Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Plato's Cave: A Human-Centered Research Verification System

Matheus Kunzler Maldaner, Raul Valle, Junsung Kim, Tonuka Sultan, Pranav Bhargava, Matthew Maloni, John Courtney, Hoang Nguyen, Aamogh Sawant, Kristian O'Connor, Stephen Wormald, Damon L. Woodard

Abstract

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.

Plato's Cave: A Human-Centered Research Verification System

Abstract

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.
Paper Structure (38 sections, 14 equations, 4 figures, 5 tables, 1 algorithm)

This paper contains 38 sections, 14 equations, 4 figures, 5 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Scientific Claim Verification
  4. Knowledge Graph Construction
  5. Trust Propagation Methods
  6. Multi-Agent Systems
  7. Positioning this Work in the Broader Literature
  8. Problem Formulation
  9. Implementation
  10. Knowledge Graph Construction
  11. Node Verification
  12. Trust-Propagating Graph Scoring
  13. Cache-First Calibration and Ablation
  14. Architecture and Implementation
  15. Browser Automation
  16. ...and 23 more sections

Figures (4)

  • Figure 1: System Overview. (a) The user provides a PDF, URL, or natural-language query. (b) For URLs or queries, a web-surfer agent browses for the specific paper. (c) All text and images from the document are extracted and stored. (d) The content is passed into an LLM and converted into a role-labeled DAG serialized as JSON (nodes and directed dependencies). (e) The frontend parses the DAG JSON and renders an interactive graph. (f) Web-surfer agents verify each node sequentially using external sources to produce normalized verification metrics. (g) Node qualities influence downstream nodes via trust-gated propagation along dependency edges. (h) The scorer aggregates node and edge signals into an overall paper-level score.
  • Figure 2: Plato's Cave interface showing a finalized run with the visualized DAG and Integrity Score
  • Figure 3: System Architecture for Plato's Cave
  • Figure 4: Paper-level mean score grouped by spreadsheet rating under the selected calibrated setting. We use a discrete, non-smoothed summary to avoid overstating distributional structure under weak supervision.