{
  "capture_id": "2026-08-22T0815Z",
  "capture_class": "pre-2026-09-15-baseline",
  "observed_from": "2026-08-22T08:28:13.633Z",
  "observed_through": "2026-08-22T08:40:54.831Z",
  "vantage": [
    "unrecorded"
  ],
  "input_list": "data/domains/tranco-74V8X-1000.csv",
  "tranco_list": "74V8X",
  "dataset_sha256": "6d6fe5b62eb7bd4c297fa6428653efa4b01d7abbf92792b7eee6a2cb813f4ca6",
  "domains": 1000,
  "rows": 10000,
  "requests_sent": 4699,
  "reachable_rate_of_sent": 0.5073,
  "by_dialect": [
    {
      "id": "browser",
      "kind": "human-baseline",
      "attempted": 1000,
      "sent": 969,
      "robots_denied": 31,
      "reachable": 522,
      "challenged": 65,
      "blocked": 26,
      "reachable_rate": 0.5387
    },
    {
      "id": "curl",
      "kind": "naive-script",
      "attempted": 1000,
      "sent": 969,
      "robots_denied": 31,
      "reachable": 500,
      "challenged": 69,
      "blocked": 42,
      "reachable_rate": 0.516
    },
    {
      "id": "canireach",
      "kind": "self-identified-agent",
      "attempted": 1000,
      "sent": 969,
      "robots_denied": 31,
      "reachable": 536,
      "challenged": 51,
      "blocked": 26,
      "reachable_rate": 0.5531
    },
    {
      "id": "gptbot",
      "kind": "vendor-token-disclosed",
      "attempted": 1000,
      "sent": 897,
      "robots_denied": 103,
      "reachable": 411,
      "challenged": 75,
      "blocked": 50,
      "reachable_rate": 0.4582
    },
    {
      "id": "claudebot",
      "kind": "vendor-token-disclosed",
      "attempted": 1000,
      "sent": 895,
      "robots_denied": 105,
      "reachable": 415,
      "challenged": 69,
      "blocked": 40,
      "reachable_rate": 0.4637
    }
  ],
  "named_vendor_penalty": {
    "browser_robots_denied": 31,
    "named_vendor_robots_denied": [
      {
        "dialect": "gptbot",
        "denied": 103
      },
      {
        "dialect": "claudebot",
        "denied": 105
      }
    ],
    "browser_reachable_rate": 0.5387,
    "unrecognised_agent_reachable_rate": 0.5531,
    "named_vendor_reachable_rate": [
      {
        "dialect": "gptbot",
        "rate": 0.4582
      },
      {
        "dialect": "claudebot",
        "rate": 0.4637
      }
    ]
  },
  "affordances": {
    "llms_txt": {
      "checked": 1000,
      "present": 102,
      "soft_404": 110,
      "not_checked": 39
    },
    "agents_md": {
      "checked": 1000,
      "present": 6,
      "soft_404": 119,
      "not_checked": 40
    },
    "wellknown_agents": {
      "checked": 1000,
      "present": 3,
      "soft_404": 101,
      "not_checked": 44
    },
    "web_bot_auth": {
      "checked": 1000,
      "present": 7,
      "soft_404": 102,
      "not_checked": 43
    }
  },
  "challenges": {
    "imperva-incapsula": 10,
    "cloudflare-challenge": 146,
    "akamai": 80,
    "datadome": 22,
    "recaptcha": 28,
    "aws-waf": 10,
    "hcaptcha": 18,
    "perimeterx": 15
  },
  "toll": {
    "status_402": 15,
    "crawler-price": 1
  },
  "outcomes": {
    "denied_by_robots": 301,
    "error": 1588,
    "reachable": 2384,
    "client_error": 139,
    "blocked": 184,
    "other": 25,
    "challenged": 329,
    "server_error": 14,
    "rate_limited": 20,
    "auth_required": 1,
    "toll": 15
  },
  "robots_txt": {
    "served_200": 575,
    "absent_or_error": 425
  },
  "limitations": {
    "identity": "GPTBot and ClaudeBot rows are disclosed simulations, not authenticated vendor traffic; see METHODOLOGY.md at the tag target.",
    "vantage_note": "This capture was taken from a residential vantage with robots-unavailable failing open. Automated captures run from GitHub-hosted dynamic egress with robots-unavailable failing closed. Those are different instruments and the repository withholds cross-capture deltas until every comparability dimension matches.",
    "single_capture": "One capture is a photograph, not a trend. No before/after claim is published until a second comparable capture exists."
  },
  "source": {
    "repository": "https://github.com/BrunoOGclaw/canireach",
    "methodology": "https://github.com/BrunoOGclaw/canireach/blob/main/METHODOLOGY.md",
    "releases": "https://github.com/BrunoOGclaw/canireach/releases"
  }
}