Unverified50% confidenceFactExact time
The PDF was generated by a scanner-style pipeline: pages were first rasterized into images, then an invisible OCR text layer was overlaid for accessibility, and the extractor read the vector outline layer (titles, bookmarks), so it returned only the title.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe PDF parser built by the developer wraps a FastAPI backend around pdfplumber, probing precise visual grid line coordinates page by page rather than performing basic text stream reading.75% similarUnverifiedMany PDF parsers preferentially follow the drawing instructions of the page content stream, and when they encounter a layer containing only vector outlines they return the result, without checking document-level density.73% similarUnverifiedThe OCR text layer works by overlaying real selectable text objects at character positions on the rasterized page image, and setting the rendering mode to invisible (Tr 3) or transparent/same as the background color, so that copy-paste, Ctrl+F search, and screen readers work normally.73% similarUnverifiedpplx-embed-v2-late can retrieve PDF pages without OCR by processing PDF pages directly as images and mapping them into the same embedding space as text.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1022475API
curl https://kongchang.com/api/v1/knowledge/claims/1022475MCP
get_claim(id=1022475)