The parse pipeline’s confidence field catches all 10 footer-number corruptions and also produces one false alarm on a correct securities table, so the signal is real but not perfectly calibrated.
What was measured
Advanced Features
Provides separate table/chart extraction and flags low-confidence OCR or ambiguous regions.
context, not decisivetransformation
Separate extraction modes and OCR confidence flags are useful workflow features, but they do not by themselves determine whether the Markdown conversion is good. (3 of 3 judges)
What was given, what came back
Test input: Hybrid Earnings Report · pdf · group: hybrid-earnings-report
Input — what we sent
Hybrid Earnings Report
A long, real-world hybrid annual report used to benchmark end-to-end PDF-to-markdown conversion. It combines native text, financial tables, charts/graphics, and scanned signature/stamp regions, stressing preservation of document structure, reading order, and embedded visual content across a multi-section report.
Why this input is hard
- · Native digital text extraction
- · Complex financial table preservation
- · Chart and graphic retention
- · Image-based signatures and stamps
- · Reading order across a long multi-section report
- · Markdown quality and consistency
Output — unretouched
Also checked on this input — same tool, 9 other criteria
Complex Document Handling◐ MixedProcesses the full 84-page mixed-content report in 25.5 seconds with no truncation and keeps the hardest nested table’s 27 values exact, but 10 footer numbers are corrupted in the back two-thirds of the file.Markdown Quality⚠ StruggledProduces usable but not clean markdown: the output contains 12 <signature> tags, 2 <empty> placeholders, and literal HTML tags such as <b>, <i>, and <u> instead of pure CommonMark.Reading Order & Structure⚠ StruggledDrops heading structure on most of the filing: the FORM 10-K opening area receives no # or ## markup, and the report says 80 of 84 pages stay as plain paragraphs rather than navigable section headings.Reading Order & Structure✓ WorkedLinearizes a two-column page correctly, reading the full left column, including all four bullets, before the right-column continuation appears, with no interleaving or sequence inversion.Table Preservation✗ FailedMis-merges two independent side-by-side lists into one table, forcing unrelated cost-of-sales and SG&A bullets into fake row pairs where no row correspondence exists in the source.Table Preservation✓ WorkedPreserves a genuinely row-paired 52-row state table as a clean grid, keeping the 1,792 stores total and 239,539 retail-square-footage total intact.Text & OCR Completeness✓ WorkedConverts the full 84-page native-digital annual report with no skipped pages; the output contains all 84 page-marker pairs, and checked high-risk numbers survive exactly, including the $51,550,988,273 market-value figure and 599,982,121 shares outstanding.Visual Content Retention✓ WorkedRetains visual content as real image outputs when requested: the portrait, donut chart, and bar chart are all returned as preserved figure/image crops rather than being dropped.Visual Content Retention✗ FailedDoes not retain handwritten signature graphics as images: a signature crop returns only the <signature> placeholder plus the printed name/title, omitting the cursive mark itself.
Provenance
- Observation
- 7fb155c1-7886-4bd4-9e2d-1fec0f47b677
- 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: "hybrid-earnings-report"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 3 other tools
measured on Advanced Features
Landing AI✓ WorkedEmits semantic attestation blocks for handwritten-signature regions and a blurry signature stamp, distinguishing the signer/company name and the signature legibility instead of leaving those regions unannotated.Tensorlake✓ WorkedProvides separate chart extraction for the SG&A waterfall, outputting chart metadata with a title, axis labels, 10 category labels, and a numeric series instead of only inline prose.Upstage AI✓ WorkedSeparately extracts chart content into textual summaries and value tables, including a waterfall chart and bar charts with year/value pairs and growth statistics.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com