Searcharxiv⌕ Search

arXiv · 2611.15274

Benchmarking Machine-Learning Top Taggers from JetClass to a Full-Simulation $Z'\to t\bar{t}$ Search: Transfer, Extrapolation, Sensitivity and Inference Cost

Abstract

Searches for heavy resonances decaying to \(t\bar{t}\) test physics beyond the Standard Model at the TeV scale, and their reach depends on how well boosted top jets are identified. Machine-learning top taggers are usually compared on fast-simulation samples without pileup and in a narrow jet-\(p_T\) window, so a benchmark ranking does not directly show how much each tagger adds to a real search. This study trains seven taggers under identical conditions on JetClass. They are a boosted decision tree, two image-based networks, ParticleNet, and three particle transformers (ParT, UParT, and GloParT). The taggers are then applied without retraining to a \(Z'\to t\bar{t}\) search with \(m_{Z'}\) between 1.2 and 2.5~TeV, using 2016 CMS Open Data simulated with Geant4 and realistic pileup. The overall benchmark order of the taggers is preserved. However, taggers with similar area under the ROC curve (AUC) differ by up to a factor of three in jet-level discovery significance. The particle transformers extend the mass reach of the search by \(400~\mathrm{GeV}\), and their lead grows with resonance mass. This gain is seen in fully merged top jets and is associated with stable performance at jet \(p_T\) above the training range. Pileup has only a minor effect on all taggers. A small convolutional network achieves competitive discrimination at a much lower computational cost. The gaps between tagger groups hold under retraining and within statistical uncertainties. The results show that a tagger must be chosen on its kinematic coverage, the working point of the analysis, its discovery sensitivity and its cost, and not on its benchmark score alone.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Manisha Kumari, Amal Sarkar. 2026-11-11. Benchmarking Machine-Learning Top Taggers from JetClass to a Full-Simulation $Z'\to t\bar{t}$ Search: Transfer, Extrapolation, Sensitivity and Inference Cost. https://searcharxiv.com/abs/2611.15274

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related papers

Model-independent ZH production cross section at FCC-ee

This paper presents prospects for measuring the model-independent ZH production cross section at the FCC-ee using the recoil-mass method at center-of-mass energies of 240 GeV and 365 GeV. Analyses are carried out in the muon, electron, and hadronic decay modes of the associated Z boson. The event selections rely primarily on the kinematics of the reconstructed Z decay products, ensuring maximal independence from specific Higgs boson decay modes, while multivariate techniques are employed to further enhance sensitivity. The statistical interpretation of the leptonic and hadronic final states at 240 GeV, with an integrated luminosity of 10.8 ab$^{-1}$, yields relative precisions of 0.52% for the combined leptonic channels and 0.38% for the hadronic channel. Their full statistical combination leads to uncertainties of 0.31% at 240 GeV and 0.52% at 365 GeV, the latter assuming an integrated luminosity of 3.12 ab$^{-1}$. Dedicated statistical tests demonstrate model independence at the level of the obtained precision. This study presents the first consistent and combined analysis of the leptonic and hadronic final states for a model-independent ZH cross-section measurement at a future lepton collider, using a unified workflow and covering both $\sqrt{s} = 240$ and 365 GeV. It provides the most precise expected measurement of the ZH production cross section at future lepton colliders, with the degree of model independence demonstrated within the achieved precision.

hep-ex↗

Prospect for measurement of CP-violating parameters of $B_s^0 \to ϕγ$ at the Tera Z factory

$b \to sγ$ transition is a critical flavor-changing neutral current (FCNC) process that could be used to probe CP violation (CPV) and new physics (NP). We quantify the anticipated precision for measuring $B_s^0 \to ϕγ$ at the CEPC Z pole operation, showing that the relative statistical uncertainty could be as low as 0.16\%, improved by approximately two orders of magnitude compared to existing measurements. Additionally, we perform a time-dependent analysis of the $B_s^0 \to ϕγ$ decay, accounting for $B_s^0/\bar{B}_s^0$ mixing extract the mixing-induced and CP-violating parameters $\boldsymbol{\mathcal{A}_{ϕγ}^Δ}$, $\boldsymbol{C_{ϕγ}}$ and $\boldsymbol{S_{ϕγ}}$. Using central value from LHCb measurement as input, we evaluate the anticipated accuracy of measurements of these parameters. The projected statistical uncertainties are $σ_{A_{ϕγ}^Δ{}^{\text{stat}}} = 0.021$, $σ_C^{\text{stat}} = 0.0092$ and $σ_S^{\text{stat}} = 0.0096$, and the systematic uncertainties are $σ_{A_{ϕγ}^Δ{}^{\text{syst}}} = 0.035$, $σ_C^{\text{syst}} = 0.0027$ and $σ_S^{\text{syst}} = 0.0064$. Furthermore, the 1$σ$ sensitivity boundaries for NP in this study are found to be $\mathcal{A}_{ϕγ}^Δ< -0.05$ or $\mathcal{A}_{ϕγ}^Δ> 0.15$, $\mathcal{C}_{ϕγ} < -0.02$ or $\mathcal{C}_{ϕγ} > 0.04$, and $\mathcal{S}_{ϕγ} < -0.04$ or $\mathcal{S}_{ϕγ} > 0.04$. We also conduct a relevant detector optimization study by establishing the correlation between the anticipated precision and the intrinsic resolution of the ECAL, as well as the performance of the PID system.

hep-ex↗

LH$μ$C Concept: Energy-Frontier Antimuon-Proton Collisions at CERN

The concept of the LH$μ$C, an energy-frontier antimuon-proton collider based on the HL-LHC, is presented. After recalling why energy-frontier lepton-hadron colliders are indispensable as QCD explorers and reviewing the history of muon-proton collider proposals, two ways of realising $μp$ collisions at the LHC are compared: with muon-collider beams and with ultra-cold $μ^+$ beams as proposed for $μ$TRISTAN. For the latter, a $μ$TRISTAN-type booster and the re-use of the LHeC energy-recovery-linac tunnel are discussed; colliding 1 TeV antimuons with 7 TeV protons gives $\sqrt{s}=5.3$ TeV and peak luminosities of $8.8\times10^{33}$ and $7.2\times10^{33}$ cm$^{-2}$s$^{-1}$, respectively. The detector concept and the physics potential, including searches for colour-octet muons and R-parity-violating squarks, are discussed together with the main challenges.

hep-ex↗