Accuracy versus precision in boosted top tagging with the ATLAS detector

Abstract

The identification of top quark decays where the top quark has a large momentum transverse to the beam axis, known as $top$ $tagging$, is a crucial component in many measurements of Standard Model processes and searches for beyond the Standard Model physics at the Large Hadron Collider. Machine learning techniques have improved the performance of top tagging algorithms, but the size of the systematic uncertainties for all proposed algorithms has not been systematically studied. This paper presents the performance of several machine learning based top tagging algorithms on a dataset constructed from simulated proton-proton collision events measured with the ATLAS detector at $\sqrt{s}=13$ TeV. The systematic uncertainties associated with these algorithms are estimated through an approximate procedure that is not meant to be used in a physics analysis, but is appropriate for the level of precision required for this study. The most performant algorithms are found to have the largest uncertainties, motivating the development of methods to reduce these uncertainties without compromising performance. To enable such efforts in the wider scientific community, the datasets used in this paper are made publicly available.

47 pages in total, author list starting page 30, 10 figures, 4 tables, published in JINST 19 (2024) P08018. All figures including auxiliary figures are available at http://atlas.web.cern.ch/Atlas/GROUPS/PHYSICS/PAPERS/JETM-2023-06

References in corpus (83)

• PYTHIA 6.4 Physics and Manual
• PYTHIA 6.2 Physics and Manual
• The anti-k_t jet clustering algorithm
• An Introduction to PYTHIA 8.2
• FastJet user manual
• A general framework for implementing NLO calculations in shower Monte Carlo programs: the POWHEG BOX
• A New Method for Combining NLO QCD with Shower Monte Carlo Algorithms
• Matching NLO QCD computations with Parton Shower simulations: the POWHEG method
• Parton distributions for the LHC Run II
• Herwig++ Physics and Manual
• Parton distributions with LHC data
• The ATLAS Simulation Infrastructure
• Herwig 7.0 / Herwig++ 3.0 Release Note
• A Positive-Weight Next-to-Leading-Order Monte Carlo for Heavy Flavour Hadroproduction
• Event Generation with Sherpa 2.2
• Identifying Boosted Objects with N-subjettiness
• Soft Drop
• The Catchment Area of Jets
• Topological cell clustering in the ATLAS calorimeters and its performance in LHC Run 1
• ParticleNet: Jet Tagging via Particle Clouds
• Energy Correlation Functions for Jet Substructure
• Deep Learning and its Application to LHC Physics
• Jet reconstruction and performance using particle flow with the ATLAS Detector
• Maximizing Boosted Top Identification by Minimizing N-subjettiness
• Boosted objects: a probe of beyond the Standard Model physics
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Jet Substructure at the Tevatron and LHC: New results, new tools, new benchmarks
• Classification without labels: Learning from mixed samples in high energy physics
• Jet-Images -- Deep Learning Edition
• Deep-learning Top Taggers or The End of QCD?
• Strategies to Identify Boosted Tops
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Energy Flow Networks: Deep Sets for Particle Jets
• The Machine Learning Landscape of Top Taggers
• Power Counting to Better Jet Observables
• A modified cluster-hadronization model
• Boosted objects and jet substructure at the LHC
• Luminosity determination in $pp$ collisions at $\sqrt{s}=13$ TeV using the ATLAS detector at the LHC
• New Angles on Energy Correlation Functions
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques
• Performance of the ATLAS Track Reconstruction Algorithms in Dense Environments in LHC Run 2
• Energy flow polynomials: A complete linear basis for jet substructure
• Automated Parton-Shower Variations in Pythia 8
• Pulling Out All the Tops with Computer Vision and Deep Learning
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• SoftKiller, a particle-level pileup removal method
• Performance of top-quark and $W$-boson tagging with ATLAS in Run 2 of the LHC
• Particle-level pileup subtraction for jets and jet shapes
• A measurement of the soft-drop jet mass in pp collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• A measurement of soft-drop jet observables in $pp$ collisions with the ATLAS detector at $\sqrt{s}=13$ TeV
