Marius CiepluchandClaude Fable 5.1 6e5d060de6 feat(hunt): registered paired ablation, repository folds, leak audit, importance table and the keep/drop rule (4.2-4.4) ...

ablation.py registers the manifest (table digest, arms as masks, folds, metric, sample, budget,
rule, seed, program id) before any run and refuses a run or an analysis that does not match it.
Arms run over the same changes through runner.run, paired by change; effects on recall and on
suspicions per ordinary push are reported pooled and per family with the repository-clustered
bootstrap and exact McNemar, plus the recall-against-suspicions curve at every reported
confidence (never a tuned cut). The importance table and decisions read held-out effects only;
a neutral annotation survives only when a kept one needs it. 30 fixture tests with a scripted
model. Implemented by Codex (gpt-6-astra), gated here.

Co-Authored-By: Claude Fable 5.1 <[email protected]>

2026-10-13 18:49:58 +02:00

..

archive/steering

docs(kiro): archive the superseded roadmap; status notes on specs

2026-10-02 08:19:48 +02:00

settings/templates

chore: add kiro spec-driven tooling and steering docs

2026-06-21 14:28:19 +02:00

specs

feat(hunt): registered paired ablation, repository folds, leak audit, importance table and the keep/drop rule (4.2-4.4)

2026-10-13 18:49:58 +02:00

steering

chore(p0): retire regress, the skill router, the module audit tool and vocabulary.sc

2026-10-13 10:50:01 +02:00

breadth.toml

spec(hunter-learning-loop): a pattern engine's miss is never evidence

2026-10-13 13:01:32 +02:00