{
  "protocol_version": "1.2.0",
  "executed_at": "2026-09-20T17:57:19.704Z",
  "environment": {
    "platform": "darwin",
    "architecture": "arm64",
    "node": "v22.12.0",
    "python": "/private/tmp/edikka-semantic-html-python-1.2/bin/python",
    "multitool_python": "/private/tmp/edikka-semantic-html-python-1.2/bin/python",
    "hostname_redacted": true
  },
  "tool_versions": {
    "@mozilla/readability": "0.6.0",
    "trafilatura": "2.2.0",
    "readability_lxml": "0.8.4.1",
    "newspaper4k": "0.9.3.1",
    "justext": "3.0.2",
    "html2text": "2025.4.15",
    "markdownify": "1.2.2"
  },
  "scope": {
    "documents": 12,
    "families": 3,
    "languages": 2,
    "variants_per_pair": 2,
    "independent_web_sample": false
  },
  "options_note": "The received fixture bytes were passed unchanged to the extractors. JSDOM did not execute scripts or fetch external resources; metadata elements were not removed.",
  "determinism_control": {
    "passed": true,
    "compared": "second real execution of all seven tools on identical fixture bytes",
    "cases": [
      {
        "id": "heading-fr-1",
        "first_sha256": "08cd76a9779538ede7eb8280d6a270e4c9ca03c5beb94d7f68aec1737ec0a693",
        "replay_sha256": "08cd76a9779538ede7eb8280d6a270e4c9ca03c5beb94d7f68aec1737ec0a693"
      },
      {
        "id": "heading-fr-2",
        "first_sha256": "07113e720ad657b729a6e535783afbe54a6ed098d1ef8b272e267d4680e48af5",
        "replay_sha256": "07113e720ad657b729a6e535783afbe54a6ed098d1ef8b272e267d4680e48af5"
      },
      {
        "id": "table-fr-1",
        "first_sha256": "d2f35a3f5a39213e4ce1e78dea642b7f73bdaf3491d58692a122fa716d61bfbb",
        "replay_sha256": "d2f35a3f5a39213e4ce1e78dea642b7f73bdaf3491d58692a122fa716d61bfbb"
      },
      {
        "id": "table-fr-2",
        "first_sha256": "ec5c83c618da19b514848778f210da7c00d5eb68ba29b1be53d8e0284c382ee9",
        "replay_sha256": "ec5c83c618da19b514848778f210da7c00d5eb68ba29b1be53d8e0284c382ee9"
      },
      {
        "id": "caveat-fr-1",
        "first_sha256": "10f0a07a218722fff427d8eaa1801a06c26cbbeb7d465272ea209d3a31dd3d82",
        "replay_sha256": "10f0a07a218722fff427d8eaa1801a06c26cbbeb7d465272ea209d3a31dd3d82"
      },
      {
        "id": "caveat-fr-2",
        "first_sha256": "768b6912a8cbed5d4df8dd73698613a44b5556195933b1b8e325923b87773be8",
        "replay_sha256": "768b6912a8cbed5d4df8dd73698613a44b5556195933b1b8e325923b87773be8"
      },
      {
        "id": "heading-en-1",
        "first_sha256": "8f6d14427390d77acbf0605b0a0586ef7737bd4cb3efa1268f1a4dcab9b27950",
        "replay_sha256": "8f6d14427390d77acbf0605b0a0586ef7737bd4cb3efa1268f1a4dcab9b27950"
      },
      {
        "id": "heading-en-2",
        "first_sha256": "af25c0dd4c11a620410bdb87bd2f205291a28904dd6a16819aa48bbbc488e9fe",
        "replay_sha256": "af25c0dd4c11a620410bdb87bd2f205291a28904dd6a16819aa48bbbc488e9fe"
      },
      {
        "id": "table-en-1",
        "first_sha256": "3314c9394fcd715c62aafa45a328407fb451fd9973d8216b9c89f6714713ae39",
        "replay_sha256": "3314c9394fcd715c62aafa45a328407fb451fd9973d8216b9c89f6714713ae39"
      },
      {
        "id": "table-en-2",
        "first_sha256": "bdbeac9d28befa9b9e37ccad892ad561d0a616b50bb0cf510fcbf4fcd6ddb83c",
        "replay_sha256": "bdbeac9d28befa9b9e37ccad892ad561d0a616b50bb0cf510fcbf4fcd6ddb83c"
      },
      {
        "id": "caveat-en-1",
        "first_sha256": "11cd8a68685280b41ebd436bb481f91ca6bd955be49678b487a9ee0d6045f5b0",
