Stage 18R Tier A verdict + Tier C design: stop condition cleared, w4 retained, rerank dropped from default
Tier A (deterministic, LF): maud pool recall now RISES with context weight (0.6028 w0 -> 0.6544 w1 -> 0.6442 w4) after the header regeneration, against 0.6028 -> 0.5788 before. Enrichment is worth ~2x what was recorded (maud lexR4 +0.193 vs +0.092). w1 is now maud-optimal but w4 wins every general metric, so w4 is RETAINED and w1 recorded - re-picking on the hardest single source is benchmark tuning. R1 clause: beats chars on every source on LF (contractnli pool rises where the original recorded a drop); maud prong still misses, so R1 stays falsified on half its recorded basis. R2: re-falsified decisively. Tier C staged for a fast first read: pools injected via --pool-jsonl so only composition is paid, four arms x1 replicate, spread-keyed escalation to 3 only for pairs inside the band. Rerank dropped from the default candidate per Eli (76.8k chars/query at p1600, gain not separable from filename matching per F1); retained as a control arm that prices it. Preview-500 isolation retired as moot. 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 | d6813dd7 |
| 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-eaf19f89.md
from inside the repo you want the change in.