Related papers: Comparison of Image Processing Models in Quark Glu…
Discriminating quark and gluon jets is a long-standing topic in collider phenomenology. In this paper, we address this question using the Lund jet plane substructure technique introduced in recent years. We present two complementary…
The past few years have seen a rapid development of machine-learning algorithms. While surely augmenting performance, these complex tools are often treated as black-boxes and may impair our understanding of the physical processes under…
We describe the construction of end-to-end jet image classifiers based on simulated low-level detector data to discriminate quark- vs. gluon-initiated jets with high-fidelity simulated CMS Open Data. We highlight the importance of precise…
The separate study of quark and gluon jets is vital for the interpretation of multiple variables behaviour observed in both high-energy hadron and heavy-ion collisions in the present and future experiments. We propose a set of jet-energy…
Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…
We measure the subjet multiplicity M in jets reconstructed with a successive combination type of jet algorithm (k_T). We select jets with 55<E_T<100 GeV and | \eta | < 0.5. We compare similar samples of jets at sqrt{s} = 1800 and 630 GeV.…
We investigate the substructure of jets produced in photoproduction events with center-of-mass energies $\sqrt{s} = 30\text{--}140$ GeV at the proposed Electron-Ion Collider (EIC). Events are generated using PYTHIA and contributions from…
The modification of quark- and gluon-initiated jets in the quark-gluon plasma produced in heavy-ion collisions is a long-standing question that has not yet received a definitive answer from experiments. In particular, the size of the…
Discriminating quark-like from gluon-like jets is, in many ways, a key challenge for many LHC analyses. First, we use a known difference in Pythia and Herwig simulations to show how decorrelated taggers would break down when the most…
Measurements of jet substructure in ultra-relativistic heavy ion collisions suggest that the jet showering process is modified by the interaction with quark gluon plasma. Modifications of the hard substructure of jets can be explored with…
Weak gravitational lensing is a powerful probe of the universe's growth history. While traditional two-point statistics capture only the Gaussian features of the convergence field, deep learning methods such as convolutional neural networks…
Being able to distinguish light-quark jets from gluon jets on an event-by-event basis could significantly enhance the reach for many new physics searches at the Large Hadron Collider. Through an exhaustive search of existing and novel jet…
We compare the performance of a convolutional neural network (CNN) trained on jet images with dense neural networks (DNNs) trained on n-subjettiness variables to study the distinguishing power of these two separate techniques applied to top…
The substructure of jets produced in an exclusive and a charm-induced dijet sample in photoproduction and in charged and neutral current interactions has been studied with the ZEUS detector at HERA. Jets were identified using the…
Jet measurements in heavy ion collisions can provide constraints on the properties of the quark gluon plasma, but the kinematic reach is limited by a large, fluctuating background. We present a novel application of symbolic regression to…
Vision Transformers (ViT) have recently emerged as a powerful alternative to convolutional networks (CNNs). Although hybrid models attempt to bridge the gap between these two architectures, the self-attention layers they rely on induce a…
Deep learning has achieved remarkable success in jet classification tasks, yet a key challenge remains: understanding what these models learn and how their features relate to known QCD observables. Improving interpretability is essential…
Texture, a significant visual attribute in images, has been extensively investigated across various image recognition applications. Convolutional Neural Networks (CNNs), which have been successful in many computer vision tasks, are…
We measure the subjet multiplicity M in jets reconstructed with a successive combination type of jet algorithm (kT). We select jets with 55<pT<100 GeV and |eta|<0.5. We compare similar samples of jets at sqrt(s)=1800 and 630 GeV. The HERWIG…
The emergence of Vision Transformers (ViTs) has revolutionized computer vision, yet their effectiveness compared to traditional Convolutional Neural Networks (CNNs) in medical imaging remains under-explored. This study presents a…