        "replay_sha256": "11cd8a68685280b41ebd436bb481f91ca6bd955be49678b487a9ee0d6045f5b0"
      },
      {
        "id": "caveat-en-2",
        "first_sha256": "15965706bcb23a51e0039fc7b0c122c8c305aac3f5cb9fe6474aac225597a8a7",
        "replay_sha256": "15965706bcb23a51e0039fc7b0c122c8c305aac3f5cb9fe6474aac225597a8a7"
      }
    ]
  },
  "evaluator_counter_tests": [
    {
      "id": "changed-value",
      "accepted": false,
      "reason": "expected numeric value changed"
    },
    {
      "id": "missing-caveat",
      "accepted": false,
      "reason": "essential caveat absent"
    },
    {
      "id": "swapped-table-values",
      "accepted": false,
      "reason": "row/column association differs"
    },
    {
      "id": "misleading-occurrence",
      "accepted": false,
      "reason": "matching text occurs outside the evaluated block"
    }
  ],
  "cases": [
    {
      "id": "heading-fr-1",
      "pair_id": "heading-fr",
      "family": "heading",
      "language": "fr",
      "variant": "heading-element",
      "synthetic_data": true,
      "html_sha256": "83625fd369cd7e5294b81f954d1f846b53c3f9f7a8aa1d48ab7d3bd6e023493d",
      "visible_text_sha256": "9c61f8a1fdfbcde96c04b3d94dce89efd4d4bb5dfbb400475c61cf33ecc15f65",
      "visible_text_equality_with_pair": true,
      "pair_markup_equal_after_masking_treatment": true,
      "tools": {
        "readability": "ok",
        "trafilatura": "ok",
        "readability_lxml": "ok",
        "newspaper4k": "ok",
        "justext": "no_output",
        "html2text": "ok",
        "markdownify": "ok"
      },
      "evaluation": {
        "visible_text_outputs": [
          "present",
          "present"
        ],
        "relation": {
          "source": "explicit_heading",
          "readability": "explicit_heading",
          "trafilatura": "explicit_heading"
        },
        "structured_output_sha256": "8855edd85d72bb62a04b92da5c8827d64e70e1f078ade40e79ca5ce2ef0d1f41"
      },
      "raw_output": "outputs/heading-fr-1.json",
      "fixture": "fixtures/heading-fr-1.html"
    },
    {
      "id": "heading-fr-2",
      "pair_id": "heading-fr",
      "family": "heading",
      "language": "fr",
      "variant": "generic-element",
      "synthetic_data": true,
      "html_sha256": "e502000054065bea220ff9f84a755015f5a6d3e7f19b2fff31809c21cb45bc33",
      "visible_text_sha256": "9c61f8a1fdfbcde96c04b3d94dce89efd4d4bb5dfbb400475c61cf33ecc15f65",
      "visible_text_equality_with_pair": true,
      "pair_markup_equal_after_masking_treatment": true,
      "tools": {
        "readability": "ok",
        "trafilatura": "ok",
        "readability_lxml": "ok",
        "newspaper4k": "ok",
        "justext": "no_output",
        "html2text": "ok",
        "markdownify": "ok"
      },
      "evaluation": {
        "visible_text_outputs": [
          "present",
          "present"
        ],
        "relation": {
          "source": "not_explicit",
          "readability": "text_only",
          "trafilatura": "text_only"
        },
        "structured_output_sha256": "bc13b8a813bde25872efe90b97881c9528efb8587ec52e6fe57b5e77c7a7d571"
      },
      "raw_output": "outputs/heading-fr-2.json",
      "fixture": "fixtures/heading-fr-2.html"
    },
    {
      "id": "table-fr-1",
      "pair_id": "table-fr",
      "family": "table",
      "language": "fr",
      "variant": "header-cells",
      "synthetic_data": true,
      "html_sha256": "7e19912f8f4337ceedbdb6b7d9cc0b43aebf2ed8f72d359f411e9a725142c556",
