AI RESEARCH
AlphaFold's Bayesian Roots in Probability Kinematics
arXiv CS.LG
•
ArXi:2505.19763v3 Announce Type: replace The seminal breakthrough of AlphaFold in protein structure prediction relied on a learned potential energy function parameterized by deep models, in contrast to its successors AlphaFold2 and AlphaFold3, which lack an explicit probabilistic interpretation. While AlphaFold's potential was originally justified by heuristic analogy to physical potentials of mean force, we show that it can instead be understood as a principled instance of probability kinematics (PK), also known as Jeffrey conditioning, a generalization of Bayesian updating.