SEMANTIC HTML · ARCHIVED RESULTS

Semantic HTML.
Compare what tools preserve.

The same text. One markup change.
Two outputs to inspect, with evidence.

Explore an archived run from 20 September 2026, re-evaluated on 21 September. No extraction runs during your visit.

EXPLORE THE CONTROLLED CORPUS

Essential caveat

Trafilatura 2.2.0 · Extractor / reading tool · English document

All 42 comparisons

The check observes whether the caveat text is present. Its attachment to the claim is not evaluated. This case does not justify removing all aside elements. Test scope.

A

VARIANT A

A caveat in a p

Output produced

Caveat text : Present. Source

01 · The HTML change

<p class="case-caveat">Essential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system.</p>

Exact input excerpt · Original HTML ↓

02 · What the tool produces XML

…
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>
  </main>
  <comments/>
</doc>

Excerpt identified by the corrected evaluator. Full output below.

03 · The documented observation

Caveat text
Present
Element containing the caveat
Other element
Attachment to the claim
Not evaluated

Verdict source: results.json · caveat-en-1 / trafilatura

Inspect the full evidence

The verdicts above come from corrected results.json. The raw file’s evaluation fields are historical and are not authoritative here.

results.json/cases/10/evaluation/relation/trafilatura

Corrected verdict, unchanged
{
  "status": "ok",
  "tool_class": "content_extractor",
  "format": "xml",
  "caveat_text": "present",
  "caveat_element": "not_aside",
  "attachment_to_claim": "not_evaluated",
  "evidence": {
    "excerpt": "Essential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system."
  },
  "output_field": "trafilatura.xml",
  "output_sha256": "38f60a02988bc76e1135237947abd632ecb41946ba385398f6fce801e04fb7be"
}
Complete studied output field

trafilatura.xml

<doc fingerprint="7bd75bcc2327f82">
  <main>
    <head rend="h1">Offline protocol for preserving relationships</head>
    <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>
    <head rend="h2">Synthetic result</head>
    <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>
  </main>
  <comments/>
</doc>
Archived version and options

Trafilatura 2.2.0 · Execution 2026-09-20

{
  "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"
    ]
  }
}

Archived runner · Python options

SHA-256 hashes
HTML input
11babb37902010f22ccbe9592ac6757c3f8543c2ab09dff81157398e1dba5fe5
Evaluated output field
38f60a02988bc76e1135237947abd632ecb41946ba385398f6fce801e04fb7be

Complete raw output file ↗

B

VARIANT B

A caveat in an aside

Output produced

Caveat text : Absent. Source

01 · The HTML change

<aside class="case-caveat">Essential caveat: this synthetic example measures neither real traffic, ranking, nor citation by an AI system.</aside>

Exact input excerpt · Original HTML ↓

02 · What the tool produces XML

<doc fingerprint="53cfcacd2327f82">
  <main>
    <head rend="h1">Offline protocol for preserving relationships</head>
    <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>
    <head rend="h2">Synthetic result</head>
    <p>The observed rate is 42% across 200 simulated operations in May 2026.</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>
  </main>
  <comments/>
</doc>

Excerpt from the start of the output; it does not establish absence on its own. Full output below.

03 · The documented observation

Caveat text
Absent
Element containing the caveat
Absent
Attachment to the claim
Not evaluated

Verdict source: results.json · caveat-en-2 / trafilatura

Inspect the full evidence

The verdicts above come from corrected results.json. The raw file’s evaluation fields are historical and are not authoritative here.

results.json/cases/11/evaluation/relation/trafilatura

Corrected verdict, unchanged
{
  "status": "ok",
  "tool_class": "content_extractor",
  "format": "xml",
  "caveat_text": "absent",
  "caveat_element": "absent",
  "attachment_to_claim": "not_evaluated",
  "evidence": {
    "excerpt": null
  },
  "output_field": "trafilatura.xml",
  "output_sha256": "1872b0aabe5e4fadfb76e8751a9084aa4c130fecd797e32e8e54f90def60e9b5"
}
Complete studied output field

trafilatura.xml

<doc fingerprint="53cfcacd2327f82">
  <main>
    <head rend="h1">Offline protocol for preserving relationships</head>
    <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>
    <head rend="h2">Synthetic result</head>
    <p>The observed rate is 42% across 200 simulated operations in May 2026.</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>
  </main>
  <comments/>
</doc>
Archived version and options

Trafilatura 2.2.0 · Execution 2026-09-20

{
  "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"
    ]
  }
}

Archived runner · Python options

SHA-256 hashes
HTML input
d364cbe27a74da20accf413f383b852914e5fa9cf4216d6e7d3960ce561cf95a
Evaluated output field
1872b0aabe5e4fadfb76e8751a9084aa4c130fecd797e32e8e54f90def60e9b5

Complete raw output file ↗

Identical text and isolated intervention within this pair, according to the protocol witnesses. Translations are not independent observations. View pair witnesses.

LOOK FURTHER

Every result has a scope.

These observations do not rank tools. They do not measure overall accessibility, search ranking, or understanding or citation by AI.

Claims excluded by the protocol