{
  "aliases": [
    "url:f4bcd696942ee04dcc42",
    "bevaya/ScreenSpot",
    "https://huggingface.co/datasets/bevaya/ScreenSpot"
  ],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "predicted click point; a predicted box is reduced to its center"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://huggingface.co/datasets/bevaya/ScreenSpot/raw/0be08781e2e188582f6131625ae1598d443b4d5d/README.md",
          "population": "Hub test split at 0be08781; not unique screenshots",
          "qualifier": "exact",
          "unit": "instruction–target examples",
          "value": 1272
        }
      ],
      "evaluation": "The SeeClick evaluator scores whether the predicted point falls inside the target box, with platform and text/icon breakdowns. The Hub packaging uses xyxy boxes, whereas the original evaluator reads xywh and converts it; adapt the loader to the chosen release.",
      "evidence_urls": [
        "https://huggingface.co/datasets/bevaya/ScreenSpot/raw/0be08781e2e188582f6131625ae1598d443b4d5d/README.md",
        "https://huggingface.co/api/datasets/rootsautomation/ScreenSpot",
        "https://raw.githubusercontent.com/njucckevin/SeeClick/HEAD/pretrain/screenspot_test.py"
      ],
      "focus": [
        "single-step GUI element grounding"
      ],
      "notes": "Offline, zero-shot evaluation across mobile, desktop, and web. The card explicitly excludes training use in its intended-use description. Public API reports ungated Parquet files and canonical Hub id bevaya/ScreenSpot; the catalog identity is preserved. Apache-2.0 is the Hub data declaration. No runtime or underlying screenshot rights audit was performed.",
      "observations": [
        "screenshot",
        "English instruction"
      ],
      "setting": "offline"
    },
    "disabled": false,
    "download_url": "https://huggingface.co/datasets/rootsautomation/ScreenSpot/tree/main",
    "gated": false,
    "hub_id": "bevaya/ScreenSpot",
    "languages": [
      "en"
    ],
    "modalities": [
      "image",
      "text"
    ],
    "size_category_reported": null
  },
  "environments": [
    "cross-platform"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:38:26Z",
      "role": "primary",
      "sha256": "9e2d2a2c076032225911ae1032b548eafa6331ea81a2779632610f0f1c82dfd9",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details.benchmark_protocol"
      ],
      "url": "https://huggingface.co/api/datasets/rootsautomation/ScreenSpot"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T14:10:00Z",
      "role": "primary",
      "sha256": "5ab2240c064502f75a6726311e10e7724ab7055347697f883b15a6ee8e7d00a6",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://huggingface.co/datasets/bevaya/ScreenSpot/raw/0be08781e2e188582f6131625ae1598d443b4d5d/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T14:22:04Z",
      "role": "primary",
      "sha256": "eb72113eefd4868114f8a8105eba2d3385da9034a5b3a4860661e03ae7dcae15",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://raw.githubusercontent.com/njucckevin/SeeClick/HEAD/pretrain/screenspot_test.py"
    },
    {
      "method": "huggingface_api",
      "retrieved_at": "2026-10-16T06:38:26Z",
      "role": "primary",
      "sha256": "9e2d2a2c076032225911ae1032b548eafa6331ea81a2779632610f0f1c82dfd9",
      "supports": [
        "details",
        "licenses.data"
      ],
      "url": "https://huggingface.co/api/datasets/rootsautomation/ScreenSpot"
    },
    {
      "method": "huggingface_repository_identity",
      "retrieved_at": "2026-10-17T19:14:56Z",
      "role": "primary",
      "sha256": "af0c4babeff84158ff196b54bf47242923bbf502d2805a1dd4eb52dba44be89c",
      "supports": [
        "aliases"
      ],
      "url": "https://huggingface.co/api/datasets/bevaya/ScreenSpot"
    },
    {
      "method": "huggingface_repository_identity",
      "retrieved_at": "2026-10-17T19:14:56Z",
      "role": "primary",
      "sha256": "af0c4babeff84158ff196b54bf47242923bbf502d2805a1dd4eb52dba44be89c",
      "supports": [
        "aliases"
      ],
      "url": "https://huggingface.co/api/datasets/rootsautomation/ScreenSpot"
    }
  ],
  "id": "url:7abb418096432f56c685",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-16T06:38:26Z",
  "licenses": {
    "code": null,
    "data": {
      "basis": "publisher model/dataset card",
      "declared": "apache-2.0",
      "retrieved_at": "2026-10-16T06:38:26Z",
      "url": "https://huggingface.co/datasets/rootsautomation/ScreenSpot"
    },
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://huggingface.co/datasets/rootsautomation/ScreenSpot"
    }
  ],
  "name": "ScreenSpot",
  "notes": "",
  "published_at": null,
  "relations": [],
  "review_status": "curated",
  "scope": "core",
  "summary": "GUI grounding test set of 1,272 screenshot instructions from iOS, Android, macOS, Windows and web interfaces, each labeled with the target element's bounding box.",
  "topics": [
    "grounding",
    "evaluation"
  ],
  "updated_at": null,
  "url": "https://huggingface.co/datasets/rootsautomation/ScreenSpot"
}