Plato's Cave: A Human-Centered Research Verification System
This addresses the need for better fact-checking and quality assessment in research publications, though it appears incremental as it builds on existing verification methods.
The paper tackles the problem of verifying research papers by developing Plato's Cave, a human-centered system that uses directed acyclic graphs and web agents to assign credibility scores, resulting in an implementation tested on 104 papers.
The growing publication rate of research papers has created an urgent need for better ways to fact-check information, assess writing quality, and identify unverifiable claims. We present Plato's Cave as an open-source, human-centered research verification system that (i) creates a directed acyclic graph (DAG) from a document, (ii) leverages web agents to assign credibility scores to nodes and edges from the DAG, and (iii) gives a final score by interpreting and evaluating the paper's argumentative structure. We report the system implementation and results on a collected dataset of 104 research papers.