{
  "schema_version": "1.0",
  "title": "AI Opt-out Signals: Who Honors What",
  "canonical_url": "https://bozos.si/reference/ai-optout-signals",
  "data_url": "https://bozos.si/ai-optout-signals.json",
  "updated": "2026-10-20",
  "license": "CC0-1.0",
  "feedback": {
    "contact": "https://bozos.si/contact",
    "email": "mailto:bozos@bozos.si",
    "subject": "[BOZOS agent] correction: ai-optout-signals-data - <summary> [via:dataset]",
    "corrections_log": "https://bozos.si/corrections.json"
  },
  "record_access": {
    "collections": [
      "signals",
      "operators"
    ],
    "permalink": "https://bozos.si/ai-optout-signals.json#{id}",
    "resolve": "https://bozos.si/ai-optout-signals.json?id={id}",
    "changes": "https://bozos.si/api/v1/changes?dataset=ai-optout-signals-data&since={YYYY-MM-DD}",
    "review_policy": "Each record is re-checked against its sources every 90 days; review_due is the date that is next due. GET /api/v1/health lists overdue records.",
    "note": "Every record has a permanent id, a permalink, and a cite line: a sentence built only from the record's own fields, with its date and permalink, that can be quoted verbatim. Fetch the resolve URL to get one record; ids are never reused."
  },
  "scope_note": "For each AI and search operator in the BOZOS crawler directory, whether its own documentation says it honors each machine-readable opt-out or preference signal. honors cells quote the operator. not-stated means the operator's pages listed in searched do not mention the signal at all; it is not evidence that the signal is ignored. Observed behavior is out of scope here; see the crawler directory's docs_vs_reports.",
  "editorial_rule": "Record what the operator states, scoped to the pages checked. A signal's own specification is quoted for what it is, never as proof that anyone honors it.",
  "stance_values": {
    "honors": "The operator's documentation says it honors the signal, for the scope given.",
    "not-stated": "The pages checked do not mention the signal. The search terms and pages are listed so the absence can be re-checked.",
    "not-applicable": "The operator says it does not do the thing the signal controls (for example, it says it does not train on crawled content).",
    "unknown": "The operator's documentation cannot be read by a script, so neither a statement nor its absence could be verified."
  },
  "not_included": [
    {
      "id": "ai-txt",
      "name": "ai.txt (Spawning)",
      "reason": "The publisher's site was under maintenance on 2026-10-20, so its specification could not be read and quoted."
    },
    {
      "id": "llms-txt",
      "name": "llms.txt",
      "reason": "A guide for language models, not an opt-out or preference signal."
    }
  ],
  "signals": [
    {
      "id": "robots-txt-training-optout",
      "permalink": "https://bozos.si/ai-optout-signals.json#robots-txt-training-optout",
      "cite": "robots.txt opt-out from AI training (ietf-standard, IETF (RFC 9309) plus each operator's own user-agent token): Whether a named crawler may fetch a path. Operators decide what blocking their token means; some offer a token only for AI training, or a control token that changes how already-crawled data is used. Source: BOZOS, AI Opt-out Signals: Who Honors What, updated 2026-10-20. https://bozos.si/ai-optout-signals.json#robots-txt-training-optout",
      "review_due": "2027-01-18",
      "name": "robots.txt opt-out from AI training",
      "kind": "ietf-standard",
      "publisher": "IETF (RFC 9309) plus each operator's own user-agent token",
      "syntax": "User-agent: GPTBot\nDisallow: /",
      "expresses": "Whether a named crawler may fetch a path. Operators decide what blocking their token means; some offer a token only for AI training, or a control token that changes how already-crawled data is used.",
      "spec": "https://www.rfc-editor.org/rfc/rfc9309.html",
      "evidence": [
        {
          "quote": "These rules are not a form of access authorization.",
          "source": "https://www.rfc-editor.org/rfc/rfc9309.html"
        }
      ],
      "terms": null
    },
    {
      "id": "robots-meta-ai",
      "permalink": "https://bozos.si/ai-optout-signals.json#robots-meta-ai",
      "cite": "Robots meta tags as AI controls (nosnippet, noarchive) (de-facto-standard, Search engines, individually): Page-level rules originally written for search. Some operators state that a specific rule also limits AI use of the page; the meaning differs by operator. Source: BOZOS, AI Opt-out Signals: Who Honors What, updated 2026-10-20. https://bozos.si/ai-optout-signals.json#robots-meta-ai",
      "review_due": "2027-01-18",
      "name": "Robots meta tags as AI controls (nosnippet, noarchive)",
      "kind": "de-facto-standard",
      "publisher": "Search engines, individually",
      "syntax": "<meta name=\"robots\" content=\"nosnippet\">  or  X-Robots-Tag: noarchive",
      "expresses": "Page-level rules originally written for search. Some operators state that a specific rule also limits AI use of the page; the meaning differs by operator.",
      "spec": "https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag",
      "evidence": [],
      "terms": [
        "noarchive",
        "nosnippet",
        "robots meta",
        "x-robots-tag"
      ]
    },
    {
      "id": "noai-meta",
      "permalink": "https://bozos.si/ai-optout-signals.json#noai-meta",
      "cite": "noai and noimageai directives (convention, DeviantArt (introduced November 2022)): That content is not authorized for use in AI datasets or as input to AI models. Source: BOZOS, AI Opt-out Signals: Who Honors What, updated 2026-10-20. https://bozos.si/ai-optout-signals.json#noai-meta",
      "review_due": "2027-01-18",
      "name": "noai and noimageai directives",
      "kind": "convention",
      "publisher": "DeviantArt (introduced November 2022)",
      "syntax": "<meta name=\"robots\" content=\"noai, noimageai\">  or  X-Robots-Tag: noai",
      "expresses": "That content is not authorized for use in AI datasets or as input to AI models.",
      "spec": "https://www.deviantart.com/team/journal/UPDATE-All-Deviations-Are-Opted-Out-of-AI-Datasets-934500371",
      "evidence": [
        {
          "quote": "DeviantArt has introduced the noai and noimageai directives to unambiguously communicate absence of such authorization.",
          "source": "https://www.deviantart.com/team/journal/UPDATE-All-Deviations-Are-Opted-Out-of-AI-Datasets-934500371"
        }
      ],
      "terms": [
        "\\bnoai\\b(?![.-])",
        "noimageai"
      ]
    },
    {
      "id": "content-signal",
      "permalink": "https://bozos.si/ai-optout-signals.json#content-signal",
      "cite": "Content-Signal (Content Signals Policy) (vendor-policy, Cloudflare): Yes/no preferences for three uses: search, ai-input (for example retrieval-augmented generation and grounding), and ai-train (training or fine-tuning). Source: BOZOS, AI Opt-out Signals: Who Honors What, updated 2026-10-20. https://bozos.si/ai-optout-signals.json#content-signal",
      "review_due": "2027-01-18",
      "name": "Content-Signal (Content Signals Policy)",
      "kind": "vendor-policy",
      "publisher": "Cloudflare",
      "syntax": "Content-Signal: search=yes, ai-input=yes, ai-train=no",
      "expresses": "Yes/no preferences for three uses: search, ai-input (for example retrieval-augmented generation and grounding), and ai-train (training or fine-tuning).",
      "spec": "https://blog.cloudflare.com/content-signals-policy/",
      "evidence": [
        {
          "quote": "This policy defines three content signals - search, ai-input, and ai-train - and their relevance to crawlers.",
          "source": "https://blog.cloudflare.com/content-signals-policy/"
        }
      ],
      "terms": [
        "content[- ]signals?"
