jedarden 9ce1b36206 P12.OP4: Add confidence intervals to score comparability benchmark ... Research doc updated with precise 95% CIs per query type. compare.py now computes and reports confidence intervals. Kendall τ = 0.79 (95% CI [0.7873, 0.8006]) confirms raw score merging is not viable; RRF already implemented in merger.rs as mitigation. Follow-up bead created (miroir-zfo) for RRF quality validation. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>		2026-04-19 00:07:42 -04:00
..
benchmarks	P12.OP3: Validate 2× transient load caveat and add CLI schedule window guard	2026-04-18 22:00:57 -04:00
dump-import	P12.OP5: Add dump import compatibility matrix	2026-04-18 21:06:46 -04:00
notes	Add repo hygiene: LICENSE, CHANGELOG, .gitignore	2026-04-18 20:47:36 -04:00
plan	P0.7: Update plan with chaos-test results, sync beads	2026-04-18 23:03:21 -04:00
research	P12.OP4: Add confidence intervals to score comparability benchmark	2026-04-19 00:07:42 -04:00
trade-offs.md	P12.OP1: Chaos-test cutover race window + hard refusal policy	2026-04-18 22:00:21 -04:00