{
 "id": "embedding-benchmark/SWEbenchCodeRetrieval",
 "owner": "embedding-benchmark",
 "name": "SWEbenchCodeRetrieval",
 "downloads": 700,
 "likes": 0,
 "last_modified": "2026-04-12T13:13:33.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-retrieval"
 ],
 "citation": "@misc{jimenez2024swebenchlanguagemodelsresolve,\n  archiveprefix = {arXiv},\n  author = {Carlos E. Jimenez and John Yang and Alexander Wettig and Shunyu Yao and Kexin Pei and Ofir Press and Karthik Narasimhan},\n  eprint = {2310.06770},\n  primaryclass = {cs.CL},\n  title = {SWE-bench: Can Language Models Resolve Real-World GitHub Issues?},\n  url = {https://arxiv.org/abs/2310.06770},\n  year = {2024},\n}\n\n@article{enevoldsen2025mmtebmassivemultilingualtext,\n  title={MMTEB: Massive Multilingual Text Embedding Benchmark},\n  author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and M\\'{a}rton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemi\\'{n}ski 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 Rystr{\\o}m and Roman Solomatin and \\\"{O}mer \\c{C}a\\u{g}atan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafa{\\l} Po\\'{s}wiata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Bj\\\"{o}rn Pl\\\"{u}ster and Jan Philipp Harries and Lo\\\"{i}c 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 \\v{S}uppa 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 Mana",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "440b0e732b8d02c16df2c95352ab6770abe997da",
 "stated_evidence": "https://huggingface.co/datasets/embedding-benchmark/SWEbenchCodeRetrieval/blob/440b0e732b8d02c16df2c95352ab6770abe997da/README.md",
 "file_evidence": "https://huggingface.co/datasets/embedding-benchmark/SWEbenchCodeRetrieval/tree/440b0e732b8d02c16df2c95352ab6770abe997da",
 "card_nc": false
}