feat(ms-ai-architect): S1 judge bake-off harness + forhåndsregistrert gate (TDD) [skip-docs]

Browse source

Deterministisk de-risk-harness for Fase 3-judgen (kjøres på frosset 373-påstands gull-sett):
- lib/judge-bakeoff.mjs: P-filter (volatil+fetchbar, price ekskl.), confusion-matrix
  for 3 armer (staleness/judge/hybrid), Wilson-bånd, forhåndsregistrert gate. 14 tester.
- extract-judge-claims.mjs: blind manifest (255 påstander, 0 label-lekkasje — testet invariant).
- judge-claim-prompt.md: blind per-påstands groundedness-judge (Opus xhigh, microsoft_docs_fetch).
- run-judge-bakeoff.mjs: join gull+results på id, gate-rapport (.json/.md).

Gate FORHÅNDSREGISTRERT (operatørvalg, før fan-out): recall ≥0.80, presisjon ≥0.70,
OG slår staleness (0/38). Evalueringspop P = 240 verifiserbare, 38 positive.
Suite 551/551 (538 + 13 nye).

...

This commit is contained in:

Kjell Tore Guttormsen 2026-06-26 20:10:58 +02:00

parent f3836b0cfe

commit 3e39f2df6b

7 changed files with 2744 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

2051

scripts/kb-eval/data/judge-bakeoff-claims.json Normal file

View file

File diff suppressed because it is too large Load diff