DataVinci: Learning Syntactic and Semantic String Repairs
Summary: DataVinci is a fully unsupervised string error detector and repairer that learns column-wide regex patterns to flag deviations. It handles mixed syntactic and semantic substrings with an LLM-based abstraction and uses data-program traces to derive repairs. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Mukul Singh (Microsoft)
- 2. José Cambronero (Microsoft)
- 3. Sumit Gulwani (Microsoft)
- 4. Vu Le (Microsoft)
- 5. Carina Negreanu (Robin AI)
- 6. Arjun Radhakrishna (Microsoft)
- 7. Gust Verbruggen (Microsoft)
BibTeX Citation
@inproceedings{singh_sigmod25,
title = {{DataVinci: Learning Syntactic and Semantic String Repairs}},
author = {Singh, Mukul and Cambronero, José and Gulwani, Sumit and Le, Vu and Negreanu, Carina and Radhakrishna, Arjun and Verbruggen, Gust},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3709677},
url = {https://dl.acm.org/doi/10.1145/3709677},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 11,343 | Generalizable Data Cleaning of Tabular Data in Latent Space | 2024 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 12 of 12 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 112 | HoloClean: Holistic Data Repairs with Probabilistic Inference | 2017 | VLDB |
| 2 | 7,880 | Learning Over Dirty Data Without Cleaning | 2020 | SIGMOD |
| 3 | 998 | Towards Certain Fixes with Editing Rules and Master Data | 2010 | VLDB |
| 4 | 2,728 | Uni-Detect: A Unified Approach to Automated Error Detection in Tables | 2019 | SIGMOD |
| 5 | 11,038 | DemandClean: A Multi-Objective Learning Framework for Balancing Model Tolerance to Data Authenticity and Diversity | 2025 | VLDB |
| 6 | 3,580 | Automatic Data Repair: Are We Ready to Deploy? | 2024 | VLDB |
| 7 | 2,981 | Towards Dependable Data Repairing with Fixing Rules | 2014 | SIGMOD |
| 8 | 3,147 | Auto-Detect: Data-Driven Error Detection in Tables | 2018 | SIGMOD |
| 9 | 3,547 | Learning Semantic String Transformations from Examples | 2012 | VLDB |
| 10 | 10,785 | Auto-Test: Learning Semantic-Domain Constraints for Unsupervised Error Detection in Tables | 2025 | SIGMOD |