=f60142ccc35dcbede6db2c28a1315ae4cccabdd1#f60142ccc35dcbede6db2c28a1315ae4cccabdd1"
 dependencies = [
  "derive-new",
  "serde",
@@ -1197,6 +1195,18 @@ dependencies = [
  "wasi",
 ]
 
+[[package]]
+name = "getrandom"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "r-efi 5.3.0",
+ "wasip2",
+]
+
 [[package]]
 name = "getrandom"
 version = "0.4.2"
@@ -1205,7 +1215,7 @@ checksum = "0de51e6874e94e7bf76d726fc5d13ba782deca734ff60d5bb2fb2607c7406555"
 dependencies = [
  "cfg-if",
  "libc",
- "r-efi",
+ "r-efi 6.0.0",
  "rand_core",
  "wasip2",
  "wasip3",
@@ -1663,13 +1673,13 @@ checksum = "8d5439c4ad607c3c23abf66de8c8bf57ba8adcd1f129e699851a6e43935d339d"
 name = "ndarray"
 version = "0.17.2"
 dependencies = [
- "blake3",
  "cblas-sys",
  "libc",
  "matrixmultiply",
  "num-complex",
  "num-integer",
  "num-traits",
+ "paste",
  "portable-atomic",
  "portable-atomic-util",
  "rawpointer",
@@ -2093,6 +2103,12 @@ dependencies = [
  "proc-macro2",
 ]
 
+[[package]]
+name = "r-efi"
+version = "5.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
+
 [[package]]
 name = "r-efi"
 version = "6.0.0"
@@ -2101,9 +2117,9 @@ checksum = "f8dcc9c7d52a811697d2151c701e0d08956f92b0e24136cf4cf27b57a6a0d9bf"
 
 [[package]]
 name = "rand"
-version = "0.10.0"
+version = "0.10.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bc266eb313df6c5c09c1c7b1fbe2510961e5bcd3add930c1e31f7ed9da0feff8"
+checksum = "c7f5fa3a058cd35567ef9bfa5e75732bee0f9e4c55fa90477bef2dfcdbc4be80"
 dependencies = [
  "chacha20",
  "getrandom 0.4.2",
@@ -2652,12 +2668,6 @@ version = "0.2.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853"
 
-[[package]]
-name = "unty"
-version = "0.0.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6d49784317cd0d1ee7ec5c716dd598ec5b4483ea832a2dced265471cc0f690ae"
-
 [[package]]
 name = "ureq"
 version = "3.3.0"
diff --git a/crates/wasm-simd-parity/Cargo.lock b/crates/wasm-simd-parity/Cargo.lock
index f734f708..d694d469 100644
--- a/crates/wasm-simd-parity/Cargo.lock
+++ b/crates/wasm-simd-parity/Cargo.lock
@@ -2,75 +2,12 @@
 # It is not intended for manual editing.
 version = 4
 
-[[package]]
-name = "arrayref"
-version = "0.3.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "76a2e8124351fda1ef8aaaa3bbd7ebbcb486bbcd4225aca0aa0d84bb2db8fecb"
-
-[[package]]
-name = "arrayvec"
-version = "0.7.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d3fb67a6e08acf24fdeccbac2cb6ac4305825bd1f117462e0e6f2f193345ad56"
-
 [[package]]
 name = "autocfg"
 version = "1.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f2032f911046de80f0a198e0901378627c33f59ea0ac00e363d481118bd70a53"
 
