Graph Neural Network Flavor Tagger and measurement of $\mathrm{sin}2\beta$ at Belle II

TL;DR

This paper introduces GFlaT, a graph neural network-based flavor tagging algorithm for neutral B mesons, demonstrating improved efficiency and applying it to measure CP violation parameters at Belle II.

Contribution

The paper presents GFlaT, a novel GNN-based flavor tagging algorithm that outperforms previous methods and is used to measure CP violation parameters in B meson decays.

Findings

Achieved an 18% improvement in tagging efficiency over previous Belle II algorithms.

Measured CP violation parameters C and S with high precision.

Determined the CKM angle β as (23.2 ± 1.5 ± 0.6)°.

Abstract

We present GFlaT, a new algorithm that uses a graph-neural-network to determine the flavor of neutral B mesons produced in $\mathrm{\Upsilon(4S)}$ decays. We evaluate its performance using $B$ decays to flavor-specific hadronic final states reconstructed in a $362$ $\mathrm{fb}^{-1}$ sample of electron-positron collisions recorded at the $\mathrm{\Upsilon(4S)}$ resonance with the Belle II detector at the SuperKEKB collider. We achieve an effective tagging efficiency of $(37.40 \pm 0.43 \pm 0.36) \%$, where the first uncertainty is statistical and the second systematic, which is $18\%$ better than the previous Belle II algorithm. Demonstrating the algorithm, we use $B^0 \to J/\psi K_\mathrm{S}^0$ decays to measure the direct and mixing-induced CP violation parameters, $C = (-0.035 \pm 0.026 \pm 0.013)$ and $S = (0.724 \pm 0.035 \pm 0.014)$, from which we obtain $\beta = (23.2 \pm 1.5 \pm 0.6)^{\circ}$.