{"total":20,"rows":[{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249,"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":"2302.14301","title":"A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking","created":"2023-02-28","cited_by_count":85,"area":null},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75,"area":null},{"id":"2205.04596","title":"When does dough become a bagel? Analyzing the remaining mistakes on ImageNet","created":"2022-05-09","cited_by_count":61,"area":null},{"id":"2410.13341","title":"Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data","created":"2024-10-17","cited_by_count":51,"area":null},{"id":"2209.00613","title":"ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets","created":"2022-09-01","cited_by_count":44,"area":null},{"id":"2205.14846","title":"Precise Learning Curves and Higher-Order Scaling Limits for Dot Product Kernel Regression","created":"2022-05-30","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":"2302.00704","title":"Pathologies of Predictive Diversity in Deep Ensembles","created":"2023-02-01","cited_by_count":16,"area":null},{"id":"2102.05242","title":"Patterns, predictions, and actions: A story about machine learning","created":"2021-02-10","cited_by_count":14,"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":"2307.10586","title":"A Holistic Assessment of the Reliability of Machine Learning Systems","created":"2023-07-20","cited_by_count":9,"area":null},{"id":"2302.10341","title":"DC4L: Distribution Shift Recovery via Data-Driven Control for Deep Learning Models","created":"2023-02-20","cited_by_count":7,"area":null},{"id":"2402.02249","title":"Don't Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget","created":"2024-02-03","cited_by_count":7,"area":null},{"id":"2401.02430","title":"Automated Classification of Model Errors on ImageNet","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2203.15100","title":"Understanding out-of-distribution accuracies through quantifying difficulty of test samples","created":"2022-03-28","cited_by_count":3,"area":null},{"id":"2210.11589","title":"Monotonic Risk Relationships under Distribution Shifts for Regularized Risk Minimization","created":"2022-10-20","cited_by_count":2,"area":null},{"id":"2606.07726","title":"Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model Similarity","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2503.11964","title":"Entropy-regularized Gradient Estimators for Approximate Bayesian Inference","created":"2025-03-15","cited_by_count":0,"area":null}],"next_cursor":null}