Marius CiepluchandClaude Fable 5.1 ea05e3357c docs(learning-harness): fold four research threads into the brief and add research.md ...

AIxCC cyber reasoning systems, self-improving harness methods (GEPA, DGM,
Self-Harness, SkillOpt, AHE), vulnerability-dataset pitfalls and CWE taxonomies,
and routing/regression-control literature. The design changes they force:
coarse verifier-aligned families instead of fine CWE, multi-label routing with
an unknown class, pair-wise outcomes with a directional-bias index, K-run
reliable-change tests, a per-class seed-noise floor as the regression budget,
a no-regression acceptance rule with ties rejected, structural edits over prose
edits, a proposer blind to the holdout, and verifier code and gold labels
outside every editable surface.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
Claude-Session: https://claude.ai/code/session_01T7XD7x5KonMdmGRkp63EQG

2026-09-06 08:22:43 +02:00

..

settings/templates

chore: add kiro spec-driven tooling and steering docs

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

specs

docs(learning-harness): fold four research threads into the brief and add research.md

2026-09-06 08:22:43 +02:00

steering

docs(specs): kick off authorization-obligations (brief + requirements, unapproved)

2026-09-05 16:31:49 +02:00