Back to feed
AR
arXiv CS.AI
7/7/2026
VERITAS: Towards a General-Purpose Replication Tool for Scientific Research

VERITAS: Towards a General-Purpose Replication Tool for Scientific Research

Short summary

VERITAS automates scientific paper replication using AI coding agents that extract claims, run methodologies, and verify results. Tested on 65 papers across computer science, social science, medicine, and astrophysics, it achieved state-of-the-art replication scores. The tool produces weighted reproducibility reports with severity-rated fixes and patched codebases.

  • •Automates reproducibility verification for research papers using coding agents
  • •Tested on 65 papers across four domains; outperforms Claude Code baselines
  • •Generates reproducibility scores, fix logs, and corrected code repositories

Generated with AI, which can make mistakes.

#ai-agents#research-breakthrough#ai-tools
Read full article at arXiv CS.AI

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

The original title is "Prompt-to-Paper: Agentic AI System for Bioinformatics"
arXiv CS.AI
Deterministic Replay for AI Agent Systems
arXiv CS.AI
The original title is: "An AI Science Workbench Needs a Reproducibility Graph, Not Just Chat History"
Dev.to
AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation
arXiv CS.AI