Metraipolis › archive › dc_a24dbd4a7bd5

Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Developers — arXiv:2609.08789

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08789
License (as archived)
CC0-1.0
Archived
2026-10-16T13:23:48.243Z
SHA-256 of the archived text
56fe9407edc7fa4e98b083ee3671b49e045765d2e25b927f0392d8df9c912d99
Stable URL of this page
https://metraipolis.com/documento/dc_a24dbd4a7bd5

How to cite

Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Developers — arXiv:2609.08789 — arXiv (en), https://arxiv.org/abs/2609.08789 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a24dbd4a7bd5 (Metraipolis archive dc_a24dbd4a7bd5, sha256 56fe9407edc7fa4e98b083ee3671b49e045765d2e25b927f0392d8df9c912d99)
BibTeX
@misc{dca24dbd4a7bd5,
  title = {Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Developers — arXiv:2609.08789},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08789},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a24dbd4a7bd5; sha256 56fe9407edc7fa4e98b083ee3671b49e045765d2e25b927f0392d8df9c912d99},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08789. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Frontier AI developers publish safety frameworks that commit them to evidencing whether their models are dangerous. The European Union and California now treat these documents as instruments of accountability, and both already impose duties on their revision. Neither requires the revision to be legible, in the sense that a reader could learn from the developer's own account what changed. We introduce the silent revision rate, the share of material changes to a framework's commitments that the developer's published account does not identify, and we release the versioned, hash-pinned corpus needed to compute it. The corpus contains every public version of the safety frameworks of the twelve developers that have published one, together with each provider's changelog, redline or announcement. We trace 710 commitment instances across twelve consecutive version pairs, code them against a frozen codebook, and adjudicate 244 individually. Three findings follow. First, 67% of material changes (95% CI 62 to 72) are silent under a strict standard and 53% under a lenient one, falling to 49% at section granularity. Second, silence appears to track the form of the account, since narrative announcements run at 74% against 63% for itemised changelogs, whereas account length in words barely matters; on the test that respects nesting the difference is suggestive. Third, 77% of traced changes weaken or remove a commitment, and in seven of eight pairs weakenings are more often silent than strengthenings. The statutory remedy therefore exists and specifies the wrong artefact. A justification explains why a framework changed, an enumeration states what changed, and only the latter makes revision auditable. We argue that publication duties should carry an enumeration duty, which one provider already meets, voluntarily and incompletely.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CY).
Categorie arXiv: Computers and Society (cs.CY) ; Artificial Intelligence (cs.AI); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.08789 — 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 2026-10-16T13:05:53.930Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).