RANs generalize moment unfolding to full phase-space unbinned unfolding via detector-level Wasserstein critics without requiring support overlap or multiple iterations.
Jet substructure at the Large Hadron Collider: a review of recent advances in theory and machine learning
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
Energy correlators can convert scaling violations into angular bump hunting for new physics, yielding projected competitive LHC sensitivity for a light hadrophilic Z'.
A MERA-based autoencoder supplies a locality-aware hierarchical inductive bias that improves reconstruction-based anomaly detection for collider jets, with disentanglers providing benefit at strong compression bottlenecks.
A physics-guided neural network embedding AdS5 Dirac equation and holographic Pomeron fits SLAC proton F2 data with chi-squared per degree of freedom of 0.91 and identifies a kinematic crossover at x approximately 0.19 while recovering Pomeron intercept of 1.0786.
In large-Nc and harmonic oscillator limits, medium-induced splittings are computed analytically double-differential in z and θ, with an improved semi-hard approximation validated for high-energy partons.
OmniMol transfers a billion-jet pre-trained PET foundation model from HEP to molecular dynamics via an interaction-matrix attention bias, delivering strong performance on the oMol dataset with minimal fine-tuning and fast inference.
A factorization theorem is derived for the joint measurement of 1-jettiness and jet charge in DIS, introducing a new universal charged jet function that enhances quark flavor separation in initial-state PDFs and probes final-state hadronization.
Spectral functions from two-point correlations serve as multiplicity-independent ML inputs and improve expected gluino mass reach by 150-250 GeV in a fully hadronic ttbar vs gluino benchmark.
Proof-of-principle for hadron-in-fat-jet AI tagging that yields an expected 95% CL limit of B(W±→π±γ) < 2.78×10^{-5} at 450 fb^{-1}.
AI-driven symbolic evolution discovers interpretable event-level observables that retain substantially more local Fisher information than angular baselines for CP-sensitive HZ interference in two collider channels.
In extended scalar sectors near the alignment limit, higher-dimensional interactions can make two-, three-, or four-Higgs final states the dominant discovery mode at the LHC via gluon fusion.
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.