BAIT-ModelZoo

The aggregate

The rank-separability score and the shipped operating point, side by side. The verdicts are a projection at a false-positive budget, not a raw score — coarse reads only, no detector numbers.

No AUC is reported for this cohort — see the caveat above. We don’t manufacture a rank-separability number where the design doesn’t support one.

AUC WITHHELD — epoch-confound is non-identifiable (Mistral collapses to 0.50 under epoch-regression). Confusion at the conservative FPR<=0.10 cut over the 39 scored (20 clean / 19 poison): all clean stayed benign (realized_fpr 0.000), 14/19 poison caught. The 91-total corpus carries 45 poison / 46 clean; 52 not yet delta-persisted.

shipped-scanner operating-point outcome (TP/FP/FN/abstain/TN); complementary to the imported engine AUC, NOT a reconciliation of it. Abstain is first-class.

Per-cohort results

Strongest first, split by the honest floor. Every miss is listed beside every catch; abstain is its own column, never folded into a clean read.

We declined to rule on 0 of 39 specimens in this corpus — a first-class outcome of the method, not a gap: with no matched benign contrast the read stays silent rather than guess.

Specimens

39 named specimens, grouped by cohort. A specimen links out only when its id resolves to a genuinely-measured scan report; specimens we have not scanned — and indices inside a parent repo (cohort members, not standalone models) — render as corpus-local rows with no link, never a click-through to a report that does not exist.