{
 "id": "lianghsun/spider-text2sql-bench",
 "owner": "lianghsun",
 "name": "spider-text2sql-bench",
 "downloads": 32,
 "likes": 0,
 "last_modified": "2026-04-15T03:12:57.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "question-answering"
 ],
 "citation": "@inproceedings{yu2018spider,\n  title={Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task},\n  author={Yu, Tao and Zhang, Rui and Yang, Kai and Yasunaga, Michihiro and Wang, Dongxu and Li, Zifan and Ma, James and Li, Irene and Yao, Qingning and Roman, Shanelle and others},\n  booktitle={EMNLP},\n  year={2018}\n}\n\n@misc{spider-text2sql-bench,\n  title        = {spider-text2sql-bench: Spider 1.0 in OpenAI Messages + Split Columns Format for Text-to-SQL SFT and Benchmark},\n  author       = {Liang Hsun Huang},\n  year         = {2024},\n  howpublished = {\\url{https://huggingface.co/datasets/lianghsun/spider-text2sql-bench}},\n  note         = {Reformatted from xlangai/spider train split (CC BY-SA 4.0) with additional system/user/assistant columns for benchmark pipelines.}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "b9f24246a1ade7e1d31900abf0329e5212c9f54f",
 "stated_evidence": "https://huggingface.co/datasets/lianghsun/spider-text2sql-bench/blob/b9f24246a1ade7e1d31900abf0329e5212c9f54f/README.md",
 "file_evidence": "https://huggingface.co/datasets/lianghsun/spider-text2sql-bench/tree/b9f24246a1ade7e1d31900abf0329e5212c9f54f",
 "card_nc": false
}