PADBench l2_adalora_r8
Matched reference — read against a recipe-matched benign population from the same corpus — the strong regime.
PADBench, Llama-2-7b AdaLoRA r8.
Part of PADBench (expanded coverage) — its specimens are materialized there.
The reading
VerdictNOT-APPLICABLE — input-contract mismatch
AdaLoRA stores the delta as B@diag(E)@A; the frozen engine's LoRA contract found n_mods=0 → unscoreable read. A matched benign population exists; only the read FORMAT is unmet (needs an engine extension). Its 60 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.