A property-registry contract for retrieve-or-refuse thermal-mechanical lattice search
cs.CE, cond-mat.mtrl-sci, cs.AI
Submitted: 2026-09-13
Updated: 2026-09-13
Comments: 30 pages, 7 figures, 22 tables. Appendices A-D give the full property registry, the generated language-model prompt, the frozen 64-query suite, and one worked tool transcript
Code: https://github.com/nbbllxx0/A-PROPERTY-REGISTRY-CONTRACT-FOR-RETRIEVE-OR-REF
License: http://creativecommons.org/licenses/by/4.0/
The gist: Early thermal-mechanical lattice requirements are knowledge-intensive and often jointly unsatisfiable: an engineer asks for a cell that is light, stiff, laterally conducting and cheap, and no cell in
Terminology
Abstract
Early thermal-mechanical lattice requirements are knowledge-intensive and often jointly unsatisfiable: an engineer asks for a cell that is light, stiff, laterally conducting and cheap, and no cell in the library satisfies it. A design system should say so, and say which requirement to loosen and by how much, rather than return the nearest row. A generative model can return a candidate even when the library holds none. This work applies established conflict diagnosis to a catalogue of homogenised properties. Search over 1,397 homogenised unit cells and 19 base materials (26,543 combinations) returns a catalogue row that a second solver can rebuild, or, for an empty feasible set of at most eight constraints, inclusion-minimal unsatisfiable subsets (MUS) and the slack of a repair, not a neighbour. One registry declaration generates the prompt and the evaluator, so undeclared parsed keys cannot reach search. On a frozen suite of 64 typed queries, retrieve-or-refuse matches min-repair on every feasible query (48/48) and refuses every empty one (16/16) with MUS and slack. Constraint-ignoring nearest-neighbour and penalty search violate stated cost or density limits. On 216 empty queries, repairs printed at three significant figures and rounded outward stay feasible in every case (216/216). When density and cost must be kept, a list of minimum-cardinality repairs keeps them on 209 of 211 queries; a protection-first repair keeps them on all 211, the same as full diagnosis. A 308-request parse benchmark is a template-text check, not unconstrained engineer prose.
Sources
- MetaGen: A DSL, Database, and Benchmark for VLM-Assisted Metamaterial Generation
- Multi-Objective Infeasibility Diagnosis for Routing Problems Using Large Language Models
- METASYMBO: Multi-Agent Language-Guided Metamaterial Discovery via Symbolic Latent Evolution
- AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design
- Why Not? Solver-Grounded Certificates for Explainable Mission Planning
Related papers
- Constrained Sensing and Reliable State Estimation with Shallow Recurrent Decoders on a TRIGA Mark II Reactor
- Evidence-Unit Fairness and the Limits of Query-Adaptive Sparse-Dense Fusion in Financial Document Retrieval
- Chemical Chain-of-Thought Functions as a Hallucination-Prone Molecular Scratchpad
- Lightweight Adaptation of EEG Foundation Models for Stroke Motor Imagery Decoding: Domain Shift and Subject-Level Robustness
- RetroDFM-R: Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning
- Wildfire Suppression: Complexity, Models, and Instances