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

Table

markdownify 1.2.2 · Markdown converter · English document

All 42 comparisons

Values must match exactly in the same row. An XML caption is not a column header; a Markdown table does not prove the input’s HTML semantics. Test scope.

A

VARIANT A

Headers with th + scope

Output produced

Expected value row : Exact values, in order · Column headers : Markdown header row · Row header : Not encoded in Markdown. Source

01 · The HTML change

<table><caption>Synthetic measurements</caption><thead><tr><th class="case-cell" scope="col">Indicator</th><th class="case-cell" scope="col">Unit</th><th class="case-cell" scope="col">Period</th><th class="case-cell" scope="col">Value</th></tr></thead><tbody><tr><th class="case-cell" scope="row">Response time</th><td class="case-cell">seconds</td><td class="case-cell">May 2026</td><td class="case-cell">1.8</td></tr></tbody></table>

Exact input excerpt · Original HTML ↓

02 · What the tool produces MARKDOWN

…
client.

## Synthetic measurements

Synthetic measurements

| Indicator | Unit | Period | Value |
| --- | --- | --- | --- |
| Response time | seconds | May 2026 | 1.8 |

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

Excerpt identified by the corrected evaluator. Full output below.

03 · The documented observation

Expected value row
Exact values, in order
Column headers
Markdown header row
Row header
Not encoded in Markdown
Output structure
Markdown layout

Verdict source: results.json · table-en-1 / markdownify

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/8/evaluation/relation/markdownify

Corrected verdict, unchanged
{
  "status": "ok",
  "tool_class": "markdown_converter",
  "format": "markdown",
  "table_structure": "markdown_layout",
  "expected_data_row": "exact_values_in_order",
  "column_header_relation": "markdown_header_row",
  "row_header_relation": "not_encoded_in_markdown",
  "column_labels": [
    "Indicator",
    "Unit",
    "Period",
    "Value"
  ],
  "data_values": [
    "Response time",
    "seconds",
    "May 2026",
    "1.8"
  ],
  "evidence": {
    "header_row": "| Indicator | Unit | Period | Value |\n| --- | --- | --- | --- |",
    "data_row": "| Response time | seconds | May 2026 | 1.8 |",
    "table_excerpt": "| Indicator | Unit | Period | Value |\n| --- | --- | --- | --- |\n| Response time | seconds | May 2026 | 1.8 |"
  },
  "output_field": "additional_extractors.markdownify.markdown",
  "output_sha256": "b89ed68e1940ec52ddc6c2ca9f80ec35d1b57d7cde93df26244dd029a4fcff13",
  "source_column_headers_explicit": true
}
Complete studied output field

additional_extractors.markdownify.markdown

Offline protocol for preserving relationships


Edikka · semantic HTML extraction protocol · v1.2.0

# Offline protocol for preserving relationships

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 measurements

Synthetic measurements

| Indicator | Unit | Period | Value |
| --- | --- | --- | --- |
| Response time | seconds | May 2026 | 1.8 |

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
Archived version and options

markdownify 1.2.2 · Execution 2026-09-20

{
  "version": "1.2.2",
  "configuration": "No configuration field in this output; consult the archived runner."
}

Archived runner · Python options

SHA-256 hashes
HTML input
374211644b0d1ad2d4ae9647d84e7e3e518ff392b9f4aaa108e438677c2b05da
Evaluated output field
b89ed68e1940ec52ddc6c2ca9f80ec35d1b57d7cde93df26244dd029a4fcff13

Complete raw output file ↗

B

VARIANT B

Ordinary td cells

Output produced

Expected value row : Exact values, in order · Column headers : Markdown header row · Row header : Not encoded in Markdown. Source

01 · The HTML change

<table><caption>Synthetic measurements</caption><thead><tr><td class="case-cell">Indicator</td><td class="case-cell">Unit</td><td class="case-cell">Period</td><td class="case-cell">Value</td></tr></thead><tbody><tr><td class="case-cell">Response time</td><td class="case-cell">seconds</td><td class="case-cell">May 2026</td><td class="case-cell">1.8</td></tr></tbody></table>

Exact input excerpt · Original HTML ↓

02 · What the tool produces MARKDOWN

…
client.

## Synthetic measurements

Synthetic measurements

| Indicator | Unit | Period | Value |
| --- | --- | --- | --- |
| Response time | seconds | May 2026 | 1.8 |

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

Excerpt identified by the corrected evaluator. Full output below.

03 · The documented observation

Expected value row
Exact values, in order
Column headers
Markdown header row
Row header
Not encoded in Markdown
Output structure
Markdown layout

Verdict source: results.json · table-en-2 / markdownify

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/9/evaluation/relation/markdownify

Corrected verdict, unchanged
{
  "status": "ok",
  "tool_class": "markdown_converter",
  "format": "markdown",
  "table_structure": "markdown_layout",
  "expected_data_row": "exact_values_in_order",
  "column_header_relation": "markdown_header_row",
  "row_header_relation": "not_encoded_in_markdown",
  "column_labels": [
    "Indicator",
    "Unit",
    "Period",
    "Value"
  ],
  "data_values": [
    "Response time",
    "seconds",
    "May 2026",
    "1.8"
  ],
  "evidence": {
    "header_row": "| Indicator | Unit | Period | Value |\n| --- | --- | --- | --- |",
    "data_row": "| Response time | seconds | May 2026 | 1.8 |",
    "table_excerpt": "| Indicator | Unit | Period | Value |\n| --- | --- | --- | --- |\n| Response time | seconds | May 2026 | 1.8 |"
  },
  "output_field": "additional_extractors.markdownify.markdown",
  "output_sha256": "b89ed68e1940ec52ddc6c2ca9f80ec35d1b57d7cde93df26244dd029a4fcff13",
  "source_column_headers_explicit": false
}
Complete studied output field

additional_extractors.markdownify.markdown

Offline protocol for preserving relationships


Edikka · semantic HTML extraction protocol · v1.2.0

# Offline protocol for preserving relationships

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 measurements

Synthetic measurements

| Indicator | Unit | Period | Value |
| --- | --- | --- | --- |
| Response time | seconds | May 2026 | 1.8 |

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
Archived version and options

markdownify 1.2.2 · Execution 2026-09-20

{
  "version": "1.2.2",
  "configuration": "No configuration field in this output; consult the archived runner."
}

Archived runner · Python options

SHA-256 hashes
HTML input
f047171076d291106cd77b19fe1195a11b287e101144a134317cf2a3f64dd654
Evaluated output field
b89ed68e1940ec52ddc6c2ca9f80ec35d1b57d7cde93df26244dd029a4fcff13

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