{
 "id": "JQL-AI/hplt2_embeddings",
 "owner": "JQL-AI",
 "name": "hplt2_embeddings",
 "downloads": 6603,
 "likes": 0,
 "last_modified": "2025-08-21T12:39:53.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "feature-extraction"
 ],
 "citation": "@article{ali2025judging,\n    title     = {Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models},\n    author    = {\n      Mehdi Ali,\n      Manuel Brack,\n      Max L\u00fcbbering,\n      Elias Wendt,\n      Abbas Goher Khan,\n      Richard Rutmann,\n      Alex Jude,\n      Maurice Kraus,\n      Alexander Arno Weber,\n      Felix Stollenwerk,\n      David Kacz\u00e9r,\n      Florian Mai,\n      Lucie Flek,\n      Rafet Sifa,\n      Nicolas Flores-Herr,\n      Joachim K\u00f6hler,\n      Patrick Schramowski,\n      Michael Fromm,\n      Kristian Kersting\n    },\n    year      = {2025},\n    journal   = {arXiv preprint arXiv:2505:22232}\n  }",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata."
}