arXiv subjects

Umar Sohail Qureshi

Publications and source records attributed to Umar Sohail Qureshi.

11 recordsLinked to original sources

arXiv2026

Parnassus for the CLD Detector: A Generative Machine-Learning Surrogate for Detector Simulation and Reconstruction at the FCC-ee

Detector simulation and event reconstruction will be computationally expensive for future $e^+e^-$ collider programs and are currently critical bottlenecks for accurate feasibility studies. To address this challenge, we build a Parnassus model for the CLD detector concept. Parnassus is a framework for automatically tuning a surrogate model, in our case, a conditional flow matching neural network, to emulate a full detector simulation and reconstruction. We train on $e^+e^-\to Z\to q\bar q$ events at $\sqrt{s}=91.2$ GeV processed through a Geant4 simulation of the CLD detector concept and the Pandora particle-flow reconstruction and reproduce single-particle kinematics, particle-IDs, and impact-parameter distributions. We also examine jet- and event-level features, inclusively and split by flavor, and find excellent fidelity, significantly better than the parameterized program Delphes. Furthermore, we train a transformer-based flavor tagger on the reconstructed particle-flow constituents and show that the surrogate preserves the $b/c/s/q$ discrimination of the full CLD reconstruction. The Parnassus CLD model achieves a generation cost of about 1.2 ms (40 ms) per event on a single GPU (CPU), over three (two) orders of magnitude faster than full simulation and reconstruction. Our model is publicly available for feasibility and design studies.

physics.ins-det↗

arXiv2026

D$e^+e^-$ffusion: Capturing the Beam-Beam Physics of $e^+e^-$ Collisions with Diffusion Models

Beam-induced backgrounds at high-luminosity $e^+e^-$ colliders, such as the FCC-ee, are dominated by incoherent pair creation (IPC), and require computationally expensive simulations with dedicated Monte Carlo (MC) event generators. Reliable detector and machine-detector interface studies necessitate event samples that are several orders of magnitude larger than what is practically attainable with existing MC. To alleviate this bottleneck, we present D$e^+e^-$ffusion, a denoising diffusion probabilistic model that operates as a permutation-equivariant, set-valued surrogate for fast IPC simulation. Trained on a small GuineaPig++ sample, D$e^+e^-$ffusion faithfully reproduces the marginal and joint kinematic, angular, and positional distributions of all three IPC production processes. In addition, we assess the fidelity at the detector level by propagating both Geant4 and D$e^+e^-$ffusion events through a Geant4 simulation of the CLD vertex detector and by training a transformer-based two-sample classifier; the classifier achieves an area under the ROC curve of $0.553 \pm 0.016$. The trained model generates events nearly four orders of magnitude faster than Geant4, paving the way for a fast-simulation surrogate for FCC-ee design studies.

hep-ph↗

arXiv2026

Reweighting Adversarial Networks for Unbinned Unfolding

Differential cross sections are the currency of scientific exchange in particle and nuclear physics. Recently, machine learning methods have enabled unbinned and high-dimensional cross section measurements through new approaches to unfolding. A key challenge with unfolding is that it is a bi-level optimization problem where constraints are available at the detector level while the target is at the particle level, linked by a stochastic detector response. Further complications arise when the particle-level and detector-level distributions have non-overlapping or only partially overlapping support, which can destabilize training and degrade unfolding performance. In this paper, we introduce a new unbinned unfolding technique called the Reweighting Adversarial Network (RAN), which can be viewed as a generalization of the Moment Unfolding protocol to accommodate full phase-space unfolding. RANs address the bi-level optimization problem through a particle-level reweighting function steered by a Wasserstein critic at the detector level. RANs do not require overlapping support at the detector level, nor multiple iterations of training. We evaluate the performance of RANs with Gaussian data and jet substructure studies, including cases specifically designed to stress test the method under vanishing support overlap. We demonstrate that RANs outperform state-of-the-art methods in accuracy and have a lower computational overhead.

hep-ph↗

arXiv2026

Higgs Physics with the XFEL Compton $\boldsymbol{γγ}$ Collider Concept at $\boldsymbol{\sqrt{s}=125}$ GeV

