4 Commits

Author	SHA1	Message	Date
Chaim	afe6894441	docs(principles): FINAL synthesis — eliminate queue; verified=chair-cited-in-context; nli 97% FP (#153) ... chaim directive 2026-06-20: no halacha queue ever; trusted = only what a chair actually cited, in context; corpus grows by citations; few-verified-now is fine. nli-audit: nli_unsupported flag is 97% false-positive (29/30) — the 'noise' was imaginary. Two layers: raw background (auto, no gate) vs verified (auto-canon from citations). +06 indexed. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-06-20 13:33:13 +00:00
Chaim	38c395d0de	docs(principles): 3-case evidence (8508/1049/1200) — aggressive lost 22-30 genuine each; no-cull decided (#153) ... Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-06-20 12:51:58 +00:00
Chaim	c1f92db2a0	docs(principles): refine synthesis — 2nd 8508 run (keep-when-in-doubt → 70/70 kept); no-cull triple-confirmed (#153) ... Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-06-20 12:40:30 +00:00
Chaim	0f7549a137	docs(principles): final synthesis — keep-all+rank-at-retrieval; 8508 test killed cap/novelty (lost Lustrenik) (#153) ... 8508-03-24 test: panel+cap cut 70→3, losing ~22 genuine principles incl. the core Lustrenik betterment rule. Lesson: cap + novelty-filter is destructive for RAG (which needs applied doctrine). Quality-at-source = dedup+noise-only, no cap. PR#304 regime flagged for revision. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-06-20 12:36:42 +00:00