{
  "entity_a": {
    "slug": "claudebot",
    "name": "ClaudeBot"
  },
  "entity_b": {
    "slug": "google-extended",
    "name": "Google-Extended"
  },
  "fields_documented": 14,
  "claims": 20,
  "last_verified": "2026-09-15",
  "fields": [
    {
      "field": "anti_circumvention_stance",
      "value_a": "documented",
      "value_b": null,
      "claim_id_a": 53,
      "claim_id_b": null,
      "same": false
    },
    {
      "field": "honours_crawl_delay",
      "value_a": "yes",
      "value_b": "n/a",
      "claim_id_a": 48,
      "claim_id_b": 56,
      "same": false
    },
    {
      "field": "observed_fetches_json",
      "value_a": "yes",
      "value_b": null,
      "claim_id_a": 143,
      "claim_id_b": null,
      "same": false
    },
    {
      "field": "observed_fetches_markdown",
      "value_a": "yes",
      "value_b": null,
      "claim_id_a": 142,
      "claim_id_b": null,
      "same": false
    },
    {
      "field": "observed_first_request_path",
      "value_a": "/sitemap.xml",
      "value_b": null,
      "claim_id_a": 144,
      "claim_id_b": null,
      "same": false
    },
    {
      "field": "observed_format_pass_order",
      "value_a": "html_json_md",
      "value_b": null,
      "claim_id_a": 145,
      "claim_id_b": null,
      "same": false
    },
    {
      "field": "publishes_ip_list",
      "value_a": "yes",
      "value_b": "no",
      "claim_id_a": 49,
      "claim_id_b": 57,
      "same": false
    },
    {
      "field": "purpose_documented",
      "value_a": "training",
      "value_b": "policy_only",
      "claim_id_a": 51,
      "claim_id_b": 59,
      "same": false
    },
    {
      "field": "respects_robots_txt",
      "value_a": "yes",
      "value_b": "n/a",
      "claim_id_a": 47,
      "claim_id_b": 55,
      "same": false
    },
    {
      "field": "robots_token_differs_from_ua",
      "value_a": null,
      "value_b": "yes",
      "claim_id_a": null,
      "claim_id_b": 62,
      "same": false
    },
    {
      "field": "separate_search_and_training_tokens",
      "value_a": "yes",
      "value_b": "yes",
      "claim_id_a": 52,
      "claim_id_b": 60,
      "same": true
    },
    {
      "field": "user_agent_string_full",
      "value_a": "not_documented",
      "value_b": null,
      "claim_id_a": 54,
      "claim_id_b": null,
      "same": false
    },
    {
      "field": "verifiable_by_rdns",
      "value_a": "not_documented",
      "value_b": "n/a",
      "claim_id_a": 50,
      "claim_id_b": 58,
      "same": false
    },
    {
      "field": "what_it_controls",
      "value_a": null,
      "value_b": "Gemini model training and grounding, not Search inclusion",
      "claim_id_a": null,
      "claim_id_b": 61,
      "same": false
    }
  ],
  "differences": [
    {
      "field": "anti_circumvention_stance",
      "statement_a": "ClaudeBot respects anti-circumvention technologies and does not bypass CAPTCHAs on crawled sites.",
      "statement_b": null,
      "claim_id_a": 53,
      "claim_id_b": null
    },
    {
      "field": "honours_crawl_delay",
      "statement_a": "Anthropic supports the non-standard robots.txt Crawl-delay extension for ClaudeBot.",
      "statement_b": "Google does not publish any Crawl-delay behaviour for the Google-Extended token.",
      "claim_id_a": 48,
      "claim_id_b": 56
    },
    {
      "field": "observed_fetches_json",
      "statement_a": "ClaudeBot made 177 JSON requests to Rattlesnakes By Mail between 2026-09-13T20:00Z and 2026-09-15T09:00Z, covering the .json twin of 170 base paths. The .json URLs of Rattlesnakes By Mail appear in no entry of the 171 URL sitemap.",
      "statement_b": null,
      "claim_id_a": 143,
      "claim_id_b": null
    },
    {
      "field": "observed_fetches_markdown",
