{
  "schema_version": 1,
  "contract_version": "newruntime-page-readership-v1",
  "type": "page_machine_readership",
  "canonical_path": "/signals/document-ocr-is-not-getting-commoditized-402503/",
  "canonical_url": "https://newruntime.com/signals/document-ocr-is-not-getting-commoditized-402503/",
  "generated_at": "2026-10-19T06:00:46.674Z",
  "refresh_hint": "30m",
  "schema_url": "https://newruntime.com/page-readership-schema.json",
  "methodology_url": "https://newruntime.com/machine-consumption/",
  "privacy": {
    "ip_addresses": "not_output",
    "visitor_ids": "not_output",
    "query_strings": "not_output",
    "raw_user_agents": "not_output",
    "raw_log_lines": "not_output",
    "session_identifiers": "not_output",
    "human_identity": "not_collected_for_this_contract"
  },
  "summary": {
    "requests_last_24h": 14,
    "requests_observed": 20,
    "named_automations_observed": 10,
    "verified_automations_observed": 1
  },
  "windows": {
    "last_24h": {
      "first_seen": "2026-10-18T06:00:49.789Z",
      "last_seen": "2026-10-19T06:00:02.823Z",
      "requests": 14,
      "formats": [
        {
          "format": "html",
          "count": 5
        },
        {
          "format": "markdown",
          "count": 5
        },
        {
          "format": "json",
          "count": 4
        }
      ],
      "agents": [
        {
          "family": "AhrefsBot",
          "count": 3,
          "category": "other_bot",
          "first_seen": "2026-10-19T02:11:49.004Z",
          "last_seen": "2026-10-19T03:57:07.511Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "ClaudeBot",
          "count": 3,
          "category": "ai_crawler",
          "first_seen": "2026-10-19T04:02:07.257Z",
          "last_seen": "2026-10-19T04:02:08.173Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "Mozilla/5.0 (Linux; Android 7.0;) AppleWebKit/537.36 (HTML, like Gecko) Mobile Safari/537.36 (compatible; PetalBot;+http",
          "count": 3,
          "category": "other_bot",
          "first_seen": "2026-10-18T09:06:56.605Z",
          "last_seen": "2026-10-18T14:44:30.261Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "MJ12bot",
          "count": 2,
          "category": "other_bot",
          "first_seen": "2026-10-18T21:01:13.552Z",
          "last_seen": "2026-10-18T21:01:15.440Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "Applebot",
          "count": 1,
          "category": "search_crawler",
          "first_seen": "2026-10-18T11:30:26.324Z",
          "last_seen": "2026-10-18T11:30:26.324Z",
          "identity_status": "verified"
        },
        {
          "family": "Mozilla/5.0 (compatible; QlyzeBot/1.0; +public-url-redacted",
          "count": 1,
          "category": "other_bot",
          "first_seen": "2026-10-18T13:57:14.344Z",
          "last_seen": "2026-10-18T13:57:14.344Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; Reflectionbot/1.0; +public-url-redacted Chrome/151",
          "count": 1,
          "category": "other_bot",
          "first_seen": "2026-10-18T08:42:05.136Z",
          "last_seen": "2026-10-18T08:42:05.136Z",
          "identity_status": "not_verifiable"
        }
      ]
    },
    "observed": {
      "first_seen": "2026-10-16T17:11:40.265Z",
      "last_seen": "2026-10-19T06:00:02.823Z",
      "requests": 20,
      "formats": [
        {
          "format": "html",
          "count": 8
        },
        {
          "format": "json",
          "count": 6
        },
        {
          "format": "markdown",
          "count": 6
        }
      ],
      "agents": [
        {
          "family": "Mozilla/5.0 (Linux; Android 7.0;) AppleWebKit/537.36 (HTML, like Gecko) Mobile Safari/537.36 (compatible; PetalBot;+http",
          "count": 4,
          "category": "other_bot",
          "first_seen": "2026-10-17T23:46:28.204Z",
          "last_seen": "2026-10-18T14:44:30.261Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "AhrefsBot",
          "count": 3,
          "category": "other_bot",
          "first_seen": "2026-10-19T02:11:49.004Z",
          "last_seen": "2026-10-19T03:57:07.511Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "Applebot",
          "count": 3,
          "category": "search_crawler",
          "first_seen": "2026-10-17T17:51:52.534Z",
          "last_seen": "2026-10-18T11:30:26.324Z",
          "identity_status": "verified"
        },
        {
          "family": "ClaudeBot",
          "count": 3,
          "category": "ai_crawler",
          "first_seen": "2026-10-19T04:02:07.257Z",
          "last_seen": "2026-10-19T04:02:08.173Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "MJ12bot",
          "count": 2,
          "category": "other_bot",
          "first_seen": "2026-10-18T21:01:13.552Z",
          "last_seen": "2026-10-18T21:01:15.440Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "Mozilla/5.0 (compatible; DotBot/1.2; +public-url-redacted help@moz.com)",
          "count": 1,
          "category": "other_bot",
          "first_seen": "2026-10-18T04:55:44.941Z",
          "last_seen": "2026-10-18T04:55:44.941Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "Mozilla/5.0 (compatible; QlyzeBot/1.0; +public-url-redacted",
          "count": 1,
          "category": "other_bot",
          "first_seen": "2026-10-18T13:57:14.344Z",
          "last_seen": "2026-10-18T13:57:14.344Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; Amazonbot/0.1; +public-url-redacted",
          "count": 1,
          "category": "other_bot",
          "first_seen": "2026-10-17T23:45:45.219Z",
          "last_seen": "2026-10-17T23:45:45.219Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; Reflectionbot/1.0; +public-url-redacted Chrome/151",
          "count": 1,
          "category": "other_bot",
          "first_seen": "2026-10-18T08:42:05.136Z",
          "last_seen": "2026-10-18T08:42:05.136Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "SemrushBot",
          "count": 1,
          "category": "other_bot",
          "first_seen": "2026-10-17T14:50:02.959Z",
          "last_seen": "2026-10-17T14:50:02.959Z",
          "identity_status": "not_verifiable"
        }
      ]
    }
  },
  "interpretation": {
    "unit": "Successful requests from named automation, not unique people.",
    "identity": "Identity status is the strongest observed family-level evidence in the identity aggregate, not verification of every page request.",
    "causality": "A request does not prove indexing, citation, model training, understanding, or referral.",
    "representations": "HTML, JSON, and Markdown twins are grouped under the canonical page."
  }
}
