A Particle Transformer jet tagger contains a sparse six-head circuit whose source-relay-readout structure recovers most performance and whose residual stream preferentially encodes 2-prong energy correlators.
Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
PHAT-JeT combines geometric message-passing with hierarchical patch attention to reach state-of-the-art accuracy and background rejection among resource-constrained jet tagging models on four benchmarks.
Higher-order Fisher tensors in exponential-family coordinates of binned energy correlators are simultaneously local KL coefficients, connected cumulants, and hyperedge weights, enabling hypergraph constructions for jet substructure analysis.
CMS reports a simultaneous measurement of 25 N-subjettiness observables in 1-, 2-, and 3-prong jets, unfolded to stable particles with particle-level correlations for QCD modeling.
CMS measures soft-drop groomed radius and momentum balance plus a charged fragmentation function for b jets, observing dead-cone suppression compared to inclusive jets.
PPO reinforcement learning accelerates identification of gravitational wave signals from supercooled phase transitions in a minimal dark U(1)_x sector compared to Monte Carlo sampling.
Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.
PaRT achieves >50% tagging efficiency for boosted H->WW jets at 1% background efficiency, decorrelated from jet mass, with data-to-simulation scale factors of 0.9-1.0 on 138 fb^{-1} of 13 TeV collisions.
citing papers explorer
-
Dissecting Jet-Tagger Through Mechanistic Interpretability
A Particle Transformer jet tagger contains a sparse six-head circuit whose source-relay-readout structure recovers most performance and whose residual stream preferentially encodes 2-prong energy correlators.
-
Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging
PHAT-JeT combines geometric message-passing with hierarchical patch attention to reach state-of-the-art accuracy and background rejection among resource-constrained jet tagging models on four benchmarks.
-
From Information Geometry to Jet Substructure: A Triality of Cumulant Tensors, Energy Correlators, and Hypergraphs
Higher-order Fisher tensors in exponential-family coordinates of binned energy correlators are simultaneously local KL coefficients, connected cumulants, and hyperedge weights, enabling hypergraph constructions for jet substructure analysis.
-
Simultaneous measurements of $N$-subjettiness observables in jets from gluons and light-flavour quarks, and in decays of boosted W bosons and top quarks
CMS reports a simultaneous measurement of 25 N-subjettiness observables in 1-, 2-, and 3-prong jets, unfolded to stable particles with particle-level correlations for QCD modeling.
-
Jet fragmentation function and groomed substructure of bottom quark jets in proton-proton collisions at 5.02 TeV
CMS measures soft-drop groomed radius and momentum balance plus a charged fragmentation function for b jets, observing dead-cone suppression compared to inclusive jets.
-
Supercool with PPO: Exploring Supercooled Phase Transitions via Reinforcement Learning
PPO reinforcement learning accelerates identification of gravitational wave signals from supercooled phase transitions in a minimal dark U(1)_x sector compared to Monte Carlo sampling.
-
The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability
Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.
-
Particle transformers for identifying Lorentz-boosted Higgs bosons decaying to a pair of W bosons
PaRT achieves >50% tagging efficiency for boosted H->WW jets at 1% background efficiency, decorrelated from jet mass, with data-to-simulation scale factors of 0.9-1.0 on 138 fb^{-1} of 13 TeV collisions.