mirror of
https://github.com/norandom/OpenUltraSAST.git
synced 2026-10-16 03:49:26 +00:00
First honest, measured unseen-repo baseline on 100 frozen never-seen repos (1300 changes, DEFAULT arm, docker lane). This is the quick pattern-rule FLOOR (no LLM: model=disabled, 0 calls; engine_covered=0, the ~200s wall) — the release gate is now a measurement, not an assertion. - catch 3/92 = 3.3% (Wilson95 1.1–9.2%); false_alarm 3.1% (cluster95 1.6–5.4%, icc 0.25); alerts_only 0%; instrument_failure 4.2% (<5%); engine_covered 0. - by family: deser 1/4, injection 2/20, rest 0. - baseline row appended to usage-p1.jsonl (freeze_digest 3371c67d) = G0 exit. Caveats in NOTES.md: machine-label (SZZ, 100 unchecked), regex-only floor (NOT the >=90%/<10% gate), docker lane, slice-1 sizing (~±10% overall, per-family too thin). Co-Authored-By: Claude Opus 4.8 <[email protected]>
2 lines
419 B
JSON
2 lines
419 B
JSON
{"date": "2026-10-11", "decision": "record07_baseline", "digest": "70a4c58dab80165d976410c952895374581ef92fad62bf47c313cbc4d3a05801", "freeze_digest": "3371c67d5360f868d13a8fc1cac93a093210f2c40baa566db533de194b32cd8a", "previous": "0000000000000000000000000000000000000000000000000000000000000000", "purpose": "baseline", "result_digest": "704ac7551630668eeaaa0fa609bc0209039b31a0d3f1ff29bdd5a0687ec34e68", "slice": 1}
|