Disproving the Feasibility of Learned Confidence Calibration Under Binary Supervision: An Information-Theoretic Impossibility

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nair, Arjun S., Sinaga, Kristina P.
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.14386