Reproduce “From PDF to Evidence: Structure-Aware Retrieval for Clinical Practice Guidelines” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Xingyu Lin, Dehui Du
The system retrieves evidence from clinical-practice guideline PDFs by parsing document elements and grouping them into context-preserving units, such as table rows attached to their headers. In hybrid retrieval, it achieves Page Hit@5 of 0.879, close to page-level retrieval’s 0.889, with 3,222 rather than 12,111 mean top-five characters. Evaluation measures retrieval, not answer correctness or clinical usefulness.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.