Stage 17 verdict: crowned stack holds on full LegalBench-RAG mini (776 cells)

↗ view on GitHub · Eli Ziff · 2026-07-30 · 25ef6ec5

651 answered (83.9%), P=0.505 answered-only grounded char precision vs
0.087 baseline at 1/7th the quoted chars; 1,358/1,358 quoted spans
verbatim-audited, zero false passes; doc-miss audit resolves 6/7 to a
byte-identical CUAD duplicate file, true rate 0.15%. Runner: fix
usage-undefined crash in the finalizer merge; add --rerank-preview so a
resume never mixes rerank configs in one receipt file.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012AgUm5EcRKbT3duVFMbrQD
Repository eliziff/Beaver
Author Eli Ziff <eliasziff@gmail.com>
Authored
Parents 1470f4f4
Stats 2 files changed , +74 , -7
Part of Legal grounding and retrieval research

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-25ef6ec5.md from inside the repo you want the change in.

⬇ Download capture-commit-25ef6ec5.md