      "visible_text_sha256": "19fe53f7b08c3d6085825a987b061ce3135657cc3fbcc233b4269ae2fe3b4fbb",
      "visible_text_equality_with_pair": true,
      "pair_markup_equal_after_masking_treatment": true,
      "tools": {
        "readability": "ok",
        "trafilatura": "ok",
        "readability_lxml": "ok",
        "newspaper4k": "ok",
        "justext": "no_output",
        "html2text": "ok",
        "markdownify": "ok"
      },
      "evaluation": {
        "visible_text_outputs": [
          "present",
          "present"
        ],
        "relation": {
          "source": "explicit_headers",
          "readability": "explicit_headers",
          "trafilatura": "explicit_headers"
        },
        "structured_output_sha256": "fc9328878aed1681eb7fdb36a770a2584e593c0ad0036ac650205e72f1f6cede"
      },
      "raw_output": "outputs/table-fr-1.json",
      "fixture": "fixtures/table-fr-1.html"
    },
    {
      "id": "table-fr-2",
      "pair_id": "table-fr",
      "family": "table",
      "language": "fr",
      "variant": "data-cells",
      "synthetic_data": true,
      "html_sha256": "1e0a3b0807f57d794396fce3fe07c0259b8c3c4c40be85cea27483f2833516b1",
      "visible_text_sha256": "19fe53f7b08c3d6085825a987b061ce3135657cc3fbcc233b4269ae2fe3b4fbb",
      "visible_text_equality_with_pair": true,
      "pair_markup_equal_after_masking_treatment": true,
      "tools": {
        "readability": "ok",
        "trafilatura": "ok",
        "readability_lxml": "ok",
        "newspaper4k": "ok",
        "justext": "no_output",
        "html2text": "ok",
        "markdownify": "ok"
      },
      "evaluation": {
        "visible_text_outputs": [
          "present",
          "present"
        ],
        "relation": {
          "source": "not_explicit",
          "readability": "table_without_explicit_headers",
          "trafilatura": "explicit_headers"
        },
        "structured_output_sha256": "df83451e75b10d57ffa44c6470b98768bc11aa1d0f2f73564c56196210615556"
      },
      "raw_output": "outputs/table-fr-2.json",
      "fixture": "fixtures/table-fr-2.html"
    },
    {
      "id": "caveat-fr-1",
      "pair_id": "caveat-fr",
      "family": "caveat",
      "language": "fr",
      "variant": "paragraph-element",
      "synthetic_data": true,
      "html_sha256": "81cf84543a529ce8dbcb55cda0f434b46b61512777cee4f3d9b167d0866c0481",
      "visible_text_sha256": "a5d4da4dadb2600c52c2216b87945fa4aeef99fb012f87f9194b5f1a8e8e00ad",
      "visible_text_equality_with_pair": true,
      "pair_markup_equal_after_masking_treatment": true,
      "tools": {
        "readability": "ok",
        "trafilatura": "ok",
        "readability_lxml": "ok",
        "newspaper4k": "ok",
        "justext": "no_output",
        "html2text": "ok",
        "markdownify": "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": "6321b220804a7368b6637224a73ca5339de21c015939fbae1380d58901b991a4"
      },
      "raw_output": "outputs/caveat-fr-1.json",
      "fixture": "fixtures/caveat-fr-1.html"
    },
    {
      "id": "caveat-fr-2",
      "pair_id": "caveat-fr",
      "family": "caveat",
      "language": "fr",
      "variant": "aside-element",
      "synthetic_data": true,
      "html_sha256": "5902c7fdfbf78740799d219bc7680ad6a3ea9d400a6ec977cb13291f28f48392",
      "visible_text_sha256": "a5d4da4dadb2600c52c2216b87945fa4aeef99fb012f87f9194b5f1a8e8e00ad",
      "visible_text_equality_with_pair": true,
      "pair_markup_equal_after_masking_treatment": true,
      "tools": {
        "readability": "ok",
