Data for: Hydrogen diffusion in TiCr2Hx Laves phases: A combined ab initio and machine-learning-potential study

This dataset supports the development and validation of machine learning interatomic potentials (MLIPs) for modeling hydrogen diffusion in C14 (hexagonal) and C15 (cubic) TiCr₂-based Laves phases. It includes fitted moment tensor potentials (Level 16) and the corresponding training dataset. The data is organized into two directories: Training_db/, which contains DFT-calculated energies, forces, and stresses for training configurations, and Trained_MTPs/, which contains the final fitted MLIPs for both the C14 (C14.mtp) and C15 (C15.mtp) phases. The dataset is fully referenced in the accompanying manuscript and supplementary materials.