{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://huggingface.co/datasets/mikewang/mobile_eval_e/raw/b8eca82988ed8d4f9dec01eaa9d51abf4b35aa83/README.md",
          "population": "Hub test split at revision b8eca829",
          "qualifier": "exact",
          "unit": "task-definition records",
          "value": 25
        }
      ],
      "evaluation": "The published task schema contains rubrics and human_reference_operations. No automated scoring protocol or single numeric agent metric is established by the inspected card; execution uses separately configured Android tooling.",
      "evidence_urls": [
        "https://huggingface.co/datasets/mikewang/mobile_eval_e/raw/b8eca82988ed8d4f9dec01eaa9d51abf4b35aa83/README.md",
        "https://huggingface.co/api/datasets/mikewang/mobile_eval_e",
        "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/Mobile-Agent-E/README.md",
        "https://export.arxiv.org/api/query?id_list=2412.04454%2C2412.04626%2C2412.05467%2C2412.09362%2C2412.09605%2C2412.10342%2C2412.10742%2C2412.10840%2C2412.13103%2C2412.13194%2C2412.13501%2C2412.14161%2C2412.14470%2C2412.16256%2C2412.17589%2C2412.18116%2C2412.18426%2C2412.19723%2C2501.01149%2C2501.04575%2C2501.07572%2C2501.11733%2C2501.12326%2C2501.13896%2C2501.16150%2C2502.01600%2C2502.01977%2C2502.02982%2C2502.06395%2C2502.07949%2C2502.08047%2C2502.08226%2C2502.11357%2C2502.13053%2C2502.13923%2C2502.14282%2C2502.18906%2C2503.00401%2C2503.02268%2C2503.03196%2C2503.04730%2C2503.05143%2C2503.06470%2C2503.09263%2C2503.11069%2C2503.11170%2C2503.12687%2C2503.15661%2C2503.15937%2C2503.16465&max_results=50"
      ],
      "focus": [
        "long-horizon multi-app Android task execution"
      ],
      "notes": "Features are task_id, instruction, type, apps, scenario, rubrics and human-reference operation strings. A task record is not an action count or recorded screenshot trajectory. Public Parquet inventory was checked but no sample rows were downloaded; companion README limits the tested agent platform to Android.",
      "observations": [
        "task instructions",
        "app/scenario metadata"
      ],
      "setting": "interactive"
    },
    "disabled": false,
    "download_url": "https://huggingface.co/datasets/mikewang/mobile_eval_e/tree/b8eca82988ed8d4f9dec01eaa9d51abf4b35aa83",
    "gated": false,
    "hub_id": "mikewang/mobile_eval_e",
    "hub_revision": "b8eca82988ed8d4f9dec01eaa9d51abf4b35aa83",
    "license_review": {
      "data": {
        "evidence_urls": [
          "https://huggingface.co/datasets/mikewang/mobile_eval_e/raw/b8eca82988ed8d4f9dec01eaa9d51abf4b35aa83/README.md"
        ],
        "reason": "No data-license declaration is present in the inspected task card; companion code MIT does not establish a dataset grant."
      }
    },
    "repository_url": "https://github.com/X-PLUG/MobileAgent/tree/main/Mobile-Agent-E"
  },
  "environments": [
    "android"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-18T04:27:15Z",
      "role": "primary",
      "sha256": "f8515fbce73ea0ef3d1d558d4567bb949244e6384e61c956ba3ddbc27294f0ae",
      "supports": [
        "name",
        "kind",
        "environments",
        "scope",
        "notes",
        "relations",
        "details.benchmark_protocol"
      ],
      "url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/Mobile-Agent-E/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-18T04:33:29Z",
      "role": "primary",
      "sha256": "f9b10eada9e0a64e26f1a7d477768f218b807103199855d893b3ab07feddc755",
      "supports": [
        "identity",
        "release_status",
        "details.hub_id",
        "details.hub_revision",
        "details.gated",
        "details.disabled",
        "details.download_url",
        "details.benchmark_protocol"
      ],
      "url": "https://huggingface.co/api/datasets/mikewang/mobile_eval_e"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-18T04:35:15Z",
      "role": "primary",
      "sha256": "9fdf43753fbfac9868d8bec57fa5601db3e03ed5c30fb981f9da88f6b75ffcc5",
      "supports": [
        "summary",
        "details.benchmark_protocol",
        "licenses.data"
      ],
      "url": "https://huggingface.co/datasets/mikewang/mobile_eval_e/raw/b8eca82988ed8d4f9dec01eaa9d51abf4b35aa83/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:31:38Z",
      "role": "primary",
      "sha256": "e96b86015c763c780e0430a8d0867b96cae947f50e888b3441c85abcaa42de78",
      "supports": [
        "summary",
        "topics",
        "details.benchmark_protocol"
      ],
      "url": "https://export.arxiv.org/api/query?id_list=2412.04454%2C2412.04626%2C2412.05467%2C2412.09362%2C2412.09605%2C2412.10342%2C2412.10742%2C2412.10840%2C2412.13103%2C2412.13194%2C2412.13501%2C2412.14161%2C2412.14470%2C2412.16256%2C2412.17589%2C2412.18116%2C2412.18426%2C2412.19723%2C2501.01149%2C2501.04575%2C2501.07572%2C2501.11733%2C2501.12326%2C2501.13896%2C2501.16150%2C2502.01600%2C2502.01977%2C2502.02982%2C2502.06395%2C2502.07949%2C2502.08047%2C2502.08226%2C2502.11357%2C2502.13053%2C2502.13923%2C2502.14282%2C2502.18906%2C2503.00401%2C2503.02268%2C2503.03196%2C2503.04730%2C2503.05143%2C2503.06470%2C2503.09263%2C2503.11069%2C2503.11170%2C2503.12687%2C2503.15661%2C2503.15937%2C2503.16465&max_results=50"
    }
  ],
  "id": "url:342b081c3668a8bbe155",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-18T04:27:15Z",
  "licenses": {
    "code": null,
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://huggingface.co/datasets/mikewang/mobile_eval_e"
    }
  ],
  "name": "Mobile-Eval-E task definitions",
  "notes": "The public Hub manifest contains one test Parquet file. This resource is the benchmark’s task-definition package, not a bundled phone environment or agent. Card metadata supplies rubrics/reference-operation fields but no data-license declaration or verified automated scorer; the code repository’s MIT license is not transferred to these records.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/Mobile-Agent-E/README.md",
      "target_id": "arxiv:2501.11733",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Task definitions for Mobile-Agent-E’s long-horizon, multi-app Android evaluation, packaged as a 25-record test split with rubrics and human-reference operation strings.",
  "topics": [
    "evaluation",
    "long-horizon",
    "cross-app"
  ],
  "updated_at": null,
  "url": "https://huggingface.co/datasets/mikewang/mobile_eval_e"
}