Auditing System-1 Models on Biosecurity-Relevant Benchmarks: Calibration, Selective Prediction, and Permutation Instability in a Non-Generative Model

Kimon Antonios Provatas, Ilias Georgakopoulos-Soares

Non-generative "System-1" models return structured probabilistic decisions in a single forward pass, without autoregressive decoding, at a small fraction of the inference cost of a…