PADBench l2_rank64
Matched reference — read against a recipe-matched benign population from the same corpus — the strong regime.
PADBench, Llama-2-7b LoRA r64.
Part of PADBench (expanded coverage) — its specimens are materialized there.
The reading
VerdictPARTIAL (budget) — benign-only
10 clean / 0 poison landed before the time budget → no poison class → no matched contrast. Resumable. Its 10 specimens are materialized as abstain under padbench-expanded.
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.