{
  "aliases": [],
  "authors": [],
  "details": {
    "dataset_profile": {
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k/raw/main/README.md",
          "population": "default/train in the dataset card metadata",
          "qualifier": "exact",
          "unit": "training rows",
          "value": 701864
        }
      ],
      "evidence_urls": [
        "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k/raw/main/README.md"
      ],
      "formats": [],
      "modalities": [
        "screenshots",
        "instructions",
        "functionality labels",
        "bounding boxes"
      ],
      "notes": "Rows are not unique screenshots. The card documents image-downscaling conventions that affect coordinates; preserve the device and original image-size fields.",
      "splits": [
        "train"
      ],
      "supervision": [
        "element grounding",
        "functionality captioning"
      ]
    },
    "download_url": "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k/tree/main",
    "modalities": [
      "image",
      "text",
      "bounding-box"
    ],
    "sample_count": 701864,
    "sample_unit": "training rows reported in the dataset card"
  },
  "environments": [
    "web",
    "cross-platform"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T10:42:13Z",
      "role": "primary",
      "sha256": "c73b46acc2ff034a443fb8dbde327de1888535267199c9fb1819adf66898f1d7",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details.sample_count",
        "details.sample_unit",
        "details.modalities",
        "details.download_url",
        "details.dataset_profile"
      ],
      "url": "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k/raw/main/README.md"
    },
    {
      "method": "huggingface_card",
      "retrieved_at": "2026-10-16T10:42:13Z",
      "role": "primary",
      "sha256": "c73b46acc2ff034a443fb8dbde327de1888535267199c9fb1819adf66898f1d7",
      "supports": [
        "licenses.data"
      ],
      "url": "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k/raw/main/README.md"
    }
  ],
  "id": "url:79287058342289aa5d45",
  "identifiers": {},
  "kind": "dataset",
  "last_verified_at": "2026-10-16T10:42:13Z",
  "licenses": {
    "code": null,
    "data": {
      "basis": "publisher model/dataset card metadata; third-party assets retain their own terms",
      "declared": "cc-by-4.0",
      "retrieved_at": "2026-10-16T10:42:13Z",
      "url": "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k/raw/main/README.md"
    },
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k"
    }
  ],
  "name": "AutoGUI v1 training data",
  "notes": "The row count is not a unique-screen count. The data card documents image scaling conventions that affect coordinate interpretation.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k/raw/main/README.md",
      "target_id": "arxiv:2502.01977",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Screenshot-based grounding and captioning samples with UI functionality descriptions, target coordinates, and bounding boxes.",
  "topics": [
    "grounding",
    "screen-understanding"
  ],
  "updated_at": null,
  "url": "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k"
}