Indexes of Charge Density data and Literature-Mined CSQD Dataset

This repository provides index files for all the dataset used in this study. The dataset for pre-training is derived from CHGCAR files based on density functional theory (DFT) calculations from the Materials Project. Due to the large size of the raw data, only the following index file is included: mpid_indexes.txt – Lists the Materials Project IDs (MPIDs) corresponding to the entries used in this work. The original charge density data should be obtained directly from the Materials Project, and literature-mined CSQD data can be obtained from the literature listed in: CSQD_DATASET_A_indexes.xlsx – Contains DOIs and composition metadata for dataset A. CSQD_DATASET_B_indexes.xlsx – Contains DOIs and composition metadata for dataset B.