{
  "aliases": [],
  "authors": [],
  "details": {
    "availability": "Ungated mixture/post-training JSON and image-archive manifests; some per-domain images and training code remain pending.",
    "dataset_profile": {
      "counts": [],
      "evidence_urls": [
        "https://huggingface.co/datasets/hkust-nlp/GUIMid/raw/main/README.md",
        "https://raw.githubusercontent.com/hkust-nlp/GUIMid/HEAD/README.md"
      ],
      "formats": [
        "JSON",
        "tar.gz image archives"
      ],
      "modalities": [
        "text",
        "images"
      ],
      "notes": "Do not treat Hub size bands or the inconsistent introductory task count as a sample total. Some constituent-domain image packages remain forthcoming.",
      "splits": [
        "train configurations for named mid-training domains"
      ],
      "supervision": [
        "mid-training instruction supervision",
        "GUI post-training trajectories"
      ]
    },
    "gated": false,
    "hub_id": "hkust-nlp/GUIMid",
    "license_review": {
      "data": {
        "evidence_urls": [
          "https://huggingface.co/datasets/hkust-nlp/GUIMid/raw/main/README.md"
        ],
        "reason": "Publisher dataset-card declaration for the released packaging; original source datasets retain their own terms."
      }
    },
    "release_revision": "b6a360815c843b5733674191b6e6d7fa68b2ea8c"
  },
  "environments": [
    "web",
    "android"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T11:23:07Z",
      "role": "primary",
      "sha256": "1cdf702c819ecf370f4191c6c71fae7b579cfbaf766908b42156964a69eddacc",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "notes",
        "relations",
        "details.dataset_profile",
        "licenses.data"
      ],
      "url": "https://huggingface.co/datasets/hkust-nlp/GUIMid/raw/main/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T11:23:07Z",
      "role": "primary",
      "sha256": "ededa2b3c8f21af8188152b028758c800db76cdbb8461ba82b8574cab375914e",
      "supports": [
        "identity",
        "release_status",
        "details.hub_id",
        "details.gated",
        "details.release_revision"
      ],
      "url": "https://huggingface.co/api/datasets/hkust-nlp/GUIMid"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T11:18:19Z",
      "role": "primary",
      "sha256": "31b836da66c6907ff9a75ebc7f06da0db67e7d9fe9ca92d0c770f5f15f90a39e",
      "supports": [
        "identity"
      ],
      "url": "https://api.github.com/repos/hkust-nlp/GUIMid"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T11:18:19Z",
      "role": "primary",
      "sha256": "d9f63a03088c37f7145725c7a182100d1593fceadd26a9bf817d434ca8d6297e",
      "supports": [
        "notes",
        "relations"
      ],
      "url": "https://raw.githubusercontent.com/hkust-nlp/GUIMid/HEAD/README.md"
    }
  ],
  "id": "url:422010da7a5c845a18f6",
  "identifiers": {},
  "kind": "dataset",
  "last_verified_at": "2026-10-17T11:23:07Z",
  "licenses": {
    "code": null,
    "data": {
      "basis": "Publisher dataset-card declaration for the released packaging; original source datasets retain their own terms.",
      "declared": "mit",
      "retrieved_at": "2026-10-17T11:23:07Z",
      "url": "https://huggingface.co/datasets/hkust-nlp/GUIMid/raw/main/README.md"
    },
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://huggingface.co/datasets/hkust-nlp/GUIMid"
    }
  ],
  "name": "GUIMid training data",
  "notes": "The public manifest includes GUIMid.json, mavis.tar.gz, GUI_trajectory.json, traj.tar.gz and domain-specific JSON files. The card says image data for some individual domains is still forthcoming and its overview inconsistently says nine tasks while later enumerating seven vision-language plus four language-only domains; no aggregate task/sample count is inferred. Training code remains marked coming soon in the repository. MIT is the publisher dataset declaration, not a relicensing of all upstream content.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://huggingface.co/datasets/hkust-nlp/GUIMid/raw/main/README.md",
      "target_id": "arxiv:2504.10127",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "A released GUI-agent mid-training mixture and supporting domain datasets, together with a post-training trajectory file and image archives for web and mobile interaction.",
  "topics": [
    "imitation-learning",
    "planning",
    "screen-understanding"
  ],
  "updated_at": null,
  "url": "https://huggingface.co/datasets/hkust-nlp/GUIMid"
}