English

Structural Certification for Reliable Physical Design with Language Models

Artificial Intelligence 2026-06-29 v1 Machine Learning

Abstract

An unreliable language model can be made to produce reliable physical designs if the authority to assert is moved out of the model: the model proposes, and a deterministic engine alone certifies, returning certified, impossible, or unknown. We introduce Physics-Anchored Certification (PHACT), a propose-certify loop spanning five scientific domains, and identify what makes such a certificate trustworthy. A checker that accepts a model-supplied value can be forged; deriving the certified quantity from fixed inputs instead makes forgery impossible by construction. Across eighty adversarial trials spanning two models, two decoding temperatures, and a deliberately faulted engine, this contract produced zero false certifications.

Cite

@article{arxiv.2606.30107,
  title  = {Structural Certification for Reliable Physical Design with Language Models},
  author = {Nakul Vyas and Iliya D. Stoev},
  journal= {arXiv preprint arXiv:2606.30107},
  year   = {2026}
}

Comments

16 pages, 5 figures, 5 tables