Factorized inverse decision model

Factorized inverse decision model improves cognitive-status classification in silico.

“FIDM provides information complementary to clinical scores, trajectory summaries, and frozen language representations, with consistent gains across all evaluated baselines in the binary setting.”

In silicon = 400

Reading Cognition as Decisions Unfold in Words: A Factorized Inverse Decision Model

arXiv·10 Aug 2026Preprint