面向AI原生MBSE的模型治理接口：读取侧充分性与写入侧可采纳性
原标题：Models as Governed Interfaces for AI-Native MBSE: Read-Side Adequacy and Write-Side Admissibility
AI 摘要
该论文提出「认知充分性」（epistemic adequacy）作为AI原生MBSE的数据架构模式，分为读取侧充分性与写入侧可采纳性两部分。作者以公开的Apollo 11 SysML v2重建模型为案例，指出结构完整的模型仍缺少推导链、认知状态标注、来源追踪和可解析证据，导致AI读取者不弃权而是从训练数据填补空白。论文提出治理查询架构框架（GQAF），包含八项可采纳性约束，并设定可证伪的测试计划，先在Apollo链上、后在工业试点中与检索增强基线对比。
正文节选
Models as Governed Interfaces for AI-Native MBSE: Read-Side Adequacy and Write-Side Admissibility Abstract. 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