From strange-quark tagging to fragmentation tagging with machine learning
arXiv:2408.12377 · doi:10.1103/PhysRevD.111.034003
Abstract
We apply advanced machine learning techniques to two challenging jet classification problems at the LHC. The first is strange-quark tagging, in particular distinguishing strange-quark jets from down-quark jets. The second, which we term fragmentation tagging, involves identifying the fragmentation channel of a quark. We exemplify the latter by training neural networks to differentiate between bottom jets containing a bottom baryon and those containing a bottom meson. The common challenge in these two problems is that neither quark lifetimes and masses nor parton showering provide discriminating tools, making it necessary to rely on differences in the distributions of the hadron types contained in each type of jet and their kinematics. For these classification tasks, we employ variations of Graph Attention Networks and the Particle Transformer, which receive jet and all constituent properties as inputs. We compare their performance to a simple Multilayer Perceptron that uses simple variables. We find that the more sophisticated architectures do not improve -quark versus -quark jet differentiation by a significant amount, but they do lead to a significant gain in -baryon versus -meson jet differentiation.
33 pages, 18 figures; v2: typo corrected; v3: improvements of presentation; published version
References in corpus (34)
- The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
- The anti-k_t jet clustering algorithm
- FastJet user manual
- Identifying Boosted Objects with N-subjettiness
- Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
- Jet Substructure at the Large Hadron Collider: Experimental Review
- AKK Update: Improvements from New Theoretical Input and Experimental Data
- The Machine Learning Landscape of Top Taggers
- Parton Fragmentation Functions
- Graph Neural Networks in Particle Physics
- ATLAS flavour-tagging algorithms for the LHC Run 2 collision dataset
- Jet Charge at the LHC
- Search for long-lived charginos based on a disappearing-track signature in collisions at TeV with the ATLAS detector
- Top Tagging
- Searches for physics beyond the standard model with the variable in hadronic final states with and without disappearing tracks in proton-proton collisions at 13 TeV
- Charm Hadrons from Fragmentation and B decays in e+e- Annihilation at 10.6 GeV
- Search for disappearing tracks in proton-proton collisions at 13 TeV
- Vincia for Hadron Colliders
- Search for long-lived charginos based on a disappearing-track signature using 136 fb of collisions at = 13 TeV with the ATLAS detector
- Performance of the reconstruction of large impact parameter tracks in the inner detector of ATLAS
- First Direct Measurement of the Parity-Violating Coupling of the Z^0 to the s-Quark
- Heavy baryons as polarimeters at colliders
- Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
- Probing the strange Higgs coupling at lepton colliders using light-jet flavor tagging
- An overview of decays
- Search for supersymmetry in final states with disappearing tracks in proton-proton collisions at = 13 TeV
- Measurement of neutral strange particle production in the underlying event in proton-proton collisions at sqrt(s) = 7 TeV
- Jet Tagging with More-Interaction Particle Transformer
- Maximum performance of strange-jet tagging at hadron colliders
- A tagger for strange jets based on tracking information using long short-term memory
- Prospects for measuring quark polarization and spin correlations in and samples at the LHC
- Addendum to "Overview of decays''
- Underlying-event studies with strange hadrons in collisions at TeV with the ATLAS detector
- Kinked tracks from baryons as a probe of light quark polarizations