Encoding off-shell effects in top pair production in Direct Diffusion networks

TL;DR

This paper proposes a neural network-based method to efficiently encode off-shell effects in top pair production simulations, aiming to improve precision for upcoming LHC runs by transforming approximate events into more accurate ones.

Contribution

The paper introduces a neural network approach to incorporate off-shell effects into top pair production simulations, extending previous methods to include higher order effects.

Findings

Method reliably transforms approximate events into full off-shell calculations at leading order.

Initial steps show potential for extending the approach to higher order effects.

Neural networks can reduce computational costs while maintaining accuracy.

Abstract

To meet the precision targets of upcoming LHC runs in the simulation of top pair production events it is essential to also consider off-shell effects. Due to their great computational cost I propose to encode them in neural networks. For that I use a combination of neural networks that take events with approximate off-shell effects and transform them into events that match those obtained with full off-shell calculations. This was shown to work reliably and efficiently at leading order. Here I discuss first steps extending this method to include higher order effects.