      "statement_a": "ClaudeBot fetched the .md twin of 170 base paths on Rattlesnakes By Mail between 2026-09-13T20:00Z and 2026-09-15T09:00Z, 170 Markdown requests of 542 ClaudeBot requests in that window. The .md URLs of Rattlesnakes By Mail appear in no entry of the 171 URL sitemap.",
      "statement_b": null,
      "claim_id_a": 142,
      "claim_id_b": null
    },
    {
      "field": "observed_first_request_path",
      "statement_a": "ClaudeBot's first request to Rattlesnakes By Mail between 2026-09-13T20:00Z and 2026-09-15T09:00Z was /sitemap.xml at 2026-09-14T19:53:45Z. ClaudeBot fetched /robots.txt on the second request to Rattlesnakes By Mail.",
      "statement_b": null,
      "claim_id_a": 144,
      "claim_id_b": null
    },
    {
      "field": "observed_format_pass_order",
      "statement_a": "ClaudeBot fetched Rattlesnakes By Mail in three format passes between 2026-09-13T20:00Z and 2026-09-15T09:00Z, HTML from 2026-09-14T20:52Z to 2026-09-14T20:57Z, then JSON from 2026-09-14T21:37Z to 2026-09-14T21:56Z, then Markdown from 2026-09-14T21:37Z to 2026-09-14T21:57Z. The same order holds on 170 of 170 base paths that ClaudeBot fetched in all three formats on Rattlesnakes By Mail.",
      "statement_b": null,
      "claim_id_a": 145,
      "claim_id_b": null
    },
    {
      "field": "publishes_ip_list",
      "statement_a": "Anthropic publishes the IP address ranges used by ClaudeBot as a JSON file at https://claude.com/crawling/bots.json.",
      "statement_b": "Google publishes no IP list for Google-Extended because Google-Extended has no separate HTTP request user agent string.",
      "claim_id_a": 49,
      "claim_id_b": 57
    },
    {
      "field": "purpose_documented",
      "statement_a": "ClaudeBot collects web content for training Anthropic generative AI models.",
      "statement_b": "Google-Extended is a standalone product token that controls whether Google uses crawled content to train Gemini models.",
      "claim_id_a": 51,
      "claim_id_b": 59
    },
    {
      "field": "respects_robots_txt",
      "statement_a": "ClaudeBot honours industry standard robots.txt directives that signal do not crawl.",
      "statement_b": "Google-Extended is a robots.txt token that publishers set to control use of crawled content for Gemini training.",
      "claim_id_a": 47,
      "claim_id_b": 55
    },
    {
      "field": "robots_token_differs_from_ua",
      "statement_a": null,
      "statement_b": "Google-Extended is a robots.txt control token and does not correspond to a crawler user agent string.",
      "claim_id_a": null,
      "claim_id_b": 62
    },
    {
      "field": "user_agent_string_full",
      "statement_a": "Anthropic does not publish a full user agent string for ClaudeBot.",
      "statement_b": null,
      "claim_id_a": 54,
      "claim_id_b": null
    },
    {
      "field": "verifiable_by_rdns",
      "statement_a": "Anthropic does not publish a reverse-DNS verification method for ClaudeBot.",
      "statement_b": "Google does not publish a reverse-DNS verification method for Google-Extended.",
      "claim_id_a": 50,
      "claim_id_b": 58
    },
    {
      "field": "what_it_controls",
      "statement_a": null,
      "statement_b": "Google-Extended controls AI training and grounding in Google systems and does not control Google Search inclusion.",
      "claim_id_a": null,
      "claim_id_b": 61
    }
  ],
  "sources": [
    "https://claude.com/crawling/bots.json",
    "https://developers.google.com/search/docs/appearance/ai-features",
    "https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers",
    "https://rattlesnakesbymail.com/observed/claudebot",
    "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-content-from-the-web-and-how-can-site-owners-block-the-crawler"
  ]
}