{
  "aliases": [],
  "authors": [],
  "details": {
    "dataset_profile": {
      "counts": [],
      "evidence_urls": [
        "https://huggingface.co/datasets/xlangai/aguvis-stage2/raw/main/README.md",
        "https://huggingface.co/api/datasets/xlangai/aguvis-stage2",
        "https://raw.githubusercontent.com/xlang-ai/aguvis/HEAD/README.md",
        "https://raw.githubusercontent.com/xlang-ai/aguvis/HEAD/data/stage2.yaml"
      ],
      "formats": [
        "JSON annotations",
        "ZIP image packages",
        "multipart TAR image packages"
      ],
      "modalities": [
        "GUI screenshots",
        "natural-language instructions",
        "action trajectories"
      ],
      "notes": "Stage 2 trajectory release, Hub revision bd6f1ed4, is distinct from Stage 1 grounding. The public manifest lists source-specific JSON levels and image ZIP/multipart TAR packages. The training recipe uses all rows for some inputs and random:33% for others; several l2 paths occur twice while the manifest also contains l3 files. Recipe rows/levels are neither independent datasets nor disjoint train/test splits. No example/action/trajectory count is inferred. Apache-2.0 is the card declaration, with separate underlying source terms.",
      "splits": [
        "training"
      ],
      "supervision": [
        "GUI trajectory supervised fine-tuning",
        "planning and reasoning with inner monologue"
      ]
    },
    "disabled": false,
    "download_url": "https://huggingface.co/datasets/xlangai/aguvis-stage2/tree/main",
    "gated": false,
    "hub_id": "xlangai/aguvis-stage2"
  },
  "environments": [
    "cross-platform"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T02:03:33Z",
      "role": "primary",
      "sha256": "550293f00905615e19e63ac896818f9875dad38fea0ffe196c6302a29719aa72",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details",
        "details.dataset_profile"
      ],
      "url": "https://huggingface.co/datasets/xlangai/aguvis-stage2/raw/main/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T02:03:33Z",
      "role": "primary",
      "sha256": "f030264a7a8c7485dc7cf15ca554d84450cc492d2ac90e5965810a0207ef370b",
      "supports": [
        "identity",
        "release_status",
        "details",
        "licenses.data",
        "details.dataset_profile"
      ],
      "url": "https://huggingface.co/api/datasets/xlangai/aguvis-stage2"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:36:00Z",
      "role": "primary",
      "sha256": "2dd9f36b818c1b7b6bd772ba8575f6c0ebab6d9e0d307edcc2f196f3e4ba502e",
      "supports": [
        "environments",
        "summary",
        "details.dataset_profile"
      ],
      "url": "https://raw.githubusercontent.com/xlang-ai/aguvis/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T14:21:11Z",
      "role": "primary",
      "sha256": "8c1b39e9d16067018ce845fd4e996f34e2b47346c342b2ba26b030f4a5338b66",
      "supports": [
        "details.dataset_profile"
      ],
      "url": "https://raw.githubusercontent.com/xlang-ai/aguvis/HEAD/data/stage2.yaml"
    },
    {
      "method": "huggingface_card",
      "retrieved_at": "2026-10-17T02:03:33Z",
      "role": "primary",
      "sha256": "550293f00905615e19e63ac896818f9875dad38fea0ffe196c6302a29719aa72",
      "supports": [
        "licenses.data"
      ],
      "url": "https://huggingface.co/datasets/xlangai/aguvis-stage2/raw/main/README.md"
    }
  ],
  "id": "url:b5e2127e07f692d516b9",
  "identifiers": {},
  "kind": "dataset",
  "last_verified_at": "2026-10-17T02:03:33Z",
  "licenses": {
    "code": null,
    "data": {
      "basis": "publisher model/dataset card metadata; third-party assets retain their own terms",
      "declared": "apache-2.0",
      "retrieved_at": "2026-10-17T02:03:33Z",
      "url": "https://huggingface.co/datasets/xlangai/aguvis-stage2/raw/main/README.md"
    },
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://huggingface.co/datasets/xlangai/aguvis-stage2"
    }
  ],
  "name": "Aguvis stage 2 trajectory data",
  "notes": "The manifest contains trajectory annotations and archives associated with mobile, desktop and web sources. The card declares Apache-2.0; underlying source content may retain separate terms. This stage has a different training purpose and files from the grounding release. No archive or training sample was downloaded.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://huggingface.co/datasets/xlangai/aguvis-stage2/raw/main/README.md",
      "target_id": "arxiv:2412.04454",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "The second-stage Aguvis collection of interface trajectories for learning action sequences, planning and reasoning after grounding pretraining.",
  "topics": [
    "planning",
    "data-generation"
  ],
  "updated_at": null,
  "url": "https://huggingface.co/datasets/xlangai/aguvis-stage2"
}