        "trafilatura": "ok",
        "readability_lxml": "ok",
        "newspaper4k": "ok",
        "justext": "no_output",
        "html2text": "ok",
        "markdownify": "ok"
      },
      "evaluation": {
        "visible_text_outputs": [
          "present",
          "present"
        ],
        "relation": {
          "source": "aside_element_without_accessible_name",
          "readability": "absent",
          "trafilatura": "absent"
        },
        "structured_output_sha256": "21b5f107d6fde360935ad26b40cbf74de74fda6c3ac0ac7d55ca12e10d4c166f"
      },
      "raw_output": "outputs/caveat-fr-2.json",
      "fixture": "fixtures/caveat-fr-2.html"
    },
    {
      "id": "heading-en-1",
      "pair_id": "heading-en",
      "family": "heading",
      "language": "en",
      "variant": "heading-element",
      "synthetic_data": true,
      "html_sha256": "e4c8dd8b2ea87f113776cfe6a51420c484a24c97750639347c1ddec38b1445c1",
      "visible_text_sha256": "e40869302b92e9b402f42258e04bf4acc51e4faf496285f71deaf8bad1ed76f5",
      "visible_text_equality_with_pair": true,
      "pair_markup_equal_after_masking_treatment": true,
      "tools": {
        "readability": "ok",
        "trafilatura": "ok",
        "readability_lxml": "ok",
        "newspaper4k": "ok",
        "justext": "no_output",
        "html2text": "ok",
        "markdownify": "ok"
      },
      "evaluation": {
        "visible_text_outputs": [
          "present",
          "present"
        ],
        "relation": {
          "source": "explicit_heading",
          "readability": "explicit_heading",
          "trafilatura": "explicit_heading"
        },
        "structured_output_sha256": "a0fdb3dfab941cd00299f62b245bc568bc05be57b36dab398faede85babed333"
      },
      "raw_output": "outputs/heading-en-1.json",
      "fixture": "fixtures/heading-en-1.html"
    },
    {
      "id": "heading-en-2",
      "pair_id": "heading-en",
      "family": "heading",
      "language": "en",
      "variant": "generic-element",
      "synthetic_data": true,
      "html_sha256": "4173dad4d266784865a6ed57bddde0f63604d5b192c97e4b434405a9427216ed",
      "visible_text_sha256": "e40869302b92e9b402f42258e04bf4acc51e4faf496285f71deaf8bad1ed76f5",
      "visible_text_equality_with_pair": true,
      "pair_markup_equal_after_masking_treatment": true,
      "tools": {
        "readability": "ok",
        "trafilatura": "ok",
        "readability_lxml": "ok",
        "newspaper4k": "ok",
        "justext": "no_output",
        "html2text": "ok",
        "markdownify": "ok"
      },
      "evaluation": {
        "visible_text_outputs": [
          "present",
          "present"
        ],
        "relation": {
          "source": "not_explicit",
          "readability": "text_only",
          "trafilatura": "text_only"
        },
        "structured_output_sha256": "06cf1304879be30fca7cdf40727c0521165c1c3d67fc279840221589b8db3e2f"
      },
      "raw_output": "outputs/heading-en-2.json",
      "fixture": "fixtures/heading-en-2.html"
    },
    {
      "id": "table-en-1",
      "pair_id": "table-en",
      "family": "table",
      "language": "en",
      "variant": "header-cells",
      "synthetic_data": true,
      "html_sha256": "374211644b0d1ad2d4ae9647d84e7e3e518ff392b9f4aaa108e438677c2b05da",
      "visible_text_sha256": "dcd87fc5c06b6fe99d76138e6bf2e4fe1aec9516f4c094b20f16ffa38e0981a1",
      "visible_text_equality_with_pair": true,
      "pair_markup_equal_after_masking_treatment": true,
      "tools": {
