Simultaneous reconstruction of boosted, resolved, and semi-boosted top-quark events with symmetry-preserving attention networks

Multiple top quark production at the LHC provides a rich environment to probe the Standard Model for signs of new physics. A substantial fraction of these events result in fully hadronic final states, where each top decays into a bottom quark and a W boson, with the latter further decaying into two light quarks. In the case of multiple hadronic tops this yields a multi-jet final state, posing a combinatorial challenge known as the jet assignment problem: matching reconstructed jets to top candidates. Symmetry-preserving attention networks (SPA-Nets) have been developed to tackle such problems by leveraging permutation-invariant representations of jet sets. However, the complexity increases when accounting for the different reconstruction topologies of top candidates depending on the top momenta: "resolved"— all decay products are reconstructed as separate jets—, "boosted"— high-momentum tops are reconstructed as merged jets, and "semi-boosted"— some decay products are merged while others are separate. Traditional top tagging approaches target either boosted or resolved topologies exclusively, or select top candidates preferentially for these topologies, leading to reduced reconstruction efficiency. In this work, we extend the SPA-Net framework to simultaneously consider all topologies, and we evaluate our model using simulated tttt and tt+jets samples at the LHC. A full code repository with a general library, the specific configuration used, and a complete dataset release are included.