Marius CiepluchandClaude Fable 5.1 9e7aef6a6b feat(pair-corpus-honesty): reject improve rounds that regress any provenance profile on holdout ...

Task 6.3.

- improve/evolve.py: evaluate_profiles and profile_regressions score the
  holdout pair split per provenance profile every round; a drop in pair
  pass rate or Youden beyond --profile-tolerance rejects the round with
  reason profile_regression:<profile>; profiles under
  --min-holdout-pairs are reported, not gated; journal records both.
- cli improve: --pair-catalog, --no-pair-gate, --profile-tolerance,
  --min-holdout-pairs; a missing catalog fails loud instead of skipping
  the gate.

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

2026-09-05 10:45:43 +02:00

..

complexity

feat(three-stage-scan): report map and honor fail-on worth-fixing

2026-09-04 00:18:33 +02:00

improve

feat(pair-corpus-honesty): reject improve rounds that regress any provenance profile on holdout

2026-09-05 10:45:43 +02:00

policy

feat(governance): Phase 1 — CWE policy store + project score (zero-dep)

2026-06-22 12:31:35 +02:00

provider

feat(three-stage-scan): attach tool hunter to map hotspots

2026-09-04 00:04:36 +02:00

regress

feat(three-stage-scan): report map and honor fail-on worth-fixing

2026-09-04 00:18:33 +02:00

ruleset

feat(propose-adjudicate-prove): overlay adjudicates inventory before prove

2026-09-04 13:57:33 +02:00

sandbox

feat(three-stage-scan): run or skip deep regression with visible degradation

2026-09-03 23:43:15 +02:00

scoring

feat(benchmark): Phase 2 (task 4) — actionable per-rule signals, ledger, FP knob

2026-06-22 15:41:17 +02:00

semantic

feat(pair-corpus-honesty): function-scoped honest scorer with mechanisms and loss counters

2026-09-05 10:45:43 +02:00

__init__.py

chore(release): 1.1.0

2026-09-04 12:00:15 +02:00

benchmark.py

feat(pair-corpus-honesty): function-scoped honest scorer with mechanisms and loss counters

2026-09-05 10:45:43 +02:00

calibration.py

feat(benchmark): Phase 2 (task 4) — actionable per-rule signals, ledger, FP knob

2026-06-22 15:41:17 +02:00

cli.py

feat(pair-corpus-honesty): reject improve rounds that regress any provenance profile on holdout

2026-09-05 10:45:43 +02:00

config.py

feat: load OpenRouter settings from a local .env

2026-09-04 14:06:18 +02:00

findings.py

feat(three-stage-scan): attach tool hunter to map hotspots

2026-09-04 00:04:36 +02:00

fusion.py

feat(fusion): Phase 13 — two-panel fusion adjudication

2026-06-22 18:57:03 +02:00

gate.py

feat(gate): Phase 4 task 8 — lock the detection gate into CI

2026-06-22 17:13:02 +02:00

harness_ext.py

feat(harnessx): configurable provider + per-task budget caps

2026-06-22 17:59:44 +02:00

harness.py

feat(hardening): Phase 15 — redaction, retry/backoff, budgets, threat-model docs

2026-06-22 20:02:34 +02:00

hunter_harness.py

feat(skills): Phase 14 — Trail of Bits skill index + router

2026-06-22 19:51:04 +02:00

hunter_tools.py

feat(three-stage-scan): add path-clamped hunter read grep and refs

2026-09-03 21:01:57 +02:00

hunter.py

feat(skills): Phase 14 — Trail of Bits skill index + router

2026-06-22 19:51:04 +02:00

index.py

ci: add quality gates and release workflows

2026-06-18 10:06:21 +02:00

map_gate.py

feat(three-stage-scan): gate stage-2 maps against split-sink ranking

2026-09-04 11:53:06 +02:00

mapping.py

ci: add quality gates and release workflows

2026-06-18 10:06:21 +02:00

mcp.py

feat(mcp): Phase 12 — narrow MCP server + ousast mcp

2026-06-22 19:42:01 +02:00

pair_gate.py

feat(real-world-vfc-slice): add labeled OpenSSL/Firefox/Chromium/curl pair corpus

2026-09-04 16:45:38 +02:00

pairs.py

feat(pair-corpus-honesty): function-scoped honest scorer with mechanisms and loss counters

2026-09-05 10:45:43 +02:00

preprocess.py

feat(detection): language-scoped rules + multi-language benchmark corpora

2026-06-21 11:49:31 +02:00

provenance.py

feat(pair-corpus-honesty): deterministic provenance fingerprint at scan time

2026-09-05 10:45:43 +02:00

rank.py

ci: add quality gates and release workflows

2026-06-18 10:06:21 +02:00

redaction.py

feat(hardening): Phase 15 — redaction, retry/backoff, budgets, threat-model docs

2026-06-22 20:02:34 +02:00

reports.py

feat(pair-corpus-honesty): deterministic provenance fingerprint at scan time

2026-09-05 10:45:43 +02:00

run.py

feat(scan): add initial SAST pipeline

2026-06-17 21:13:51 +02:00

skills.py

feat(skills): Phase 14 — Trail of Bits skill index + router

2026-06-22 19:51:04 +02:00

slot_contract.py

feat(slots): Phase 3 task 6.3 — model-disabled, slot-contracted deterministic stages

2026-06-22 18:39:09 +02:00

stage_processors.py

feat(slots): Phase 3 task 6.3 — model-disabled, slot-contracted deterministic stages

2026-06-22 18:39:09 +02:00

stages.py

feat(three-stage-scan): keep quick as stage-1 inventory

2026-09-03 23:14:00 +02:00

tool_hunter.py

feat(three-stage-scan): attach tool hunter to map hotspots

2026-09-04 00:04:36 +02:00

vectorstore.py

ci: add quality gates and release workflows

2026-06-18 10:06:21 +02:00

verification.py

ci: add quality gates and release workflows

2026-06-18 10:06:21 +02:00

verify_judge.py

feat(harnessx): configurable provider + per-task budget caps

2026-06-22 17:59:44 +02:00