Learning to identify semi-visible jets

A bstract We train a network to identify jets with fractional dark decay (semi-visible jets) using the pattern of their low-level jet constituents, and explore nature information used by mapping it space substructure observables. Semi-visible arise from matter particles which into mixture sector (invisible) Standard Model (visible) particles. Such objects are challenging due complex alignment momentum imbalance axis, but such do not yet benefit construction dedicated theoretically-motivated deep operating on constituents is as probe available indicates that classification power captured current high-level observables arises primarily low- p T constituents.