Stage 15 confirm verdict: 7x coverage, invariants held; pool-recall probe

↗ view on GitHub · Eli Ziff · 2026-07-30 · 128e4c0f

Answered 21/32 (pilot 3/32), unlocated 0, wrong-doc 0, answered-only
precision 0.44 (57x original baseline). Pool recall 0.52@12 / 0.68@24 /
0.85@48: gold is in the lexical pool below the cut, so the flat-rate
model lever is deep-pool reranking, not query expansion.

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 83dcc467
Stats 1 file changed , +30
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-128e4c0f.md from inside the repo you want the change in.

⬇ Download capture-commit-128e4c0f.md