New graph-neural-network flavor tagger for Belle II and measurement of sin2φ₁ in B⁰ → J/ψ K⁰S decays

We present GFlaT, a new algorithm that uses a graph-neural-network to determine the flavor of neutral B mesons produced in Υ(4S) decays. It improves previous algorithms by using the information from all charged final-state particles and the relations between them. We evaluate its performance using B decays to flavor-specific hadronic final states reconstructed in a 362 fb⁻¹ sample of electron-positron collisions collected at the Υ(4S) resonance with the Belle II detector at the SuperKEKB collider. We achieve an effective tagging efficiency of (37.40 ± 0.43 ± 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 B⁰→ J/ψ K⁰S decays to measure the mixing-induced and direct $CP$ violation parameters, S = (0.724 ± 0.035 ± 0.009) and C = (-0.035 ± 0.026 ± 0.029).