      ]
    },
    {
      "id": "aipref-content-usage",
      "permalink": "https://bozos.si/ai-optout-signals.json#aipref-content-usage",
      "cite": "IETF AI preferences (Content-Usage) (internet-draft, IETF AIPREF working group): A shared vocabulary for usage preferences, attached through robots.txt or an HTTP header. Not yet an RFC. Source: BOZOS, AI Opt-out Signals: Who Honors What, updated 2026-10-20. https://bozos.si/ai-optout-signals.json#aipref-content-usage",
      "review_due": "2027-01-18",
      "name": "IETF AI preferences (Content-Usage)",
      "kind": "internet-draft",
      "publisher": "IETF AIPREF working group",
      "syntax": "Content-Usage: train-ai=n  (robots.txt rule or HTTP header; vocabulary still in draft)",
      "expresses": "A shared vocabulary for usage preferences, attached through robots.txt or an HTTP header. Not yet an RFC.",
      "spec": "https://datatracker.ietf.org/doc/draft-ietf-aipref-attach/",
      "evidence": [
        {
          "quote": "This document defines attachment methods using the Robots Exclusion Protocol and HTTP header fields.",
          "source": "https://datatracker.ietf.org/doc/draft-ietf-aipref-attach/"
        },
        {
          "quote": "It is inappropriate to use Internet-Drafts as reference material or to cite them other than as \"work in progress.\"",
          "source": "https://datatracker.ietf.org/doc/draft-ietf-aipref-vocab/"
        }
      ],
      "terms": [
        "aipref",
        "content-usage"
      ]
    },
    {
      "id": "tdmrep",
      "permalink": "https://bozos.si/ai-optout-signals.json#tdmrep",
      "cite": "TDM Reservation Protocol (TDMRep) (w3c-community-group-report, W3C TDM Reservation Protocol Community Group): A reservation of text-and-data-mining rights under Article 4 of the EU copyright directive (2019/790), optionally pointing to a licensing policy. Source: BOZOS, AI Opt-out Signals: Who Honors What, updated 2026-10-20. https://bozos.si/ai-optout-signals.json#tdmrep",
      "review_due": "2027-01-18",
      "name": "TDM Reservation Protocol (TDMRep)",
      "kind": "w3c-community-group-report",
      "publisher": "W3C TDM Reservation Protocol Community Group",
      "syntax": "tdm-reservation: 1  (HTTP header), <meta name=\"tdm-reservation\" content=\"1\">, or /.well-known/tdmrep.json",
      "expresses": "A reservation of text-and-data-mining rights under Article 4 of the EU copyright directive (2019/790), optionally pointing to a licensing policy.",
      "spec": "https://w3c-cg.github.io/tdm-reservation-protocol/spec/",
      "evidence": [
        {
          "quote": "This specification defines a simple and practical Web protocol, capable of expressing the reservation of rights relative to text & data mining (TDM) applied to lawfully accessible Web content",
          "source": "https://w3c-cg.github.io/tdm-reservation-protocol/spec/"
        }
      ],
      "terms": [
        "tdmrep",
        "tdm-reservation",
        "text and data mining"
      ]
    },
    {
      "id": "rsl",
      "permalink": "https://bozos.si/ai-optout-signals.json#rsl",
      "cite": "Really Simple Licensing (RSL) (industry-specification, RSL Collective): Machine-readable licensing, payment, and legal terms for AI use, with discovery through robots.txt, HTTP, HTML, or RSS. Source: BOZOS, AI Opt-out Signals: Who Honors What, updated 2026-10-20. https://bozos.si/ai-optout-signals.json#rsl",
      "review_due": "2027-01-18",
      "name": "Really Simple Licensing (RSL)",
      "kind": "industry-specification",
      "publisher": "RSL Collective",
      "syntax": "License: https://example.com/license.xml  (robots.txt), or a Link header with rel=\"license\"",
      "expresses": "Machine-readable licensing, payment, and legal terms for AI use, with discovery through robots.txt, HTTP, HTML, or RSS.",
      "spec": "https://rslstandard.org/rsl",
      "evidence": [
        {
          "quote": "machine-readable usage, licensing, payment, and legal terms that govern how digital assets may be accessed or licensed by AI systems and automated agents.",
          "source": "https://rslstandard.org/rsl"
        }
      ],
      "terms": [
        "really simple licensing",
        "\\bRSL\\b"
      ]
    }
  ],
  "operators": [
    {
      "id": "openai",
      "permalink": "https://bozos.si/ai-optout-signals.json#openai",
      "cite": "OpenAI: robots-txt-training-optout honors (Disallow GPTBot in robots.txt); robots-meta-ai not-stated; noai-meta not-stated; content-signal not-stated; aipref-content-usage not-stated; tdmrep not-stated; rsl not-stated. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#openai",
      "review_due": "2027-01-18",
      "operator": "OpenAI",
      "crawler_tokens": [
        "GPTBot",
        "OAI-SearchBot",
        "ChatGPT-User",
        "OAI-AdsBot"
      ],
      "sources": [
        "https://developers.openai.com/api/docs/bots"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "honors",
          "scope": "Disallow GPTBot in robots.txt.",
          "tokens": [
            "GPTBot"
          ],
          "quotes": [
            {
              "quote": "Disallowing GPTBot indicates a site's content should not be used in training generative AI foundation models.",
              "source": "https://developers.openai.com/api/docs/bots"
            }
          ]
        },
        "robots-meta-ai": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developers.openai.com/api/docs/bots"
            ],
            "terms": [
              "noarchive",
              "nosnippet",
              "robots meta",
              "x-robots-tag"
            ],
            "checked": "2026-10-20"
          }
        },
        "noai-meta": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developers.openai.com/api/docs/bots"
            ],
            "terms": [
              "\\bnoai\\b(?![.-])",
              "noimageai"
            ],
            "checked": "2026-10-20"
          }
        },
        "content-signal": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developers.openai.com/api/docs/bots"
            ],
