{"total":113,"rows":[{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172,"area":null},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145,"area":null},{"id":"2206.13089","title":"Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift","created":"2022-06-27","cited_by_count":94,"area":null},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89,"area":null},{"id":"2402.01444","title":"Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning","created":"2024-02-02","cited_by_count":77,"area":null},{"id":"2112.10327","title":"Classifier Calibration: A survey on how to assess and improve predicted class probabilities","created":"2021-12-20","cited_by_count":73,"area":null},{"id":"2202.05834","title":"Predicting Out-of-Distribution Error with the Projection Norm","created":"2022-02-11","cited_by_count":50,"area":null},{"id":"2303.17132","title":"C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation","created":"2023-03-30","cited_by_count":50,"area":null},{"id":"2206.02757","title":"Robust Calibration with Multi-domain Temperature Scaling","created":"2022-06-06","cited_by_count":39,"area":null},{"id":"2310.16524","title":"Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data","created":"2023-10-25","cited_by_count":32,"area":null},{"id":"2302.03020","title":"RLSbench: Domain Adaptation Under Relaxed Label Shift","created":"2023-02-06","cited_by_count":30,"area":null},{"id":"2405.05012","title":"The Entropy Enigma: Success and Failure of Entropy Minimization","created":"2024-05-08","cited_by_count":24,"area":null},{"id":"2207.07065","title":"On the Strong Correlation Between Model Invariance and Generalization","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2302.01094","title":"Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation","created":"2023-02-02","cited_by_count":22,"area":null},{"id":"2403.01874","title":"A Survey on Evaluation of Out-of-Distribution Generalization","created":"2024-03-04","cited_by_count":21,"area":null},{"id":"2305.15640","title":"Characterizing Out-of-Distribution Error via Optimal Transport","created":"2023-05-25","cited_by_count":20,"area":null},{"id":"2202.09931","title":"Deconstructing Distributions: A Pointwise Framework of Learning","created":"2022-02-20","cited_by_count":19,"area":null},{"id":"2209.08436","title":"Estimating and Explaining Model Performance When Both Covariates and Labels Shift","created":"2022-09-18","cited_by_count":19,"area":null},{"id":"2310.14586","title":"GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels","created":"2023-10-23","cited_by_count":17,"area":null},{"id":"2408.03573","title":"AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling","created":"2024-08-07","cited_by_count":17,"area":null},{"id":"2306.00312","title":"(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy","created":"2023-06-01","cited_by_count":16,"area":null},{"id":"2303.15488","title":"On the Importance of Feature Separability in Predicting Out-Of-Distribution Error","created":"2023-03-27","cited_by_count":15,"area":null},{"id":"2406.07320","title":"A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimation","created":"2024-06-11","cited_by_count":14,"area":null},{"id":"2302.05018","title":"Predicting Out-of-Distribution Error with Confidence Optimal Transport","created":"2023-02-10","cited_by_count":13,"area":null},{"id":"2301.13371","title":"Demystifying Disagreement-on-the-Line in High Dimensions","created":"2023-01-31","cited_by_count":12,"area":null},{"id":"2310.04414","title":"CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis","created":"2023-10-06","cited_by_count":12,"area":null},{"id":"2403.09953","title":"Online GNN Evaluation Under Test-time Graph Distribution Shifts","created":"2024-03-15","cited_by_count":12,"area":null},{"id":"2205.13577","title":"Understanding new tasks through the lens of training data via exponential tilting","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2303.13251","title":"A Bag-of-Prototypes Representation for Dataset-Level Applications","created":"2023-03-23","cited_by_count":11,"area":null},{"id":"2310.04941","title":"Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line","created":"2023-10-07","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":"2112.00694","title":"Label-Free Model Evaluation with Semi-Structured Dataset Representations","created":"2021-12-01","cited_by_count":10,"area":null},{"id":"2207.09957","title":"Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scores","created":"2022-07-20","cited_by_count":10,"area":null},{"id":"2412.12910","title":"Sequential Harmful Shift Detection Without