{
 "id": "maisonOP/spia",
 "owner": "maisonOP",
 "name": "spia",
 "downloads": 31,
 "likes": 0,
 "last_modified": "2026-04-24T11:17:49.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "% TAB benchmark\n@article{pilan2022tab,\n    author = {Pil{\\'a}n, Ildik{\\'o} and Lison, Pierre and {\\O}vrelid, Lilja and Papadopoulou, Anthi and S{\\'a}nchez, David and Batet, Montserrat},\n    title = {The Text Anonymization Benchmark ({TAB}): A Dedicated Corpus and Evaluation Framework for Text Anonymization},\n    journal = {Computational Linguistics},\n    volume = {48},\n    number = {4},\n    pages = {1053--1101},\n    year = {2022},\n    doi = {10.1162/coli_a_00458},\n    url = {https://aclanthology.org/2022.cl-4.19/}\n}\n\n% PANORAMA dataset\n@article{selvam2025panorama,\n    author = {Selvam, Sriram and Ghosh, Anneswa},\n    title = {{PANORAMA}: A Synthetic {PII}-laced Dataset for Studying Sensitive Data Memorization in {LLM}s},\n    journal = {Computing Research Repository},\n    volume = {arXiv:2505.12238},\n    year = {2025},\n    url = {http://arxiv.org/abs/2505.12238}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "be588c0d3f81d5762fff78868326fdd8d2fafb96",
 "stated_evidence": "https://huggingface.co/datasets/maisonOP/spia/blob/be588c0d3f81d5762fff78868326fdd8d2fafb96/README.md",
 "file_evidence": "https://huggingface.co/datasets/maisonOP/spia/tree/be588c0d3f81d5762fff78868326fdd8d2fafb96",
 "card_nc": false
}