ResearchBenchmarksProbability Calibration on Obesity dataset (Xt)Follow0.16ECE (sqrt(n) bins)Random Forest0.1520.1560.160.164Feb 20, 2026Evaluation ResultsMethodMethodLinksECE (sqrt(n) bins)MCLLO p-valueAccuracyLabel Change (%)Random ForestCalibration set=Xt, n=396Calibration set=Xt, n=3962026.020.16—85.1—