Skip to content

CRASM-Gate: Deterministic-First Constraint- and Role-Aware Semantic Mapping with Selective Model Assistance Across Heterogeneous Industrial Standards

Sep 2026 · arXiv.org · Vol abs/2609.37458 · 0 citations · 21 references
Computer Science

TL;DR

CRASM, a deterministic constraint- and role-aware semantic mapping method, and CRASM-Gate, its selectively model-assisted extension, support a deterministic-first interoperability architecture in which model assistance is optional, measurable, candidate-bounded, and unable to bypass structural validation.

Abstract

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.

View source

Similar papers

Preprint Oct 2026

Reflective Compositional Grounding for Natural-Language-to-SPARQL

A monotone refinement discipline that accumulates scoped interpretation requirements and establish conditions under which changes to the composed process preserve previously validated interpretations is formalised.

Isabelle Mohr, John Dujany, André Freitas · 0 citations
Review Open access Oct 2026

Text-to-SQL in the Era of Large Language Models: A Survey of Reasoning-Centric and Efficiency-Centric Approaches

Text-to-SQL translates natural-language questions into executable SQL, enabling non-expert access to relational databases. Despite advances in large language models (LLMs), reliable systems must ground questions in schemas and values, handle large schemas, and preserve semantic correctness. This survey reviews the evol...

Gunhee Choi, Dayeon Wee, Jongmoo Choi · 0 citations
Preprint Oct 2026

ASNER: Software Architecture Recovery with Adaptive Semantic Neighborhoods and Evidence-Grounded Refinement

Automated software architecture recovery provides architectural context for software engineering and repository-level LLM agents. Existing methods combine structural and semantic signals, but functional relatedness does not necessarily imply shared architectural responsibility. Fixed thresholds or Top-K neighborhoods a...

Wen-Hao Wang, Zhi Jin, J. Li et al. · 0 citations
#machine learning Preprint Oct 2026

ACED: Reference-Anchored Aggregation of Natural-Language and Executable Evidence for Mathematical Reasoning

Natural-language self-consistency and executable programs provide complementary test-time evidence for mathematical reasoning, yet either channel may support the same semantic error. Thus we propose ACED, a reference-anchored framework that treats the self-consistency answer as the default and executable outputs as sup...

Yi-Yi Lu, Jia-Xiang Geng, Bing Luo · 0 citations

Who Gets Linked? Protocol-Conditioned Linkability and Trace-Level Evidence in Italian Cultural-Heritage Entity Linking

On 450 ArCo person and cultural-property records, a preliminary study separates target establishment, candidate generation, link selection, and trace-level evidence, distinguishing three stage-specific conditions: no reference target established, an established target absent from the candidate set, and scoring-stage ab...

Unknown authors · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.