            "terms": [
              "content[- ]signals?"
            ],
            "checked": "2026-10-20"
          }
        },
        "aipref-content-usage": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developers.openai.com/api/docs/bots"
            ],
            "terms": [
              "aipref",
              "content-usage"
            ],
            "checked": "2026-10-20"
          }
        },
        "tdmrep": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developers.openai.com/api/docs/bots"
            ],
            "terms": [
              "tdmrep",
              "tdm-reservation",
              "text and data mining"
            ],
            "checked": "2026-10-20"
          }
        },
        "rsl": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developers.openai.com/api/docs/bots"
            ],
            "terms": [
              "really simple licensing",
              "\\bRSL\\b"
            ],
            "checked": "2026-10-20"
          }
        }
      }
    },
    {
      "id": "anthropic",
      "permalink": "https://bozos.si/ai-optout-signals.json#anthropic",
      "cite": "Anthropic: robots-txt-training-optout honors (Disallow ClaudeBot in robots.txt); robots-meta-ai not-stated; noai-meta not-stated; content-signal not-stated; aipref-content-usage not-stated; tdmrep not-stated; rsl not-stated. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#anthropic",
      "review_due": "2027-01-18",
      "operator": "Anthropic",
      "crawler_tokens": [
        "ClaudeBot",
        "Claude-SearchBot",
        "Claude-User"
      ],
      "sources": [
        "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "honors",
          "scope": "Disallow ClaudeBot in robots.txt.",
          "tokens": [
            "ClaudeBot"
          ],
          "quotes": [
            {
              "quote": "Anthropic's Bots respect \"do not crawl\" signals by honoring industry standard directives in robots.txt.",
              "source": "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler"
            }
          ]
        },
        "robots-meta-ai": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler"
            ],
            "terms": [
              "noarchive",
              "nosnippet",
              "robots meta",
              "x-robots-tag"
            ],
            "checked": "2026-10-20"
          }
        },
        "noai-meta": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler"
            ],
            "terms": [
              "\\bnoai\\b(?![.-])",
              "noimageai"
            ],
            "checked": "2026-10-20"
          }
        },
        "content-signal": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler"
            ],
            "terms": [
              "content[- ]signals?"
            ],
            "checked": "2026-10-20"
          }
        },
        "aipref-content-usage": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler"
            ],
            "terms": [
              "aipref",
              "content-usage"
            ],
            "checked": "2026-10-20"
          }
        },
        "tdmrep": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler"
            ],
            "terms": [
              "tdmrep",
              "tdm-reservation",
              "text and data mining"
            ],
            "checked": "2026-10-20"
          }
        },
        "rsl": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler"
            ],
            "terms": [
              "really simple licensing",
              "\\bRSL\\b"
            ],
            "checked": "2026-10-20"
          }
        }
      }
    },
    {
      "id": "google",
      "permalink": "https://bozos.si/ai-optout-signals.json#google",
      "cite": "Google: robots-txt-training-optout honors (Disallow Google-Extended in robots.txt); robots-meta-ai honors (nosnippet also keeps a page from being used as direct input for AI Overviews and AI Mode. It does not address training); noai-meta not-stated; content-signal not-stated; aipref-content-usage not-stated; tdmrep not-stated; rsl not-stated. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#google",
      "review_due": "2027-01-18",
      "operator": "Google",
      "crawler_tokens": [
        "Googlebot",
        "Google-Extended",
        "GoogleOther",
        "Google-CloudVertexBot"
      ],
      "sources": [
        "https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers",
        "https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "honors",
          "scope": "Disallow Google-Extended in robots.txt.",
          "tokens": [
            "Google-Extended"
          ],
          "quotes": [
            {
              "quote": "Google-Extended is a standalone product token that web publishers can use to manage whether content Google crawls from their sites may be used for training future generations of Gemini models",
              "source": "https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers"
            }
          ]
        },
        "robots-meta-ai": {
          "stance": "honors",
          "scope": "nosnippet also keeps a page from being used as direct input for AI Overviews and AI Mode. It does not address training.",
          "quotes": [
            {
              "quote": "will also prevent the content from being used as a direct input for AI Overviews and AI Mode.",
              "source": "https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag"
            }
          ]
        },
        "noai-meta": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers",
              "https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag"
            ],
            "terms": [
              "\\bnoai\\b(?![.-])",
              "noimageai"
            ],
            "checked": "2026-10-20"
          }
        },
        "content-signal": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers",
              "https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag"
            ],
            "terms": [
              "content[- ]signals?"
