Skip to content
#

held-out

Star

Here is 1 public repository matching this topic...

hmbseaotter / goldset-triad-harness

Star 0

Deterministic evaluation harness for AP document-matching agents. Scores 3-way findings against a hand-audited, held-out golden dataset: per-category precision and recall, over-flagging measured on a zero-defect control, byte-reproducible scorecards, answer key structurally out of reach.

python benchmark reproducibility determinism data-contamination llm-evaluation agent-evaluation evaluation-harness golden-dataset held-out
  • Updated Jul 28, 2026
  • Python

Improve this page

Add a description, image, and links to the held-out topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the held-out topic, visit your repo's landing page and select "manage topics."

Learn more