{"total":49,"rows":[{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172,"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":"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":"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":"2212.02742","title":"A Learning Based Hypothesis Test for Harmful Covariate Shift","created":"2022-12-06","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":"2401.12689","title":"Energy-based Automated Model Evaluation","created":"2024-01-23","cited_by_count":17,"area":null},{"id":"2210.00706","title":"Information-Theoretic Analysis of Unsupervised Domain Adaptation","created":"2022-10-03","cited_by_count":15,"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":"2303.03300","title":"Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach","created":"2023-03-06","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":"2305.14802","title":"Estimating Large Language Model Capabilities without Labeled Test Data","created":"2023-05-24","cited_by_count":9,"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":"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":"2407.04949","title":"Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients","created":"2024-07-06","cited_by_count":7,"area":null},{"id":"2308.11111","title":"CAME: Contrastive Automated Model Evaluation","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2404.05219","title":"Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Survey","created":"2024-04-08","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":"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":"2412.17284","title":"Towards Unsupervised Model Selection for Domain Adaptive Object Detection","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2501.19032","title":"Error Slice Discovery via Manifold Compactness","created":"2025-01-31","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":"2401.08909","title":"Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift","created":"2024-01-17","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":"2504.20121","title":"Benchmarking Transferability: A Framework for Fair and Robust Evaluation","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2311.09422","title":"Predicting generalization performance with correctness discriminators","created":"2023-11-15","cited_by_count":1,"area":null},{"id":"2403.01582","title":"Selection, Ensemble, and Adaptation: Advancing Multi-Source-Free Domain Adaptation via Architecture Zoo","created":"2024-03-03","cited_by_count":1,"area":null},{"id":"2407.14306","title":"Label-Free Model Failure Detection for Lidar-based Point Cloud Segmentation","created":"2024-07-19","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":"2408.13738","title":"Poor-Supervised Evaluation for SuperLLM via Mutual Consistency","created":"2024-08-25","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":"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":"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":"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},{"id":"2508.19613","title":"ALSA: Anchors in Logit Space for Out-of-Distribution Accuracy Estimation","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2511.00964","title":"Using Synthetic Data to estimate the True Error is theoretically and practically doable","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2607.03522","title":"Co-Adaptive Multi-Task LoRA: Transfer-Aware, Label-Free Control of Domain Participation","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2609.31996","title":"Can Circuit Alignment Predict OOD Generalization?","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32672","title":"STAMP: Predicting Out-of-Distribution Generalization without Target Data","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}