{
 "id": "uw-math-ai/theorem-search-dataset",
 "owner": "uw-math-ai",
 "name": "theorem-search-dataset",
 "downloads": 461,
 "likes": 26,
 "last_modified": "2026-10-02T01:33:21.000Z",
 "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": [
  "question-answering",
  "feature-extraction",
  "sentence-similarity"
 ],
 "citation": "@inproceedings{alexander2026semantic,\n  author        = {Alexander, Luke and Leonen, Eric and Szeto, Sophie and Remizov, Artemii and Tejeda, Ignacio and Alper, Jarod and Inchiostro, Giovanni and Ilin, Vasily},\n  title         = {Semantic Search over 9 Million Mathematical Theorems},\n  booktitle     = {Advances in Neural Information Processing Systems},\n  volume        = {39},\n  year          = {2026},\n  note          = {Evaluations and Datasets Track},\n  archivePrefix = {arXiv},\n  eprint        = {2602.05216},\n  primaryClass  = {cs.IR},\n  url           = {https://arxiv.org/abs/2602.05216}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "aaf30d748ae24e7207bdfa41e5a3e580b327d532",
 "stated_evidence": "https://huggingface.co/datasets/uw-math-ai/theorem-search-dataset/blob/aaf30d748ae24e7207bdfa41e5a3e580b327d532/README.md",
 "file_evidence": "https://huggingface.co/datasets/uw-math-ai/theorem-search-dataset/tree/aaf30d748ae24e7207bdfa41e5a3e580b327d532",
 "card_nc": false
}