Metraipolis › archive › dc_90b79afdaa8b
Models as Governed Interfaces for AI-Native MBSE: Read-Side Adequacy and Write-Side Admissibility — arXiv:2609.16252
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.16252
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T18:32:48.778Z
- SHA-256 of the archived text
90f64a45469958d643fa6733af2e45d3abc75bdb176e71aa43f42e78502a2866- Stable URL of this page
https://metraipolis.com/documento/dc_90b79afdaa8b
How to cite
Models as Governed Interfaces for AI-Native MBSE: Read-Side Adequacy and Write-Side Admissibility — arXiv:2609.16252 — arXiv (en), https://arxiv.org/abs/2609.16252 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_90b79afdaa8b (Metraipolis archive dc_90b79afdaa8b, sha256 90f64a45469958d643fa6733af2e45d3abc75bdb176e71aa43f42e78502a2866)
BibTeX
@misc{dc90b79afdaa8b,
title = {Models as Governed Interfaces for AI-Native MBSE: Read-Side Adequacy and Write-Side Admissibility — arXiv:2609.16252},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.16252},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_90b79afdaa8b; sha256 90f64a45469958d643fa6733af2e45d3abc75bdb176e71aa43f42e78502a2866},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16252. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Machine-readable models such as SysML v2 are now programmatically accessible, and a growing body of work treats that access as the enabling condition for AI participation in systems engineering. Access is necessary, but not sufficient. The remaining work lies not in the modelling language but in the data architecture around it. An AI reader that queries a structurally complete model for a derivation still runs into absent derivation chains, untagged epistemic status, missing provenance, and evidence that the model cannot resolve. Faced with these gaps, it does not abstain; it fills them from training data, a source that is neither verifiable nor governed. To make the case on a model that is exemplary by current practice rather than deficient, we probe the public Apollo 11 SysML v2 reconstruction. We name the missing property epistemic adequacy and offer it as a candidate data-architecture pattern in two halves. Read-side adequacy lets derivation, status, and provenance answer a query rather than invite a guess; write-side admissibility gates an AI contribution before it enters the record. The property is broken down into five criteria. Four sit on the read side, evidenced by the case and convergent literature; the fifth sits on the participation side, advanced as a hypothesis this paper does not yet test. The architecture space runs from an inline metadata extension up to a substrate-native multi-model store, and over it, we propose the Governed-Query Architecture Framework, which governs agent participation through the viewpoint conventions that engineers already use. We commit the reframing to falsification: the epistemic layer counts as refuted if it cannot beat a retrieval-augmented baseline on the same model, tested first on the Apollo chain and then in an industrial pilot. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.16252 — 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 2026-10-15T18:03:09.601Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).