← Back to all news
arXiv AI By Zhaohe Dong, Yuhao Chen

CrossAudit: A Git-Native, Cross-Vendor Audit Loop for Agentic Science

Read the original on arXiv AI →

CrossAudit proposes a Git‑native, cross‑vendor audit protocol for autonomous research pipelines, ensuring each work increment is reviewed by an agent from a different vendor against a human‑written rulebook. Audit outcomes, disputes, and rulings are stored as git commits, providing a replayable, versioned supervision history. The authors implemented the protocol with GitHub Actions and Python, deployed it in a computational‑chemistry pipeline, and conducted a seeded‑defect trial that revealed differing interpretations of the same rulebook by two vendors.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Oct 22

What Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories

The paper audits two single‑investigator AI‑assisted research repositories to assess how well they record provenance of AI tool use. One repository contains a prescriptive trace of rule files, with 85.6% of committed lines still visible, while the other holds a narrative trace of an agent’s scratchpad, showing only 21.8% visibility. The study finds that repository‑level indicators such as the Co‑Authored‑By trailer are inconsistent and unreliable for measuring AI involvement, and it outlines which provenance claims each trace type can support or fail to support.

By Koutian Wu, Zesen Huang, Hejia Geng
agents
More like this →
arXiv AI
Oct 19

Author-in-the-loop Agentic Reproducibility Auditing for a Machine Learning Conference

The paper introduces an author‑in‑the‑loop collaborative audit system for reproducibility checks during peer review, where authors explicitly declare reproduction instructions via a structured checklist. An AI agent uses these declarations to investigate and assess reproducibility, while human reviewers approve requests and decide on issue resolution. The system was deployed on 36 conference papers, identifying 20 issues that were subsequently resolved, and the study examined how different checklist conditions affected the agent’s assessment.

By Yukun Dong, Linjun Zhang, Tian Zheng
agents
More like this →