Rules of proof for maximal entropy inference

This paper investigates rules of proof for maximal entropy inference. It provides the first study of rules of proof for maximal entropy inference on infinite predicate languages. The main result of this paper is the con- struction of a set of rules, in which all rules are sound for maximal entropy inference on finite domains but are not sound for Williamson’s Maximal Entropy Approach on infinite predicate languages. This elucidates differ- ences between explications of the Maximum Entropy Principle on finite domains and on infinite predicate languages.