{
  "protocol_version": "1.2.0",
  "executed_at": "2026-09-20T17:57:19.704Z",
  "id": "caveat-en-1",
  "pair_id": "caveat-en",
  "family": "caveat",
  "language": "en",
  "variant": "paragraph-element",
  "synthetic_data": true,
  "html_sha256": "11babb37902010f22ccbe9592ac6757c3f8543c2ab09dff81157398e1dba5fe5",
  "visible_text_sha256": "066ed1dc21744337022e89ba1f88625cb1f4eeba9f9e2a3fd673ee2cdd499ded",
  "visible_text_equality_with_pair": true,
  "pair_markup_equal_after_masking_treatment": true,
  "dom_witness": {
    "headings": [
      {
        "level": 1,
        "text": "Offline protocol for preserving relationships"
      },
      {
        "level": 2,
        "text": "Synthetic result"
      }
    ],
    "tables": [],
    "asides": [],
    "paragraphs": [
      "Edikka · semantic HTML extraction protocol · v1.2.0",
      "This synthetic document compares two markups while text, order, classes and surroundings remain identical. The data are fictional and describe neither Edikka nor a client.",
      "The observed rate is 42% across 200 simulated operations in May 2026.",
      "Essential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system.",
      "The conclusion must be read with its unit, period, scope and caveat. Finding a word in an output is not enough to prove that the relationship was preserved.",
      "Offline synthetic fixture · v1.2.0"
    ]
  },
  "readability": {
    "tool": "@mozilla/readability",
    "version": "0.6.0",
    "configuration": {
      "keepClasses": false,
      "charThreshold": 500,
      "disableJSONLD": false
    },
    "status": "ok",
    "title": "Offline protocol for preserving relationships",
    "byline": null,
    "dir": null,
    "lang": "en",
    "siteName": null,
    "publishedTime": null,
    "excerpt": "This synthetic document compares two markups while text, order, classes and surroundings remain identical. The data are fictional and describe neither Edikka nor a client.",
    "content": "<div id=\"readability-page-1\" class=\"page\"><div><article><p>This synthetic document compares two markups while text, order, classes and surroundings remain identical. The data are fictional and describe neither Edikka nor a client.</p><h2>Synthetic result</h2><p>The observed rate is 42% across 200 simulated operations in May 2026.</p><p>Essential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system.</p><p>The conclusion must be read with its unit, period, scope and caveat. Finding a word in an output is not enough to prove that the relationship was preserved.</p></article></div></div>",
    "textContent": "This synthetic document compares two markups while text, order, classes and surroundings remain identical. The data are fictional and describe neither Edikka nor a client.Synthetic resultThe observed rate is 42% across 200 simulated operations in May 2026.Essential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system.The conclusion must be read with its unit, period, scope and caveat. Finding a word in an output is not enough to prove that the relationship was preserved.",
    "length": 522
  },
  "trafilatura": {
    "tool": "trafilatura",
    "version": "2.2.0",
    "configuration": {
      "include_comments": false,
      "include_links": true,
      "include_tables": true,
      "no_fallback": false,
      "favor_precision": false,
      "favor_recall": false,
      "formats": [
        "xml",
        "txt"
      ]
    },
    "source": "caveat-en-1.html",
    "xml": "<doc fingerprint=\"7bd75bcc2327f82\">\n  <main>\n    <head rend=\"h1\">Offline protocol for preserving relationships</head>\n    <p>This synthetic document compares two markups while text, order, classes and surroundings remain identical. The data are fictional and describe neither Edikka nor a client.</p>\n    <head rend=\"h2\">Synthetic result</head>\n    <p>The observed rate is 42% across 200 simulated operations in May 2026.</p>\n    <p>Essential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system.</p>\n    <p>The conclusion must be read with its unit, period, scope and caveat. Finding a word in an output is not enough to prove that the relationship was preserved.</p>\n  </main>\n  <comments/>\n</doc>",
    "text": "Offline protocol for preserving relationships\nThis synthetic document compares two markups while text, order, classes and surroundings remain identical. The data are fictional and describe neither Edikka nor a client.\nSynthetic result\nThe observed rate is 42% across 200 simulated operations in May 2026.\nEssential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system.\nThe conclusion must be read with its unit, period, scope and caveat. Finding a word in an output is not enough to prove that the relationship was preserved.",
    "status": "ok"
  },
  "additional_extractors": {
    "source": "caveat-en-1.html",
    "readability_lxml": {
      "tool": "readability-lxml",
      "version": "0.8.4.1",
      "title": "Offline protocol for preserving relationships",