            ],
            "checked": "2026-10-20"
          }
        },
        "aipref-content-usage": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers",
              "https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag"
            ],
            "terms": [
              "aipref",
              "content-usage"
            ],
            "checked": "2026-10-20"
          }
        },
        "tdmrep": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers",
              "https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag"
            ],
            "terms": [
              "tdmrep",
              "tdm-reservation",
              "text and data mining"
            ],
            "checked": "2026-10-20"
          }
        },
        "rsl": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers",
              "https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag"
            ],
            "terms": [
              "really simple licensing",
              "\\bRSL\\b"
            ],
            "checked": "2026-10-20"
          }
        }
      }
    },
    {
      "id": "microsoft",
      "permalink": "https://bozos.si/ai-optout-signals.json#microsoft",
      "cite": "Microsoft: robots-txt-training-optout unknown; robots-meta-ai unknown; noai-meta unknown; content-signal unknown; aipref-content-usage unknown; tdmrep unknown; rsl unknown. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#microsoft",
      "review_due": "2027-01-18",
      "operator": "Microsoft",
      "crawler_tokens": [
        "bingbot"
      ],
      "sources": [
        "https://www.bing.com/webmasters/help/which-crawlers-does-bing-use-8c184ec0"
      ],
      "unreadable_sources": [
        "https://www.bing.com/webmasters/help/which-crawlers-does-bing-use-8c184ec0"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "unknown",
          "scope": "The operator's documentation page cannot be read by a script.",
          "quotes": []
        },
        "robots-meta-ai": {
          "stance": "unknown",
          "scope": "The operator's documentation page cannot be read by a script, so absence of a mention cannot be checked.",
          "quotes": []
        },
        "noai-meta": {
          "stance": "unknown",
          "scope": "The operator's documentation page cannot be read by a script, so absence of a mention cannot be checked.",
          "quotes": []
        },
        "content-signal": {
          "stance": "unknown",
          "scope": "The operator's documentation page cannot be read by a script, so absence of a mention cannot be checked.",
          "quotes": []
        },
        "aipref-content-usage": {
          "stance": "unknown",
          "scope": "The operator's documentation page cannot be read by a script, so absence of a mention cannot be checked.",
          "quotes": []
        },
        "tdmrep": {
          "stance": "unknown",
          "scope": "The operator's documentation page cannot be read by a script, so absence of a mention cannot be checked.",
          "quotes": []
        },
        "rsl": {
          "stance": "unknown",
          "scope": "The operator's documentation page cannot be read by a script, so absence of a mention cannot be checked.",
          "quotes": []
        }
      }
    },
    {
      "id": "apple",
      "permalink": "https://bozos.si/ai-optout-signals.json#apple",
      "cite": "Apple: robots-txt-training-optout honors (Disallow Applebot-Extended in robots.txt); robots-meta-ai honors (nosnippet keeps content out of AI-generated answers in Apple products. Training is controlled by Applebot-Extended instead); noai-meta not-stated; content-signal not-stated; aipref-content-usage not-stated; tdmrep not-stated; rsl not-stated. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#apple",
      "review_due": "2027-01-18",
      "operator": "Apple",
      "crawler_tokens": [
        "Applebot",
        "Applebot-Extended"
      ],
      "sources": [
        "https://support.apple.com/en-us/119829"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "honors",
          "scope": "Disallow Applebot-Extended in robots.txt.",
          "tokens": [
            "Applebot-Extended"
          ],
          "quotes": [
            {
              "quote": "Web publishers can opt-out from having their content used to train generative foundation models by disallowing Applebot-Extended in the robots.txt file.",
              "source": "https://support.apple.com/en-us/119829"
            }
          ]
        },
        "robots-meta-ai": {
          "stance": "honors",
          "scope": "nosnippet keeps content out of AI-generated answers in Apple products. Training is controlled by Applebot-Extended instead.",
          "quotes": [
            {
              "quote": "Apple will not use data tagged nosnippet as additional context and up-to-date content when AI models are used to generate output for display in Apple products and services.",
              "source": "https://support.apple.com/en-us/119829"
            }
          ]
        },
        "noai-meta": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://support.apple.com/en-us/119829"
            ],
            "terms": [
              "\\bnoai\\b(?![.-])",
              "noimageai"
            ],
            "checked": "2026-10-20"
          }
        },
        "content-signal": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://support.apple.com/en-us/119829"
            ],
            "terms": [
              "content[- ]signals?"
