{
  "version": "v2",
  "generated_from": [
    "Phase 2B frozen observations v2",
    "Phase 3 frozen analysis v2"
  ],
  "license": {
    "name": "Creative Commons Attribution 4.0 International (CC BY 4.0)",
    "url": "https://creativecommons.org/licenses/by/4.0/",
    "scope": "searchDecoded's original and derived datasets published with this study",
    "exclusions": [
      "third-party robots.txt content and source material",
      "company names, logos and trademarks",
      "searchDecoded branding, website copy, design and other original creative assets"
    ],
    "suggested_attribution": "Source: searchDecoded, UK consumer AI crawler and content-use study 2026",
    "study_url": "https://searchdecoded.co.uk/research/uk-consumer-ai-crawler-study-2026/",
    "attribution_note": "The suggested wording is not the only valid form of attribution under CC BY 4.0."
  },
  "observation_fields": {
    "sample_id": "Public Phase 2B field: sample id",
    "sector": "Public Phase 2B field: sector",
    "consumer_brand": "Public Phase 2B field: consumer brand",
    "hostname": "Public Phase 2B field: hostname",
    "collection_timestamp": "Public Phase 2B field: collection timestamp",
    "robots_url": "Public Phase 2B field: robots url",
    "http_status": "Public Phase 2B field: http status",
    "final_robots_url": "Public Phase 2B field: final robots url",
    "robots_present": "Public Phase 2B field: robots present",
    "robots_fetch_status": "Public Phase 2B field: robots fetch status",
    "content_sha256": "Public Phase 2B field: content sha256",
    "content_length_bytes": "Public Phase 2B field: content length bytes",
    "content_type": "Public Phase 2B field: content type",
    "encoding_state": "Public Phase 2B field: encoding state",
    "crawler_registry_version": "Public Phase 2B field: crawler registry version",
    "classifier_version": "Public Phase 2B field: classifier version",
    "provider": "Public Phase 2B field: provider",
    "control_name": "Public Phase 2B field: control name",
    "user_agent_token": "Public Phase 2B field: user agent token",
    "control_type": "Public Phase 2B field: control type",
    "purpose_category": "Public Phase 2B field: purpose category",
    "included_in_primary_analysis": "Public Phase 2B field: included in primary analysis",
    "agent_explicitly_named": "Public Phase 2B field: agent explicitly named",
    "applicable_group_source": "Public Phase 2B field: applicable group source",
    "effective_access_state": "Public Phase 2B field: effective access state",
    "classification": "Public Phase 2B field: classification",
    "review_state": "Public Phase 2B field: review state"
  },
  "site_file": "One row per frozen cohort site with Phase 3 governance fields."
}