{
  "schema_version": 1,
  "contract_version": "newruntime-page-readership-v1",
  "type": "page_machine_readership",
  "canonical_path": "/posts/clear-compared-tokenization-across-roughly-200-languages-and-e64ac3/",
  "canonical_url": "https://newruntime.com/posts/clear-compared-tokenization-across-roughly-200-languages-and-e64ac3/",
  "generated_at": "2026-11-06T18:01:00.094Z",
  "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": 5,
    "requests_observed": 10,
    "named_automations_observed": 7,
    "verified_automations_observed": 1
  },
  "windows": {
    "last_24h": {
      "first_seen": "2026-11-05T18:00:51.776Z",
      "last_seen": "2026-11-06T18:00:04.454Z",
      "requests": 5,
      "formats": [
        {
          "format": "json",
          "count": 2
        },
        {
          "format": "markdown",
          "count": 2
        },
        {
          "format": "html",
          "count": 1
        }
      ],
      "agents": [
        {
          "family": "AhrefsBot",
          "count": 3,
          "category": "other_bot",
          "first_seen": "2026-11-06T01:06:52.004Z",
          "last_seen": "2026-11-06T01:08:52.007Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "Mozilla/5.0 (compatible; ElevenlabsCrawler/1.0; +public-url-redacted",
          "count": 2,
          "category": "other_bot",
          "first_seen": "2026-11-05T19:13:14.867Z",
          "last_seen": "2026-11-05T19:13:16.595Z",
          "identity_status": "not_verifiable"
        }
      ]
    },
    "observed": {
      "first_seen": "2026-11-05T07:01:06.773Z",
      "last_seen": "2026-11-06T18:00:04.454Z",
      "requests": 10,
      "formats": [
        {
          "format": "html",
          "count": 5
        },
        {
          "format": "markdown",
          "count": 3
        },
        {
          "format": "json",
          "count": 2
        }
      ],
      "agents": [
        {
          "family": "AhrefsBot",
          "count": 3,
          "category": "other_bot",
          "first_seen": "2026-11-06T01:06:52.004Z",
          "last_seen": "2026-11-06T01:08:52.007Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "Mozilla/5.0 (compatible; ElevenlabsCrawler/1.0; +public-url-redacted",
          "count": 2,
          "category": "other_bot",
          "first_seen": "2026-11-05T19:13:14.867Z",
          "last_seen": "2026-11-05T19:13:16.595Z",
          "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": "2026-11-05T15:47:52.333Z",
          "last_seen": "2026-11-05T15:47:52.333Z",
          "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": "2026-11-05T12:37:47.967Z",
          "last_seen": "2026-11-05T12:37:47.967Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; ShapBot/0.1.0",
          "count": 1,
          "category": "other_bot",
          "first_seen": "2026-11-05T07:02:29.807Z",
          "last_seen": "2026-11-05T07:02:29.807Z",
          "identity_status": "not_verifiable"
        },
        {
          "family": "PerplexityBot",
          "count": 1,
          "category": "ai_crawler",
          "first_seen": "2026-11-05T14:38:13.200Z",
          "last_seen": "2026-11-05T14:38:13.200Z",
          "identity_status": "verified"
        },
        {
          "family": "SemrushBot",
          "count": 1,
          "category": "other_bot",
          "first_seen": "2026-11-05T16:14:37.446Z",
          "last_seen": "2026-11-05T16:14:37.446Z",
          "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."
  }
}