            ],
            "checked": "2026-10-20"
          }
        },
        "aipref-content-usage": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://support.apple.com/en-us/119829"
            ],
            "terms": [
              "aipref",
              "content-usage"
            ],
            "checked": "2026-10-20"
          }
        },
        "tdmrep": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://support.apple.com/en-us/119829"
            ],
            "terms": [
              "tdmrep",
              "tdm-reservation",
              "text and data mining"
            ],
            "checked": "2026-10-20"
          }
        },
        "rsl": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://support.apple.com/en-us/119829"
            ],
            "terms": [
              "really simple licensing",
              "\\bRSL\\b"
            ],
            "checked": "2026-10-20"
          }
        }
      }
    },
    {
      "id": "perplexity",
      "permalink": "https://bozos.si/ai-optout-signals.json#perplexity",
      "cite": "Perplexity: robots-txt-training-optout not-applicable; robots-meta-ai not-stated; noai-meta not-stated; content-signal not-stated; aipref-content-usage not-stated; tdmrep not-stated; rsl not-stated. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#perplexity",
      "review_due": "2027-01-18",
      "operator": "Perplexity",
      "crawler_tokens": [
        "PerplexityBot",
        "Perplexity-User"
      ],
      "sources": [
        "https://docs.perplexity.ai/guides/bots"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "not-applicable",
          "scope": "The operator says its crawlers are not used for AI training.",
          "quotes": [
            {
              "quote": "It is not used to crawl content for AI foundation models.",
              "source": "https://docs.perplexity.ai/guides/bots"
            }
          ]
        },
        "robots-meta-ai": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://docs.perplexity.ai/guides/bots"
            ],
            "terms": [
              "noarchive",
              "nosnippet",
              "robots meta",
              "x-robots-tag"
            ],
            "checked": "2026-10-20"
          }
        },
        "noai-meta": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://docs.perplexity.ai/guides/bots"
            ],
            "terms": [
              "\\bnoai\\b(?![.-])",
              "noimageai"
            ],
            "checked": "2026-10-20"
          }
        },
        "content-signal": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://docs.perplexity.ai/guides/bots"
            ],
            "terms": [
              "content[- ]signals?"
            ],
            "checked": "2026-10-20"
          }
        },
        "aipref-content-usage": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://docs.perplexity.ai/guides/bots"
            ],
            "terms": [
              "aipref",
              "content-usage"
            ],
            "checked": "2026-10-20"
          }
        },
        "tdmrep": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://docs.perplexity.ai/guides/bots"
            ],
            "terms": [
              "tdmrep",
              "tdm-reservation",
              "text and data mining"
            ],
            "checked": "2026-10-20"
          }
        },
        "rsl": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://docs.perplexity.ai/guides/bots"
            ],
            "terms": [
              "really simple licensing",
              "\\bRSL\\b"
            ],
            "checked": "2026-10-20"
          }
        }
      }
    },
    {
      "id": "meta",
      "permalink": "https://bozos.si/ai-optout-signals.json#meta",
      "cite": "Meta: robots-txt-training-optout honors (Disallow meta-externalagent in robots.txt); robots-meta-ai unknown; noai-meta unknown; content-signal unknown; aipref-content-usage unknown; tdmrep unknown; rsl unknown. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#meta",
      "review_due": "2027-01-18",
      "operator": "Meta",
      "crawler_tokens": [
        "meta-externalagent",
        "meta-webindexer",
        "meta-externalfetcher",
        "facebookexternalhit"
      ],
      "sources": [
        "https://developers.facebook.com/docs/sharing/webmasters/web-crawlers"
      ],
      "unreadable_sources": [
        "https://developers.facebook.com/docs/sharing/webmasters/web-crawlers"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "honors",
          "scope": "Disallow meta-externalagent in robots.txt.",
          "tokens": [
            "meta-externalagent"
          ],
          "quotes": [],
          "evidence_status": "not-machine-verifiable: the documentation page refuses automated requests (HTTP 400), so quotes cannot be checked automatically. Last read in a browser on the verified date."
        },
        "robots-meta-ai": {
          "stance": "unknown",
          "scope": "The operator's documentation page cannot be read by a script, so absence of a mention cannot be checked.",
          "quotes": []
        },
        "noai-meta": {
          "stance": "unknown",
          "scope": "The operator's documentation page cannot be read by a script, so absence of a mention cannot be checked.",
          "quotes": []
        },
        "content-signal": {
          "stance": "unknown",
          "scope": "The operator's documentation page cannot be read by a script, so absence of a mention cannot be checked.",
          "quotes": []
        },
        "aipref-content-usage": {
          "stance": "unknown",
          "scope": "The operator's documentation page cannot be read by a script, so absence of a mention cannot be checked.",
          "quotes": []
        },
        "tdmrep": {
          "stance": "unknown",
          "scope": "The operator's documentation page cannot be read by a script, so absence of a mention cannot be checked.",
          "quotes": []
        },
        "rsl": {
          "stance": "unknown",
          "scope": "The operator's documentation page cannot be read by a script, so absence of a mention cannot be checked.",
          "quotes": []
        }
      }
    },
    {
      "id": "common-crawl",
      "permalink": "https://bozos.si/ai-optout-signals.json#common-crawl",
      "cite": "Common Crawl: robots-txt-training-optout honors (Disallow CCBot in robots.txt); robots-meta-ai not-stated; noai-meta not-stated; content-signal not-stated; aipref-content-usage not-stated; tdmrep not-stated; rsl not-stated. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#common-crawl",
      "review_due": "2027-01-18",
      "operator": "Common Crawl",
      "crawler_tokens": [
        "CCBot"
      ],
      "sources": [
        "https://commoncrawl.org/ccbot"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "honors",
          "scope": "Disallow CCBot in robots.txt.",
          "tokens": [
            "CCBot"
          ],
          "quotes": [
            {
              "quote": "To prevent Common Crawl from crawling your website, include the following in your robots.txt",
              "source": "https://commoncrawl.org/ccbot"
            }
          ]
        },
        "robots-meta-ai": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://commoncrawl.org/ccbot"
            ],
            "terms": [
              "noarchive",
              "nosnippet",
              "robots meta",
              "x-robots-tag"
            ],
            "checked": "2026-10-20"
          }
        },
        "noai-meta": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://commoncrawl.org/ccbot"
            ],
            "terms": [
              "\\bnoai\\b(?![.-])",
              "noimageai"
            ],
            "checked": "2026-10-20"
          }
        },
        "content-signal": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://commoncrawl.org/ccbot"
            ],
            "terms": [
              "content[- ]signals?"
