{
 "id": "kirco567/ScamWeb-Dataset",
 "owner": "kirco567",
 "name": "ScamWeb-Dataset",
 "downloads": 281,
 "likes": 2,
 "last_modified": "2026-10-10T02:54:17.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-4.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-classification",
  "text-classification"
 ],
 "citation": "The accompanying paper is an **anonymous AAAI 2027 submission**:\n\n> **ScamWeb: A Multimodal Benchmark for Grounded Understanding of Cyber-enabled Fraud Webpages.** Anonymous submission, AAAI 2027.\n\nAn archival citation will be added when public author and publication information becomes available. The anonymous code mirror linked above provides the benchmark protocol and ScamMark implementation.\n\nBenign webpage source: Potpelwar, R. S.; Kulkarni, U.; and Waghmare, J. 2025. *LegitPhish: A large-scale annotated dataset for URL-based phishing detection.* Data in Brief, 63: 111972.",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "744481558392ce6b140581f33281d7bae5a77255",
 "stated_evidence": "https://huggingface.co/datasets/kirco567/ScamWeb-Dataset/blob/744481558392ce6b140581f33281d7bae5a77255/README.md",
 "file_evidence": "https://huggingface.co/datasets/kirco567/ScamWeb-Dataset/blob/744481558392ce6b140581f33281d7bae5a77255/LICENSE",
 "card_nc": false
}