[2603.00063] Measuring What AI Systems Might Do: Towards A Measurement Science in AI

Computer Science > Computers and Society arXiv:2603.00063 (cs) [Submitted on 10 Feb 2026] Title:Measuring What AI Systems Might Do: Towards A Measurement Science in AI Authors:Konstantinos Voudouris, Mirko Thalmann, Alex Kipnis, José Hernández-Orallo, Eric Schulz View a PDF of the paper titled Measuring What AI Systems Might Do: Towards A Measurement Science in AI, by Konstantinos Voudouris and Mirko Thalmann and Alex Kipnis and Jos\'e Hern\'andez-Orallo and Eric Schulz View PDF HTML (experimental) Abstract:Scientists, policy-makers, business leaders, and members of the public care about what modern artificial intelligence systems are disposed to do. Yet terms such as capabilities, propensities, skills, values, and abilities are routinely used interchangeably and conflated with observable performance, with AI evaluation practices rarely specifying what quantity they purport to measure. We argue that capabilities and propensities are dispositional properties - stable features of systems characterised by counterfactual relationships between contextual conditions and behavioural outputs. Measuring a disposition requires (i) hypothesising which contextual properties are causally relevant, (ii) independently operationalising and measuring those properties, and (iii) empirically mapping how variation in those properties affects the probability of the behaviour. Dominant approaches to AI evaluation, from benchmark averages to data-driven latent-variable models such as Item Respon...