Abstract

Despite over a century of inquiry, intelligence still lacks a definition that is both species-agnostic and experimentally tractable. We propose a minimal, category-based criterion: intelligence is the ability, given sample(s) from a category, to produce sample(s) from the same category. We formalise this intuition as ε-category intelligence: it is ε-intelligent with respect to a category if no chosen admissible distinguisher can separate generated from original samples beyond tolerance ε. This indistinguishability principle subsumes generative modelling, classification, and goal-directed decision making without anthropocentric or task-specific bias. We present the formal framework, outline empirical protocols, and discuss implications for evaluation, safety, and generalisation. By reducing intelligence to categorical sample fidelity, our definition provides a single yardstick for comparing biological, artificial, and hybrid systems, and invites further theoretical refinement and empirical validation.