Processed result data for graph neural network-based surrogate modelling of finite element stress fields in stiffened cylindrical shells

This dataset contains processed result data supporting the manuscript entitled "Graph Neural Network-Based Surrogate Modelling of Finite Element Stress Fields in Stiffened Cylindrical Shells and Out-of-Distribution Generalisation". The data package includes aggregate model-performance metrics, sample-wise error metrics for CDF and boxplot figures, node-level prediction data for a representative stress-field visualization, parameter-range information, dataset partition information, and selected source files related to model input representations and architectures. The shared files support Tables 1-8 and Figures 4-13 of the manuscript. Large raw finite element intermediate files, full training tensors, model checkpoints, temporary files and software-specific cache files are not included because of file size and software-dependency constraints.