Metraipolis › archive › dc_4e6e7ed48ab5
CrossAudit: A Git-Native, Cross-Vendor Audit Loop for Agentic Science — arXiv:2608.28631
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28631
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:41:45.727Z
- SHA-256 of the archived text
2557ddad21e880402b1536fb9efc597b92407e0cb81f34e12ac08263ad9e73d0- Stable URL of this page
https://metraipolis.com/documento/dc_4e6e7ed48ab5
How to cite
CrossAudit: A Git-Native, Cross-Vendor Audit Loop for Agentic Science — arXiv:2608.28631 — arXiv (en), https://arxiv.org/abs/2608.28631 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e6e7ed48ab5 (Metraipolis archive dc_4e6e7ed48ab5, sha256 2557ddad21e880402b1536fb9efc597b92407e0cb81f34e12ac08263ad9e73d0)
BibTeX
@misc{dc4e6e7ed48ab5,
title = {CrossAudit: A Git-Native, Cross-Vendor Audit Loop for Agentic Science — arXiv:2608.28631},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28631},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e6e7ed48ab5; sha256 2557ddad21e880402b1536fb9efc597b92407e0cb81f34e12ac08263ad9e73d0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28631. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
An AI scientist should not grade its own homework. Yet in the systems we examined, the agent that reviews the work usually comes from the same model family as the agent that produced it, or at least from the same vendor. Model evaluators are known to favour their own generations. Whether models trained alike also share blind spots is a conjecture, not a settled finding, but if they do, the reviewer inherits the author's. The record of what was flagged and what was waved through often sits in platform logs that nobody outside can replay. We present CrossAudit, a protocol for supervising autonomous research pipelines. It rests on three commitments. Each increment of work is audited by an agent from a different vendor against a rulebook a human wrote and versioned. Reports, verdicts, disputes and rulings are git commits, so the supervision history can be re-read and cited; raw model exchanges are not yet part of that record. Scripted checks run before any model does. Advisory judgement never gates the pipeline: a model blocks only by citing a rule, and no model may waive a deterministic failure. Blockers that survive a bounded number of revision rounds go to a person. We state the protocol as eight invariants. We describe a reference implementation built from GitHub Actions and a few hundred lines of Python, and report a live deployment of a closely related variant in a computational-chemistry pipeline. We also ran a seeded-defect trial (30 increments, 43 seeded defects, one run per configuration). A cross-vendor audit of our own repository then voided its blinding. We adopt that audit's findings and report the corrected results. The trial shows that two vendors read the same rulebook differently. It does not show that either is better. The strongest evidence here is the committed, uncontrolled record of cross-vendor audits of this paper itself. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computational Engineering, Finance, and Science (cs.CE); Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2608.28631 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T07:28:26.460Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).