            ],
            "checked": "2026-10-20"
          }
        },
        "aipref-content-usage": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://commoncrawl.org/ccbot"
            ],
            "terms": [
              "aipref",
              "content-usage"
            ],
            "checked": "2026-10-20"
          }
        },
        "tdmrep": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://commoncrawl.org/ccbot"
            ],
            "terms": [
              "tdmrep",
              "tdm-reservation",
              "text and data mining"
            ],
            "checked": "2026-10-20"
          }
        },
        "rsl": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://commoncrawl.org/ccbot"
            ],
            "terms": [
              "really simple licensing",
              "\\bRSL\\b"
            ],
            "checked": "2026-10-20"
          }
        }
      }
    },
    {
      "id": "amazon",
      "permalink": "https://bozos.si/ai-optout-signals.json#amazon",
      "cite": "Amazon: robots-txt-training-optout honors (Disallow Amazonbot in robots.txt); robots-meta-ai honors (noarchive means do not use the page for model training); noai-meta not-stated; content-signal not-stated; aipref-content-usage not-stated; tdmrep not-stated; rsl not-stated. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#amazon",
      "review_due": "2027-01-18",
      "operator": "Amazon",
      "crawler_tokens": [
        "Amazonbot",
        "Amzn-SearchBot",
        "Amzn-User"
      ],
      "sources": [
        "https://developer.amazon.com/amazonbot"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "honors",
          "scope": "Disallow Amazonbot in robots.txt.",
          "tokens": [
            "Amazonbot"
          ],
          "quotes": [
            {
              "quote": "may be used to train Amazon AI models.",
              "source": "https://developer.amazon.com/amazonbot"
            }
          ]
        },
        "robots-meta-ai": {
          "stance": "honors",
          "scope": "noarchive means do not use the page for model training.",
          "quotes": [
            {
              "quote": "page level robots meta tags of noarchive (do not use the page for model training)",
              "source": "https://developer.amazon.com/amazonbot"
            }
          ]
        },
        "noai-meta": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developer.amazon.com/amazonbot"
            ],
            "terms": [
              "\\bnoai\\b(?![.-])",
              "noimageai"
            ],
            "checked": "2026-10-20"
          }
        },
        "content-signal": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developer.amazon.com/amazonbot"
            ],
            "terms": [
              "content[- ]signals?"
            ],
            "checked": "2026-10-20"
          }
        },
        "aipref-content-usage": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developer.amazon.com/amazonbot"
            ],
            "terms": [
              "aipref",
              "content-usage"
            ],
            "checked": "2026-10-20"
          }
        },
        "tdmrep": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developer.amazon.com/amazonbot"
            ],
            "terms": [
              "tdmrep",
              "tdm-reservation",
              "text and data mining"
            ],
            "checked": "2026-10-20"
          }
        },
        "rsl": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://developer.amazon.com/amazonbot"
            ],
            "terms": [
              "really simple licensing",
              "\\bRSL\\b"
            ],
            "checked": "2026-10-20"
          }
        }
      }
    },
    {
      "id": "mistral-ai",
      "permalink": "https://bozos.si/ai-optout-signals.json#mistral-ai",
      "cite": "Mistral AI: robots-txt-training-optout honors (Disallow MistralAI-Training in robots.txt); robots-meta-ai not-stated; noai-meta not-stated; content-signal not-stated; aipref-content-usage not-stated; tdmrep not-stated; rsl not-stated. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#mistral-ai",
      "review_due": "2027-01-18",
      "operator": "Mistral AI",
      "crawler_tokens": [
        "MistralAI-Training",
        "MistralAI-Index",
        "MistralAI-User"
      ],
      "sources": [
        "https://docs.mistral.ai/robots"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "honors",
          "scope": "Disallow MistralAI-Training in robots.txt.",
          "tokens": [
            "MistralAI-Training"
          ],
          "quotes": [
            {
              "quote": "Webmasters can disallow this user agent in their robots.txt file.",
              "source": "https://docs.mistral.ai/robots"
            }
          ]
        },
        "robots-meta-ai": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://docs.mistral.ai/robots"
            ],
            "terms": [
              "noarchive",
              "nosnippet",
              "robots meta",
              "x-robots-tag"
            ],
            "checked": "2026-10-20"
          }
        },
        "noai-meta": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://docs.mistral.ai/robots"
            ],
            "terms": [
              "\\bnoai\\b(?![.-])",
              "noimageai"
            ],
            "checked": "2026-10-20"
          }
        },
        "content-signal": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://docs.mistral.ai/robots"
            ],
            "terms": [
              "content[- ]signals?"
            ],
            "checked": "2026-10-20"
          }
        },
        "aipref-content-usage": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://docs.mistral.ai/robots"
            ],
            "terms": [
              "aipref",
              "content-usage"
            ],
            "checked": "2026-10-20"
          }
        },
        "tdmrep": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://docs.mistral.ai/robots"
            ],
            "terms": [
              "tdmrep",
              "tdm-reservation",
              "text and data mining"
            ],
            "checked": "2026-10-20"
          }
        },
        "rsl": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://docs.mistral.ai/robots"
            ],
            "terms": [
              "really simple licensing",
              "\\bRSL\\b"
            ],
            "checked": "2026-10-20"
          }
        }
      }
    },
    {
      "id": "duckduckgo",
      "permalink": "https://bozos.si/ai-optout-signals.json#duckduckgo",
      "cite": "DuckDuckGo: robots-txt-training-optout not-applicable; robots-meta-ai not-stated; noai-meta not-stated; content-signal not-stated; aipref-content-usage not-stated; tdmrep not-stated; rsl not-stated. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#duckduckgo",
      "review_due": "2027-01-18",
      "operator": "DuckDuckGo",
      "crawler_tokens": [
        "DuckAssistBot"
      ],
      "sources": [
        "https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "not-applicable",
          "scope": "The operator says its crawlers are not used for AI training.",
          "quotes": [
            {
              "quote": "This data is not used in any way to train AI models.",
              "source": "https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot"
            }
          ]
        },
        "robots-meta-ai": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot"
            ],
            "terms": [
              "noarchive",
              "nosnippet",
              "robots meta",
              "x-robots-tag"
            ],
            "checked": "2026-10-20"
          }
        },
        "noai-meta": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot"
            ],
            "terms": [
              "\\bnoai\\b(?![.-])",
              "noimageai"
            ],
            "checked": "2026-10-20"
          },
          "note": "The page links to noai.duckduckgo.com, a DuckDuckGo product setting, not the noai directive.",
          "ignored_hits": 0
        },
        "content-signal": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot"
            ],
            "terms": [
              "content[- ]signals?"
