Enabling stable preservation of ML algorithms in high-energy physics with petrifyML
SciPost Physics Codebases · 21.08.2026
DOI: 10.21468/scipostphyscodeb.78 ↗Kurz gefasst
Fachartikel in der Zeitschrift SciPost Physics Codebases, online erschienen am 21.08.2026. Verfasst von Andy Buckley und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council, Infrastruktura PL-Grid, Narodowe Centrum Nauki.
Abstract (Originalsprache)
Machine learning (ML) in high-energy physics (HEP) has moved in the LHC era from an internal detail of experiment software, to an unavoidable public component of many physics data analyses. Scientific reproducibility thus requires that it be possible to accurately and stably preserve the behaviours of these, sometimes very complex algorithms. We present and document the petrifyML package, which provides missing mechanisms to convert configurations from commonly used HEP ML tools to either the industry- standard ONNX format or to native Python or C++ code, enabling future re-use and re-interpretation of many ML-based experimental studies.
Förderung
- Engineering and Physical Sciences Research Council
- Infrastruktura PL-Grid
- Narodowe Centrum Nauki
- UK Research and Innovation
Zitieren
APA
Buckley, A., Corpe, L., Habedank, M., & Procter, T. (2026). Enabling stable preservation of ML algorithms in high-energy physics with petrifyML. SciPost Physics Codebases. https://doi.org/10.21468/scipostphyscodeb.78
Vancouver
Buckley A, Corpe L, Habedank M, Procter T. Enabling stable preservation of ML algorithms in high-energy physics with petrifyML. SciPost Physics Codebases. 2026. doi:10.21468/scipostphyscodeb.78
BibTeX
@article{Buckley2026,
author = {Buckley, Andy and Corpe, Louie and Habedank, Martin and Procter, Tomasz},
title = {Enabling stable preservation of ML algorithms in high-energy physics with petrifyML},
journal = {SciPost Physics Codebases},
year = {2026},
doi = {10.21468/scipostphyscodeb.78}
}
EUVIMED