The AI Measurement Science Workshop will be held on 9 October 2026 at COLM 2026 in San Francisco, and the call for papers is now open.
The workshop treats evaluation as a first-class scientific problem: measurement under interaction, strategic optimization, and non-stationarity. It brings together researchers across machine learning, statistics, psychometrics, economics, and policy.
There are two tracks: a research track, with submissions due June 23, and a competition track for participants in the Predictive AI Evaluation Challenge. Submission details are on the workshop page.