Results from the ML model vs binning in two features, O(\Lambda^{-4})
Results from the ML model vs binning in two features, \(O(\Lambda^{-4})\)#
Figure 5.4 of [Gomez Ambrosio et al., 2022].
95% CL intervals for the \(n_{eft} = 8\) Wilson coefficients relevant for the description of top quark pair production at the quadratic \(O(\Lambda^{-4})\) level.
The black cross indicates the SM values used to generate the pseudo-data that enters the inference. We present marginalised intervals, obtained from the full posterior distribution provided by Nested Sampling.
We compare the constraints obtained from the ML model trained on one feature, \(p_{\ell \ell}\), and on two features, \(p_{\ell \ell}\) and \(\eta_{\ell}\), with those obtained from a binned analysis of the same two features.
See also the next page for the comparison of the ML model trained on two features with the ML model trained on the full set of \(n_{k} = 18\) kinematic features.
