{"total":31,"rows":[{"id":"2410.15361","title":"A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample Estimators","created":"2024-10-20","cited_by_count":15,"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":"2607.14817","title":"Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2505.22843","title":"On the Reliability and Stability of Selective Methods in Malware Classification Tasks","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2509.01455","title":"Trusted Uncertainty in Large Language Models: A Unified Framework for Confidence Calibration and Risk-Controlled Refusal","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2601.22570","title":"Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2603.29941","title":"Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2605.18045","title":"Confidence-Gated Robot Autonomy: When Does Uncertainty Actually Help?","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.18911","title":"Does Your Wildfire Prediction Model Actually Work, or Just Score Well?","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2610.02293","title":"HakemBench: A Turkish Benchmark of Typed Decisions","created":"2026-10-01","cited_by_count":1,"area":null},{"id":"2510.17764","title":"Evaluating Medical LLMs by Levels of Autonomy: A Survey Moving from Benchmarks to Applications","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2510.24368","title":"Filtering instances and rejecting predictions to obtain reliable models in healthcare","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2511.11934","title":"A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2602.20947","title":"Estimation of Confidence Bounds in Binary Classification using Wilson Score Kernel Density Estimation","created":"2026-02-24","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":"2603.09947","title":"The Confidence Gate Theorem: When Should Ranked Decision Systems Abstain?","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.08454","title":"Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.01346","title":"CHASE: Competing Hypotheses for Ambiguity-Aware Selective Prediction","created":"2026-05-02","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":"2608.14639","title":"Valid Per-Field Selective Risk Control for Document Extraction: Three Failure Modes, a Validity Ladder, and When Conditioning Pays","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.14683","title":"One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.15951","title":"ReliaGate: Reliability Routing for Low-Stakes Wearable Stress Prediction","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.18836","title":"Verifiable abstention makes AI leak diagnosis accountable in urban water distribution networks","created":"2026-08-19","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},{"id":"2609.18622","title":"How Many Labels Does Model Choice Need? Certificates and Budgets for Selective Prediction","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.29836","title":"SplatLabel: Pseudo-Labelling through 4D Gaussian Splatting","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.30714","title":"CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.06744","title":"ufakzeka-karar: An Open Turkish Typed-Decision Model with Order-Invariant Option Scoring","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.07019","title":"Calibrated Evidence Inference With a Small, Permissively Licensed Open Model","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.17902","title":"Visual Dependence Does Not Imply Answerability: A Systematic Analysis of Answerability Signals in Frozen InstructBLIP","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19394","title":"Selective Next-Location Prediction with MetaModelSelect: A Lightweight Post-Hoc Confidence Metamodel","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}