A Graph Neural Network for B decays reconstruction at Belle II

The Belle II experiment has unique features that allow to study B meson decays with neutrinos in the final state. It is possible to deduce the presence of such particles from the energy-momentum imbalance obtained after reconstructing the companion B meson produced in the event. This task is complicated by the thousands of possible final states in which B mesons can decay, and is currently performed at Belle II by the Full Event Interpretation, an algorithm based on Boosted Decision Trees and limited to specific, hard-coded decay processes. In recent years, graph neural networks have proven to be very effective tools to describe relations in physical systems, with applications in a range of fields. Particle decays can be naturally represented in the form of rooted directed acyclic tree graphs, with nodes corresponding to particles and edges representing the parent-child relations between them. In this work, we present a graph neural network approach to generically reconstruct B decays at Belle II by exploiting the information on the final-state particles alone, without formulating any prior assumption about the nature of the decay. Preliminary results show that the graph neural network approach outperforms the Full Event Interpretation by a factor of about 2 in terms of number of decays whose topologies are correctly reconstructed.