ProvMind achieves 52.84% accuracy on a strict dual-OOD split for seven process-reasoning tasks by retrieving analogous processes from MatPROV graphs and applying provenance-aware compatibility scoring.
arXiv preprint arXiv:2502.04289 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
RETROSPECT reports 55.00% top-1 and 86.18% top-10 accuracy on USPTO-50K with a ChemAlign Transformer plus LambdaMART reranker reaching 59.4% top-1 on candidate pools using proposal scores and template statistics.
citing papers explorer
-
ProvMind: Provenance-grounded reasoning for materials synthesis
ProvMind achieves 52.84% accuracy on a strict dual-OOD split for seven process-reasoning tasks by retrieving analogous processes from MatPROV graphs and applying provenance-aware compatibility scoring.
-
RETROSPECT: RETROsynthesis via Sequential Prediction, and Chemically Transformed-ranking
RETROSPECT reports 55.00% top-1 and 86.18% top-10 accuracy on USPTO-50K with a ChemAlign Transformer plus LambdaMART reranker reaching 59.4% top-1 on candidate pools using proposal scores and template statistics.