{"list":"other","total":79,"rows":[{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"1407.7722","title":"OpenML: networked science in machine learning","created":"2014-07-29","cited_by_count":526},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"1810.07758","title":"The UCR Time Series Archive","created":"2018-10-17","cited_by_count":431},{"id":"2103.14749","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","created":"2021-03-26","cited_by_count":395},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2003.12206","title":"Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)","created":"2020-03-27","cited_by_count":322},{"id":"2012.05345","title":"Data and its (dis)contents: A survey of dataset development and use in machine learning research","created":"2020-12-09","cited_by_count":260},{"id":"2006.16923","title":"Large image datasets: A pyrrhic win for computer vision?","created":"2020-06-24","cited_by_count":237},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"2103.03098","title":"Accounting for Variance in Machine Learning Benchmarks","created":"2021-03-01","cited_by_count":201},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182},{"id":"1708.03731","title":"OpenML Benchmarking Suites","created":"2017-08-11","cited_by_count":178},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172},{"id":"2204.01075","title":"Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI","created":"2022-04-03","cited_by_count":171},{"id":"1912.07726","title":"Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy","created":"2019-12-16","cited_by_count":156},{"id":"1506.04878","title":"End-to-end people detection in crowded scenes","created":"2015-06-16","cited_by_count":140},{"id":"1703.00512","title":"PMLB: A Large Benchmark Suite for Machine Learning Evaluation and Comparison","created":"2017-03-01","cited_by_count":140},{"id":"2010.13561","title":"Towards Accountability for Machine Learning Datasets: Practices from Software Engineering and Infrastructure","created":"2020-10-23","cited_by_count":138},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136},{"id":"2111.08006","title":"Disparities in Dermatology AI: Assessments Using Diverse Clinical Images","created":"2021-11-15","cited_by_count":134},{"id":"1912.10389","title":"Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learning","created":"2019-12-22","cited_by_count":116},{"id":"1807.03341","title":"Troubling Trends in Machine Learning Scholarship","created":"2018-07-09","cited_by_count":108},{"id":"1411.2664","title":"Preserving Statistical Validity in Adaptive Data Analysis","created":"2014-11-10","cited_by_count":103},{"id":"2112.01716","title":"Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research","created":"2021-12-03","cited_by_count":102},{"id":"2005.11295","title":"From ImageNet to Image Classification: Contextualizing Progress on Benchmarks","created":"2020-05-22","cited_by_count":90},{"id":"2108.04308","title":"Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development","created":"2021-08-09","cited_by_count":85},{"id":"2403.19546","title":"Croissant: A Metadata Format for ML-Ready Datasets","created":"2024-03-28","cited_by_count":81},{"id":"1911.01914","title":"A Comparative Analysis of XGBoost","created":"2019-11-05","cited_by_count":80},{"id":"1901.10436","title":"Diversity in Faces","created":"2019-01-29","cited_by_count":77},{"id":"1909.06674","title":"A Step Toward Quantifying Independently Reproducible Machine Learning Research","created":"2019-09-14","cited_by_count":77},{"id":"2005.09241","title":"On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law","created":"2020-05-19","cited_by_count":74},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":73},{"id":"1502.04585","title":"The Ladder: A Reliable Leaderboard for Machine Learning Competitions","created":"2015-02-16","cited_by_count":69},{"id":"1905.10498","title":"Cold Case: The Lost MNIST Digits","created":"2019-05-25","cited_by_count":62},{"id":"2110.12773","title":"Scientific Machine Learning Benchmarks","created":"2021-10-25","cited_by_count":60},{"id":"2108.02922","title":"Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers","created":"2021-08-06","cited_by_count":49},{"id":"2007.04792","title":"Targeting the Benchmark: On Methodology in Current