A new AI-based Full Event Interpretation model for flavour physics
Abstract
The increasing event complexity and data rates foreseen for future LHC coinditions motivate a transition from selecting proton-proton (pp) collision events by reconstructing predefined signal candidates to constructing a reduced data stream by interpreting the relevant event features in a signal-agnostic way. We explore the capabilities of deep-learning-based architectures on heavy-flavour physics using LHCb as a case study. Graph-based full-event interpretation techniques address the problem by representing visible products of pp collisions as nodes of a graph, and reconstructing heavy-hadron decay chains hierarchically. A new neutral-particle-aware architecture extends the input data from charged tracks to calorimeter clusters, and uses metric learning to clusterize particles from the same decay chain in a common latent space. Tests on inclusive simulated pp→ bb̅ events show that this approach retains its ability to reconstruct decay chains across a broad range of topologies and multiplicities. We discuss the resulting physics opportunities, with a focus on inclusive b→ sℓℓ measurements and on searches for exotic hadrons.
Related
- A graph neural network for deep learning-based full event interpretation at FCC-ee
- Full Event Interpretation at Belle II: Current Status and Recent Developments
- Full-event anomaly detection for new physics searches at the Electron-Ion Collider
- Theoretical Perspectives on Flavour Physics
- Environment-dependent mass splitting to suppress solar capture in the inelastic-doublet interpretation of the LZ event
BibTeX
@misc{barbieri2026aibased,
title = {{A new AI-based Full Event Interpretation model for flavour physics}},
author = {Matteo Barbieri and Marta Calvi and Elena Graverini and Rafael Silva Coutinho and Felipe Luan Souza de Almeida},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.16021},
eprint = {2610.16021},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.16021},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - A new AI-based Full Event Interpretation model for flavour physics
AU - Matteo Barbieri
AU - Marta Calvi
AU - Elena Graverini
AU - Rafael Silva Coutinho
AU - Felipe Luan Souza de Almeida
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2610.16021
UR - https://arxiv.org/abs/2610.16021
AB - The increasing event complexity and data rates foreseen for future LHC coinditions motivate a transition from selecting proton-proton (pp) collision events by reconstructing predefined signal candidates to constructing a reduced data stream by interpreting the relevant event features in a signal-agnostic way. We explore the capabilities of deep-learning-based architectures on heavy-flavour physics using LHCb as a case study. Graph-based full-event interpretation techniques address the problem by representing visible products of pp collisions as nodes of a graph, and reconstructing heavy-hadron decay chains hierarchically. A new neutral-particle-aware architecture extends the input data from charged tracks to calorimeter clusters, and uses metric learning to clusterize particles from the same decay chain in a common latent space. Tests on inclusive simulated pp→ bb̅ events show that this approach retains its ability to reconstruct decay chains across a broad range of topologies and multiplicities. We discuss the resulting physics opportunities, with a focus on inclusive b→ sℓℓ measurements and on searches for exotic hadrons.
ER -