DBScholar

Back to papers

CodexDB: Synthesizing Code for Query Processing from Natural Language Instructions using GPT-3 Codex

Summary: CodexDB leverages GPT-3 Codex to synthesize query-processing code from natural-language instructions. Decomposing complex SQL into stepwise, NL-described processing stages augmented by user guidance and database properties; prototype attains 81% WikiSQL and 62% SPIDER. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
12963
Venue
VLDB
Year
2022
Pagerank
8.4729505e-05
Overall Rank
2,521 | 82.71%
DOI
10.14778/3551793.3551841

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{trummer_vldb22,
        title = {{CodexDB: Synthesizing Code for Query Processing from Natural Language Instructions using GPT-3 Codex}},
        author = {Trummer, Immanuel},
        journal = {PVLDB},
        series = {{VLDB} '22},
        volume = {15},
        number = {11},
        pages = {2921--2928},
        doi = {10.14778/3551793.3551841},
        url = {https://doi.org/10.14778/3551793.3551841},
        year = {2022}
}

Incoming Citations (Sorted by Pagerank)

Showing 12 of 12 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 9 of 9 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