Natural Language Processing Research","created":"2020-07-07","cited_by_count":45},{"id":"2007.07399","title":"Bringing the People Back In: Contesting Benchmark Machine Learning Datasets","created":"2020-07-14","cited_by_count":43},{"id":"2204.10149","title":"WebFace260M: A Benchmark for Million-Scale Deep Face Recognition","created":"2022-04-21","cited_by_count":42},{"id":"2002.08512","title":"The Problem with Metrics is a Fundamental Problem for AI","created":"2020-02-20","cited_by_count":37},{"id":"1709.09500","title":"Replicability Analysis for Natural Language Processing: Testing Significance with Multiple Datasets","created":"2017-09-27","cited_by_count":32},{"id":"2204.07610","title":"Sources of Irreproducibility in Machine Learning: A Review","created":"2022-04-15","cited_by_count":32},{"id":"2206.02923","title":"Understanding Machine Learning Practitioners' Data Documentation Perceptions, Needs, Challenges, and Desiderata","created":"2022-06-06","cited_by_count":28},{"id":"2102.00813","title":"About Face: A Survey of Facial Recognition Evaluation","created":"2021-02-01","cited_by_count":27},{"id":"2401.13822","title":"Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on Hugging Face","created":"2024-01-24","cited_by_count":27},{"id":"2201.03954","title":"The Dataset Nutrition Label (2nd Gen): Leveraging Context to Mitigate Harms in Artificial Intelligence","created":"2022-01-10","cited_by_count":26},{"id":"1912.01172","title":"Value-laden Disciplinary Shifts in Machine Learning","created":"2019-12-03","cited_by_count":25},{"id":"1903.12262","title":"Towards Standardization of Data Licenses: The Montreal Data License","created":"2019-03-21","cited_by_count":19},{"id":"2111.04424","title":"A Framework for Deprecating Datasets: Standardizing Documentation, Identification, and Communication","created":"2021-10-18","cited_by_count":18},{"id":"2405.02703","title":"Machine Learning Data Practices through a Data Curation Lens: An Evaluation Framework","created":"2024-05-04","cited_by_count":18},{"id":"2011.02832","title":"Pitfalls in Machine Learning Research: Reexamining the Development Cycle","created":"2020-11-04","cited_by_count":17},{"id":"2011.10098","title":"The Fundamental Principles of Reproducibility","created":"2020-11-19","cited_by_count":17},{"id":"2302.03629","title":"Ethical Considerations for Responsible Data Curation","created":"2023-02-07","cited_by_count":17},{"id":"2103.09058","title":"Understanding the Representation and Representativeness of Age in AI Data Sets","created":"2021-03-10","cited_by_count":15},{"id":"1911.01875","title":"Metrology for AI: From Benchmarks to Instruments","created":"2019-11-05","cited_by_count":12},{"id":"2102.12887","title":"Significant Improvements over the State of the Art? A Case Study of the MS MARCO Document Ranking Leaderboard","created":"2021-02-25","cited_by_count":12},{"id":"2207.02848","title":"A domain-specific language for describing machine learning datasets","created":"2022-07-05","cited_by_count":12},{"id":"2311.13028","title":"DMLR: Data-centric Machine Learning Research -- Past, Present and Future","created":"2023-11-21","cited_by_count":11},{"id":"2006.08589","title":"The role of metadata in reproducible computational research","created":"2020-06-15","cited_by_count":10},{"id":"2111.02374","title":"Can I use this publicly available dataset to build commercial AI software? -- A Case Study on Publicly Available Image Datasets","created":"2021-11-03","cited_by_count":6},{"id":"1706.07976","title":"Theory and Practice of Data Citation","created":"2017-06-24","cited_by_count":5},{"id":"2211.15937","title":"Robustness Disparities in Face Detection","created":"2022-11-29","cited_by_count":5},{"id":"2006.11105","title":"Classifier uncertainty: evidence, potential impact, and probabilistic treatment","created":"2020-06-19","cited_by_count":4},{"id":"1401.2134","title":"10 Simple Rules for the Care and Feeding of Scientific Data","created":"2014-01-09","cited_by_count":3},{"id":"1612.07140","title":"A Guide to Teaching Data Science","created":"2016-12-21","cited_by_count":2},{"id":"2109.01694","title":"Why it takes a village to manage and share data","created":"2021-09-03","cited_by_count":2},{"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}],"next_cursor":null}