{
 "id": "WesleyWzq/MobileJudgeBench",
 "owner": "WesleyWzq",
 "name": "MobileJudgeBench",
 "downloads": 106,
 "likes": 1,
 "last_modified": "2026-10-19T18:05:41.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "mit",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-text-to-text"
 ],
 "citation": "@misc{wang2026benchmarkingllmjudgesmobile,\n  title         = {Benchmarking LLM Judges for Mobile Agent Evaluation},\n  author        = {Ziqiang Wang and Li Gu and Zhixiang Chi and Zhi Liu and Seyed Mehdi Ayyoubzadeh and Yuanhao Yu and Yang Wang},\n  year          = {2026},\n  eprint        = {2608.11434},\n  archivePrefix = {arXiv},\n  primaryClass  = {cs.AI},\n  url           = {https://arxiv.org/abs/2608.11434}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "2170e51c79ba52d8c8d1e0e224c8f7f42b004324",
 "stated_evidence": "https://huggingface.co/datasets/WesleyWzq/MobileJudgeBench/blob/2170e51c79ba52d8c8d1e0e224c8f7f42b004324/README.md",
 "file_evidence": "https://huggingface.co/datasets/WesleyWzq/MobileJudgeBench/blob/2170e51c79ba52d8c8d1e0e224c8f7f42b004324/LICENSE",
 "card_nc": false
}