PLuM multimodal transformer improves top and H->bb jet tagging by jointly processing particle constituents and Lund plane splittings, yielding 25% higher background rejection at 25% di-Higgs efficiency.
Aadet al.(ATLAS), Transforming jet flavour tag- ging at ATLAS, Nature Commun.17, 541 (2026), arXiv:2505.19689 [hep-ex]
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
method 2
citation-polarity summary
representative citing papers
Explainability techniques applied to LundNet show that assigned node importance correlates with classical jet substructure observables such as N-subjettiness ratios and energy correlation functions, with shifts across transverse-momentum regimes.
A DNN tags the hardest FSR jet from leading-jet 4-momenta to correct di-jet invariant mass, improving signal resolution and search sensitivity by over 10% with minimal background distortion across a broad mass range.
A 10 TeV lepton collider using the effective gamma-W to W process could improve m_W precision beyond 10 MeV and extract CKM elements like V_cb with reduced hadronic uncertainties via high-precision hadronic calorimetry and flavor tagging.
Higgs boson cross-section in H→4ℓ measured as 3.65 fb with new LHC data, consistent with SM expectation of 3.68 fb and signal strength 0.99±0.13.
No evidence for charginos and neutralinos in R-parity violating Higgs-decay channels; masses 150-1100 GeV excluded at 95% CL assuming equal lepton branching fractions.
A color-octet scalar Θ pair-produced via gluons and decaying to quark pairs can account for the CMS excess in equal-mass dijet pairs at 0.95 TeV with a 65 fb cross section for the real case.
No significant excess observed in search for X → S(bb)H(γγ); 95% CL limits on σ×BR set from 9 fb to 0.06 fb over m_X 170-1000 GeV and m_S 15-500 GeV in 199 fb^{-1} of ATLAS data.
Updated ATLAS search for HH → bbγγ with 308 fb⁻¹ yields observed μ_HH = 0.9^{+1.4}_{-1.1}, 95% CL limit μ_HH < 3.7, and κ_λ in [-1.6, 6.6].
ATLAS Inner Detector track and vertex reconstruction maintains high efficiency, good resolution, and low fake rates for up to 80 simultaneous proton-proton interactions in Run 2 and Run 3 data and simulations.
citing papers explorer
-
Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane
Explainability techniques applied to LundNet show that assigned node importance correlates with classical jet substructure observables such as N-subjettiness ratios and energy correlation functions, with shifts across transverse-momentum regimes.
-
Track and Vertex Reconstruction with the ATLAS Inner Detector
ATLAS Inner Detector track and vertex reconstruction maintains high efficiency, good resolution, and low fake rates for up to 80 simultaneous proton-proton interactions in Run 2 and Run 3 data and simulations.