            ],
            "checked": "2026-10-20"
          }
        },
        "aipref-content-usage": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot"
            ],
            "terms": [
              "aipref",
              "content-usage"
            ],
            "checked": "2026-10-20"
          }
        },
        "tdmrep": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot"
            ],
            "terms": [
              "tdmrep",
              "tdm-reservation",
              "text and data mining"
            ],
            "checked": "2026-10-20"
          }
        },
        "rsl": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot"
            ],
            "terms": [
              "really simple licensing",
              "\\bRSL\\b"
            ],
            "checked": "2026-10-20"
          }
        }
      }
    },
    {
      "id": "diffbot",
      "permalink": "https://bozos.si/ai-optout-signals.json#diffbot",
      "cite": "Diffbot: robots-txt-training-optout not-applicable; robots-meta-ai not-stated; noai-meta not-stated; content-signal not-stated; aipref-content-usage not-stated; tdmrep not-stated; rsl not-stated. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#diffbot",
      "review_due": "2027-01-18",
      "operator": "Diffbot",
      "crawler_tokens": [
        "Diffbot",
        "Diffbot-User"
      ],
      "sources": [
        "https://www.diffbot.com/docs/crawl/faq/robots-txt"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "not-applicable",
          "scope": "The operator says its crawlers are not used for AI training.",
          "quotes": [
            {
              "quote": "It is not used for AI training.",
              "source": "https://www.diffbot.com/docs/crawl/faq/robots-txt"
            }
          ]
        },
        "robots-meta-ai": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://www.diffbot.com/docs/crawl/faq/robots-txt"
            ],
            "terms": [
              "noarchive",
              "nosnippet",
              "robots meta",
              "x-robots-tag"
            ],
            "checked": "2026-10-20"
          }
        },
        "noai-meta": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://www.diffbot.com/docs/crawl/faq/robots-txt"
            ],
            "terms": [
              "\\bnoai\\b(?![.-])",
              "noimageai"
            ],
            "checked": "2026-10-20"
          }
        },
        "content-signal": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://www.diffbot.com/docs/crawl/faq/robots-txt"
            ],
            "terms": [
              "content[- ]signals?"
            ],
            "checked": "2026-10-20"
          }
        },
        "aipref-content-usage": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://www.diffbot.com/docs/crawl/faq/robots-txt"
            ],
            "terms": [
              "aipref",
              "content-usage"
            ],
            "checked": "2026-10-20"
          }
        },
        "tdmrep": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://www.diffbot.com/docs/crawl/faq/robots-txt"
            ],
            "terms": [
              "tdmrep",
              "tdm-reservation",
              "text and data mining"
            ],
            "checked": "2026-10-20"
          }
        },
        "rsl": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://www.diffbot.com/docs/crawl/faq/robots-txt"
            ],
            "terms": [
              "really simple licensing",
              "\\bRSL\\b"
            ],
            "checked": "2026-10-20"
          }
        }
      }
    },
    {
      "id": "you-com",
      "permalink": "https://bozos.si/ai-optout-signals.json#you-com",
      "cite": "You.com: robots-txt-training-optout not-stated; robots-meta-ai not-stated; noai-meta not-stated; content-signal not-stated; aipref-content-usage not-stated; tdmrep not-stated; rsl not-stated. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#you-com",
      "review_due": "2027-01-18",
      "operator": "You.com",
      "crawler_tokens": [
        "YouBot"
      ],
      "sources": [
        "https://you.com/docs/youbot"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "not-stated",
          "scope": "No crawler of this operator is documented as an AI training crawler or control token.",
          "quotes": []
        },
        "robots-meta-ai": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://you.com/docs/youbot"
            ],
            "terms": [
              "noarchive",
              "nosnippet",
              "robots meta",
              "x-robots-tag"
            ],
            "checked": "2026-10-20"
          }
        },
        "noai-meta": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://you.com/docs/youbot"
            ],
            "terms": [
              "\\bnoai\\b(?![.-])",
              "noimageai"
            ],
            "checked": "2026-10-20"
          }
        },
        "content-signal": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://you.com/docs/youbot"
            ],
            "terms": [
              "content[- ]signals?"
            ],
            "checked": "2026-10-20"
          }
        },
        "aipref-content-usage": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://you.com/docs/youbot"
            ],
            "terms": [
              "aipref",
              "content-usage"
            ],
            "checked": "2026-10-20"
          }
        },
        "tdmrep": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://you.com/docs/youbot"
            ],
            "terms": [
              "tdmrep",
              "tdm-reservation",
              "text and data mining"
            ],
            "checked": "2026-10-20"
          }
        },
        "rsl": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://you.com/docs/youbot"
            ],
            "terms": [
              "really simple licensing",
              "\\bRSL\\b"
            ],
            "checked": "2026-10-20"
          }
        }
      }
    },
    {
      "id": "allen-institute-for-ai",
      "permalink": "https://bozos.si/ai-optout-signals.json#allen-institute-for-ai",
      "cite": "Allen Institute for AI (Ai2): robots-txt-training-optout not-stated; robots-meta-ai not-stated; noai-meta not-stated; content-signal not-stated; aipref-content-usage not-stated; tdmrep not-stated; rsl not-stated. Source: BOZOS, AI Opt-out Signals: Who Honors What, verified 2026-10-20. https://bozos.si/ai-optout-signals.json#allen-institute-for-ai",
      "review_due": "2027-01-18",
      "operator": "Allen Institute for AI (Ai2)",
      "crawler_tokens": [
        "AI2Bot"
      ],
      "sources": [
        "https://allenai.org/crawler"
      ],
      "verified": "2026-10-20",
      "cells": {
        "robots-txt-training-optout": {
          "stance": "not-stated",
          "scope": "AI2Bot is used for AI training, but the documentation does not say robots.txt rules are honored; it says the crawler page does not mention robots.txt. It says the user-agent string can be used to filter or reject the crawler's traffic.",
          "tokens": [
            "AI2Bot"
          ],
          "quotes": [
            {
              "quote": "This user agent string can be used to filter or reject traffic from our crawler if desired.",
              "source": "https://allenai.org/crawler"
            }
          ]
        },
        "robots-meta-ai": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://allenai.org/crawler"
            ],
            "terms": [
              "noarchive",
              "nosnippet",
              "robots meta",
              "x-robots-tag"
            ],
            "checked": "2026-10-20"
          }
        },
        "noai-meta": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://allenai.org/crawler"
            ],
            "terms": [
              "\\bnoai\\b(?![.-])",
              "noimageai"
            ],
            "checked": "2026-10-20"
          }
        },
        "content-signal": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://allenai.org/crawler"
            ],
            "terms": [
              "content[- ]signals?"