      "html": "<div><body id=\"readabilityBody\"><main><article><h1>Offline protocol for preserving relationships</h1><p>This synthetic document compares two markups while text, order, classes and surroundings remain identical. The data are fictional and describe neither Edikka nor a client.</p><h2>Synthetic result</h2><p>The observed rate is 42% across 200 simulated operations in May 2026.</p><p class=\"case-caveat\">Essential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system.</p><p>The conclusion must be read with its unit, period, scope and caveat. Finding a word in an output is not enough to prove that the relationship was preserved.</p></article></main></body></div>",
      "status": "ok"
    },
    "newspaper4k": {
      "tool": "newspaper4k",
      "version": "0.9.3.1",
      "title": "Offline protocol for preserving relationships",
      "text": "This synthetic document compares two markups while text, order, classes and surroundings remain identical. The data are fictional and describe neither Edikka nor a client.\n\nSynthetic result\n\nThe observed rate is 42% across 200 simulated operations in May 2026.\n\nEssential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system.\n\nThe conclusion must be read with its unit, period, scope and caveat. Finding a word in an output is not enough to prove that the relationship was preserved.",
      "html": "<div><h1>Offline protocol for preserving relationships</h1><p>This synthetic document compares two markups while text, order, classes and surroundings remain identical. The data are fictional and describe neither Edikka nor a client.</p><h2>Synthetic result</h2><p>The observed rate is 42% across 200 simulated operations in May 2026.</p><p class=\"case-caveat\">Essential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system.</p><p>The conclusion must be read with its unit, period, scope and caveat. Finding a word in an output is not enough to prove that the relationship was preserved.</p></div>",
      "status": "ok"
    },
    "justext": {
      "tool": "jusText",
      "version": "3.0.2",
      "text": null,
      "paragraphs": [
        {
          "text": "Edikka · semantic HTML extraction protocol · v1.2.0",
          "is_boilerplate": true
        },
        {
          "text": "Offline protocol for preserving relationships",
          "is_boilerplate": true
        },
        {
          "text": "This synthetic document compares two markups while text, order, classes and surroundings remain identical. The data are fictional and describe neither Edikka nor a client.",
          "is_boilerplate": true
        },
        {
          "text": "Synthetic result",
          "is_boilerplate": true
        },
        {
          "text": "The observed rate is 42% across 200 simulated operations in May 2026.",
          "is_boilerplate": true
        },
        {
          "text": "Essential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system.",
          "is_boilerplate": true
        },
        {
          "text": "The conclusion must be read with its unit, period, scope and caveat. Finding a word in an output is not enough to prove that the relationship was preserved.",
          "is_boilerplate": true
        },
        {
          "text": "Offline synthetic fixture · v1.2.0",
          "is_boilerplate": true
        }
      ],
      "status": "no_output"
    },
    "html2text": {
      "tool": "html2text",
      "version": "2025.4.15",
      "markdown": "Edikka · semantic HTML extraction protocol · v1.2.0\n\n# Offline protocol for preserving relationships\n\nThis synthetic document compares two markups while text, order, classes and surroundings remain identical. The data are fictional and describe neither Edikka nor a client.\n\n## Synthetic result\n\nThe observed rate is 42% across 200 simulated operations in May 2026.\n\nEssential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system.\n\nThe conclusion must be read with its unit, period, scope and caveat. Finding a word in an output is not enough to prove that the relationship was preserved.\n\nOffline synthetic fixture · v1.2.0\n",
      "status": "ok"
    },
    "markdownify": {
      "tool": "markdownify",
      "version": "1.2.2",
      "markdown": "Offline protocol for preserving relationships\n\n\nEdikka · semantic HTML extraction protocol · v1.2.0\n\n# Offline protocol for preserving relationships\n\nThis synthetic document compares two markups while text, order, classes and surroundings remain identical. The data are fictional and describe neither Edikka nor a client.\n\n## Synthetic result\n\nThe observed rate is 42% across 200 simulated operations in May 2026.\n\nEssential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system.\n\nThe conclusion must be read with its unit, period, scope and caveat. Finding a word in an output is not enough to prove that the relationship was preserved.\n\nOffline synthetic fixture · v1.2.0",
      "status": "ok"
    }
  },
  "evaluation": {
    "visible_text_outputs": [
      "present",
      "present"
    ],
    "relation": {
      "source": "ordinary_paragraph",
      "readability": "text_preserved_element_not_preserved",
      "trafilatura": "text_preserved_element_not_preserved"
    },
    "structured_output_sha256": "879af1b5eed7720b5767fd5ef15f2f638c26dbaa865ba768ef9734762c9d6c79"
  }
}