Adversarial Neural Network-based data-simulation corrections for heavy-flavour jet-tagging

Variable-dependent scale factors are used in heavy-flavour jet-tagging to improve shape agreement of data and simulation. The choice of the underlying model is of great importance, but often requires a lot of manual tuning e.g. of bin sizes or fitted functions. This is a novel and generalized method for producing scale factors using an adversarial neural network. The primary network uses the jet variables as inputs to derive the scale factor for a single jet. It is trained through the use of a second network, the adversary, which aims to differentiate between the data and rescaled simulation. The viability and general agreement with traditional methods is shown.