-[[package]]
-name = "blake3"
-version = "1.8.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0aa83c34e62843d924f905e0f5c866eb1dd6545fc4d719e803d9ba6030371fce"
-dependencies = [
- "arrayref",
- "arrayvec",
- "cc",
- "cfg-if",
- "constant_time_eq",
- "cpufeatures",
-]
-
-[[package]]
-name = "cc"
-version = "1.2.67"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e17dd265a7d0f31ef544e1b20e03add05d3b45b491b633b10d67145d2acc1a38"
-dependencies = [
- "find-msvc-tools",
- "shlex",
-]
-
-[[package]]
-name = "cfg-if"
-version = "1.0.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
-
-[[package]]
-name = "constant_time_eq"
-version = "0.4.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3d52eff69cd5e647efe296129160853a42795992097e8af39800e1060caeea9b"
-
-[[package]]
-name = "cpufeatures"
-version = "0.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8b2a41393f66f16b0823bb79094d54ac5fbd34ab292ddafb9a0456ac9f87d201"
-dependencies = [
- "libc",
-]
-
-[[package]]
-name = "find-msvc-tools"
-version = "0.1.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582"
-
 [[package]]
 name = "fractal"
 version = "0.1.0"
@@ -78,12 +15,6 @@ dependencies = [
  "libm",
 ]
 
-[[package]]
-name = "libc"
-version = "0.2.186"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "68ab91017fe16c622486840e4c83c9a37afeff978bd239b5293d61ece587de66"
-
 [[package]]
 name = "libm"
 version = "0.2.16"
@@ -104,7 +35,6 @@ dependencies = [
 name = "ndarray"
 version = "0.17.2"
 dependencies = [
- "blake3",
  "fractal",
  "matrixmultiply",
  "num-complex",
@@ -178,12 +108,6 @@ version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "60a357793950651c4ed0f3f52338f53b2f809f32d83a07f72909fa13e4c6c1e3"
 
-[[package]]
-name = "shlex"
-version = "2.0.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f8fadd59c855ef2080decdef8ff161eb6661b86933c9d82e5ba29dc602a55aba"
-
 [[package]]
 name = "wasm-simd-parity"
 version = "0.0.0"
diff --git a/src/hpc/compression_curves.rs b/src/hpc/compression_curves.rs
index 0c7bcb6c..22f0ec66 100644
--- a/src/hpc/compression_curves.rs
+++ b/src/hpc/compression_curves.rs
@@ -14,6 +14,8 @@
 //! - **Product Quantization** (sub-vector k-means, simplified): PQ-lite
 //! - **Random Projection + Binarize**: JL-lemma based
 
+use super::blake3;
+
 // ============================================================================
 // PRNG (self-contained, deterministic)
 // ============================================================================
diff --git a/src/hpc/crystal_encoder.rs b/src/hpc/crystal_encoder.rs
index 26188f9a..f878bb55 100644
--- a/src/hpc/crystal_encoder.rs
+++ b/src/hpc/crystal_encoder.rs
@@ -8,6 +8,7 @@
 //! 3. **Pure Crystal Encoding** — hash-based word encoding via a 65-entry
 //!    NSM semantic-primes codebook, bundled into SPO nodes.
 
+use super::blake3;
 use super::fingerprint::Fingerprint;
 use super::node::Node;
 use super::plane::Plane;
diff --git a/src/hpc/deepnsm.rs b/src/hpc/deepnsm.rs
index 86daf045..be7abdfe 100644
--- a/src/hpc/deepnsm.rs
+++ b/src/hpc/deepnsm.rs
@@ -7,6 +7,7 @@
 //! Transcoded from Python DeepNSM (<https://github.com/AdaWorldAPI/DeepNSM>).
 //! Rust 1.94.0 · SIMD via `crate::simd::F32x16` · Arrow 57 / DataFusion 51 ready.
 
+use super::blake3;
 use std::collections::{HashMap, HashSet};
 use std::sync::LazyLock;
 
diff --git a/src/hpc/merkle_tree.rs b/src/hpc/merkle_tree.rs
index a1f77e44..d9f848f9 100644
--- a/src/hpc/merkle_tree.rs
+++ b/src/hpc/merkle_tree.rs
@@ -5,6 +5,7 @@
 //! on 16Kbit Containers (CLAM, CHAODA, CHESS, CAKES, panCAKES, BNN,
 //! cascade) should also work on the 8Kbit tree at higher speed.
 
