{
 "id": "ellamind/RefinedGAW",
 "owner": "ellamind",
 "name": "RefinedGAW",
 "downloads": 190,
 "likes": 1,
 "last_modified": "2026-10-27T21:41:25.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@misc{refinedgaw2026,\n  title  = {RefinedGAW: A Refined German Academic Web Dataset},\n  author = {Idahl, Maximilian and Astappiev, Oleh and Droste, Benedikt and Scholz, Robert and Pl{\\\"u}ster, Bj{\\\"o}rn and Harries, Jan Philipp and J{\\\"a}schke, Robert and Nejdl, Wolfgang},\n  year   = {2026},\n  eprint = {2610.34572},\n  archivePrefix = {arXiv},\n  primaryClass  = {cs.CL},\n  url    = {https://arxiv.org/abs/2610.34572}\n}\n\n@inproceedings{paris2020gaw,\n  title     = {How to Assess the Exhaustiveness of Longitudinal Web Archives: A Case Study of the {German Academic Web}},\n  author    = {Paris, Michael and J{\\\"a}schke, Robert},\n  booktitle = {Proceedings of the 31st ACM Conference on Hypertext and Social Media},\n  pages     = {85--89},\n  publisher = {Association for Computing Machinery},\n  year      = {2020},\n  doi       = {10.1145/3372923.3404836},\n  url       = {https://doi.org/10.1145/3372923.3404836}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "e2b1eec52f4b8070c572bf2c2340477cc9645393",
 "stated_evidence": "https://huggingface.co/datasets/ellamind/RefinedGAW/blob/e2b1eec52f4b8070c572bf2c2340477cc9645393/README.md",
 "file_evidence": "https://huggingface.co/datasets/ellamind/RefinedGAW/tree/e2b1eec52f4b8070c572bf2c2340477cc9645393",
 "card_nc": false
}