Labels","created":"2024-12-17","cited_by_count":10,"area":null},{"id":"2305.14802","title":"Estimating Large Language Model Capabilities without Labeled Test Data","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2307.10586","title":"A Holistic Assessment of the Reliability of Machine Learning Systems","created":"2023-07-20","cited_by_count":9,"area":null},{"id":"2401.08348","title":"Estimating Model Performance Under Covariate Shift Without Labels","created":"2024-01-16","cited_by_count":9,"area":null},{"id":"2404.01351","title":"AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation","created":"2024-04-01","cited_by_count":9,"area":null},{"id":"2401.03350","title":"Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks","created":"2024-01-07","cited_by_count":8,"area":null},{"id":"2405.18979","title":"MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2407.08649","title":"Confidence-based Estimators for Predictive Performance in Model Monitoring","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2505.14903","title":"When to retrain a machine learning model","created":"2025-05-20","cited_by_count":8,"area":null},{"id":"2507.19703","title":"The wall confronting large language models","created":"2025-07-25","cited_by_count":8,"area":null},{"id":"2309.09403","title":"Selecting which Dense Retriever to use for Zero-Shot Search","created":"2023-09-18","cited_by_count":7,"area":null},{"id":"2404.01542","title":"Predicting the Performance of Foundation Models via Agreement-on-the-Line","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2209.08443","title":"HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2209.14969","title":"Transfer Learning with Pretrained Remote Sensing Transformers","created":"2022-09-28","cited_by_count":6,"area":null},{"id":"2308.11111","title":"CAME: Contrastive Automated Model Evaluation","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2310.13040","title":"Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2403.13803","title":"Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2406.09908","title":"What Does Softmax Probability Tell Us about Classifiers Ranking Across Diverse Test Conditions?","created":"2024-06-14","cited_by_count":6,"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":"2207.02093","title":"Predicting Out-of-Domain Generalization with Neighborhood Invariance","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2302.08287","title":"Unsupervised Evaluation of Out-of-distribution Detection: A Data-centric Perspective","created":"2023-02-16","cited_by_count":4,"area":null},{"id":"2304.09758","title":"K-means Clustering Based Feature Consistency Alignment for Label-free Model Evaluation","created":"2023-04-17","cited_by_count":4,"area":null},{"id":"2408.13648","title":"Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance","created":"2024-08-24","cited_by_count":4,"area":null},{"id":"2412.17284","title":"Towards Unsupervised Model Selection for Domain Adaptive Object Detection","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2501.11866","title":"Evaluating multiple models using labeled and unlabeled data","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2505.22356","title":"Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2206.10697","title":"Performance Prediction Under Dataset Shift","created":"2022-06-21","cited_by_count":3,"area":null},{"id":"2210.04166","title":"Test-time Recalibration of Conformal Predictors Under Distribution Shift Based on Unlabeled Examples","created":"2022-10-09","cited_by_count":3,"area":null},{"id":"2302.00775","title":"Model Monitoring and Robustness of In-Use Machine Learning Models: Quantifying Data Distribution Shifts Using Population Stability Index","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2307.10062","title":"Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples","created":"2023-07-19","cited_by_count":3,"area":null},{"id":"2401.08909","title":"Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift","created":"2024-01-17","cited_by_count":3,"area":null},{"id":"2404.19452","title":"How to Sustainably Monitor ML-Enabled Systems? Accuracy and Energy Efficiency Tradeoffs in Concept Drift Detection","created":"2024-04-30","cited_by_count":3,"area":null},{"id":"2405.09934","title":"Detecting Domain Shift in Multiple Instance Learning for Digital Pathology Using Fr\\'echet Domain Distance","created":"2024-05-16","cited_by_count":3,"area":null},{"id":"2410.02384","title":"Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors","created":"2024-10-03","cited_by_count":3,"area":null},{"id":"2207.05796","title":"Estimating Test Performance for