Code and results for "Stable Discrimination Can Hide Reliability Failures in AI Decision Support Under Distribution Shift and Changing Target Definitions". Computers 15(9), 560 (2026). DOI: 10.3390/computers15090560
benchmark machine-learning open-science reproducibility uncertainty-quantification robustness target-definition probability-calibration conformal-prediction research-software model-monitoring abstention trustworthy-ai target-shift selective-prediction dataset-shift distribution-shifts model-reliability ai-decision-support reliability-auditing
-
Updated
Sep 13, 2026 - Python