{
  "aliases": [],
  "authors": [],
  "details": {
    "availability": "Public archived TFRecord annotation files for both downstream tasks.",
    "dataset_profile": {
      "counts": [],
      "evidence_urls": [
        "https://raw.githubusercontent.com/google-research-datasets/uibert/HEAD/README.md"
      ],
      "formats": [
        "TFRecord"
      ],
      "modalities": [
        "text",
        "bounding boxes",
        "UI hierarchy metadata",
        "Rico image identifiers"
      ],
      "notes": "Original UI images are retrieved separately by Rico IDs. No release-specific sample count is established.",
      "splits": [
        "AppSim train/dev/test",
        "RefExp train/dev/test"
      ],
      "supervision": [
        "similar UI element retrieval",
        "referring-expression component retrieval"
      ]
    },
    "license_review": {
      "data": {
        "evidence_urls": [
          "https://raw.githubusercontent.com/google-research-datasets/uibert/HEAD/README.md"
        ],
        "reason": "The README explicitly says the datasets are licensed under CC BY 4.0; original Rico materials keep their source terms."
      }
    },
    "repository_revision": "eceafbde7567959899bfb7f8d9e6fd71a52aaa12"
  },
  "environments": [
    "android"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T12:30:54Z",
      "role": "primary",
      "sha256": "45d1ca0f5c727cf58b2671dc5579f0628f4d78e07b977a5d8b018295c6fe1f58",
      "supports": [
        "name",
        "kind",
        "summary",
        "topics",
        "scope",
        "notes",
        "relations",
        "details.dataset_profile",
        "licenses.data"
      ],
      "url": "https://raw.githubusercontent.com/google-research-datasets/uibert/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T12:30:54Z",
      "role": "primary",
      "sha256": "24a7838d425bdae363a7d5872702996b22068c1f0e47be274fdfbc4b0e20144f",
      "supports": [
        "identity"
      ],
      "url": "https://api.github.com/repos/google-research-datasets/uibert"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T12:32:05Z",
      "role": "primary",
      "sha256": "9a6fc19c6b407309943fe645f4addb3d032f153856976c4f8d7a8cfb6d2ffe6b",
      "supports": [
        "release_status",
        "details.repository_revision"
      ],
      "url": "https://api.github.com/repos/google-research-datasets/uibert/git/trees/main?recursive=1"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T12:36:55Z",
      "role": "primary",
      "sha256": "f752ebfb2598b7f848d343f428502b28e0f591f27849ab707f14bee398d4eb8d",
      "supports": [
        "environments",
        "notes"
      ],
      "url": "https://interactionmining.org/rico"
    }
  ],
  "id": "github:google-research-datasets/uibert",
  "identifiers": {},
  "kind": "dataset",
  "last_verified_at": "2026-10-17T12:30:54Z",
  "licenses": {
    "code": null,
    "data": {
      "basis": "The README explicitly says the datasets are licensed under CC BY 4.0; original Rico materials keep their source terms.",
      "declared": "CC-BY-4.0",
      "retrieved_at": "2026-10-17T12:30:54Z",
      "url": "https://raw.githubusercontent.com/google-research-datasets/uibert/HEAD/README.md"
    },
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/google-research-datasets/uibert"
    }
  ],
  "name": "UIBert AppSim and RefExp annotations",
  "notes": "The archived repository retains TFRecord train/dev/test files for AppSim and RefExp. These are annotation and UI-structure records with Rico image identifiers, not a republished complete screenshot collection or a UIBert checkpoint. The README’s 72k figure describes the upstream Rico source, not the number of released AppSim/RefExp examples; no sample total is inferred. The publisher explicitly assigns CC-BY-4.0 to these datasets.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/google-research-datasets/uibert/HEAD/README.md",
      "target_id": "url:0b134b082a7bd507fc6a",
      "type": "uses"
    },
    {
      "evidence_url": "https://raw.githubusercontent.com/google-research-datasets/uibert/HEAD/README.md",
      "target_id": "arxiv:2107.13731",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Two Rico-derived UI component retrieval datasets: AppSim pairs semantically similar elements across screens, while RefExp links referring expressions to target elements.",
  "topics": [
    "grounding",
    "screen-understanding",
    "evaluation"
  ],
  "updated_at": null,
  "url": "https://github.com/google-research-datasets/uibert"
}