CP-analyses with symbolic regression

Bahl, Henning; Fuchs, Elina; Menen, Marco; Plehn, Tilman

doi:https://doi.org/10.21468/scipostphys.20.2.040

Zugriffsnummer	56307
Dokumenttyp	Zeitschriftenartikel
Peer Review	mit Peer Review
Sprache	Englisch
Titel	CP-analyses with symbolic regression
Autor(in); Institution	Bahl, Henning; Universität Heidelberg, Institut für Theoretische Physik, Heidelberg, GERMANY Fuchs, Elina; FPM, Fundamentale Physik für Metrologie, PTB-Braunschweig; Leibniz Universität Hannover, Institut für Theoretische Physik, Hannover, GERMANY; Deutsches Elektronen-Synchrotron (DESY), Hamburg, GERMANY Menen, Marco; FPM, Fundamentale Physik für Metrologie, PTB-Braunschweig; Leibniz Universität Hannover, Institut für Theoretische Physik, Hannover, GERMANY Plehn, Tilman; Universität Heidelberg, Institut für Theoretische Physik, Heidelberg, GERMANY; Universität Heidelberg, Interdisciplinary Center for Scientific Computing (IWR), Heidelberg, GERMANY
Quelle/Jahr	SciPost Physics: 20 (2026), 2, 1 - 36
Artikelnummer	040
ISSN	2542-4653 (PDF)
DOI	https://doi.org/10.21468/scipostphys.20.2.040
URL	https://scipost.org/10.21468/SciPostPhys.20.2.040/pdf
Verlag	Amsterdam: SciPost Foundation
Freie Schlagworte	CP violation ; Higgs physcis ; Large Hadron Collider ; Symbolic regression ; Interpretable machine learning
Zusammenfassung	Searching for violation in Higgs interactions at the LHC is as challenging as it is important. Although modern machine learning outperforms traditional methods, its results are difficult to control and interpret, which is especially important if an unambiguous probe of a fundamental symmetry is required. We propose solving this problem by learning analytic formulas with symbolic regression. Using the complementary PySR and SymbolNet approaches, we learn CP-sensitive observables at the detector level for WBF Higgs production and top-associated Higgs production. We find that they offer advantages in interpretability and performance.

Kostenfreier Zugang	Open Access Gold
Rechteinformation	CC BY 4.0 ; Creative Commons Attribution 4.0 License ; Diamond

Themenbereich der Metrologie	Zeit und Frequenz
Innovationscluster	Quantentechnologie
Geschäftsfelder	Grundlagen der Metrologie
Forschungsprojekt	HB and TP acknowledge support through the KISS consortium (05D2022) funded by the German Federal Ministry of Education and Research BMBF in the ErUM-Data action plan, by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under grant 396021762 - TRR 257: Particle Physics Phenomenology after the Higgs Discovery, and through Germany’s Excellence Strategy EXC 2181/1 – 390900948 (the Heidelberg STRUCTURES Excellence Cluster) and by the state of Baden-Württemberg through bwHPC and the German Research Foundation (DFG) through grant INST 35/1597-1 FUGG. EF and MM were funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy – EXC-2123 QuantumFrontiers – 390837967. The authors acknowledge resources provided by the LUIS computing cluster at Leibniz University Hannover, which is funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – Projektnummern INST 187/742-1 FUGG, INST 187/592-1 FUGG, and INST 187/430-1. This work has been partially funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - 491245950.

Zitierung

Bahl, H., Fuchs, E., Menen, M., & Plehn, T. (2026). CP-analyses with symbolic regression. SciPost Physics, 20(2), 1–36. https://doi.org/10.21468/scipostphys.20.2.040

Exportieren

RIS BibTeX

Zitierung

Exportieren

PTB-Publica Menü