{"total":23,"rows":[{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203,"area":null},{"id":"2312.12112","title":"Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes","created":"2023-12-19","cited_by_count":52,"area":null},{"id":"2301.04819","title":"Data-centric AI: Perspectives and Challenges","created":"2023-01-12","cited_by_count":43,"area":null},{"id":"2310.16524","title":"Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data","created":"2023-10-25","cited_by_count":32,"area":null},{"id":"2211.14611","title":"The Principles of Data-Centric AI (DCAI)","created":"2022-11-26","cited_by_count":26,"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":"2312.05327","title":"Better, Not Just More: Data-Centric Machine Learning for Earth Observation","created":"2023-12-08","cited_by_count":19,"area":null},{"id":"2304.13174","title":"Dynamic Datasets and Market Environments for Financial Reinforcement Learning","created":"2023-04-25","cited_by_count":15,"area":null},{"id":"2309.10979","title":"Towards Data-centric Graph Machine Learning: Review and Outlook","created":"2023-09-20","cited_by_count":15,"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":"2205.06935","title":"DendroMap: Visual Exploration of Large-Scale Image Datasets for Machine Learning with Treemaps","created":"2022-05-14","cited_by_count":12,"area":null},{"id":"2301.01228","title":"DMOps: Data Management Operation and Recipes","created":"2023-01-02","cited_by_count":7,"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":"2204.01607","title":"Modern Views of Machine Learning for Precision Psychiatry","created":"2022-04-04","cited_by_count":5,"area":null},{"id":"2306.03481","title":"Transition Role of Entangled Data in Quantum Machine Learning","created":"2023-06-06","cited_by_count":5,"area":null},{"id":"2306.04349","title":"GPT Self-Supervision for a Better Data Annotator","created":"2023-06-07","cited_by_count":5,"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":"2505.06621","title":"Minimizing Risk Through Minimizing Model-Data Interaction: A Protocol For Relying on Proxy Tasks When Designing Child Sexual Abuse Imagery Detection Models","created":"2025-05-10","cited_by_count":4,"area":null},{"id":"2302.04418","title":"Learning to Select Pivotal Samples for Meta Re-weighting","created":"2023-02-09","cited_by_count":3,"area":null},{"id":"2407.19784","title":"Survey and Taxonomy: The Role of Data-Centric AI in Transformer-Based Time Series Forecasting","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2310.19503","title":"Trust, Accountability, and Autonomy in Knowledge Graph-based AI for Self-determination","created":"2023-10-30","cited_by_count":2,"area":null},{"id":"2306.14377","title":"Synthetic Alone: Exploring the Dark Side of Synthetic Data for Grammatical Error Correction","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2309.11608","title":"Dataset Factory: A Toolchain For Generative Computer Vision Datasets","created":"2023-09-20","cited_by_count":0,"area":null}],"next_cursor":null}