Simplex Demixing: Disentangling Multiple Light-Flavor Jets at Colliders

2026-07-27

AI Summary

Existing methods struggle to perform data-driven, hadron-level classification of multiple light-flavor jets—such as those initiated by up quarks, down quarks, and gluons. This work proposes a “simplex unmixing” framework that, for the first time, introduces statistical topic modeling into high-energy physics. By mapping a multi-class neural network classifier onto the geometry of a T-dimensional simplex, the approach enables unsupervised decomposition of jet flavor composition. It overcomes the traditional limitation of binary quark/gluon discrimination and supports separable identification of three or more jet flavors. Validated on mixtures of synthetic and real collider data, the method successfully recovers the underlying flavor fractions and demonstrates feasibility in dijet events, thereby opening a new avenue for multi-flavor jet studies at the LHC.

Abstract

Providing a practical and hadron-level definition of multiple jet flavors has been a long-standing challenge in collider physics. Previous work has introduced a data-driven, operational definition of quark and gluon jets, but no robust generalization beyond two jet categories presently exists. To address this, we introduce a machine-learning framework called"simplex demixing''to extract $T$ jet flavors (or topics in the statistics literature) from $M$ data samples (or mixtures) with minimal constraints. Intuitively, our procedure identifies the maximally separable categories in the data, translating a multi-category classifier on the $M$ mixtures into a bounded geometric object with $T$ vertices. We first demonstrate our procedure on a toy problem to infer the truth-level fractions of down-quark, up-quark, and gluon jets from synthetic mixtures of the three pure samples. We then propose a tag-and-probe strategy to extract multiple light-flavor categories in a more realistic collider setting involving dijet production. As expected, the identifiability of jet flavors depends on their relative abundance in the samples and the hadron-level information available to the classifier architecture. Our work opens the door to data-driven extractions of multiple jet flavor properties at the Large Hadron Collider.

Problem

• jet flavor
• collider physics
• light-flavor jets
• multi-category classification
• hadron-level definition

Innovation

• simplex demixing
• jet flavor tagging
• unsupervised learning
• topic modeling
• hadron-level jet classification