Overview
System that extracts structured nodes (claims, evidence, limitations, etc.) from papers and scores them to support literature review and comparison across a collection.
Reading dozens of papers is slow partly because the structure is inconsistent. Plato’s Cave uses modern language models to extract a consistent structure (e.g., claims, evidence, limitations) and then runs a scoring pipeline so papers can be compared more systematically.
What I built
- A batch pipeline that processes PDFs, extracts structured ‘nodes’ (e.g., claims/evidence), and stores results in machine-readable formats.
- Scoring and normalization routines so outputs are comparable across papers.
- Run outputs designed for auditing (logs, summaries, and artifacts).
How it works
- Convert a paper to text.
- Use a language model to label and structure key statements.
- Score the resulting graph for quality and consistency.
- Export summaries so humans can review quickly.
