Withdraw the similarity/defined-term retirement too; adopt a retirement standard

↗ view on GitHub · Eli Ziff · 2026-07-31 · d2c5edbb

The gold-span objection applies to the weak layers as well, and letting their
retirement stand on "they lost to a deterministic control" was wrong: a clean
control does not repair a metric that cannot express the mechanism. A
defined-term edge exists precisely to reach a definition, and a definition is
by construction never the answer span. One untuned implementation each, 14-31
fragments, 24/69 documents refused.

Nothing in this round is retired. Adopted standard, since the existing ensemble
doctrine already required it (never discard a witness on weak solo performance;
retire only on demonstrated redundancy): retiring any layer needs a metric that
can express the mechanism, adequate n with the band computed from that n, full
instrument strength with the refusal rate reported, and testing in concert
rather than solo.

Honest status of every layer in this round: built and unproven.

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 0d5e4568
Stats 1 file changed , +36 , -7
Part of Legal agent-surface and context-compaction experiments

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-d2c5edbb.md from inside the repo you want the change in.

⬇ Download capture-commit-d2c5edbb.md