Probing lepton flavor mixing in ${W}_{R}$ searches with machine learning at the LHC

Right-handed lepton flavor mixing in the left-right symmetric model directly affects the production and decay of heavy Majorana neutrinos ${N}_{R}$, yet its impact on collider searches remains less explored. Using a deep neural network, we analyze the Keung-Senjanovi\ifmmode \acute{c}\else \'{c}\fi{} process $pp\ensuremath{\rightarrow}{W}_{R}\ensuremath{\rightarrow}{\ensuremath{\ell}}_{\ensuremath{\alpha}}{N}_{R}\ensuremath{\rightarrow}{\ensuremath{\ell}}_{\ensuremath{\alpha}}{\ensuremath{\ell}}_{\ensuremath{\beta}}jj$ with ${\ensuremath{\ell}}_{\ensuremath{\alpha},\ensuremath{\beta}}=e$, $\ensuremath{\mu}$ at LHC Run 2 and the HL-LHC, considering both same-sign and opposite-sign dilepton channels. We adopt three benchmark mixing scenarios: unmixed, maximal mixing, and Pontecorvo-Maki-Nakagawa-Sakata (PMNS)-like. In the unmixed scenario, the deep neural network improves the expected significance over the cut-based analyses performed by ATLAS, leading to stronger expected sensitivit