{"total":22,"rows":[{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203,"area":null},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2101.03970","title":"How Much Automation Does a Data Scientist Want?","created":"2021-01-07","cited_by_count":20,"area":null},{"id":"2312.15561","title":"README: Bridging Medical Jargon and Lay Understanding for Patient Education through Data-Centric NLP","created":"2023-12-24","cited_by_count":17,"area":null},{"id":"2211.05764","title":"DC-Check: A Data-Centric AI checklist to guide the development of reliable machine learning systems","created":"2022-11-09","cited_by_count":14,"area":null},{"id":"2403.11395","title":"Automated data processing and feature engineering for deep learning and big data applications: a survey","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2411.02454","title":"Graph-based Confidence Calibration for Large Language Models","created":"2024-11-03","cited_by_count":10,"area":null},{"id":"2308.10915","title":"DiffPrep: Differentiable Data Preprocessing Pipeline Search for Learning over Tabular Data","created":"2023-08-20","cited_by_count":9,"area":null},{"id":"2310.01765","title":"Data Cleaning and Machine Learning: A Systematic Literature Review","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2106.05484","title":"A Unified Framework for Task-Driven Data Quality Management","created":"2021-06-10","cited_by_count":7,"area":null},{"id":"2304.11749","title":"Missing Values and Imputation in Healthcare Data: Can Interpretable Machine Learning Help?","created":"2023-04-23","cited_by_count":6,"area":null},{"id":"2310.02540","title":"Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data","created":"2023-10-04","cited_by_count":5,"area":null},{"id":"2401.08513","title":"X Hacking: The Threat of Misguided AutoML","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2206.05625","title":"Exploring the Intersection between Neural Architecture Search and Continual Learning","created":"2022-06-11","cited_by_count":4,"area":null},{"id":"2508.01556","title":"Empowering Tabular Data Preparation with Language Models: Why and How?","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2312.04546","title":"Adversarial Learning for Feature Shift Detection and Correction","created":"2023-12-07","cited_by_count":2,"area":null},{"id":"2501.07487","title":"Data and System Perspectives of Sustainable Artificial Intelligence","created":"2025-01-13","cited_by_count":2,"area":null},{"id":"2108.12193","title":"Man versus Machine: AutoML and Human Experts' Role in Phishing Detection","created":"2021-08-27","cited_by_count":0,"area":null},{"id":"2111.01868","title":"From Strings to Data Science: a Practical Framework for Automated String Handling","created":"2021-11-02","cited_by_count":0,"area":null},{"id":"2205.08018","title":"A Survey on Semantics in Automated Data Science","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2311.16185","title":"Enhancing Sentiment Analysis Results through Outlier Detection Optimization","created":"2023-11-25","cited_by_count":0,"area":null},{"id":"2506.09101","title":"Feature Shift Localization Network","created":"2025-06-10","cited_by_count":0,"area":null}],"next_cursor":null}