Parton Labeling without Matching: Unveiling Emergent Labelling Capabilities in Regression Models

TL;DR

This paper introduces a novel method for parton labeling in collider event reconstruction that eliminates the need for matched training data by recycling regression models to assign final state objects to parent particles.

Contribution

It presents a new approach that bypasses the requirement for matched simulation data, improving the accuracy of parton labeling in collider physics.

Findings

Outperforms the traditional $$ method in simulated top quark events.

Does not require matched training data, simplifying the labeling process.

Demonstrates effectiveness in complex collider event scenarios.

Abstract

Parton labeling methods are widely used when reconstructing collider events with top quarks or other massive particles. State-of-the-art techniques are based on machine learning and require training data with events that have been matched using simulations with truth information. In nature, there is no unique matching between partons and final state objects due to the properties of the strong force and due to acceptance effects. We propose a new approach to parton labeling that circumvents these challenges by recycling regression models. The final state objects that are most relevant for a regression model to predict the properties of a particular top quark are assigned to said parent particle without having any parton-matched training data. This approach is demonstrated using simulated events with top quarks and outperforms the widely-used $\chi^2$ method.