            ],
            "checked": "2026-10-20"
          }
        },
        "aipref-content-usage": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://allenai.org/crawler"
            ],
            "terms": [
              "aipref",
              "content-usage"
            ],
            "checked": "2026-10-20"
          }
        },
        "tdmrep": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://allenai.org/crawler"
            ],
            "terms": [
              "tdmrep",
              "tdm-reservation",
              "text and data mining"
            ],
            "checked": "2026-10-20"
          }
        },
        "rsl": {
          "stance": "not-stated",
          "scope": "No mention in the operator's pages checked.",
          "quotes": [],
          "searched": {
            "sources": [
              "https://allenai.org/crawler"
            ],
            "terms": [
              "really simple licensing",
              "\\bRSL\\b"
            ],
            "checked": "2026-10-20"
          }
        }
      }
    }
  ],
  "source_snapshots": [
    {
      "url": "https://allenai.org/crawler",
      "archived": "https://web.archive.org/web/20261002130200/https://allenai.org/crawler",
      "captured": "2026-10-02",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://blog.cloudflare.com/content-signals-policy/",
      "archived": "https://web.archive.org/web/20261006064721/https://blog.cloudflare.com/content-signals-policy/",
      "captured": "2026-10-06",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://commoncrawl.org/ccbot",
      "archived": "https://web.archive.org/web/20261005215406/https://commoncrawl.org/ccbot",
      "captured": "2026-10-05",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://datatracker.ietf.org/doc/draft-ietf-aipref-attach/",
      "archived": "https://web.archive.org/web/20261016034531/https://datatracker.ietf.org/doc/draft-ietf-aipref-attach/",
      "captured": "2026-10-16",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://datatracker.ietf.org/doc/draft-ietf-aipref-vocab/",
      "archived": "https://web.archive.org/web/20261005001438/https://datatracker.ietf.org/doc/draft-ietf-aipref-vocab/",
      "captured": "2026-10-05",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://developer.amazon.com/amazonbot",
      "archived": "https://web.archive.org/web/20261007220743/https://developer.amazon.com/amazonbot",
      "captured": "2026-10-07",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers",
      "archived": "https://web.archive.org/web/20261020085128/https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers",
      "captured": "2026-10-20",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag",
      "archived": "https://web.archive.org/web/20261015205432/https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag",
      "captured": "2026-10-15",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://developers.openai.com/api/docs/bots",
      "archived": "https://web.archive.org/web/20261016233530/https://developers.openai.com/api/docs/bots",
      "captured": "2026-10-16",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://docs.mistral.ai/robots",
      "archived": "https://web.archive.org/web/20261010094213/https://docs.mistral.ai/robots",
      "captured": "2026-10-10",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://docs.perplexity.ai/guides/bots",
      "archived": "https://web.archive.org/web/20261020085457/https://docs.perplexity.ai/guides/bots",
      "captured": "2026-10-20",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot",
      "archived": "https://web.archive.org/web/20261013204641/https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot",
      "captured": "2026-10-13",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://rslstandard.org/rsl",
      "archived": "https://web.archive.org/web/20261003152013/https://rslstandard.org/rsl",
      "captured": "2026-10-03",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://support.apple.com/en-us/119829",
      "archived": "https://web.archive.org/web/20261016065936/https://support.apple.com/en-us/119829",
      "captured": "2026-10-16",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler",
      "archived": "https://web.archive.org/web/20261016233536/https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler",
      "captured": "2026-10-16",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://w3c-cg.github.io/tdm-reservation-protocol/spec/",
      "archived": "https://web.archive.org/web/20261020100031/https://w3c-cg.github.io/tdm-reservation-protocol/spec/",
      "captured": "2026-10-20",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://www.deviantart.com/team/journal/UPDATE-All-Deviations-Are-Opted-Out-of-AI-Datasets-934500371",
      "archived": "https://web.archive.org/web/20261010025422/https://www.deviantart.com/team/journal/UPDATE-All-Deviations-Are-Opted-Out-of-AI-Datasets-934500371",
      "captured": "2026-10-10",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://www.diffbot.com/docs/crawl/faq/robots-txt",
      "archived": "https://web.archive.org/web/20261020090915/https://www.diffbot.com/docs/crawl/faq/robots-txt",
      "captured": "2026-10-20",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    },
    {
      "url": "https://www.rfc-editor.org/rfc/rfc9309.html",
      "archived": "https://web.archive.org/web/20261016023724/https://www.rfc-editor.org/rfc/rfc9309.html",
      "captured": "2026-10-16",
      "checked": "2026-10-20",
      "quotes_in_snapshot": true
    }
  ]
}