{"total":16,"rows":[{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2408.04154","title":"The Data Addition Dilemma","created":"2024-08-08","cited_by_count":15,"area":null},{"id":"2406.17433","title":"Mind the Graph When Balancing Data for Fairness or Robustness","created":"2024-06-25","cited_by_count":9,"area":null},{"id":"2501.10727","title":"In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review","created":"2025-01-18","cited_by_count":8,"area":null},{"id":"2402.06353","title":"Copycats: the many lives of a publicly available medical imaging dataset","created":"2024-02-09","cited_by_count":6,"area":null},{"id":"2504.16277","title":"DataS^3: Dataset Subset Selection for Specialization","created":"2025-04-22","cited_by_count":6,"area":null},{"id":"2510.01232","title":"Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2406.16846","title":"Data Debiasing with Datamodels (D3M): Improving Subgroup Robustness via Data Selection","created":"2024-06-24","cited_by_count":5,"area":null},{"id":"2508.05435","title":"Competing Risks: Impact on Risk Estimation and Algorithmic Fairness","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2502.05765","title":"Privacy-Preserving Dataset Combination","created":"2025-02-09","cited_by_count":1,"area":null},{"id":"2505.11771","title":"Residual Feature Integration is Sufficient to Prevent Negative Transfer","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2603.15276","title":"Dataset Diversity Metrics and Impact on Classification Models","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2504.10080","title":"Learning to Harmonize Cross-vendor X-ray Images by Non-linear Image Dynamics Correction","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2605.11237","title":"DeconDTN-Toolkit: A Library for Evaluation and Enhancement of Robustness to Provenance Shift","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.00620","title":"Identifying Latent Concepts and Structures for Generalized Category Discovery","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.17382","title":"Team DACTYL at PAN 2026: Bayesian Data Mixing and Empirical X-risk Minimization for AI-text Detection","created":"2026-07-19","cited_by_count":0,"area":null}],"next_cursor":null}