Machine learning the Higgs boson-top quark CP phase

Abstract

We explore the direct Higgs boson-top $CP$ measurement via the $pp\ensuremath{\rightarrow}t\overline{t}h$ channel at the high-luminosity LHC. We show that a combination of machine learning techniques and efficient kinematic reconstruction methods can boost new physics sensitivity, effectively probing the complex $t\overline{t}h$ multiparticle phase space. Special attention is devoted to top quark polarization observables, uplifting the analysis from a raw rate to a polarization study. Through a combination of hadronic, semileptonic, and dileptonic top pair final states in association with $h\ensuremath{\rightarrow}\ensuremath{\gamma}\ensuremath{\gamma}$, we obtain that the HL-LHC can probe the Higgs boson-top coupling modifier and $CP$ phase, respectively, up to $|{\ensuremath{\kappa}}_{t}|\ensuremath{\lesssim}8%$ and $|\ensuremath{\alpha}|\ensuremath{\lesssim}13\ifmmode^\circ\else\textdegree\fi{}$ at 68% C.L.