ColabFit Paper - BibTeX Citation

@article{10.1063/5.0163882,
    author = {Vita, Joshua A. and Fuemmeler, Eric G. and Gupta, Amit and Wolfe, Gregory P. and Tao, Alexander Quanming and Elliott, Ryan S. and Martiniani, Stefano and Tadmor, Ellad B.},
    title = "{ColabFit exchange: Open-access datasets for data-driven interatomic potentials}",
    journal = {The Journal of Chemical Physics},
    volume = {159},
    number = {15},
    pages = {154802},
    year = {2023},
    month = {10},
    abstract = "{Data-driven interatomic potentials (IPs) trained on large collections of first principles calculations are rapidly becoming essential tools in the fields of computational materials science and chemistry for performing atomic-scale simulations. Despite this, apart from a few notable exceptions, there is a distinct lack of well-organized, public datasets in common formats available for use with IP development. This deficiency precludes the research community from implementing widespread benchmarking, which is essential for gaining insight into model performance and transferability, and also limits the development of more general, or even universal, IPs. To address this issue, we introduce the ColabFit Exchange, the first database providing open access to a large collection of systematically organized datasets from multiple domains that is especially designed for IP development. The ColabFit Exchange is publicly available at https://colabfit.org, providing a web-based interface for exploring, downloading, and contributing datasets. Composed of data collected from the literature or provided by community researchers, the ColabFit Exchange currently (September 2023) consists of 139 datasets spanning nearly 70,000 unique chemistries, and is intended to continuously grow. In addition to outlining the software framework used for constructing and accessing the ColabFit Exchange, we also provide analyses of the data, quantifying the diversity of the database and proposing metrics for assessing the relative diversity of multiple datasets. Finally, we demonstrate an end-to-end IP development pipeline, utilizing datasets from the ColabFit Exchange, fitting tools from the KLIFF software package, and validation tests provided by the OpenKIM framework.}",
    issn = {0021-9606},
    doi = {10.1063/5.0163882},
    url = {https://doi.org/10.1063/5.0163882},
    eprint = {https://pubs.aip.org/aip/jcp/article-pdf/doi/10.1063/5.0163882/18177819/154802\_1\_5.0163882.pdf},
}