Enabling stable preservation of ML algorithms in high-energy physics with petrifyML

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Buckley, Andy, Corpe, Louie, Habedank, Martin, Procter, Tomasz
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917539263545344
author Buckley, Andy
Corpe, Louie
Habedank, Martin
Procter, Tomasz
author_facet Buckley, Andy
Corpe, Louie
Habedank, Martin
Procter, Tomasz
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11830
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enabling stable preservation of ML algorithms in high-energy physics with petrifyML
Buckley, Andy
Corpe, Louie
Habedank, Martin
Procter, Tomasz
High Energy Physics - Phenomenology
High Energy Physics - Experiment
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.
title Enabling stable preservation of ML algorithms in high-energy physics with petrifyML
topic High Energy Physics - Phenomenology
High Energy Physics - Experiment
url https://arxiv.org/abs/2509.11830