AI RESEARCH
Refereed Learning
arXiv CS.LG
•
ArXi:2510.05440v2 Announce Type: replace-cross We initiate an investigation of learning tasks in a setting where the learner is given access to two competing provers, only one of which is honest. Specifically, we consider the power of such learners in assessing purported properties of opaque models. Following prior work in complexity theory that considers the power of competing provers in various settings, we call this setting refereed learning.