Evidential Deep Learning for Interatomic Potentials

<b>Dataset Description</b><b>This repository provides model checkpoints, simulation trajectories, and implementation code accompanying the paper </b><b><i>“Evidential Deep Learning for Interatomic Potentials.”</i></b><b>ckpt.zip:</b> Contains checkpoints of the eIP model trained on multiple datasets. For the silica glass dataset, additional checkpoints are included for models trained with ensemble, Monte Carlo dropout, Gaussian Mixture Model (GMM), and Maximum Variance Estimation (MVE).<b>traj.zip:</b> Includes molecular dynamics (MD) and uncertainty-driven dynamics (UDD) trajectories for water, lithium iron phosphate (LiFePO₄), and polydimethylsiloxane (PDMS). All trajectories are stored in the extended XYZ format.<b>AlphaNet&amp;TorchMDNet.zip:</b> Contains code implementations based on AlphaNet and TorchMD-Net backbones, integrating uncertainty quantification (UQ) methods including eIP and DPOSE (shallow ensemble).<b>Source Data.zip: </b>Contains<b> </b>the source data for paper <i>“Evidential Deep Learning for Interatomic Potentials.”</i><br>