{"total":24,"rows":[{"id":"2309.12236","title":"Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing","created":"2023-09-21","cited_by_count":63,"area":null},{"id":"2211.16886","title":"A Unifying Theory of Distance from Calibration","created":"2022-11-30","cited_by_count":53,"area":null},{"id":"2404.03163","title":"Uncertainty in Language Models: Assessment through Rank-Calibration","created":"2024-04-04","cited_by_count":41,"area":null},{"id":"2206.02757","title":"Robust Calibration with Multi-domain Temperature Scaling","created":"2022-06-06","cited_by_count":39,"area":null},{"id":"2205.09680","title":"Metrics of calibration for probabilistic predictions","created":"2022-05-19","cited_by_count":32,"area":null},{"id":"2501.19047","title":"Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE)","created":"2025-01-31","cited_by_count":20,"area":null},{"id":"2210.01964","title":"The Calibration Generalization Gap","created":"2022-10-05","cited_by_count":18,"area":null},{"id":"2402.00857","title":"Early Time Classification with Accumulated Accuracy Gap Control","created":"2024-02-01","cited_by_count":11,"area":null},{"id":"2305.10886","title":"Minimum-Risk Recalibration of Classifiers","created":"2023-05-18","cited_by_count":10,"area":null},{"id":"2402.13187","title":"Testing Calibration in Nearly-Linear Time","created":"2024-02-20","cited_by_count":10,"area":null},{"id":"2406.04068","title":"Reassessing How to Compare and Improve the Calibration of Machine Learning Models","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2407.16550","title":"A Kernel-Based Conditional Two-Sample Test Using Nearest Neighbors (with Applications to Calibration, Regression Curves, and Simulation-Based Inference)","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2307.15247","title":"Is this model reliable for everyone? Testing for strong calibration","created":"2023-07-28","cited_by_count":6,"area":null},{"id":"2402.10046","title":"How Flawed Is ECE? An Analysis via Logit Smoothing","created":"2024-02-15","cited_by_count":6,"area":null},{"id":"2506.11251","title":"Measuring multi-calibration","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2502.11465","title":"All Models Are Miscalibrated, But Some Less So: Comparing Calibration with Conditional Mean Operators","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2502.14545","title":"An Entropic Metric for Measuring Calibration of Machine Learning Models","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2510.14711","title":"Fast and Scalable Score-Based Kernel Calibration Tests","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2209.02064","title":"GRASP: A Goodness-of-Fit Test for Classification Learning","created":"2022-09-05","cited_by_count":1,"area":null},{"id":"2510.25458","title":"Scalable Utility-Aware Multiclass Calibration","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2512.13872","title":"Measuring Uncertainty Calibration","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2605.01796","title":"Beyond ECE: Calibrated Size Ratio, Risk Assessment, and Confidence-Weighted Metrics","created":"2026-05-03","cited_by_count":1,"area":null},{"id":"2505.19396","title":"Uniform convergence of the smooth calibration error and its relationship with functional gradient","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2605.07808","title":"The Minimax Rate of Perturbed Second-Order Calibration","created":"2026-05-08","cited_by_count":0,"area":null}],"next_cursor":null}