feat(lab): Stage 0 replay validators pass - W4/W5 modules + report

↗ view on GitHub · Eli Ziff · 2026-08-05 · 679b14f2

Three wings validated by deterministic replay over the 21 judged cells,
zero model calls:
- legalNegativeAssertionGuard (W4): negative assertions citing unserved
  anchors; 2 firings, both true (banking C-011/C-012 on index_v1),
  silent on all 11 whole-read cells; precision 1.00
- legalFigureReconciliation (W5): competing-base detection; 4/4 true
  findings separating DPA floor/index_floor FAIL cells from PASS cells,
  0 false positives across 3,052 figures (naive signal fires 289 -
  the mechanism ladder is in the report)
- W7 find normalization probe: 7/7 quoted-defined-term queries
  recovered; corpus zero-hit census 16.0% -> 11.7%; second defect
  found: the pandoc markdown plane bolds terms inside quotes, breaking
  the same grammar (fold-both-sides matcher recovers 12/45)

Replay substrate proven byte-exact (131/131 planes, exposure ratios to
4 decimals). Design doc: corrected $210M case attribution (white-collar
DPA, not banking) and folded Stage 0 verdicts + W4 addressability
caveat into §1.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011pfUVhNFTRvhYGXBwoKNj6
Repository eliziff/Beaver
Author Eli Ziff <eliasziff@gmail.com>
Authored
Parents 96b39f35
Stats 4 files changed , +1671 , -3
Part of Evaluation harness: Beaver-CAN and LegalBench-RAG adapters

Capture this commit into my fork

Download a Markdown prompt that tells Claude how to port this exact commit into your working tree. Run it via claude -p < capture-commit-679b14f2.md from inside the repo you want the change in.

⬇ Download capture-commit-679b14f2.md