{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "mobile UI actions",
        "clarification responses"
      ],
      "counts": [],
      "evaluation": "Paper defines multi-path and noise/ambiguity evaluations; the public card identifies which files are full common-task sets and which are samples.",
      "evidence_urls": [
        "https://huggingface.co/datasets/xwk123/MobileBench-v2/raw/main/README.md",
        "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"
      ],
      "focus": [
        "offline multi-path evaluation",
        "noisy interfaces",
        "ambiguous instructions"
      ],
      "notes": "Release completeness differs by split. No full-benchmark sample total is inferred from the archive manifest.",
      "observations": [
        "mobile screenshots",
        "XML UI state",
        "instructions"
      ],
      "setting": "offline"
    },
    "disabled": false,
    "download_url": "https://huggingface.co/datasets/xwk123/MobileBench-v2/tree/main",
    "gated": false,
    "hub_id": "xwk123/MobileBench-v2",
    "license_review": {
      "data": {
        "evidence_urls": [
          "https://huggingface.co/datasets/xwk123/MobileBench-v2/raw/main/README.md"
        ],
        "reason": "The same first-party card has an Apache-2.0 metadata header but explicitly assigns Apache-2.0 to code and CC-BY-NC-SA-4.0 to the dataset in its License section. Preserve both declarations and leave a single data license unresolved instead of displaying the permissive header as the data permission."
      }
    }
  },
  "environments": [
    "android"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T04:01:33Z",
      "role": "primary",
      "sha256": "13424be795c7b75b8c2195469c1252a7b3ec633e8bb31f1f6d7e44476611cbe9",
      "supports": [
        "name",
        "kind",
        "summary",
        "topics",
        "scope",
        "relations",
        "details",
        "licenses.data"
      ],
      "url": "https://huggingface.co/datasets/xwk123/MobileBench-v2/raw/main/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T04:01:33Z",
      "role": "primary",
      "sha256": "247b1766b8cbdb2943c4602d2667f9f06dec8b84f0d24457080d499177475f22",
      "supports": [
        "identity",
        "release_status",
        "details"
      ],
      "url": "https://huggingface.co/api/datasets/xwk123/MobileBench-v2"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:31:42Z",
      "role": "primary",
      "sha256": "afe4e75ffb8a5c44f4c088a90ffa5f53553036f514aa768f5aee0c5aa38d731e",
      "supports": [
        "relations",
        "summary"
      ],
      "url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:38:26Z",
      "role": "primary",
      "sha256": "356a8dca28fa3dc46bc05b13eaf04a3db273e63c06be4fd15d0e87e0343c0824",
      "supports": [
        "environments",
        "notes"
      ],
      "url": "https://huggingface.co/api/datasets/xwk123/Mobile3M"
    }
  ],
  "id": "url:1d5b85321b98765141fc",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-17T04:01:33Z",
  "licenses": {
    "code": null,
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://huggingface.co/datasets/xwk123/MobileBench-v2"
    }
  ],
  "name": "Mobile-Bench-v2 released data",
  "notes": "The card distinguishes complete common-simple/common-complex JSON files from sampled noisy and ambiguous subsets; common tasks also require the separately cataloged Mobile3M dataset. Card metadata says Apache-2.0, while the prose explicitly assigns Apache-2.0 to code and CC-BY-NC-SA-4.0 to data. Do not apply the permissive header to dataset payloads, and do not describe every announced split as fully released.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://export.arxiv.org/api/query?id_list=2503.16788%2C2503.17709%2C2503.18492%2C2503.19537%2C2503.20978%2C2503.21620%2C2503.23434%2C2504.01382%2C2504.07981%2C2504.10445%2C2504.10458%2C2504.11257%2C2504.11281%2C2504.12679%2C2504.13805%2C2504.13865%2C2504.14239%2C2504.18575%2C2504.19838%2C2504.20464%2C2505.10924%2C2505.11891%2C2505.12299%2C2505.12632%2C2505.13227%2C2505.13887%2C2505.13909%2C2505.14289%2C2505.15810%2C2505.16282%2C2505.16827%2C2505.18829%2C2505.19897%2C2505.21496%2C2505.21499%2C2505.21936%2C2505.22648%2C2505.23762%2C2505.24838%2C2506.00618%2C2506.01391%2C2506.01968%2C2506.02456%2C2506.03143%2C2506.03569%2C2506.04135%2C2506.04614%2C2506.07672%2C2506.08012%2C2506.08972&max_results=50",
      "target_id": "arxiv:2505.11891",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Offline mobile-agent task data spanning common tasks and released noisy, contaminated and ambiguous-instruction subsets.",
  "topics": [
    "evaluation",
    "mobile-navigation",
    "robustness"
  ],
  "updated_at": null,
  "url": "https://huggingface.co/datasets/xwk123/MobileBench-v2"
}