+use super::blake3;
 use super::seal::MerkleRoot;
 
 /// Number of branches in the Merkle tree.
diff --git a/src/hpc/plane.rs b/src/hpc/plane.rs
index a94769ea..36a81d0c 100644
--- a/src/hpc/plane.rs
+++ b/src/hpc/plane.rs
@@ -9,6 +9,7 @@
 //!
 //! SIMD wired through: all bulk operations delegate to ndarray's bitwise dispatch.
 
+use super::blake3;
 use super::fingerprint::Fingerprint;
 use std::cell::RefCell;
 
diff --git a/src/hpc/seal.rs b/src/hpc/seal.rs
index 350ed222..b0d47cdb 100644
--- a/src/hpc/seal.rs
+++ b/src/hpc/seal.rs
@@ -3,6 +3,7 @@
 //! [`MerkleRoot`] is a 48-bit truncated blake3 hash of data masked by alpha.
 //! [`Seal`] is the verification result: `Wisdom` (matches) or `Staunen` (differs).
 
+use super::blake3;
 use super::plane::Plane;
 
 /// Integrity seal. Byte equality comparison of blake3 hashes.
diff --git a/src/hpc/spo_bundle.rs b/src/hpc/spo_bundle.rs
index 2b2f6665..28c649f1 100644
--- a/src/hpc/spo_bundle.rs
+++ b/src/hpc/spo_bundle.rs
@@ -260,6 +260,7 @@ fn to_ranks(v: &[f64]) -> Vec<f64> {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::hpc::blake3;
     use std::collections::HashSet;
 
     // ========================================================================
diff --git a/src/hpc/vsa.rs b/src/hpc/vsa.rs
index 0515ef1e..0aed0e83 100644
--- a/src/hpc/vsa.rs
+++ b/src/hpc/vsa.rs
@@ -12,6 +12,8 @@
 //! tier (FP16x32 / FP32x16 / F64x8). Matches the Binary16K / Vsa16k carrier
 //! shared with lance-graph-contract (`crystal::fingerprint`).
 
+use super::blake3;
+
 /// VSA dimensionality: 16,384 bits (Binary16K).
 pub const VSA_DIMS: usize = 16_384;
 
diff --git a/src/lib.rs b/src/lib.rs
index 2c787693..0b510eb5 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -485,16 +485,21 @@ pub mod backend;
 /// extra deps. Cognitive/research modules (p64_bridge, crystal_encoder,
 /// deepnsm, etc.) are gated behind `hpc-extras` inside `hpc/mod.rs`.
 ///
-/// ## blake3 transitive dep
-///
-/// Enabling `std` (the default) automatically pulls `blake3`, which the
-/// cognitive substrate modules (`plane`, `seal`, `merkle_tree`, `vsa`,
-/// `spo_bundle`, `crystal_encoder`, `compression_curves`, `deepnsm`)
-/// import directly and unconditionally. There is no separate feature
-/// to enable; `std` is enough. Consumers building `default-features = false`
-/// without `std` (e.g. the `thumbv6m-none-eabi` nostd target) skip both
-/// the `hpc` module and the blake3 dep. See the `blake3` comment block
-/// in `Cargo.toml` for the rationale.
+/// ## BLAKE3 is in-tree — there is no `blake3` dependency
+///
+/// The cognitive substrate modules (`plane`, `seal`, `merkle_tree`, `vsa`,
+/// `spo_bundle`, `crystal_encoder`, `compression_curves`, `deepnsm`) hash
+/// with `hpc::blake3`, a portable pure-Rust transcription of the BLAKE3
+/// reference implementation that ships inside this crate.
+///
+/// **Enabling `std` no longer pulls the external `blake3` crate.** It, and
+/// its transitive `constant_time_eq`, `arrayref` and `arrayvec`, are gone
+/// from the dependency graph entirely.
+///
+/// Consumers building `default-features = false` without `std` (e.g. the
+/// `thumbv6m-none-eabi` nostd target) skip the `hpc` module, and with it
+/// the BLAKE3 code. See the `blake3` comment block in `Cargo.toml` for why
+/// the dependency was dropped and what it cost.
 #[cfg(feature = "std")]
 #[allow(clippy::all, unused_imports, unused_variables, unused_mut, dead_code)]
 pub mod hpc;