A Fiber Criterion for Representation Identifiability in Supervised Learning 事件

A Fiber Criterion for Representation Identifiability in Supervised Learning arXiv:2606.01092v1 Announce Type: cross Abstract: Supervised learning evaluates predictors through their input-output behavior. When a predictor is implemented as a composition $f=c\circ h$, supervised evidence constrains the composite map $f$ but need not determine the representation-head factorization $(h,c)$. This paper formalizes the resulting representation-level identifiability problem: for a class of admissible r