AI RESEARCH
A Perfectly Truthful Calibration Measure
arXiv CS.LG
•
ArXi:2508.13100v3 Announce Type: replace Calibration requires that predictions are conditionally unbiased and, therefore, reliably interpretable as probabilities. A calibration measure quantifies how far a predictor is from perfect calibration. As We design a simple, perfectly and strictly truthful, sound and complete calibration measure in the batch setting: averaged two-bin calibration error (ATB). ATB is quadratically related to two existing calibration measures: the smooth calibration error smCal and the lower distance to calibration distCal.