% IMPORTANT: The following is UTF-8 encoded. This means that in the presence % of non-ASCII characters, it will not work with BibTeX 0.99 or older. % Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or % “biber”. @ARTICLE{Villamar:1043152, author = {Villamar, Jose and Kelbling, Matthias and More, Heather and Denker, Michael and Tetzlaff, Tom and Senk, Johanna and Thober, Stephan}, title = {{M}etadata practices for simulation workflows}, journal = {Scientific data}, volume = {12}, issn = {2052-4436}, address = {London}, publisher = {Nature Publ. Group}, reportid = {FZJ-2025-02769}, pages = {942}, year = {2025}, abstract = {Computer simulations are an essential pillar of knowledge generation in science. Exploring, understanding, reproducing, and sharing the results of simulations relies on tracking and organizing the metadata describing the numerical experiments. The models used to understand real-world systems, and the computational machinery required to simulate them, are typically complex, and produce large amounts of heterogeneous metadata. Here, we present general practices for acquiring and handling metadata that are agnostic to software and hardware, and highly flexible for the user. These consist of two steps: 1) recording and storing raw metadata, and 2) selecting and structuring metadata. As a proof of concept, we develop the Archivist, a Python tool to help with the second step, and use it to apply our practices to distinct high-performance computing use cases from neuroscience and hydrology. Our practices and the Archivist can readily be applied to existing workflows without the need for substantial restructuring. They support sustainable numerical workflows, fostering replicability, reproducibility, data exploration, and data sharing in simulation-based research.}, keywords = {Information Retrieval (cs.IR) (Other) / FOS: Computer and information sciences (Other)}, cin = {IAS-6 / IAS-9}, ddc = {500}, cid = {I:(DE-Juel1)IAS-6-20130828 / I:(DE-Juel1)IAS-9-20201008}, pnm = {5232 - Computational Principles (POF4-523) / 5235 - Digitization of Neuroscience and User-Community Building (POF4-523) / MetaMoSim - Generic metadata management for reproducible high-performance-computing simulation workflows - MetaMoSim (ZT-I-PF-3-026) / HiRSE - Helmholtz Platform for Research Software Engineering (HiRSE-20250220) / Advanced Computing Architectures $(aca_20190115)$ / EBRAINS 2.0 - EBRAINS 2.0: A Research Infrastructure to Advance Neuroscience and Brain Health (101147319) / Brain-Scale Simulations $(jinb33_20220812)$ / ICEI - Interactive Computing E-Infrastructure for the Human Brain Project (800858) / JL SMHB - Joint Lab Supercomputing and Modeling for the Human Brain (JL SMHB-2021-2027) / DFG project G:(GEPRIS)491111487 - Open-Access-Publikationskosten / 2025 - 2027 / Forschungszentrum Jülich (OAPKFZJ) (491111487)}, pid = {G:(DE-HGF)POF4-5232 / G:(DE-HGF)POF4-5235 / G:(DE-Juel-1)ZT-I-PF-3-026 / G:(DE-Juel-1)HiRSE-20250220 / $G:(DE-Juel1)aca_20190115$ / G:(EU-Grant)101147319 / $G:(DE-Juel1)jinb33_20220812$ / G:(EU-Grant)800858 / G:(DE-Juel1)JL SMHB-2021-2027 / G:(GEPRIS)491111487}, typ = {PUB:(DE-HGF)16}, pubmed = {40473681}, UT = {WOS:001503948500006}, doi = {10.1038/s41597-025-05126-1}, url = {https://juser.fz-juelich.de/record/1043152}, }