Correction: Beyond training data: how elemental features enhance ML-based formation energy predictions

Correction for “Beyond training data: how elemental features enhance ML-based formation energy predictions” by Hamed Mahdavi et al., Digital Discovery, 2025, 4, 2972-2982, https://doi.org/10.1039/D5DD00182J. In the original version of the article the DOI link to the code, relevant scripts, and data deposited in the Mendeley repository for this article in the Data availability statement was not present. An updated data availability statement can be found here. Data availability Our experiments used the Matbench v0.1 test suite, publicly accessible via the Matminer (https://url.uk.m.mimecastprotect.com/s/Tp92CK1VQF4zm16uMf1u5fpWW?domain=hackingmaterials.lbl.gov) Python library. The complete implementation of the experiments—including code, scripts, and data—is available in the paper's Mendeley repository: https://doi.org/10.17632/n3cwj2hb7w.2. Supplementary information is available. See DOI: https://doi.org/10.1039/d5dd00182j. The Royal Society of Chemistry apologises for these errors and any consequent inconvenience to authors and readers.