{
  "aliases": [],
  "authors": [],
  "details": {
    "dataset_profile": {
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_preference_pair/raw/main/README.md",
          "population": "Hub split named test",
          "qualifier": "exact",
          "unit": "rows",
          "value": 9460
        }
      ],
      "evidence_urls": [
        "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_preference_pair/raw/main/README.md",
        "https://raw.githubusercontent.com/kyle8581/Web-Shepherd/HEAD/README.md"
      ],
      "formats": [
        "Parquet"
      ],
      "modalities": [
        "screenshots",
        "text",
        "action history"
      ],
      "notes": "Preserves the publisher’s split label despite the collection’s training purpose. Rows are not individual preference pairs because rejected is a list. Data license is unknown.",
      "splits": [
        "test"
      ],
      "supervision": [
        "preferred and rejected continuations",
        "task checklists"
      ]
    },
    "disabled": false,
    "download_url": "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_preference_pair/tree/main",
    "gated": false,
    "hub_id": "LangAGI-Lab/WebPRMCollection_preference_pair"
  },
  "environments": [
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T02:44:50Z",
      "role": "primary",
      "sha256": "9c091c5fc625ce53f53f8262f5cee8d08194e4fd1b8eeed543ff1c3723c823fd",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details"
      ],
      "url": "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_preference_pair/raw/main/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T02:44:50Z",
      "role": "primary",
      "sha256": "28a1d5d12e84fc38515bd3c5031ae0cf315c5f8772b90d982d926b98f2857563",
      "supports": [
        "identity",
        "release_status",
        "details",
        "licenses.data"
      ],
      "url": "https://huggingface.co/api/datasets/LangAGI-Lab/WebPRMCollection_preference_pair"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T02:44:04Z",
      "role": "primary",
      "sha256": "07431058d8b9a71b80e75b7a74a40a8346c1503eec240628459cc4d4e2f0802f",
      "supports": [
        "summary",
        "environments"
      ],
      "url": "https://raw.githubusercontent.com/kyle8581/Web-Shepherd/HEAD/README.md"
    }
  ],
  "id": "url:8dfc84eb4016204fe70a",
  "identifiers": {},
  "kind": "dataset",
  "last_verified_at": "2026-10-17T02:44:50Z",
  "licenses": {
    "code": null,
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_preference_pair"
    }
  ],
  "name": "WebPRM Collection preference data",
  "notes": "Ten public Parquet shards are present. The card names its split test and reports 9,460 rows; the project’s 40K-plus preference-annotation claim is a different grain and is not substituted for this row count. A row can contain multiple rejected alternatives. No data-license declaration is present.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_preference_pair/raw/main/README.md",
      "target_id": "arxiv:2505.15277",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Checklist-annotated web decision records with page observations, prior actions, one preferred continuation and rejected alternatives for process-reward learning.",
  "topics": [
    "web-navigation",
    "reward-models",
    "evaluation"
  ],
  "updated_at": null,
  "url": "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_preference_pair"
}