{
  "id": "test-set:webarena-v1",
  "_kind": "TestSet",
  "_file": "benchmarks/test-sets/source-backed-benchmark-test-sets.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "displayName": "WebArena v1 task suite",
    "benchmarkId": "benchmark:webarena",
    "caseCount": 812,
    "releasedAt": "2023-07-26",
    "composition": "WebArena's original long-horizon web task suite over realistic\nself-hosted sites for shopping, forum, GitLab-style collaboration,\nand content management workflows.\n",
    "homepageUrl": "https://webarena.dev/static/paper.pdf",
    "description": "Canonical WebArena task artifact for autonomous web-agent evaluation.\n"
  },
  "outgoingEdges": [
    {
      "from": "test-set:webarena-v1",
      "to": "benchmark:webarena",
      "kind": "belongs_to_benchmark"
    }
  ],
  "incomingEdges": []
}