{"total":28,"rows":[{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203,"area":null},{"id":"2301.04819","title":"Data-centric AI: Perspectives and Challenges","created":"2023-01-12","cited_by_count":43,"area":null},{"id":"2310.04987","title":"Data-centric Graph Learning: A Survey","created":"2023-10-08","cited_by_count":22,"area":null},{"id":"2511.10192","title":"Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL","created":"2025-11-13","cited_by_count":11,"area":null},{"id":"2406.10261","title":"FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination","created":"2024-06-11","cited_by_count":10,"area":null},{"id":"2407.11784","title":"Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2412.09712","title":"Investigating the Impact of Balancing, Filtering, and Complexity on Predictive Multiplicity: A Data-Centric Perspective","created":"2024-12-12","cited_by_count":7,"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":"2501.02004","title":"General Information Metrics for Improving AI Model Training Efficiency","created":"2025-01-02","cited_by_count":4,"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":"2512.01045","title":"Med-CRAFT: An Information System for Explainable and Configurable Construction of Multimodal Medical QA Datasets","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2607.20532","title":"Position: Stop Reactively Patching Your Model Every Time and Start Proactive Test-Driven AI Development","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2307.11170","title":"UMLS-KGI-BERT: Data-Centric Knowledge Integration in Transformers for Biomedical Entity Recognition","created":"2023-07-20","cited_by_count":1,"area":null},{"id":"2407.01608","title":"Deriva-ML: A Continuous FAIRness Approach to Reproducible Machine Learning Models","created":"2024-06-27","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":"2512.19723","title":"End-to-End Data Quality-Driven Framework for Machine Learning in Production Environment","created":"2025-12-16","cited_by_count":1,"area":null},{"id":"2602.14357","title":"Key Considerations for Domain Expert Involvement in LLM Design and Evaluation: An Ethnographic Study","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2407.14210","title":"Fair Overlap Number of Balls (Fair-ONB): A Data-Morphology-based Undersampling Method for Bias Reduction","created":"2024-07-19","cited_by_count":0,"area":null},{"id":"2506.16051","title":"From Data to Decision: Data-Centric Infrastructure for Reproducible ML in Collaborative eScience","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2507.12105","title":"Out-of-distribution data supervision towards biomedical semantic segmentation","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2508.02281","title":"Do Edges Matter? Investigating Edge-Enhanced Pre-Training for Medical Image Segmentation","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.16255","title":"Chunked Data Shapley: A Scalable Dataset Quality Assessment for Machine Learning","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2509.11588","title":"Optimizing Class Distributions for Bias-Aware Multi-Class Learning","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2509.24420","title":"A Data-Centric Perspective on the Influence of Image Data Quality in Machine Learning Models","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2601.06061","title":"AI Application Operations -- A Socio-Technical Framework for Data-driven Organizations","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2602.03686","title":"QuAIL: Quality-Aware Inertial Learning for Robust Training under Data Corruption","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2604.14449","title":"Crowdsourcing of Real-world Image Annotation via Visual Properties","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2609.33754","title":"Collaborative Synthetic Data for Privacy-Preserving Financial Fraud Detection Across Organizational Silos","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}