Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2605.28487 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910266839531520 |
|---|---|
| author | Zhang, Yiming Tamura, Ryo Tsuda, Koji |
| author_facet | Zhang, Yiming Tamura, Ryo Tsuda, Koji |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28487 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ProvMind: Provenance-grounded reasoning for materials synthesis Zhang, Yiming Tamura, Ryo Tsuda, Koji Artificial Intelligence Machine Learning 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. |
| title | ProvMind: Provenance-grounded reasoning for materials synthesis |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2605.28487 |