DBScholar

Back to papers

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)

Paper ID
7087
Venue
SIGMOD
Year
2025
Pagerank
5.2528121e-05
Overall Rank
9,539 | 34.56%
DOI
10.1145/3709677

Incoming Non-self Citations Over Time

Authors

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