{"total":15,"rows":[{"id":"2310.16981","title":"Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark","created":"2023-10-25","cited_by_count":23,"area":null},{"id":"2210.13043","title":"Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data","created":"2022-10-24","cited_by_count":22,"area":null},{"id":"2404.05779","title":"Data Readiness for AI: A 360-Degree Survey","created":"2024-04-08","cited_by_count":15,"area":null},{"id":"2403.04551","title":"Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI","created":"2024-03-07","cited_by_count":11,"area":null},{"id":"2406.19256","title":"AI Data Readiness Inspector (AIDRIN) for Quantitative Assessment of Data Readiness for AI","created":"2024-06-27","cited_by_count":9,"area":null},{"id":"2310.18970","title":"TRIAGE: Characterizing and auditing training data for improved regression","created":"2023-10-29","cited_by_count":6,"area":null},{"id":"2203.10384","title":"Data Smells: Categories, Causes and Consequences, and Detection of Suspicious Data in AI-based Systems","created":"2022-03-19","cited_by_count":4,"area":null},{"id":"2304.07296","title":"MLOps Spanning Whole Machine Learning Life Cycle: A Survey","created":"2023-04-13","cited_by_count":3,"area":null},{"id":"2406.13733","title":"You can't handle the (dirty) truth: Data-centric insights improve pseudo-labeling","created":"2024-06-19","cited_by_count":3,"area":null},{"id":"2403.01832","title":"Model-Based Data-Centric AI: Bridging the Divide Between Academic Ideals and Industrial Pragmatism","created":"2024-03-04","cited_by_count":1,"area":null},{"id":"2502.17060","title":"Analytics Modelling over Multiple Datasets using Vector Embeddings","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2411.03007","title":"Data Quality Awareness: A Journey from Traditional Data Management to Data Science Systems","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2502.08669","title":"Assessing the Impact of the Quality of Textual Data on Feature Representation and Machine Learning Models","created":"2025-02-12","cited_by_count":0,"area":null},{"id":"2505.23849","title":"CADRE: Customizable Assurance of Data Readiness in Privacy-Preserving Federated Learning","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2507.11960","title":"d-DQIVAR: Data-centric Visual Analytics and Reasoning for Data Quality Improvement","created":"2025-07-16","cited_by_count":0,"area":null}],"next_cursor":null}