{"total":40,"rows":[{"id":"2303.17093","title":"OpenMix: Exploring Outlier Samples for Misclassification Detection","created":"2023-03-30","cited_by_count":38,"area":null},{"id":"2407.01032","title":"Overcoming Common Flaws in the Evaluation of Selective Classification Systems","created":"2024-07-01","cited_by_count":37,"area":null},{"id":"2403.04272","title":"Active Generalized Category Discovery","created":"2024-03-07","cited_by_count":31,"area":null},{"id":"2305.15508","title":"How to Fix a Broken Confidence Estimator: Evaluating Post-hoc Methods for Selective Classification with Deep Neural Networks","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2306.01710","title":"A Data-Driven Measure of Relative Uncertainty for Misclassification Detection","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2308.03172","title":"Two Sides of Miscalibration: Identifying Over and Under-Confidence Prediction for Network Calibration","created":"2023-08-06","cited_by_count":14,"area":null},{"id":"2403.14715","title":"Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2507.08721","title":"Monitoring Risks in Test-Time Adaptation","created":"2025-07-11","cited_by_count":11,"area":null},{"id":"2403.02886","title":"Revisiting Confidence Estimation: Towards Reliable Failure Prediction","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2311.13355","title":"Unified Classification and Rejection: A One-versus-All Framework","created":"2023-11-22","cited_by_count":9,"area":null},{"id":"2403.00543","title":"SURE: SUrvey REcipes for building reliable and robust deep networks","created":"2024-03-01","cited_by_count":8,"area":null},{"id":"2407.14029","title":"PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning","created":"2024-07-19","cited_by_count":8,"area":null},{"id":"2502.05275","title":"Interpretable Failure Detection with Human-Level Concepts","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2408.00331","title":"DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation","created":"2024-08-01","cited_by_count":6,"area":null},{"id":"2411.01981","title":"Typicalness-Aware Learning for Failure Detection","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2305.05912","title":"A Hybrid of Generative and Discriminative Models Based on the Gaussian-coupled Softmax Layer","created":"2023-05-10","cited_by_count":4,"area":null},{"id":"2308.03179","title":"Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection","created":"2023-08-06","cited_by_count":4,"area":null},{"id":"2403.02998","title":"Towards Calibrated Deep Clustering Network","created":"2024-03-04","cited_by_count":4,"area":null},{"id":"2502.15798","title":"MaxSup: Overcoming Representation Collapse in Label Smoothing","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2404.16188","title":"Pearls from Pebbles: Improved Confidence Functions for Auto-labeling","created":"2024-04-24","cited_by_count":3,"area":null},{"id":"2406.10775","title":"A Rate-Distortion View of Uncertainty Quantification","created":"2024-06-16","cited_by_count":3,"area":null},{"id":"2506.17968","title":"h-calibration: Rethinking Classifier Recalibration with Probabilistic Error-Bounded Objective","created":"2025-06-22","cited_by_count":2,"area":null},{"id":"2510.20242","title":"What Does It Take to Build a Performant Selective Classifier?","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2310.06380","title":"CAST: Cluster-Aware Self-Training for Tabular Data via Reliable Confidence","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2404.14419","title":"Evaluation and Improvement of Fault Detection for Large Language Models","created":"2024-04-14","cited_by_count":1,"area":null},{"id":"2412.17411","title":"Pretraining with random noise for uncertainty calibration","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2512.12925","title":"Sharpness-aware Dynamic Anchor Selection for Generalized Category Discovery","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2602.12039","title":"The Implicit Bias of Logit Regularization","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2603.02200","title":"Adaptive Confidence Regularization for Multimodal Failure Detection","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2408.02906","title":"Dual-View Pyramid Pooling in Deep Neural Networks for Improved Medical Image Classification and Confidence Calibration","created":"2024-08-06","cited_by_count":0,"area":null},{"id":"2506.06048","title":"TRUST: Test-time Resource Utilization for Superior Trustworthiness","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2512.18406","title":"Automated Mosaic Tesserae Segmentation via Deep Learning Techniques","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2602.06638","title":"Temperature Scaling Attack Disrupting Model Confidence in Federated Learning","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.03903","title":"From Misclassifications to Outliers: Joint Reliability Assessment in Classification","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2605.18648","title":"An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.20490","title":"ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.01702","title":"KDH-CAD: Knowledge-data hybrid CAD learning under data scarcity","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2608.20326","title":"$TCP_\\alpha$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.28052","title":"Explainable Uncertainty Estimation for Reliable Medical AI","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.00366","title":"Counterfactual Fragility Certificates: Exposing High-Confidence Brittleness under Structured Evidence Failure","created":"2026-06-29","cited_by_count":0,"area":null}],"next_cursor":null}