Research framework for analyzing calibration collapse under class imbalance in tabular machine learning, with adaptive calibration methods, stress-test benchmarks, and minority reliability evaluation.
machine-learning reliability tabular-data pytorch calibration class-imbalance uncertainty-estimation ece smote robustness probability-calibration imbalanced-learning calibration-error expected-calibration-error calibration-collapse
-
Updated
May 8, 2026 - Python