PDF→Markdown fixture corpus — round 1
A shared pinned PDF corpus used as input for both PDF-to-Markdown benchmark versions.
What this resource provides or represents
This resource provides the pinned PDF input corpus used in PDF-to-Markdown evaluations. The same shared corpus supports both benchmark versions, and a single PDF can serve more than one test case.
Scope and composition
The boundaries of the resource and how its meaningful parts are organized for evaluation.
Shared pinned PDF inputs for the two PDF-to-Markdown benchmark versions.
Version 1 contains 12 distinct pinned PDF files. One PDF can carry several content types and can support more than one test case.
Supplies the source artifacts that test cases are written against and executed on.
The corpus is shared across both tracks, and fixture count is not identity-defining.
Versions
Public context for the resource versions used in evaluation.
Version 1
12 distinct pinned PDF files shared across both PDF-to-Markdown benchmark tracks.
Benchmarks that use this resource
A resource has global identity and may be reused across benchmarks.
Converting a complex PDF into clean Markdown with a hosted API
Uses Version 1.
→Converting a complex PDF into clean Markdown with an open-source library
Uses Version 1.
→