Kolmogorov-Arnold networks trained on GEM-Selektor output accurately approximate chemical equilibria for cement and radium-sulfate solid-solution systems, outperforming MLPs on the cement benchmark and cutting evaluation time by 87-93%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Kolmogorov-Arnold Surrogate Model for Chemical Equilibria: Application to Solid Solutions
Kolmogorov-Arnold networks trained on GEM-Selektor output accurately approximate chemical equilibria for cement and radium-sulfate solid-solution systems, outperforming MLPs on the cement benchmark and cutting evaluation time by 87-93%.