The Ceiling Is in the Channel: Auditing Learner Gaps and Measurement Frontiers in Clinical Prediction

Abstract

arXiv:2609.01909v1 Announce Type: new Abstract: Clinical prediction can saturate for two different reasons: a fitted learner may fail to extract available information, or the recorded variables may impose a population frontier. We separate these quantities through the \emph{learner gap} and the \emph{measurement-channel ceiling}. Optimal balanced accuracy is characterized by total-variation separation, yielding architecture invariance, a sharp partial-identification result under replacement cont