Stage 18 instrument fix: committed pool re-scorer + --output on the ctx sweep

↗ view on GitHub · Eli Ziff · 2026-07-31 · e37ca5f3

legalbench_pool_rescore.py corrects a raw-coordinate pool sidecar at SCORE
time (raw -> LF offset mapping + union-merge + clip), for receipts that
cannot be re-run for free. It prints the three readings separately so the
coordinate defect and the double-count defect stay attributable.

On stage18-fused-pools.jsonl it reproduces the audit's corrected figures
exactly: maud pool R@48 0.6795 recorded -> 0.9205 lf-mapped -> 0.8625
corrected; ALL 0.9584. Independent code path, same numbers.

--output lets a sweep write receipts under an explicit name.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01H9ToHYJVDxfeJcJwdzrP2H
Repository eliziff/Beaver
Author Eli Ziff <eliasziff@gmail.com>
Authored
Parents 328eb32b
Stats 2 files changed , +180 , -4
Part of Deterministic legal-text tools ("SLA audit organs")

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-e37ca5f3.md from inside the repo you want the change in.

⬇ Download capture-commit-e37ca5f3.md