docs: Stage 10 verdict - H18 witness panel falsified; persistence is a latency lever, not reliability

↗ view on GitHub · Eli Ziff · 2026-07-30 · faabcc04

P1 falsified (no first-sub acceptance gain any model); P2 partial (no-sub
direction holds, mini misses <=5); P3 perfect (zero parroting, accepted or
attempted); P4 controls within floor; P5 split (claude median 29.5s->20.2s,
errors 4->4 + 8 new; content-shaped JSON failures recur on identical cells
across arms, plus 90s-cap stream aborts under sustained persist load).
Amendment: Stage 9 escape-hatch zero was behavioral, not gate-enforced;
2/246 recurrence recorded, hardening candidate noted. Receipts hashed.

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 ab22fc81
Stats 1 file changed , +68
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-faabcc04.md from inside the repo you want the change in.

⬇ Download capture-commit-faabcc04.md