We investigate single Higgs production in $\sqrt{s}=125$ GeV $γγ$ collisions at the X-Ray Free Electron (XFEL) Compton Collider (XCC) concept and present an analysis targeting the major hadronic, semi-leptonic, and fully leptonic final states of the Higgs boson, including $H\to s\overline{s}$. In addition to studying Higgs production at a novel collider concept, our approach couples a novel set transformer-based deep learning framework that acts on particle-flow object point clouds with a genetic algorithm optimizer for signal-background discrimination, yielding significantly higher sensitivity than traditional methods. Our results demonstrate that an XFEL $γγ$ collider can probe the Higgs sector with extremely high precision and enable new physics opportunities, complementary to proposed $e^+e^-$ machines.

hep-ph↗

arXiv2026

Probing the Higgs Self-Coupling with an XFEL Compton $γγ$ Collider at $\sqrt{s} = 380$ GeV

We present a study probing the Higgs self-coupling with the X-ray free-electron laser Compton $γγ$ Collider (XCC) concept. The analysis is performed considering the $γγ\to HH \to bb\overline{bb}$ channel, and results are then extrapolated to obtain a projection on the Higgs self-coupling sensitivity that ranges between 7% and 12%. An ensemble of boosted decision trees is trained to discriminate between signal and backgrounds, paired with a genetic algorithm optimizer to combine the final classifier outputs. This study suggests that an X-ray FEL-based $γγ$ collider is a powerful tool to probe the mechanism of electroweak symmetry breaking, complementary to $e^+e^-$ Higgs factories and future high-energy hadron colliders.

hep-ph↗

arXiv2026

PanopTag: Simultaneously Tagging All Jets in a Particle Collision Event

Jet tagging, identifying the origin of jets produced in particle collisions, is a critical classification task in high-energy physics. Despite the revolutionary impact of deep learning on jet tagging over the past decade, the paradigm has remained unchanged. In particular, jets are classified independently, one at a time. This single-jet approach ignores correlations, overlaps, and wider event context between jets. We introduce PanopTag, a new paradigm for jet tagging that departs from traditional single-jet tagging approaches. Rather than classifying jets independently, PanopTag simultaneously tags all jets by employing an encoder-decoder architecture that uses jet kinematics as queries to cross-attend to particle flow object embeddings. We evaluate PanopTag on heavy-flavor $(b/c)$-tagging and demonstrate remarkable performance improvements over state-of-the-art single-jet baselines that are only accessible by exploiting event-level features and correlations between jets.

hep-ph↗

arXiv2025

Deep Image Reconstruction for Background Subtraction in Heavy-Ion Collisions

Jet reconstruction in an ultra-relativistic heavy-ion collision suffers from a notoriously large, fluctuating thermal background. Traditional background subtraction methods struggle to remove this soft background while preserving the jet's hard substructure. In this Letter, we present DeepSub, the first machine learning-based approach for full-event background subtraction. DeepSub utilizes a model based on Swin Transformer layers to denoise jet images and disentangle hard jets from the heavy-ion background. DeepSub significantly outperforms existing subtraction techniques by reproducing key jet observables such as jet $p_\mathrm{T}$ and mass, and substructure observables such as girth and the energy correlation function, at the sub-percent to percent level. As such, DeepSub paves the way for precision heavy-ion measurements in hitherto inaccessible kinematic regimes.

