{
  "aliases": [],
  "authors": [],
  "details": {
    "availability": "Public task definitions, execution harness and an ungated VM-file manifest.",
    "benchmark_protocol": {
      "actions": [
        "actions executed by the OSWorld-derived DesktopEnv"
      ],
      "counts": [
        {
          "basis": "computed",
          "evidence_url": "https://raw.githubusercontent.com/OS-Copilot/OS-Map/HEAD/evaluation_examples/all.json",
          "population": "evaluation_examples/all.json",
          "qualifier": "exact",
          "unit": "category/task references",
          "value": 416
        }
      ],
      "evaluation": "Task configurations provide evaluators for application/system state, using an OSWorld-derived runtime.",
      "evidence_urls": [
        "https://raw.githubusercontent.com/OS-Copilot/OS-Map/HEAD/README.md",
        "https://raw.githubusercontent.com/OS-Copilot/OS-Map/HEAD/evaluation_examples/all.json",
        "https://raw.githubusercontent.com/OS-Copilot/OS-Map/HEAD/evaluation_examples/README.md"
      ],
      "focus": [
        "breadth of desktop task coverage",
        "depth of desktop task execution"
      ],
      "notes": "416 category/task pairs are unique, but only 412 bare ID strings are unique across categories. This is a manifest-reference count, not a claim of 416 semantically distinct tasks. Main runtime documentation specifies Ubuntu; the subdirectory README retains older Windows-only wording.",
      "observations": [
        "desktop observations from an Ubuntu virtual machine"
      ],
      "setting": "interactive"
    },
    "license_review": {
      "code": {
        "evidence_urls": [
          "https://raw.githubusercontent.com/OS-Copilot/OS-Map/HEAD/LICENSE"
        ],
        "reason": "Repository code LICENSE; no license is inferred for the VM image or bundled third-party applications."
      }
    },
    "repository_revision": "191efd0e6766acab444a31685b437565e1a94ac2"
  },
  "environments": [
    "desktop",
    "linux"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:12:14Z",
      "role": "primary",
      "sha256": "fc9f3c8d9fffdff8b51e312b013be0d9fdfc10e57fdc2ec4a8a8d012c4b42475",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "notes",
        "relations",
        "details"
      ],
      "url": "https://raw.githubusercontent.com/OS-Copilot/OS-Map/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:12:14Z",
      "role": "primary",
      "sha256": "d6c91b4910e92f40cc694b4cb6467c1a20f42c0c14047b95a1e777aca0892677",
      "supports": [
        "identity"
      ],
      "url": "https://api.github.com/repos/OS-Copilot/OS-Map"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:14:07Z",
      "role": "primary",
      "sha256": "41342157c53f28ad2729137491930225ac11da922e7b16762e84ac958a2e9d28",
      "supports": [
        "release_status"
      ],
      "url": "https://api.github.com/repos/OS-Copilot/OS-Map/git/trees/main?recursive=1"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:14:07Z",
      "role": "primary",
      "sha256": "1dd924135cbf0a85ce72d75025259adb7b849970d400af4ed854327a34e7ee41",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/OS-Copilot/OS-Map/HEAD/LICENSE"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:17:22Z",
      "role": "primary",
      "sha256": "4199af4c8bc60451079d8a2e7598ab7386bd82b0d5c9ad7e6927d6cb8e03ad6f",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://raw.githubusercontent.com/OS-Copilot/OS-Map/HEAD/evaluation_examples/all.json"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:17:22Z",
      "role": "primary",
      "sha256": "a6b60d5721cfdd26416e7d0ae3192360896427a97ccb3793812cc150e9cd7126",
      "supports": [
        "details.benchmark_protocol",
        "notes"
      ],
      "url": "https://raw.githubusercontent.com/OS-Copilot/OS-Map/HEAD/evaluation_examples/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:14:16Z",
      "role": "primary",
      "sha256": "d2da837872b123f2927a069a020aeb14fb4b22148599c9f2e8b6689ee444ec88",
      "supports": [
        "release_status",
        "details"
      ],
      "url": "https://huggingface.co/api/datasets/os-map/OSMAP"
    }
  ],
  "id": "github:os-copilot/os-map",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-17T09:12:14Z",
  "licenses": {
    "code": {
      "basis": "Repository code LICENSE; no license is inferred for the VM image or bundled third-party applications.",
      "declared": "MIT",
      "retrieved_at": "2026-10-17T09:14:07Z",
      "url": "https://raw.githubusercontent.com/OS-Copilot/OS-Map/HEAD/LICENSE"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/OS-Copilot/OS-Map"
    }
  ],
  "name": "OS-Map",
  "notes": "Public task manifests, agent runner and evaluator code are present, and the linked ungated Hub manifest lists Ubuntu0.zip and task files. The main setup supports x86 VMware Workstation and says ARM/Docker alternatives are still in development. An inherited evaluation-examples README still mentions Windows 10 and under-construction status; those statements are retained as a documentation inconsistency, not interpreted as verified Windows support. The manifest has 416 category/task references but 412 globally distinct ID strings.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/OS-Copilot/OS-Map/HEAD/README.md",
      "target_id": "github:xlang-ai/osworld",
      "type": "uses"
    },
    {
      "evidence_url": "https://raw.githubusercontent.com/OS-Copilot/OS-Map/HEAD/README.md",
      "target_id": "arxiv:2507.19132",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "An OSWorld-derived desktop benchmark with an Ubuntu virtual-machine environment and expanded task configurations for measuring breadth and depth of computer interaction.",
  "topics": [
    "evaluation",
    "long-horizon",
    "cross-app"
  ],
  "updated_at": null,
  "url": "https://github.com/OS-Copilot/OS-Map"
}