Captures scanned-page library stamps and barcode-like artifacts directly into the OCR text flow, adding noise such as `186153` and `CSX` to the title region.

✓ Worked🧾 artifact-verifiedinput + output shownTest date not recordeddocling
What was measured
Bonus: Unique or Anomalous Behaviors

Captures distinctive tool-specific behavior worth noting, positive or negative, that does not fit the main criteria.

transformation

What was given, what came back

Input — what we sent
image
No input — this is a capability finding
The observation is about the tool itself rather than one test input, so there is nothing to show on this side by design.
Output — unretouched
image
Provenance
Observation
fa872ad5-e808-40e2-b39d-0c5b34cd9bab
Evidence run
723182be-ace6-41cc-afa9-0772af8566c0
Study
PDF to markdown using open source libraries
Research task
86ban5kjq
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: "docling"
})
MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 0 other tools
measured on Bonus: Unique or Anomalous Behaviors

No other tool was measured on this criterion for this input.

Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com