        "readability": "ok",
        "trafilatura": "ok",
        "readability_lxml": "ok",
        "newspaper4k": "ok",
        "justext": "no_output",
        "html2text": "ok",
        "markdownify": "ok"
      },
      "evaluation": {
        "visible_text_outputs": [
          "present",
          "present"
        ],
        "relation": {
          "source": "explicit_headers",
          "readability": "explicit_headers",
          "trafilatura": "explicit_headers"
        },
        "structured_output_sha256": "49632bd6105f1759d06d225ab848dd3f95e4722045b78c82940ef0c65a439c60"
      },
      "raw_output": "outputs/table-en-1.json",
      "fixture": "fixtures/table-en-1.html"
    },
    {
      "id": "table-en-2",
      "pair_id": "table-en",
      "family": "table",
      "language": "en",
      "variant": "data-cells",
      "synthetic_data": true,
      "html_sha256": "f047171076d291106cd77b19fe1195a11b287e101144a134317cf2a3f64dd654",
      "visible_text_sha256": "dcd87fc5c06b6fe99d76138e6bf2e4fe1aec9516f4c094b20f16ffa38e0981a1",
      "visible_text_equality_with_pair": true,
      "pair_markup_equal_after_masking_treatment": true,
      "tools": {
        "readability": "ok",
        "trafilatura": "ok",
        "readability_lxml": "ok",
        "newspaper4k": "ok",
        "justext": "no_output",
        "html2text": "ok",
        "markdownify": "ok"
      },
      "evaluation": {
        "visible_text_outputs": [
          "present",
          "present"
        ],
        "relation": {
          "source": "not_explicit",
          "readability": "table_without_explicit_headers",
          "trafilatura": "explicit_headers"
        },
        "structured_output_sha256": "669d5a2b1519bf2faa870e6eeaaba2b8422324156f7f58bd70b42f770662f180"
      },
      "raw_output": "outputs/table-en-2.json",
      "fixture": "fixtures/table-en-2.html"
    },
    {
      "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,
      "tools": {
        "readability": "ok",
        "trafilatura": "ok",
        "readability_lxml": "ok",
        "newspaper4k": "ok",
        "justext": "no_output",
        "html2text": "ok",
        "markdownify": "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"
      },
      "raw_output": "outputs/caveat-en-1.json",
      "fixture": "fixtures/caveat-en-1.html"
    },
    {
      "id": "caveat-en-2",
      "pair_id": "caveat-en",
      "family": "caveat",
      "language": "en",
      "variant": "aside-element",
      "synthetic_data": true,
      "html_sha256": "d364cbe27a74da20accf413f383b852914e5fa9cf4216d6e7d3960ce561cf95a",
      "visible_text_sha256": "066ed1dc21744337022e89ba1f88625cb1f4eeba9f9e2a3fd673ee2cdd499ded",
      "visible_text_equality_with_pair": true,
      "pair_markup_equal_after_masking_treatment": true,
      "tools": {
        "readability": "ok",
        "trafilatura": "ok",
        "readability_lxml": "ok",
        "newspaper4k": "ok",
        "justext": "no_output",
        "html2text": "ok",
        "markdownify": "ok"
      },
      "evaluation": {
        "visible_text_outputs": [
          "present",
          "present"
        ],
        "relation": {
          "source": "aside_element_without_accessible_name",
          "readability": "absent",
          "trafilatura": "absent"
        },
        "structured_output_sha256": "b44475d6777e25039765977268a711d4cc0ca0f5e7cf25957bcec93c0064c15a"
      },
      "raw_output": "outputs/caveat-en-2.json",
      "fixture": "fixtures/caveat-en-2.html"
    }
  ]
}