hep-ph↗

arXiv2024

Probing Light Scalars and Vector-like Quarks at the High-Luminosity LHC

A model based on a $U(1)_{T^3_R}$ extension of the Standard Model can address the mass hierarchy between generations of fermions, explain thermal dark matter abundance, and the muon $g - 2$, $R_{(D)}$, and $R_{(D^*)}$ anomalies. The model contains a light scalar boson $ϕ'$ and a heavy vector-like quark $χ_\mathrm{u}$ that can be probed at CERN's Large Hadron Collider (LHC). We perform a phenomenology study on the production of $ϕ'$ and $χ_u$ particles from proton-proton $(\mathrm{pp})$ collisions at the LHC at $\sqrt{s}=13.6$ TeV, primarily through $g{-g}$ and $t{-χ_\mathrm{u}}$ fusion. We work under an effective field theory approach, in which the $χ_\mathrm{u}$ and $ϕ'$ masses are free parameters. We perform a phenomenological analysis considering $χ_\mathrm{u}$ final states to b-quarks, muons, and neutrinos, and $ϕ'$ decays to $μ^+μ^-$. A machine learning algorithm is used to maximize the signal sensitivity, considering an integrated luminosity of $3000$ $\textrm{fb}^{-1}$. The proposed methodology can be a key mode for discovery over a large mass range, including low masses, traditionally considered difficult due to experimental constraints.

hep-ph↗

arXiv2024

Model-Agnostic Tagging of Quenched Jets in Heavy-Ion Collisions

Measurements of jet substructure in ultra-relativistic heavy-ion collisions indicate that interactions with the quark-gluon plasma quench the jet showering process. Modern data-driven methods have shown promise in probing these modifications in the jet's hard substructure. In this Letter, we present a machine learning framework to identify quenched jets while accounting for pileup, uncorrelated soft particle background, and detector effects; a more experimentally realistic and challenging scenario than previously addressed. Our approach leverages an interpretable sequential attention-based mechanism that integrates representations of individual jet constituents alongside global jet observables as features. The framework sets a new benchmark for tagging quenched jets with reduced model dependence.

hep-ph↗

arXiv2024

A New Herwig7 Underlying Event Tune: from RHIC to LHC Energies

We present parameter sets corresponding to new underlying event tunes for the Herwig7.3 Monte Carlo event generator. The existing Herwig tunes are in good agreement with LHC data, however, they are not typically designed for center-of-mass energies below $\sqrt{s}=300$ GeV. The tunes presented in this study can describe mid-rapidity data collected at the nominal RHIC energy of $\sqrt{s }=200$ GeV, as well as higher center-of-mass energies utilized by experiments elsewhere, such as the LHC. The base "New Haven" tune is developed by fitting minimum-bias simulations of proton-proton collisions to mid-rapidity identified hadron and jet data from the STAR experiment. The "Nashville" tune includes a separate set of parameters developed by tuning to Tevatron proton-antiproton data at $\sqrt{s}=300$, $900$ and $1960$ GeV from CDF, and LHC proton-proton measurements from CMS at $\sqrt{s}=7$ TeV, in addition to the STAR measurements. Both new tunes demonstrate significant improvements over the recommended default tune currently included in the latest version of Herwig for minimum bias production. As such, we advocate using these tunes for future simulation studies at mid-rapidity by the experimental collaborations at RHIC (STAR and sPHENIX) and the LHC (ATLAS, ALICE, CMS).

hep-ph↗

arXiv2024

Probing Compressed Mass Spectrum Supersymmetry at the LHC with the Vector Boson Fusion Topology

We present a phenomenology study probing pair production of supersymmetric charginos and neutralinos ("electroweakinos") with the vector boson fusion (VBF) topology in proton-proton collisions at CERN's Large Hadron Collider (LHC). In particular, we examine the compressed-mass spectrum phase space that has been traditionally challenging due to experimental constraints. The final states considered have two jets, large missing transverse momentum, and one, two, or three light leptons. Different model scenarios are considered for the production and decays of the electroweakinos. A novel high-performance and interpretable sequential attention-based machine learning algorithm is employed for signal-background discrimination and is observed to significantly improve signal sensitivity over traditional methods. We report expected signal significances for integrated luminosities of $137$, $300$, and $3000$ $\textrm{fb}^{-1}$ corresponding to the current data acquired at the LHC, expectation for the end of Run 3, and the expectation for the high-luminosity LHC. Our methodology results in projected 95\% confidence level bounds that cover chargino masses up to 1.1 TeV in compressed-mass spectrum scenarios within the R-parity conserving minimal supersymmetric standard model. This parameter space, currently beyond the reach of ATLAS and CMS searches at the LHC, is traditionally challenging to explore due to significant Standard Model backgrounds and low signal cross-sections.

hep-ph↗