{
 "id": "Aleph-Alpha/Aleph-Alpha-GermanWeb",
 "owner": "Aleph-Alpha",
 "name": "Aleph-Alpha-GermanWeb",
 "downloads": 558,
 "likes": 27,
 "last_modified": "2026-03-31T16:55:12.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "open-aleph-license",
 "licence_link": "LICENSE",
 "file_licence": null,
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@misc{burns2025alephalphagermanwebimprovinggermanlanguagellm,\n      title={Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation}, \n      author={Thomas F Burns and Letitia Parcalabescu and Stephan Wäldchen and Michael Barlow and Gregor Ziegltrum and Volker Stampa and Bastian Harren and Björn Deiseroth},\n      year={2025},\n      eprint={2505.00022},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2505.00022}, \n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "0d3a976b5c1acbeeaa204d5d2b9e5d322e1ec7d7",
 "stated_evidence": "https://huggingface.co/datasets/Aleph-Alpha/Aleph-Alpha-GermanWeb/blob/0d3a976b5c1acbeeaa204d5d2b9e5d322e1ec7d7/README.md",
 "file_evidence": "https://huggingface.co/datasets/Aleph-Alpha/Aleph-Alpha-GermanWeb/blob/0d3a976b5c1acbeeaa204d5d2b9e5d322e1ec7d7/LICENSE",
 "card_nc": false
}