{"total":30,"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":"2312.01678","title":"Jellyfish: A Large Language Model for Data Preprocessing","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2212.07588","title":"DeepJoin: Joinable Table Discovery with Pre-trained Language Models","created":"2022-12-15","cited_by_count":15,"area":null},{"id":"2407.21523","title":"Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI","created":"2024-07-31","cited_by_count":15,"area":null},{"id":"2310.07736","title":"Observatory: Characterizing Embeddings of Relational Tables","created":"2023-10-05","cited_by_count":12,"area":null},{"id":"2104.04659","title":"Auto-Validate: Unsupervised Data Validation Using Data-Domain Patterns Inferred from Data Lakes","created":"2021-04-10","cited_by_count":7,"area":null},{"id":"2306.00932","title":"Cross Modal Data Discovery over Structured and Unstructured Data Lakes","created":"2023-06-01","cited_by_count":5,"area":null},{"id":"2307.15516","title":"YOLOv8 for Defect Inspection of Hexagonal Directed Self-Assembly Patterns: A Data-Centric Approach","created":"2023-07-28","cited_by_count":5,"area":null},{"id":"2502.16813","title":"Snoopy: Effective and Efficient Semantic Join Discovery via Proxy Columns","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2306.11843","title":"Retrieval-Based Transformer for Table Augmentation","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2303.02204","title":"KGLiDS: A Platform for Semantic Abstraction, Linking, and Automation of Data Science","created":"2023-03-03","cited_by_count":2,"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":"2403.02327","title":"Model Lakes","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2407.08227","title":"DALL-M: Context-Aware Clinical Data Augmentation with LLMs","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2601.01015","title":"HyperJoin: LLM-augmented Hypergraph Link Prediction for Joinable Table Discovery","created":"2026-01-03","cited_by_count":2,"area":null},{"id":"2308.03883","title":"Generative Benchmark Creation for Table Union Search","created":"2023-08-07","cited_by_count":1,"area":null},{"id":"2407.01619","title":"TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes","created":"2024-06-28","cited_by_count":1,"area":null},{"id":"2502.15819","title":"Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nesting","created":"2025-02-20","cited_by_count":1,"area":null},{"id":"2507.02819","title":"Measurement as Bricolage: Examining How Data Scientists Construct Target Variables for Predictive Modeling Tasks","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2509.04632","title":"Conceptual Schema Inference for Tabular Datasets using Large Language Models","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2512.16106","title":"ModelTables: A Corpus of Tables about Models","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2602.08186","title":"Nexus: Inferring Join Graphs from Metadata Alone via Iterative Low-Rank Matrix Completion","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2605.18199","title":"PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.03049","title":"Alignment-Guided Largest Table Overlap Size Estimation","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.05970","title":"Faithful or Findable? Evaluating LLM-Generated Metadata for RDF Dataset Search","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.19847","title":"Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.21781","title":"MosaicJoin: Compact Semantic Sketches for Value-Level Join Discovery","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.26750","title":"Discovering Relationships in Data Lakes Using Large Language Models: An Industrial Case","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2610.00817","title":"TabJoinBench: A Benchmark for Joinable Table Discovery","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}