Pré-Publication, Document De Travail Année : 2025

Automatizing the search for mass resonances using BumpNet

Jean-Francois Arguin
  • Fonction : Auteur
Georges Azuelos
  • Fonction : Auteur
Émile Baril
  • Fonction : Auteur
Ilan Bessudo
  • Fonction : Auteur
Fannie Bilodeau
  • Fonction : Auteur
Maryna Borysova
  • Fonction : Auteur
Shikma Bressler
  • Fonction : Auteur
Etienne Dreyer
  • Fonction : Auteur
Michael Kwok Lam Chu
  • Fonction : Auteur
Ethan Meszaros
  • Fonction : Auteur
Nilotpal Kakati
  • Fonction : Auteur
Joséphine Potdevin
  • Fonction : Auteur
Amit Shkuri
  • Fonction : Auteur
Muhammad Usman
  • Fonction : Auteur

Résumé

The search for resonant mass bumps in invariant-mass distributions remains a cornerstone strategy for uncovering Beyond the Standard Model (BSM) physics at the Large Hadron Collider (LHC). Traditional methods often rely on predefined functional forms and exhaustive computational and human resources, limiting the scope of tested final states and selections. This work presents BumpNet, a machine learning-based approach leveraging advanced neural network architectures to generalize and enhance the Data-Directed Paradigm (DDP) for resonance searches. Trained on a diverse dataset of smoothly-falling analytical functions and realistic simulated data, BumpNet efficiently predicts statistical significance distributions across varying histogram configurations, including those derived from LHC-like conditions. The network's performance is validated against idealized likelihood ratio-based tests, showing minimal bias and strong sensitivity in detecting mass bumps across a range of scenarios. Additionally, BumpNet's application to realistic BSM scenarios highlights its capability to identify subtle signals while managing the look-elsewhere effect. These results underscore BumpNet's potential to expand the reach of resonance searches, paving the way for more comprehensive explorations of LHC data in future analyses.

Dates et versions

hal-04909860 , version 1 (24-01-2025)

Identifiants

Citer

Jean-Francois Arguin, Georges Azuelos, Émile Baril, Ilan Bessudo, Fannie Bilodeau, et al.. Automatizing the search for mass resonances using BumpNet. 2025. ⟨hal-04909860⟩
1 Consultations
0 Téléchargements

Partager

More