模型作为AI原生MBSE的受治理接口：读侧充分性与写侧可接受性
Models as Governed Interfaces for AI-Native MBSE: Read-Side Adequacy and Write-Side Admissibility
浏览论文内容
中文总结 AI 辅助
针对AI读取SysML v2模型时因缺失推导、状态和来源信息而依赖训练数据填补的问题，提出认识论充分性数据架构模式，分读侧充分性与写侧可接受性，并给出受治理查询架构框架及证伪检验方案。
中文摘要 AI 辅助
SysML v2等机器可读模型现在可以通过编程方式访问，越来越多的研究将这种访问视为AI参与系统工程的前提条件。访问是必要的，但还不够。剩余的工作不在于建模语言，而在于其周围的数据架构。一个AI读取器查询结构完整的模型以获取推导时，仍然会遇到缺失的推导链、未标记的认识论状态、缺失的来源信息，以及模型无法解决的证据。面对这些缺口，它不会弃权（不执行），而是从训练数据中填补这些缺口，而训练数据既不可验证也不受治理。为了在一个按当前实践堪称典范而非有缺陷的模型上论证这一观点，我们探查了公开的阿波罗11号SysML v2重建模型。我们将缺失的属性命名为认识论充分性，并将其作为候选数据架构模式提出，分为两部分。读侧充分性让推导、状态和来源信息能够回答查询，而不是引发猜测；写侧可接受性在AI贡献进入记录之前对其进行门控。该属性被细分为五个标准。四个位于读侧，由案例和趋同文献佐证；第五个位于参与侧，作为本文尚未验证的假设提出。架构空间从内联元数据扩展延伸到基于底层的多模型存储，在此之上，我们提出了受治理查询架构框架，该框架通过工程师已经使用的视角约定来治理智能体参与。我们将这一重新框架提交给证伪检验：如果认识论层在相同模型上无法击败检索增强基线，则视为被推翻，首先在阿波罗链上测试，然后在工业试点中测试。
英文摘要
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.
发表机构
- Loughborough University（拉夫堡大学）
机构由 AI 辅助整理，请以论文原文为准。
