{
 "id": "MultiSynt/MT-HPLT2c",
 "owner": "MultiSynt",
 "name": "MT-HPLT2c",
 "downloads": 120,
 "likes": 0,
 "last_modified": "2026-02-13T22:46:37.000Z",
 "stated_licence": "cc0-1.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@dataset{mt_hplt2c_2025,\n    title   = {MT-HPLT2c: Large-Scale Machine-Translated Web Text},\n    author  = {MultiSynt},\n    year    = {2025},\n    note    = {A translated variant of HPLT v2 cleaned (HPLT2c) for cross-lingual LLM pretraining experiments},\n    url     = {https://huggingface.co/datasets/MultiSynt/MT-HPLT2c}\n}\n\n@misc{rei2025towerplus,\n    title={Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs}, \n    author={Ricardo Rei and Nuno M. Guerreiro and José Pombal and João Alves and Pedro Teixeirinha and Amin Farajian and André F. T. Martins},\n    year={2025},\n    eprint={2506.17080},\n    archivePrefix={arXiv},\n    primaryClass={cs.CL},\n    url={https://arxiv.org/abs/2506.17080}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (cc0-1.0) is classified as permissive.",
 "revision": "cc9ff064754cf76ca1ccd5ac74466b927a2cc740",
 "stated_evidence": "https://huggingface.co/datasets/MultiSynt/MT-HPLT2c/blob/cc9ff064754cf76ca1ccd5ac74466b927a2cc740/README.md",
 "file_evidence": "https://huggingface.co/datasets/MultiSynt/MT-HPLT2c/tree/cc9ff064754cf76ca1ccd5ac74466b927a2cc740",
 "card_nc": false
}