{"total":23,"rows":[{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2106.04531","title":"RobustNav: Towards Benchmarking Robustness in Embodied Navigation","created":"2021-06-08","cited_by_count":54,"area":null},{"id":"2312.02974","title":"Describing Differences in Image Sets with Natural Language","created":"2023-12-05","cited_by_count":53,"area":null},{"id":"2403.08632","title":"A Decade's Battle on Dataset Bias: Are We There Yet?","created":"2024-03-13","cited_by_count":47,"area":null},{"id":"2302.07865","title":"Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation","created":"2023-02-15","cited_by_count":35,"area":null},{"id":"2106.03805","title":"3DB: A Framework for Debugging Computer Vision Models","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2106.07393","title":"Cross-replication Reliability -- An Empirical Approach to Interpreting Inter-rater Reliability","created":"2021-06-11","cited_by_count":31,"area":null},{"id":"2202.12690","title":"On Modality Bias Recognition and Reduction","created":"2022-02-25","cited_by_count":20,"area":null},{"id":"2105.12437","title":"The statistical advantage of automatic NLG metrics at the system level","created":"2021-05-26","cited_by_count":18,"area":null},{"id":"2109.11126","title":"A Framework for Cluster and Classifier Evaluation in the Absence of Reference Labels","created":"2021-09-23","cited_by_count":16,"area":null},{"id":"2306.15769","title":"What Makes ImageNet Look Unlike LAION","created":"2023-06-27","cited_by_count":9,"area":null},{"id":"2204.04372","title":"A Siren Song of Open Source Reproducibility","created":"2022-04-09","cited_by_count":8,"area":null},{"id":"2107.12052","title":"Using Synthetic Corruptions to Measure Robustness to Natural Distribution Shifts","created":"2021-07-26","cited_by_count":7,"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":"2202.04136","title":"Generative multitask learning mitigates target-causing confounding","created":"2022-02-08","cited_by_count":4,"area":null},{"id":"2305.15889","title":"Quantitatively Measuring and Contrastively Exploring Heterogeneity for Domain Generalization","created":"2023-05-25","cited_by_count":4,"area":null},{"id":"2401.17736","title":"Leveraging Human-Machine Interactions for Computer Vision Dataset Quality Enhancement","created":"2024-01-31","cited_by_count":2,"area":null},{"id":"2102.06162","title":"Defuse: Harnessing Unrestricted Adversarial Examples for Debugging Models Beyond Test Accuracy","created":"2021-02-11","cited_by_count":1,"area":null},{"id":"2209.01848","title":"A Principled Evaluation Protocol for Comparative Investigation of the Effectiveness of DNN Classification Models on Similar-but-non-identical Datasets","created":"2022-09-05","cited_by_count":1,"area":null},{"id":"2303.10888","title":"Self-Improving-Leaderboard(SIL): A Call for Real-World Centric Natural Language Processing Leaderboards","created":"2023-03-20","cited_by_count":1,"area":null},{"id":"2410.12814","title":"Leveraging generative models to characterize the failure conditions of image classifiers","created":"2024-10-01","cited_by_count":1,"area":null},{"id":"2412.18409","title":"The Impact of the Single-Label Assumption in Image Recognition Benchmarking","created":"2024-12-24","cited_by_count":1,"area":null},{"id":"2301.12527","title":"Diverse, Difficult, and Odd Instances (D2O): A New Test Set for Object Classification","created":"2023-01-29","cited_by_count":0,"area":null}],"next_cursor":null}