AI RESEARCH

Descriptive versus Regulatory Uncertainty in Bounded Predictive Systems

arXiv CS.LG

ArXi:2605.18909v1 Announce Type: new Any system that models the world under finite representational capacity must compress; any compression entails a prior; and the prior is the system's bias. What has not been established is whether uncertainty participates in the dynamics governing future behavior, or merely describes the output distribution without consequence. We