发表机构
Institue of Smart System Technologies, University of Klagenfurt; Faculté Polytechnique, Université de Kinshasa（克拉根福大学智能系统技术研究所; 金沙萨大学理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出CRASM及CRASM-Gate，一种确定性优先的约束与角色感知语义映射方法，通过选择性模型辅助提升跨工业标准映射的准确性和效率，显著降低错误率和延迟。
AI 中文摘要
工业标准常常通过不兼容的层级、标识符、角色和结构约束来编码相同的工程概念，因此最近的词汇或嵌入匹配在技术上仍可能是不可接受的。本文提出了CRASM，一种确定性的约束与角色感知语义映射方法，以及CRASM-Gate，其选择性模型辅助扩展。该框架将标准特定的规范化、有界检索、确定性规则、目标与来源角色解释、语义与结构排序、歧义弃权（不执行）以及目标验证分离开来。CRASM-Gate增加了一个置信度/分歧门控，可能调用候选约束的大型语言模型，而最终权威仍由确定性验证掌握。一个受控工件覆盖了六个有向工业标准对、三个难度级别和十种配置，产生了14,400个样本级决策。使用固定的本地模型端点，CRASM-Gate达到了平均F1分数0.9938和实现的结构有效性率1.0000；确定性CRASM在无生成模型调用的情况下达到0.9931；而仅模型基线达到0.5347。相对于仅模型基线，CRASM将top-1错误从670减少到10，同时表现出0.0688秒/样本而非24.5263秒/样本的观测延迟。CRASM-Gate通过1,440个额外正确决策改进了CRASM，观测延迟增加到15.7666秒/样本。结果支持一种确定性优先的互操作性架构，其中模型辅助是可选的、可测量的、候选有界的，并且无法绕过结构验证。
英文摘要
Industrial standards often encode the same engineering concept through incompatible hierarchies, identifiers, roles, and structural constraints, so the nearest lexical or embedding match can still be technically inadmissible. This article presents CRASM, a deterministic constraint- and role-aware semantic mapping method, and CRASM-Gate, its selectively model-assisted extension. The framework separates standard-specific canonicalization, bounded retrieval, deterministic rules, destination-versus-origin role interpretation, semantic and structural ranking, ambiguity refusal, and target validation. CRASM-Gate adds a confidence/disagreement gate that may invoke a candidate-constrained large language model, while final authority remains with deterministic validation. A controlled artifact covers six directed industrial-standard pairs, three difficulty levels, and ten configurations, yielding 14,400 sample-level decisions. With a fixed local model endpoint, CRASM-Gate reaches mean F1 0.9938 and an implemented structural-validity rate of 1.0000; deterministic CRASM reaches 0.9931 without generative-model calls; and the model-only baseline reaches 0.5347. Relative to the model-only baseline, CRASM reduces top-1 errors from 670 to 10 while exhibiting 0.0688 s/sample rather than 24.5263 s/sample observed latency. CRASM-Gate improves CRASM by one additional correct decision out of 1,440, with observed latency increasing to 15.7666 s/sample. The results support a deterministic-first interoperability architecture in which model assistance is optional, measurable, candidate-bounded, and unable to bypass structural validation.
