Evidence · first-party tested

Misreads page layout enough to place the abstract before the title, showing a layout-driven ordering error in the extracted page structure.

✗ Failed🧾 artifact-verifiedTested Jun 20, 2026Nutrient.io →
Output — unretouched
Scanned first page of a USDA Forest Service research note.
Scanned first page of a USDA Forest Service research note.
Output — unretouched
OCR-extracted text for the first page of the report.
OCR-extracted text for the first page of the report.
The observation

Misreads page layout enough to place the abstract before the title, showing a layout-driven ordering error in the extracted page structure.

Criterion: Reading Order & Structure · Scenario: Scanned Research Paper (group: scanned-research-paper)
Query this
get_evidence({
  tool: "nutrient-io",
  scenario: "scanned-research-paper"
})
MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, other tools
Adobe PDF Extract API ✗ FailedExtend AI ✓ WorkedLanding AI ✗ FailedLlamaparse ✓ WorkedMistral AI ✗ FailedTensorlake ✓ WorkedUpstage AI ✗ Failed
Real outputs, no retouching · every cell queryable via API & MCP · aidemos.com