# Models as Governed Interfaces for AI-Native MBSE: Read-Side Adequacy and Write-Side Admissibility

arXiv: https://arxiv.org/abs/2609.16252 · HTML: https://mlsanity.com/paper/2609.16252/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 45 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 10 of 10)

- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [Selective Question Answering under Domain Shift](https://mlsanity.com/paper/2006.09462/) (2020)
- [Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools](https://mlsanity.com/paper/2405.20362/) (2024)
- [On the use of Large Language Models in Model-Driven Engineering](https://mlsanity.com/paper/2410.17370/) (2024)
- [Automotive Engineering-Centric Agentic AI Workflow Framework](https://mlsanity.com/paper/2604.07784/) (2026)
- [The Provenance Gap in Clinical AI: Evidence-Traceable Temporal Knowledge Graphs for Rare Disease Reasoning](https://mlsanity.com/paper/2604.17114/) (2026)
- [Survey: On the Landscape of Graph Databases](https://mlsanity.com/paper/2505.24758/) (2025)
- [Engineering Decisions in MBSE: Insights for a Decision Capture Framework Development](https://mlsanity.com/paper/2601.07301/) (2026)
- [AI as Consumer and Participant: A Co-Design Agenda for MBSE Substrates and Methodology](https://mlsanity.com/paper/2604.25526/) (2026)

## Abstract (arXiv)

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.