AI Medical Devices under Distribution Shift with Conformal Prediction","created":"2022-07-12","cited_by_count":2,"area":null},{"id":"2210.10897","title":"Window-Based Distribution Shift Detection for Deep Neural Networks","created":"2022-10-19","cited_by_count":2,"area":null},{"id":"2302.05137","title":"Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement","created":"2023-02-10","cited_by_count":2,"area":null},{"id":"2308.07223","title":"Distance Matters For Improving Performance Estimation Under Covariate Shift","created":"2023-08-14","cited_by_count":2,"area":null},{"id":"2404.04969","title":"Temporal Generalization Estimation in Evolving Graphs","created":"2024-04-07","cited_by_count":2,"area":null},{"id":"2505.05295","title":"Performance Estimation in Binary Classification Using Calibrated Confidence","created":"2025-05-08","cited_by_count":2,"area":null},{"id":"2505.11380","title":"On the Interconnections of Calibration, Quantification, and Classifier Accuracy Prediction under Dataset Shift","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2507.12894","title":"LanePerf: a Performance Estimation Framework for Lane Detection","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2603.01879","title":"Diagnosing Generalization Failures from Representational Geometry Markers","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.07841","title":"An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2207.04075","title":"Models Out of Line: A Fourier Lens on Distribution Shift Robustness","created":"2022-07-08","cited_by_count":1,"area":null},{"id":"2303.05331","title":"Adaptive Calibrator Ensemble for Model Calibration under Distribution Shift","created":"2023-03-09","cited_by_count":1,"area":null},{"id":"2310.10490","title":"On the Transferability of Learning Models for Semantic Segmentation for Remote Sensing Data","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2311.09422","title":"Predicting generalization performance with correctness discriminators","created":"2023-11-15","cited_by_count":1,"area":null},{"id":"2407.03549","title":"POSTURE: Pose Guided Unsupervised Domain Adaptation for Human Body Part Segmentation","created":"2024-07-04","cited_by_count":1,"area":null},{"id":"2408.02209","title":"Source-Free Domain-Invariant Performance Prediction","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2503.18195","title":"Shapley-Guided Utility Learning for Effective Graph Inference Data Valuation","created":"2025-03-23","cited_by_count":1,"area":null},{"id":"2505.07023","title":"Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2506.14978","title":"ODD: Overlap-aware Estimation of Model Performance under Distribution Shift","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2510.02956","title":"Confidence and Dispersity as Signals: Unsupervised Model Evaluation and Ranking","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2510.27263","title":"ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2512.20070","title":"Progressive Learned Image Compression for Machine Perception","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2605.08870","title":"TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selection","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.23595","title":"Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.06335","title":"Bridging Domain Expertise and Generalization for Performance Estimation","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2303.13589","title":"On the Efficacy of Generalization Error Prediction Scoring Functions","created":"2023-03-23","cited_by_count":0,"area":null},{"id":"2304.08855","title":"A Domain-Region Based Evaluation of ML Performance Robustness to Covariate Shift","created":"2023-04-18","cited_by_count":0,"area":null},{"id":"2306.10160","title":"On Orderings of Probability Vectors and Unsupervised Performance Estimation","created":"2023-06-16","cited_by_count":0,"area":null},{"id":"2309.10976","title":"Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2309.10977","title":"PAGER: A Framework for Failure Analysis of Deep Regression Models","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2402.01095","title":"Minimal Sufficient Views: A DNN model making predictions with more evidence has higher accuracy","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2406.09257","title":"Assessing Model Generalization in Vicinity","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2409.04241","title":"Calibration of Network Confidence for Unsupervised Domain Adaptation Using Estimated Accuracy","created":"2024-09-06","cited_by_count":0,"area":null}],"next_cursor":"100"}