{"slug": "veritas-towards-a-general-purpose-replication-tool-for-scientific-research", "title": "VERITAS: Towards a General-Purpose Replication Tool for Scientific Research", "summary": "Researchers introduced VERITAS, a domain-agnostic replication framework that uses CLI coding agents to automatically verify scientific claims from papers and code repositories. In tests across 65 papers in computer science, social science, medicine, and astrophysics, VERITAS achieved state-of-the-art performance on two benchmarks, outperforming strong baselines on every metric.", "body_md": "arXiv:2607.02931v1 Announce Type: new\nAbstract: AI tools are accelerating scientific publication while the systems that review it struggle to keep up, and independent verification of published research has become both harder and more important. As manual replication is slow and expensive, a growing line of work uses coding agents to automate parts of the process. Existing efforts are largely packaged as benchmarks with companion agents that only run inside the benchmark's own pipeline, and no general-purpose replication tool exists. We present VERITAS, a domain-agnostic replication framework built around CLI coding agents. Given a paper, a code repository, or both, VERITAS extracts the paper's claims, runs the methodology while resolving issues as they arise, and judges each claim against the evidence from experiment runs. The pipeline returns an importance-weighted Replication Score, a severity-rated log of every fix applied, and the patched codebase. We evaluate VERITAS on CORE-Bench and ReplicationBench, 65 papers spanning computer science, social science, medicine, and astrophysics. Against two strong Claude Code baselines on the same model and host environment, VERITAS achieves state-of-the-art performance and leads on every metric on both benchmarks.", "url": "https://wpnews.pro/news/veritas-towards-a-general-purpose-replication-tool-for-scientific-research", "canonical_source": "https://arxiv.org/abs/2607.02931", "published_at": "2026-07-07 04:00:00+00:00", "updated_at": "2026-07-07 04:03:41.506919+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-tools", "ai-agents", "ai-research"], "entities": ["VERITAS", "CORE-Bench", "ReplicationBench", "Claude Code"], "alternates": {"html": "https://wpnews.pro/news/veritas-towards-a-general-purpose-replication-tool-for-scientific-research", "markdown": "https://wpnews.pro/news/veritas-towards-a-general-purpose-replication-tool-for-scientific-research.md", "text": "https://wpnews.pro/news/veritas-towards-a-general-purpose-replication-tool-for-scientific-research.txt", "jsonld": "https://wpnews.pro/news/veritas-towards-a-general-purpose-replication-tool-for-scientific-research.jsonld"}}