grounding: Stage 5 pre-registration - scale 4x, cross the checker model

↗ view on GitHub · Eli Ziff · 2026-07-30 · 29bc7e6f

Controls for the composing model being inherently more trustworthy at
legal: verification passes can now run on a different model than the
composer (finalize gains checkerModel; composition and the repair pass
stay on the composer), and the runner gains a --checker-models factor
(same | cross | explicit id) recorded per receipt, with control cells
running once. Matrix scales to 24 held-constant items: 12 CSLB (4
ordinary case, 4 ordinary legislation, 4 adversarial), 4 CLERC
continuations, 8 HousingQA rows (audited 163/0 sufficiency pair plus
six unaudited yes/no-balanced rows whose benchmark labels are NOT
treated as sufficiency gold). Frozen Hypothesis 5, predictions, and
falsification conditions recorded in the log before the run; unit
tests 12 passed, tsc clean.

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 413f7032
Stats 3 files changed , +118 , -6
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-29bc7e6f.md from inside the repo you want the change in.

⬇ Download capture-commit-29bc7e6f.md