Les Houches guide to reusable ML models in LHC analyses
SciPost Physics Community Reports2024
Citations Over TimeTop 10% of 2024 papers
Jack Y. Araz, A. G. Buckley, Gregor Kasieczka, J. Kieseler, Sabine Kraml, Anders Kvellestad, André Lessa, T. Procter, Are Raklev, Humberto Reyes-González, Krzysztof Rolbiecki, S. Sekmen, G. Ünel
Abstract
With the increasing usage of machine-learning in high-energy physics analyses, the publication of the trained models in a reusable form has become a crucial question for analysis preservation and reuse. The complexity of these models creates practical issues for both reporting them accurately and for ensuring the stability of their behaviours in different environments and over extended timescales. In this note we discuss the current state of affairs, highlighting specific practical issues and focusing on the most promising technical and strategic approaches to ensure trustworthy analysis-preservation. This material originated from discussions in the LHC Reinterpretation Forum and the 2023 PhysTeV workshop at Les Houches.
Related Papers
- → The reinterpretation of histories in identities of newly established regions: The case of Local Action Groups in Czechia(2017)8 cited
- Summary and Commentary of the "Reinterpretation" study(2010)
- Susquehanna Chorale Spring Concert "Roots and Wings"(2017)
- → Rietveld Joint. Metamorphic Reinterpretation, Representation and Physical Modeling in the Didactic Experience of Industrial Design(2017)
- → The Strategies of Adaptation of Ivan Bunin in the Cinema: Interpretation and Reinterpretation(2020)