{
  "aliases": [],
  "authors": [],
  "details": {
    "dataset_profile": {
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md",
          "population": "WebSRC v1.0 train",
          "qualifier": "exact",
          "unit": "question–answer examples",
          "value": 307315
        },
        {
          "basis": "reported",
          "evidence_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md",
          "population": "WebSRC v1.0 train",
          "qualifier": "exact",
          "unit": "web pages",
          "value": 4549
        },
        {
          "basis": "reported",
          "evidence_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md",
          "population": "WebSRC v1.0 dev",
          "qualifier": "exact",
          "unit": "question–answer examples",
          "value": 52826
        },
        {
          "basis": "reported",
          "evidence_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md",
          "population": "WebSRC v1.0 dev",
          "qualifier": "exact",
          "unit": "web pages",
          "value": 913
        },
        {
          "basis": "reported",
          "evidence_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md",
          "population": "WebSRC v1.0 test",
          "qualifier": "exact",
          "unit": "question–answer examples",
          "value": 40357
        },
        {
          "basis": "reported",
          "evidence_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md",
          "population": "WebSRC v1.0 test",
          "qualifier": "exact",
          "unit": "web pages",
          "value": 985
        }
      ],
      "evidence_urls": [
        "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md",
        "https://huggingface.co/api/datasets/X-LANCE/WebSRC_v1.0",
        "https://x-lance.github.io/WebSRC/"
      ],
      "formats": [
        "CSV",
        "HTML",
        "JSON",
        "ZIP packages"
      ],
      "modalities": [
        "questions and answers",
        "HTML",
        "screenshots",
        "layout metadata"
      ],
      "notes": "Each dataset.csv row is a QA example; web pages and QA examples are different units. Use the v1.0 split table rather than merging the older project headline into it. The card retains email-evaluation instructions, while the manifest now includes test answers; no submission was made. Payload archives were not downloaded.",
      "splits": [
        "train",
        "dev",
        "test"
      ],
      "supervision": [
        "extractive or yes/no answers",
        "answer DOM-element references"
      ]
    },
    "disabled": false,
    "download_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/tree/7aa0bc6efc7ef43f68c192e2091108541acbaf1a",
    "gated": false,
    "hub_id": "X-LANCE/WebSRC_v1.0",
    "hub_revision": "7aa0bc6efc7ef43f68c192e2091108541acbaf1a",
    "license_review": {
      "data": {
        "evidence_urls": [
          "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md"
        ],
        "reason": "Publisher dataset-card declaration for this release; it does not establish rights to all upstream screenshots, applications or source content."
      }
    }
  },
  "environments": [
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-18T04:35:16Z",
      "role": "primary",
      "sha256": "061e5bcaa49e819f0133afb912ad5ce20a8c2b6c28ca60319a4635d6ce835ddb",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "notes",
        "relations",
        "licenses.data",
        "details.dataset_profile"
      ],
      "url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-18T04:33:29Z",
      "role": "primary",
      "sha256": "a7976dd931c3fcf11de2456614f95eb071978599bd70fb89c0ea009d31da4300",
      "supports": [
        "identity",
        "release_status",
        "details.hub_id",
        "details.hub_revision",
        "details.gated",
        "details.disabled",
        "details.download_url",
        "details.dataset_profile"
      ],
      "url": "https://huggingface.co/api/datasets/X-LANCE/WebSRC_v1.0"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T15:37:04Z",
      "role": "primary",
      "sha256": "3c2c601d8b4ad2f379cac9b97a2cbb901883d9bc6c1a682359f9b4135e6dd4bc",
      "supports": [
        "notes",
        "details.dataset_profile"
      ],
      "url": "https://x-lance.github.io/WebSRC/"
    }
  ],
  "id": "url:e0ba328ae1a643b0a5aa",
  "identifiers": {},
  "kind": "dataset",
  "last_verified_at": "2026-10-18T04:35:16Z",
  "licenses": {
    "code": null,
    "data": {
      "basis": "Publisher dataset-card declaration for this release; it does not establish rights to all upstream screenshots, applications or source content.",
      "declared": "CC-BY-4.0",
      "retrieved_at": "2026-10-18T04:35:16Z",
      "url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md"
    },
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0"
    }
  ],
  "name": "WebSRC v1.0",
  "notes": "Public release includes train+dev and test ZIP packages plus a test-answer JSON file. The v1.0 card’s exact split table differs from the older project-page headline of 0.44M questions/6.5K pages; counts are kept with their sources. This is static webpage understanding, not an interactive browser-agent trajectory dataset. CC-BY-4.0 is the data-card declaration.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md",
      "target_id": "arxiv:2101.09465",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "adjacent",
  "summary": "Webpage segments, questions, answers, HTML, screenshots and layout metadata for structural reading comprehension.",
  "topics": [
    "screen-understanding",
    "grounding"
  ],
  "updated_at": null,
  "url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0"
}