Related papers: Aspen Open Jets: Unlocking LHC Data for Foundation…
Multiple proton-proton collisions (pile-up) occur at every bunch crossing at the LHC, with the mean number of interactions expected to reach 80 during Run 3 and up to 200 at the High-Luminosity LHC. As a direct consequence, events with…
Foundation models for tabular data, like TabPFN, achieve strong performance on small datasets when pre-trained solely on synthetic data. We show that this performance can be significantly boosted by a targeted continued pre-training phase.…
We apply gradient boosting machine learning techniques to the problem of hadronic jet substructure recognition using classical subjettiness variables available within a common parameterized detector simulation package DELPHES. Per-jet…
During the 2015-2018 data-taking period, the Large Hadron Collider delivered proton-proton bunch crossings at a centre-of-mass energy of 13 TeV to the ATLAS experiment at a rate of roughly 30 MHz, where each bunch crossing contained an…
There has been a recent explosion in research into machine-learning-based generative modeling to tackle computational challenges for simulations in high energy physics (HEP). In order to use such alternative simulators in practice, we need…
The state-of-the-art deep learning (DL) models for jet classification use jet constituent information directly, improving performance tremendously. This draws attention to interpretability, namely, the decision-making process, correlations…
Deciphering the complex information contained in jets produced in collider events requires a physical organization of the jet data. We introduce two-particle correlations (2PCs) by pairing individual particles as the initial jet…
Recent advancements in deep learning models have significantly enhanced jet classification performance by analyzing low-level features (LLFs). However, this approach often leads to less interpretable models, emphasizing the need to…
Forward (di)jet measurements are a useful tool to constrain the Parton Distribution Functions (PDFs) at low values of parton momentum fraction x, and to study the possible onset of BFKL or gluon saturation QCD evolutions in the proton. We…
A broad program of measurements is planned for heavy ion collisions in ATLAS. With up to a factor of 30 increase in collision energy compared to existing data, significant new insights are anticipated to be obtained with the first data…
Large transverse momentum jets provide unique tools to study dense QCD matter in high-energy heavy-ion collisions. Results from RHIC on suppression of high transverse momentum particles in Au+Au collisions indicate a significant energy loss…
Artificial Intelligence for scientific applications increasingly requires training large models on data that cannot be centralized due to privacy constraints, data sovereignty, or the sheer volume of data generated. Federated learning (FL)…
Transformers have become the primary architecture for natural language processing. In this study, we explore their use for auto-regressive density estimation in high-energy jet physics, which involves working with a high-dimensional space.…
Jet quenching is the process of color-charged partons losing energy via interactions with quark-gluon plasma droplets created in heavy-ion collisions. The collective expansion of such droplets is well described by viscous hydrodynamics.…
Understanding the properties of the quark-gluon plasma (QGP) that is produced in ultra-relativistic nucleus-nucleus collisions has been one of the top priorities of the heavy ion program at the LHC. Energetic jets are produced and…
A method allowing for a direct comparison of data with theoretical predictions is proposed for forward jet production at HERA. It avoids the reconstruction of multi-parton contributions by expressing the experimental data directly as…
The LHC has provided an unprecedented amount of proton-proton collision data, bringing forth exciting opportunities to address fundamental open questions in particle physics. These questions can potentially be answered by performing…
We explore the potential to use machine learning methods to search for heavy neutrinos, from their hadronic final states including a fat-jet signal, via the processes $pp \rightarrow W^{\pm *}\rightarrow \mu^{\pm} N \rightarrow \mu^{\pm}…
The study of jets, collimated sprays of particles associated with hard partons, is an important tool in testing perturbative quantum chromodynamics (pQCD) and probing hot and dense nuclear matter created in high energy heavy-ion collisions.…
We introduce 1P1Q, a novel quantum data encoding scheme for high-energy physics (HEP), where each particle is assigned to an individual qubit, enabling direct representation of collision events without classical compression. We demonstrate…