{"total":31,"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":"2502.19851","title":"Can a calibration metric be both testable and actionable?","created":"2025-02-27","cited_by_count":12,"area":null},{"id":"2301.10803","title":"Evaluating Probabilistic Classifiers: The Triptych","created":"2023-01-25","cited_by_count":8,"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":"2412.12767","title":"A Survey of Calibration Process for Black-Box LLMs","created":"2024-12-17","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":"2402.10046","title":"How Flawed Is ECE? An Analysis via Logit Smoothing","created":"2024-02-15","cited_by_count":6,"area":null},{"id":"2306.14343","title":"TCE: A Test-Based Approach to Measuring Calibration Error","created":"2023-06-25","cited_by_count":5,"area":null},{"id":"2509.19884","title":"MCGrad: Multicalibration at Web Scale","created":"2025-09-24","cited_by_count":5,"area":null},{"id":"2506.11251","title":"Measuring multi-calibration","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2411.04276","title":"Labels in Extremes: How Well Calibrated are Extreme Multi-label Classifiers?","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2510.26566","title":"Multiclass Local Calibration with the Jensen-Shannon Distance","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2605.16405","title":"Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2605.17749","title":"Testable and Actionable Calibration for Full Swap Regret","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.30188","title":"CalArena: A Large-Scale Post-Hoc Calibration Benchmark","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2607.14407","title":"Decision Making Needs Uncertainty Quantification [Lecture Notes]","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2302.01574","title":"An Operational Perspective to Fairness Interventions: Where and How to Intervene","created":"2023-02-03","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":"2605.21060","title":"Divide et Calibra: Multiclass Local Calibration via Vector Quantization","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2311.06292","title":"Towards a data-driven debt collection strategy based on an advanced machine learning framework","created":"2023-11-03","cited_by_count":0,"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":"2511.02738","title":"Calibration improves detection of mislabeled examples","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2512.08953","title":"SimClinician: A Multimodal Simulation Testbed for Reliable Psychologist AI Collaboration in Mental Health Diagnosis","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2604.08639","title":"VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.21549","title":"Multicalibration for Unbiased Model-Based Prevalence Estimation","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2606.27001","title":"Uncertainty quantification via conformal prediction in data assimilation","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2606.29925","title":"Bandwidth Selection in Kernel Density Estimation for Model Calibration","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2609.23731","title":"Marginal Calibration Does Not Compose: Hidden Dependence in Modular Robot Navigation","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2610.18108","title":"A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judge","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}