5930bbcd3fa8dbb3f4305cc2ae347d33e14581af
25 primary sources, 21/25 claims verified (3-vote adversarial). Verdict: keep all principles, rank by precedent-level citation centrality at retrieval time (not a destructive holding-level cull — that's where automation provably errs), gate human review near-zero via conformal/selective-prediction. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
docs(principles): deep-research report — rank-at-retrieval over destructive cull, near-zero review (#153)
Merge pull request 'fix(principles): cull resumability + cap criterion-A (consensus-first) (#152)' (#305) from worktree-canonical-synthesis into main
Description
AI Legal Decision Drafting System — MCP server, web upload, RAG search
Languages
Python
65.2%
TypeScript
32.7%
JavaScript
1.1%
Shell
0.7%
CSS
0.2%