{
 "id": "cyberagent/CAT-Thinking-Dataset",
 "owner": "cyberagent",
 "name": "CAT-Thinking-Dataset",
 "downloads": 48,
 "likes": 3,
 "last_modified": "2026-07-14T04:10:36.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-4.0",
 "licence_files": [
  "LICENSE.txt"
 ],
 "sources": [],
 "gated": "auto",
 "tasks": [],
 "citation": "This dataset is constructed on top of several open-source datasets. We are grateful to the original creators. The original data subsets retain their respective licenses:\n- [Swallow-Nemotron-Post-Training-Dataset by Swallow LLM, 2025 (CC BY 4.0)](https://huggingface.co/datasets/tokyotech-llm/Swallow-Nemotron-Post-Training-Dataset-v1)\n- [Big-Math-Verified by SynthLabsAI, 2025 (Apache 2.0)](https://huggingface.co/datasets/SynthLabsAI/Big-Math-RL-Verified)\n- [DAPO-Math by BytedTsinghua-SIA, 2025 (Apache 2.0)](https://huggingface.co/datasets/BytedTsinghua-SIA/DAPO-Math-17k)\n- [rStar-Coder by Microsoft, 2025 (CC BY 4.0)](https://huggingface.co/datasets/microsoft/rStar-Coder)\n- [AReaL-boba-2-RL-Code by inclusionAI, 2025 (Apache 2.0)](https://huggingface.co/datasets/inclusionAI/AReaL-boba-2-RL-Code)\n- [xlam-function-calling-60k by Salesforce, 2024 (CC BY 4.0)](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)\n- [extraction-wiki-ja by LLM-jp, 2025 (Apache 2.0)](https://huggingface.co/datasets/llm-jp/extraction-wiki-ja)\n- [magpie by LLM-jp, 2024 (Apache 2.0)](https://huggingface.co/datasets/llm-jp/magpie-sft-v1.0)\n\nSource datasets are editted by the author (filtered, translated, and added prefix/postfix) and formatted into a data format to be used for supervised fine-tuning and reinforcement learning.",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "1b303c73d3ef9b2393d446cad81f9a0431c03610",
 "stated_evidence": "https://huggingface.co/datasets/cyberagent/CAT-Thinking-Dataset/blob/1b303c73d3ef9b2393d446cad81f9a0431c03610/README.md",
 "file_evidence": "https://huggingface.co/datasets/cyberagent/CAT-Thinking-Dataset/blob/1b303c73d3ef9b2393d446cad81f9a0431c03610/LICENSE.txt",
 "card_nc": false
}