{
 "id": "codelion/synth-10M",
 "owner": "codelion",
 "name": "synth-10M",
 "downloads": 31,
 "likes": 0,
 "last_modified": "2025-11-11T04:04:11.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@dataset{synth_sampled_10000000,\n  title={PleIAs/SYNTH Sampled Dataset (10,000,000 tokens)},\n  author={CodeLion},\n  year={2025},\n  howpublished={\\url{https://huggingface.co/datasets/codelion/synth-10M}},\n  note={Sampled from PleIAs/SYNTH using reservoir sampling}\n}\n\n@dataset{synth_original,\n  title={SYNTH: The First Open Generalist Synthetic Dataset},\n  author={PleIAs},\n  year={2025},\n  howpublished={\\url{https://huggingface.co/datasets/PleIAs/SYNTH}}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "bb177a09c63c40dc61b0e81d7c1eb6d4a3e4790a",
 "stated_evidence": "https://huggingface.co/datasets/codelion/synth-10M/blob/bb177a09c63c40dc61b0e81d7c1eb6d4a3e4790a/README.md",
 "file_evidence": "https://huggingface.co/datasets/codelion/synth-10M/tree/bb177a09c63c40dc61b0e81d7c1eb6d4a3e4790a",
 "card_nc": false
}