SOURCE-LINKED INTELLIGENCE

A Unifying Perspective on Probabilities as Model Predictions

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Although probabilistic statements are ubiquitous, foundational disagreements persist about their understanding, as exemplified by debates between Bayesians and frequentists; moreover, it is unclear when and why acting on them actually leads to desirable outcomes. Here, we argue that every probability is the output of a \emph{prediction method}, that is, it depends on both a particular way of constructing abstractions and a way of transforming them into predictions. Through this, we provide a unifying perspective on supposedly different kinds of probabilities and show that even supposedly objec

Read original source ↗ Open in workspace

recordType

paper

region

Global