Jet reconstruction with Mamba networks in collider events

We introduce a novel end-to-end framework for jet reconstruction in high-energy collider events, leveraging the efficiency and long-range modeling capabilities of the Mamba architecture. Our model unifies instance segmentation, classification, and kinematic regression into a single multitask learning system, enabling a sophisticated multilevel reconstruction that simultaneously identifies primary heavy jets (<a:math xmlns:a="http://www.w3.org/1998/Math/MathML" display="inline"><a:mi>t</a:mi></a:math>, <c:math xmlns:c="http://www.w3.org/1998/Math/MathML" display="inline"><c:mi>H</c:mi></c:math>, <e:math xmlns:e="http://www.w3.org/1998/Math/MathML" display="inline"><e:mi>W</e:mi><e:mo>/</e:mo><e:mi>Z</e:mi></e:math>) and their constituent subjets. To facilitate supervised learning for this complex task, we develop a novel method for assigning final-state hadrons to their ancestor colored partons using a mixed-integer linear programming solver, which generates high-fidelity ground-truth labels. The model achieves high classification accuracy, with an average precision score of 0.569 for <g:math xmlns:g="http://www.w3.org/1998/Math/MathML" display="inline"><g:mi>W</g:mi><g:mo>/</g:mo><g:mi>Z</g:mi></g:math>-jets and 0.568 for <i:math xmlns:i="http://www.w3.org/1998/Math/MathML" display="inline"><i:mi>b</i:mi></i:math>-jets, and shows exceptional precision in kinematic reconstruction. Furthermore, we show that the model not only maintains stable performance in high-pileup environments but also successfully reconstructs the mass peaks of beyond the standard model particles. This work presents a powerful and versatile new tool for comprehensive event reconstruction at the LHC.