Machine learning the Higgs boson-top quark CP phase

TL;DR

This paper demonstrates that combining machine learning with kinematic reconstruction in the $pp\to t\bar{t}h$ channel at the HL-LHC enhances sensitivity to the Higgs-top CP phase, enabling precise measurements of the coupling modifier and CP-phase.

Contribution

It introduces a novel approach using machine learning and polarization observables to improve direct Higgs-top CP phase measurement at the HL-LHC.

Findings

HL-LHC can probe the Higgs-top coupling modifier up to ~8%.

HL-LHC can measure the CP-phase up to ~13 degrees.

Machine learning boosts sensitivity in multi-particle phase space analysis.

Abstract

We explore the direct Higgs-top CP measurement via the $pp\to t\bar{t}h$ 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 $t\bar{t}h$ multi-particle 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, semi-leptonic, and di-leptonic top pair final states in association with $h\to \gamma\gamma$, we obtain that the HL-LHC can probe the Higgs-top coupling modifier and CP-phase, respectively, up to $|\kappa_t|\lesssim 8\%$ and $|\alpha|\lesssim 13^{\circ}$ at $68\%$~CL.