BAIT-ModelZoo specificity sham-null (n=13)
Matched reference — read against a recipe-matched benign population from the same corpus — the strong regime.
BAIT-ModelZoo llama2_7b — random-direction (sham) specificity control.
Part of BAIT-ModelZoo — its specimens are materialized there.
The reading
VerdictPENDING — complementary specificity control owed
The exhaustive label-permutation perm_p is the primary null; the random-direction sham specificity control did not complete under load. Complementary, not blocking.
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.