@article{0930a98dac6848b5aa5f2d3e872a30d6,
title = "A FAIR and AI-ready Higgs boson decay dataset",
abstract = "To enable the reusability of massive scientific datasets by humans and machines, researchers aim to adhere to the principles of findability, accessibility, interoperability, and reusability (FAIR) for data and artificial intelligence (AI) models. This article provides a domain-agnostic, step-by-step assessment guide to evaluate whether or not a given dataset meets these principles. We demonstrate how to use this guide to evaluate the FAIRness of an open simulated dataset produced by the CMS Collaboration at the CERN Large Hadron Collider. This dataset consists of Higgs boson decays and quark and gluon background, and is available through the CERN Open Data Portal. We use additional available tools to assess the FAIRness of this dataset, and incorporate feedback from members of the FAIR community to validate our results. This article is accompanied by a Jupyter notebook to visualize and explore this dataset. This study marks the first in a planned series of articles that will guide scientists in the creation of FAIR AI models and datasets in high energy particle physics.",
author = "Yifan Chen and Huerta, {E. A.} and Javier Duarte and Philip Harris and Katz, {Daniel S.} and Neubauer, {Mark S.} and Daniel Diaz and Farouk Mokhtar and Raghav Kansal and Park, {Sang Eon} and Kindratenko, {Volodymyr V.} and Zhizhen Zhao and Roger Rusack",
note = "Funding Information: We thank Tom Honeyman from the Australian Research Data Commons (ARDC) and Chris Erdmann from the American Geophysical Union (AGU) for their help and advice on both FAIR data principles in general and on their application to our specific dataset, though any errors in interpretation of the principles are ours. We thank the CMS Collaboration for making the dataset publicly available and for helpful discussions in the preparation of this work. We also thank Tibor Simko, Kati Lassila-Perini, and the rest of CERN Open Data Portal Team. This work was performed as part of the FAIR Framework for Physics-Inspired Artificial Intelligence in High Energy Physics (FAIR4HEP) project (DE-SC0021258, DE-SC0021395, DE-SC0021225, and DE-SC0021396), support by the Office of Advanced Scientific Computing Research within U.S. Department of Energy Office of Science. FM was partially supported by an Halcoğlu Data Science Fellowship. Funding Information: We thank Tom Honeyman from the Australian Research Data Commons (ARDC) and Chris Erdmann from the American Geophysical Union (AGU) for their help and advice on both FAIR data principles in general and on their application to our specific dataset, though any errors in interpretation of the principles are ours. We thank the CMS Collaboration for making the H (b b) dataset publicly available and for helpful discussions in the preparation of this work. We also thank Tibor Simko, Kati Lassila-Perini, and the rest of CERN Open Data Portal Team. This work was performed as part of the FAIR Framework for Physics-Inspired Artificial Intelligence in High Energy Physics (FAIR4HEP) project (DE-SC0021258, DE-SC0021395, DE-SC0021225, and DE-SC0021396), support by the Office of Advanced Scientific Computing Research within U.S. Department of Energy Office of Science. FM was partially supported by an Halco?lu Data Science Fellowship. Publisher Copyright: {\textcopyright} 2022, The Author(s).",
year = "2022",
month = dec,
doi = "10.1038/s41597-021-01109-0",
language = "English (US)",
volume = "9",
journal = "Scientific Data",
issn = "2052-4463",
publisher = "Nature Publishing Group",
number = "1",
}