• Measurement of the Lund jet plane using charged particles in 13 TeV proton-proton collisions with the ATLAS detector
• Uncertainty Aware Learning for High Energy Physics
• Optimisation of large-radius jet reconstruction for the ATLAS detector in 13 TeV proton-proton collisions
• A measurement of the calorimeter response to single hadrons and determination of the jet energy scale uncertainty using LHC Run-1 $pp$-collision data with the ATLAS detector
• Measurement of jet-substructure observables in top quark, $W$ boson and light jet production in proton-proton collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Measurement of the $\mathrm{t}\bar{\mathrm{t}}\mathrm{b}\bar{\mathrm{b}}$ production cross section in the all-jet final state in pp collisions at $\sqrt{s}=$ 13 TeV
• New approach to identifying boosted hadronically-decaying particle using jet substructure in its center-of-mass frame
• Alignment of the ATLAS Inner Detector in Run-2
• Search for $t\bar{t}$ resonances in fully hadronic final states in $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Pileup and Underlying Event Mitigation with Iterative Constituent Subtraction
• Search for single production of a vector-like $T$ quark decaying into a Higgs boson and top quark with fully hadronic final states using the ATLAS detector
• Search for Higgs boson decay to a charm quark-antiquark pair in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Identification of high transverse momentum top quarks in $pp$ collisions at $\sqrt{s}$ = 8 TeV with the ATLAS detector
• Measurement of the jet mass in highly boosted t t-bar events from pp collisions at sqrt(s) = 8 TeV
• Search for electroweak production of a vector-like quark decaying to a top quark and a Higgs boson using boosted topologies in fully hadronic final states
• Explainable Equivariant Neural Networks for Particle Physics: PELICAN
• Measurement of the charge asymmetry in highly boosted top-quark pair production in $\sqrt{s}=$ 8 TeV $pp$ collision data collected by the ATLAS experiment
• Search for single production of a vector-like T quark decaying to a top quark and a Z boson in the final state with jets and missing transverse momentum at $\sqrt{s}=$ 13 TeV
• Search for nonresonant pair production of highly energetic Higgs bosons decaying to bottom quarks
• Measurement of kT splitting scales in W->lv events at sqrt(s)=7 TeV with the ATLAS detector
• Measurement of differential $\mathrm{t}\bar{\mathrm{t}}$ production cross sections using top quarks at large transverse momenta in pp collisions at $\sqrt{s}=$ 13 TeV
• Measurement of the energy asymmetry in $t\bar{t}j$ production at 13 TeV with the ATLAS experiment and interpretation in the SMEFT framework
• Search for a massive scalar resonance decaying to a light scalar and a Higgs boson in the four b quarks final state with boosted topology
• Differential $t\bar{t}$ cross-section measurements using boosted top quarks in the all-hadronic final state with 139 fb${}^{-1}$ of ATLAS data
• Measurement of the energy response of the ATLAS calorimeter to charged pions from $W^{\pm }\to {\tau }^{\pm }(\to {\pi }^{\pm }{\nu }_{\tau }){\nu }_{\tau }$ events in Run 2 data
• Does Lorentz-symmetric design boost network performance in jet physics?
• Search for a heavy resonance decaying to a top quark and a W boson at $\sqrt{s}=$ 13 TeV in the fully hadronic final state
• Improving Robustness of Jet Tagging Algorithms with Adversarial Training
• Safe but Incalculable: Energy-weighting is not all you need
• Measurement of the $\mathrm{t}\bar{\mathrm{t}}$ charge asymmetry in events with highly Lorentz-boosted top quarks in pp collisions at $\sqrt{s}$ = 13 TeV
• Measurements of Lund subjet multiplicities in 13 TeV proton-proton collisions with the ATLAS detector
• Measurement of jet substructure in boosted $t\bar{t}$ events with the ATLAS detector using 140 fb${}^{-1}$ of 13 TeV $pp$ collisions

Cited by in corpus (4)

• Boosting Beyond: A Novel Approach to Probing Top-Philic Resonances at the LHC
• OmniLearned: A Foundation Model Framework for All Tasks Involving Jet Physics
• Strong CWoLa: Binary Classification Without Background Simulation
• Enhancing generalization in high energy physics using white-box adversarial attacks