{"total":13,"rows":[{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2405.01719","title":"Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks","created":"2024-05-02","cited_by_count":28,"area":null},{"id":"2102.13189","title":"Rip van Winkle's Razor: A Simple Estimate of Overfit to Test Data","created":"2021-02-25","cited_by_count":8,"area":null},{"id":"2307.08364","title":"Q(D)O-ES: Population-based Quality (Diversity) Optimisation for Post Hoc Ensemble Selection in AutoML","created":"2023-07-17","cited_by_count":8,"area":null},{"id":"2405.15393","title":"Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2506.19540","title":"Overtuning in Hyperparameter Optimization","created":"2025-06-24","cited_by_count":5,"area":null},{"id":"2303.07272","title":"Inventing a coin-flip classifier: Accounting for multiplicity in machine learning benchmark performance","created":"2023-03-10","cited_by_count":2,"area":null},{"id":"2312.03577","title":"Improving Bias Mitigation through Bias Experts in Natural Language Understanding","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2512.21080","title":"LLM Personas as a Substitute for Field Experiments in Method Benchmarking","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2204.12651","title":"Generating Self-Serendipity Preference in Recommender Systems for Addressing Cold Start Problems","created":"2022-04-27","cited_by_count":0,"area":null},{"id":"2310.09986","title":"On Statistical Learning of Branch and Bound for Vehicle Routing Optimization","created":"2023-10-15","cited_by_count":0,"area":null},{"id":"2311.14079","title":"Empirical Comparison between Cross-Validation and Mutation-Validation in Model Selection","created":"2023-11-23","cited_by_count":0,"area":null},{"id":"2609.32109","title":"How Reusable Are Benchmarks with Richer Feedback?","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}