ProvMind: Provenance-grounded reasoning for materials synthesis
For materials science researchers, this work provides a benchmark and method for reasoning over synthesis processes with causal dependencies, though the gains are incremental.
The paper introduces MatProcBench, a provenance-grounded benchmark for materials synthesis reasoning, and ProvMind, a framework that achieves 52.84% accuracy on a dual-OOD split, outperforming baselines.
Materials process optimization requires reasoning over routes, conditions, tools and causal dependencies, yet most computational formulations flatten synthesis procedures into text or ordered steps. We introduce MatProcBench, a provenance-grounded benchmark constructed from literature-mined MatPROV graphs, to evaluate seven process-reasoning tasks spanning route continuity, step-level variable inference and global causal consistency under both same-split and shift-aware evaluation, including a strict dual-OOD split that combines temporal and material-class shift. We further introduce ProvMind, a process-memory reasoning framework that retrieves analogous training processes, converts them into provenance-aware option-level compatibility scores, and uses a language model for constrained final decision making. ProvMind achieves 52.84\% accuracy on the dual-OOD split, outperforming prompting, retrieval-augmented and supervised fine-tuning baselines.