{
 "id": "vinsblack/The_Stack_Processed-v2",
 "owner": "vinsblack",
 "name": "The_Stack_Processed-v2",
 "downloads": 91,
 "likes": 4,
 "last_modified": "2025-08-18T07:48:25.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "feature-extraction",
  "text-classification"
 ],
 "citation": "@dataset{the_stack_processed_v2_2025,\n  title={The Stack Processed V2: A Balanced Multi-Language Programming Dataset for AI Training},\n  author={Gallo, Vincenzo},\n  year={2025},\n  month={January},\n  publisher={Hugging Face},\n  url={https://huggingface.co/datasets/vinsblack/The_Stack_Processed-v2},\n  version={2.0.0},\n  note={Curated and balanced version of The Stack dataset optimized for multi-language code generation and analysis},\n  keywords={code generation, machine learning, programming languages, software engineering, artificial intelligence}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "25e5f1c4e952dd7d78926b3a6a1688133c1df4bc",
 "stated_evidence": "https://huggingface.co/datasets/vinsblack/The_Stack_Processed-v2/blob/25e5f1c4e952dd7d78926b3a6a1688133c1df4bc/README.md",
 "file_evidence": "https://huggingface.co/datasets/vinsblack/The_Stack_Processed-v2/tree/25e5f1c4e952dd7d78926b3a6a1688133c1df4bc",
 "card_nc": false
}