Metraipolis › archive › dc_446482604eac

Protected Cores Are Not Enough: Certifying AI-Proposed Revisions of Temporal Specifications — arXiv:2609.33461

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33461
License (as archived)
CC0-1.0
Archived
2026-10-07T21:01:29.143Z
SHA-256 of the archived text
9ec1899e0c3de1dc148e7899f270fc53756fab9074669e93d3f7012ca5e1e503
Stable URL of this page
https://metraipolis.com/documento/dc_446482604eac

How to cite

Protected Cores Are Not Enough: Certifying AI-Proposed Revisions of Temporal Specifications — arXiv:2609.33461 — arXiv (en), https://arxiv.org/abs/2609.33461 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_446482604eac (Metraipolis archive dc_446482604eac, sha256 9ec1899e0c3de1dc148e7899f270fc53756fab9074669e93d3f7012ca5e1e503)
BibTeX
@misc{dc446482604eac,
  title = {Protected Cores Are Not Enough: Certifying AI-Proposed Revisions of Temporal Specifications — arXiv:2609.33461},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33461},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_446482604eac; sha256 9ec1899e0c3de1dc148e7899f270fc53756fab9074669e93d3f7012ca5e1e503},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33461. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Runtime monitoring traditionally evaluates a specification that is fixed before execution or externally modified when requirements change. In learning-enabled and data-intensive systems, however, the temporal relationships represented by a specification may themselves evolve. Allowing an AI component to directly replace a formal specification is unsafe: it may overfit transient behavior, weaken protected requirements, or activate statistically unsupported revisions. We introduce an intersymbolic architecture in which an untrusted AI proposer suggests temporal specification revisions and a symbolic governor controls their activation. Two results organize the framework. First, origin-version semantics makes the outcome of each obligation invariant to later revisions. Second, aggregate certification can conceal systematic failures on protected triggers; simultaneous aggregate and core-conditional post-selection certification controls both targets. A structural invariant preserves designer-protected components, and a proposer-independent lifetime error bound supports repeated activation decisions. The statistical bound concerns the predictable means of completed certification samples; interpreting it as future operational validity requires an additional stability assumption. Controlled synthetic experiments use a frozen supervised AI proposer to illustrate the masked-core failure at one decision and across repeated governed revisions. The proposer is a supervised regressor trained offline on synthetic tasks and frozen before use; it ranks candidates by predicted aggregate margin and never observes the protected-trigger success rate, so the masked-core failure arises from optimising the aggregate rather than from an adversary constructed by hand.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Logic in Computer Science (cs.LO) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.33461 — 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 2026-10-07T20:29:02.668Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).