{
  "aliases": [],
  "authors": [],
  "details": {
    "availability": "Public evaluation harness and ungated web-application archive manifest.",
    "benchmark_protocol": {
      "actions": [
        "browser interaction",
        "test checklist generation",
        "defect reports"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/friedrichor/WebTestBench/HEAD/README.md",
          "population": "publisher benchmark overview",
          "qualifier": "exact",
          "unit": "application categories",
          "value": 7
        },
        {
          "basis": "computed",
          "evidence_url": "https://huggingface.co/api/datasets/friedrichor/WebTestBench",
          "population": "Hub file manifest",
          "qualifier": "exact",
          "unit": "web-application archives",
          "value": 100
        }
      ],
      "evaluation": "The supplied WebTester pipeline separates checklist generation from interactive defect detection and provides a scoring workflow.",
      "evidence_urls": [
        "https://raw.githubusercontent.com/friedrichor/WebTestBench/HEAD/README.md",
        "https://huggingface.co/api/datasets/friedrichor/WebTestBench",
        "https://huggingface.co/datasets/friedrichor/WebTestBench/raw/main/README.md"
      ],
      "focus": [
        "web functionality testing",
        "latent permission and business constraints"
      ],
      "notes": "The 100 archive files are not counted as 100 independent test tasks or defects. Backend/tool versions and deployment settings affect reproducibility.",
      "observations": [
        "web application interface",
        "development instruction"
      ],
      "setting": "interactive"
    },
    "license_review": {
      "code": {
        "evidence_urls": [
          "https://raw.githubusercontent.com/friedrichor/WebTestBench/HEAD/LICENSE"
        ],
        "reason": "Repository source LICENSE; external tools and services retain their own licenses."
      },
      "data": {
        "evidence_urls": [
          "https://huggingface.co/datasets/friedrichor/WebTestBench/raw/main/README.md"
        ],
        "reason": "Publisher Hub-card license declaration for the released benchmark dataset."
      }
    },
    "repository_revision": "04873065bdb0938ed53d809559d4ab473c7ccd31"
  },
  "environments": [
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T11:18:18Z",
      "role": "primary",
      "sha256": "b41472026cd7d4f81a01d58bf39193dc1fabc7875c61e370090a20cc77500cdd",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "notes",
        "relations",
        "details.benchmark_protocol"
      ],
      "url": "https://raw.githubusercontent.com/friedrichor/WebTestBench/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T11:18:18Z",
      "role": "primary",
      "sha256": "7203ecc2aae5f1697eeeb804ca8f21d47b9f22a8b8fa43a4064c4e1c49f5e72c",
      "supports": [
        "identity"
      ],
      "url": "https://api.github.com/repos/friedrichor/WebTestBench"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T11:22:55Z",
      "role": "primary",
      "sha256": "bd1f09149b00d59a0078d414216bd2fb78e09ce7212d15bbda84ddec7052c8af",
      "supports": [
        "release_status",
        "details.repository_revision"
      ],
      "url": "https://api.github.com/repos/friedrichor/WebTestBench/git/trees/main?recursive=1"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T11:23:08Z",
      "role": "primary",
      "sha256": "db1e97f40107038ae03835dc20f17b13b37e74b5c8587f8c39b441271618f017",
      "supports": [
        "identity",
        "release_status",
        "details.benchmark_protocol"
      ],
      "url": "https://huggingface.co/api/datasets/friedrichor/WebTestBench"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T11:23:08Z",
      "role": "primary",
      "sha256": "6f2f94a25ed66a14779f6b4e6686044d0510eb32a0187645cc473978d93f7c5b",
      "supports": [
        "licenses.data",
        "details.benchmark_protocol"
      ],
      "url": "https://huggingface.co/datasets/friedrichor/WebTestBench/raw/main/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T11:22:55Z",
      "role": "primary",
      "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/friedrichor/WebTestBench/HEAD/LICENSE"
    }
  ],
  "id": "github:friedrichor/webtestbench",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-17T11:18:18Z",
  "licenses": {
    "code": {
      "basis": "Repository source LICENSE; external tools and services retain their own licenses.",
      "declared": "Apache-2.0",
      "retrieved_at": "2026-10-17T11:22:55Z",
      "url": "https://raw.githubusercontent.com/friedrichor/WebTestBench/HEAD/LICENSE"
    },
    "data": {
      "basis": "Publisher Hub-card license declaration for the released benchmark dataset.",
      "declared": "apache-2.0",
      "retrieved_at": "2026-10-17T11:23:08Z",
      "url": "https://huggingface.co/datasets/friedrichor/WebTestBench/raw/main/README.md"
    },
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/friedrichor/WebTestBench"
    }
  ],
  "name": "WebTestBench",
  "notes": "Public evaluation/deployment scripts accompany an ungated Hub release with JSON/JSONL metadata and 100 application ZIP files. The ZIP count is an artifact inventory, not an asserted test-case or defect count. The documented baseline uses Claude Agent SDK and a pinned Playwright MCP version with external model credentials; these were not installed or run. Code and data Apache-2.0 declarations are retained separately.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/friedrichor/WebTestBench/HEAD/README.md",
      "target_id": "arxiv:2603.25226",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "An end-to-end web-testing benchmark where agents derive test checklists from development instructions, interact with deployed applications and report functional or constraint-related defects.",
  "topics": [
    "evaluation",
    "web-navigation",
    "tool-integration"
  ],
  "updated_at": null,
  "url": "https://github.com/friedrichor/WebTestBench"
}