Displaces the byline by a full column: the author line that sits above the two-column split in the source is emitted only after the entire left column, and its footnote markers are rendered inconsistently.
What was measured
Reading Order & Structure
Maintains headings, sections, column order, document hierarchy, and overall flow.
decisive for this rankingtransformation
Clean Markdown requires the original reading order, headings, sections, and hierarchy to be maintained correctly. (3 of 3 judges)
What was given, what came back
Test input: Scanned Research Paper · pdf · group: scanned-research-paper
Input — what we sent
An image-only scanned research paper used to stress OCR and layout recovery in a multi-column academic document with figures, charts, tables, captions, and references.
Why this input is hard
- · OCR on scanned pages
- · Multi-column reading order
- · Figure and chart handling
- · Table reconstruction from scans
- · Caption association
- · Reference extraction
- · Overall document structure retention
Output — unretouched
Also checked on this input — same tool, 8 other criteria
Advanced Features✓ WorkedSchema-driven extract.run fully recovers the corrupted Table 4 rows, returning all 12 checked rows exactly, including the 10-inch-cut 1979 MPB row whose parse.run output was badly garbled.Advanced Features◐ MixedThe confidence signal flags the faint handwritten margin note and the garbled Table 4 as low confidence, but it misses the hallucinated 'USA' word in the title, which is still rated 0.9354 confident.Complex Document Handling⚠ StruggledHandles the 12-page scan in 10.6 seconds with no truncation, but the densest 17-column table has unreadable stretches with injected glyphs and run-on numbers.Markdown Quality✓ WorkedUses no invented tags or malformed markdown; the only HTML seen is legitimate <br /> inside table cells, so the syntax stays clean even though the document does not surface real heading markup.Table Preservation✗ FailedCatastrophically corrupts the dense 17-column Table 4, injecting non-Latin glyphs into numeric cells and producing run-on strings such as 238-563NT, 2231, and 8998 6 in the 10-inch and 12-inch blocks.Table Preservation◐ MixedPartially reconstructs Table 1: most of the roughly 90 numeric values are exact, but literal 0 values in the 12-inch column become blanks, one mean cell picks up stray digits (33.0 830000), and a row-label-only section header is broadcast across all six columns in one instance.Text & OCR Completeness✓ WorkedConverts all 12 scanned pages with no gaps; the page-11-to-page-12 handoff is preserved verbatim, and a separate page-marker output shows pages 1 through 12 present with no missing markers.Visual Content Retention✓ WorkedSegments a shield logo out of a single full-page raster scan and also retains Figure 1 as an image with an accurate synthesized caption; the returned logo crop is a tight 77x81px cut with legible shield text.
Provenance
- Observation
- 7840c24e-489b-4551-b576-148911ebe640
- Evidence run
- 6e3160de-fe46-4b45-b071-72560b5c5d0e
- Study
- Convert a Complex PDF into Clean Markdown with an API
- Research task
- 86b9h7t37
- Tested at
- not recorded
- Source
- first-party
- Evidence state
- verified
- Proof shown
- input + output shown
- Cost / latency
- not captured
- Repeat run
- not captured
- Tester
- not captured
The last three rows are honest blanks, not placeholders — our capture has no field for them yet.
Query this
get_evidence({
tool: "reducto",
scenario: "scanned-research-paper"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 8 other tools
measured on Reading Order & Structure
Adobe API✗ FailedDumps the scanned title page as a dense OCR block without section boundaries or other structural cues, so the document hierarchy is lost.Extend AI✓ WorkedReconstructs a multi-column research page so the 'STUDY AREA' heading, its paragraphs, and the following 'STAND PRESCRIPTIONS' section stay in order.Landing AI✓ WorkedReconstructs a dense two-column section with its hierarchy intact, keeping the section heading attached to the correct body text across the columns.LlamaParse✓ WorkedReflows a two-column scanned page into a single coherent reading order while preserving section-to-body flow.Mistral AI✗ FailedThe opening page loses the distinction between the document title and the abstract, flattening the semantic organization of the first page.Nutrient.io✗ FailedMisorders the first page so the abstract is placed before the title, showing a layout-reading-order inversion on the scanned article.Tensorlake✓ WorkedRetains section-level reading order in a scanned multi-column paper, with headings continuing to guide the flow across columns and into the next section.Upstage AI✗ FailedBreaks paragraph-level segmentation in the scanned two-column page, so the extracted text no longer follows the source column order cleanly.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com