# Deep learning approach to the Higgs boson CP measurement in H to tau tau decay and associated systematics

## TL;DR

This paper advances deep learning methods for measuring the Higgs boson CP properties in tau tau decays, addressing systematic uncertainties from experimental effects and decay modeling to improve measurement accuracy.

## Contribution

It extends previous work by incorporating partial experimental effect modeling and systematic uncertainties from tau decay modeling into deep learning-based CP measurements.

## Key findings

- Deep learning techniques are viable for Higgs CP measurement.
- Systematic effects from tau decay modeling impact measurement accuracy.
- Various parameterizations using collision data are evaluated.

## Abstract

The H to tau tau decays form the prime channel for the measurement of the Higgs boson state and tests of the CP invariance of Higgs boson couplings. A previous study has shown the viability of deep learning techniques for the measurement. In this paper, the study is expanded. Effects due to the partial modelling of experimental effects are discussed. Furthermore, systematics due to ? decay modelling for complex cascade decays to tau^pm to a_1^pm nu_tau to rho^0 pi^pm nu_tau to 3pi^\pm nu_tau are also addressed. Various parameterisations are considered using low-energy collision data.