{
 "id": "mteb/DS1000Retrieval",
 "owner": "mteb",
 "name": "DS1000Retrieval",
 "downloads": 195,
 "likes": 1,
 "last_modified": "2025-10-21T08:28:19.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "embedding-benchmark/DS1000",
   "licence": null,
   "found": true,
   "evidence": "https://huggingface.co/datasets/embedding-benchmark/DS1000/blob/25cd4dc8172e799235d83c66439b6b7b8e6583ec/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "text-retrieval"
 ],
 "citation": "@article{lai2022ds,\n  author = {Lai, Yuhang and Li, Chengxi and Wang, Yiming and Zhang, Tianyi and Zhong, Ruiqi and Zettlemoyer, Luke and Yih, Wen-tau and Fried, Daniel and Wang, Sida and Yu, Tao},\n  journal = {arXiv preprint arXiv:2211.11501},\n  title = {DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation},\n  year = {2022},\n}\n\n\n@article{enevoldsen2025mmtebmassivemultilingualtext,\n  title={MMTEB: Massive Multilingual Text Embedding Benchmark},\n  author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zhang and Roberta Rocca and Mohammed Hamdy and Andrianos Michail and John Yang and Manuel Faysse and Aleksei Vatolin and Nandan Thakur and Manan Dey and Dipam Vasani and Pranjal Chitale and Simone Tedeschi and Nguyen Tai and Artem Snegir",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID for at least one declared source dataset.",
 "revision": "26779eaf6daa2b7984cb33ec450817fd188aab30",
 "stated_evidence": "https://huggingface.co/datasets/mteb/DS1000Retrieval/blob/26779eaf6daa2b7984cb33ec450817fd188aab30/README.md",
 "file_evidence": "https://huggingface.co/datasets/mteb/DS1000Retrieval/tree/26779eaf6daa2b7984cb33ec450817fd188aab30",
 "card_nc": false
}