AI RESEARCH
Decomposing the Generalization Gap in PROTAC Activity Prediction: Variance Attribution and the Inter-Laboratory Ceiling
arXiv CS.LG
•
ArXi:2605.11764v1 Announce Type: new Machine-learning predictors of biochemical activity often exhibit large random-split-to-leave-one-target-out generalisation gaps that have been documented but not decomposed. We frame this as an evaluation-science question and use targeted protein degradation as the empirical test bed.