arXiv subjects

Roberto Ruiz de Austri

Publications and source records attributed to Roberto Ruiz de Austri.

At least 19 recordsLinked to original sources

arXiv2026

Masked-Token Prediction for Anomaly Detection at the Large Hadron Collider

Anomaly detection in High Energy Physics requires identifying rare signals against overwhelming backgrounds, without prior knowledge of the signal. We present the first application of masked-token prediction, a technique from Large Language Models, to this problem. A lightweight encoder architecture trained solely on background events captures the structure of Standard Model (SM) physics; at inference, sequences deviating from this learned structure are flagged as anomalous. We evaluate the approach on searches for four-top-quark production and supersymmetric gluino pair production, both featuring top-rich final states with substantial missing transverse energy, covering SM and beyond the Standard Model (BSM) scenarios. Strong performance on the four-top signature, which closely resembles background, demonstrates the method's sensitivity to subtle deviations. We further show that the tokenization strategy significantly impacts performance: deep-learned tokenization via vector-quantized variational autoencoders (VQ-VAE) outperforms look-up table tokenization. Comparison with established anomaly detection baselines confirms robustness. These results highlight the potential of token-based collider data representations combined with transformer architectures for new-physics discovery. Once trained on SM background, the model transfers across different BSM searches, enabling scalable, model-independent anomaly detection at reduced computational cost.

hep-ph↗

arXiv2026

What has the LHC told us about the electroweakino sector of the Minimal Supersymmetric Standard Model?

We perform global fits of the electroweak sector of the Minimal Supersymmetric Standard Model (MSSM) using a comprehensive set of LEP searches, 34 Run 2 LHC searches, and 63 Run 2 LHC measurements. Scanning the bino, wino and Higgsino mass parameters, and the ratio of the Higgs vacuum expectation values, we find that for a light, bino $\tildeχ_{1}^0$, the mass of the next-to-lightest neutralino must be $m_{\tildeχ_{2}^0} \gtrsim 760$ GeV. While MSSM electroweakinos can explain individual excesses observed by ATLAS and CMS in searches targeting compressed spectra, we find no scenarios that fit these excesses simultaneously. When we add a light gravitino, neutralinos are further excluded up to about 1 TeV, though this depends on their composition; Higgsino-dominated $\tildeχ_{1}^0$ requires only $m_{\tildeχ_{1}^0} \approx m_{\tildeχ_{2}^0} \gtrsim 650$ GeV. Lastly, the newer LHC searches and measurements exclude a low-mass region that was preferred in a previous study. This is the most complete summary of collider constraints on the electroweakino sector of the MSSM performed to date.

hep-ph↗

arXiv2026

Hits to Higgs: Hit-Level Higgs Classification from Raw LHC Detector Data Using Higgsformer

We present Higgsformer, a transformer-based architecture that classifies Higgs events at the Large Hadron Collider directly from raw inner tracker hits, bypassing the traditional reconstruction chain of intermediate physics objects. As a benchmark, we focus on distinguishing $t\bar{t}H$ from $t\bar{t}$ events with $H \to b\bar{b}$, a particularly challenging task due to their similar final state topologies. Our pipeline begins with event generation in Pythia8, fast simulation with ACTS/Fatras, and classification directly from raw detector hits. We show for the first time that a transformer model originally developed for inner tracker hit-to-track assignment can be retrained to classify Higgs signal events directly from raw hits. For comparison, we reconstruct the same events with Delphes and train a Particle Transformer as an object-based classifier. We evaluate both approaches under varying dataset sizes and pileup levels. Despite relying exclusively on inner tracker hits, our large Higgsformer achieves an AUC of $0.855$, matching the performance of the traditional reconstruction pipeline at a $b$-tagging efficiency of $\approx 40\%$ under the same detector constraints.

hep-ph↗

arXiv2026

BGRem: A background noise remover for astronomical images based on a diffusion model

Context: Astronomical imaging aims to maximize signal capture while minimizing noise. Enhancing the signal-to-noise ratio directly on detectors is difficult and expensive, leading to extensive research in advanced post-processing techniques. Aims: Removing background noise from images is a valuable pre-processing step catalog-building tasks. We introduce BGRem, a machine learning (ML) based tool to remove background noise from astronomical images. Methods: BGRem uses a diffusion-based model with an attention U-Net as backbone, trained on simulated images for optical and gamma (γ)-ray data from the MeerLICHT and Fermi-LAT telescopes. In a supervised manner, BGRem learns to denoise astronomical images over several diffusion steps. Results: BGRem performance was compared with a widely used tool for cataloging astronomical sources, SourceExtractor (SExtractor). It was shown that the amount of true positive sources using SExtractor increased by about 7% for MeerLICHT data when BGRem was used as a pre-processing step. We also show the generalizability of BGRem by testing it with optical images from different telescopes and also on simulated γ-ray data representative of the Fermi-LAT telescope. We show that in both cases, BGRem improves the source detection efficiency. Conclusions: BGRem can improve the accuracy in source detection of traditional pixel-based methods by removing complex background noise. Using zero-shot approach, BGRem can generalize well to a wide range of optical images. The successful application of BGRem to simulated γ-ray images, alongside optical data, demonstrates its adaptability to distinct noise characteristics and observational domains. This cross-wavelength performance highlights its potential as a general-purpose background removal framework for multi-wavelength astronomical surveys.

astro-ph.IM↗

arXiv2026

Towards a foundation model for astrophysical source detection: An End-to-End Gamma-Ray Data Analysis Pipeline Using Deep Learning

The increasing volume of gamma-ray data demands new analysis approaches that can handle large-scale datasets while providing robustness for source detection. We present a Deep Learning (DL) based pipeline for detection, localization, and characterization of gamma-ray sources. We extend our AutoSourceID (ASID) method, initially tested with \textit{Fermi}-LAT simulated data and optical data (MeerLICHT), to Cherenkov Telescope Array Observatory (CTAO) simulated data. This end-to-end pipeline demonstrates a versatile framework for future application to other surveys and potentially serves as a building block for a foundational model for astrophysical source detection.

astro-ph.IM↗

arXiv2026

Event Tokenization and Masked-Token Prediction for Anomaly Detection at the Large Hadron Collider

We propose a novel use of Large Language Models (LLMs) as unsupervised anomaly detectors in particle physics. Using lightweight LLM-like networks with encoder-based architectures trained to reconstruct background events via masked-token prediction, our method identifies anomalies through deviations in reconstruction performance, without prior knowledge of signal characteristics. Applied to searches for simultaneous four-top-quark production, this token-based approach shows competitive performance against established unsupervised methods and effectively captures subtle discrepancies in collider data, suggesting a promising direction for model-independent searches for new physics.

hep-ex↗

arXiv2025

Global fits and the search for new physics: past, present and future

In this work, we review the history and current role of global fits in the search for physics beyond the Standard Model~(BSM), including precision tests of the Standard Model (SM). Although BSM global fits were initially focused on minimal supersymmetric models, we describe how fits have evolved in response to new data from the Large Hadron Collider (LHC) and elsewhere, expanding to encompass a broad spectrum of BSM scenarios including non-minimal supersymmetry, axion-like particles, extended Higgs sectors, dark matter models, and effective field theories such as SMEFT. We discuss how the role of global fits has shifted from forecasting possible signals of new physics at the LHC to understanding the impact of null results from LHC run-I and II and the discovery of the Higgs boson, and how interest has shifted from global fits for parameter estimation to comprehensive model comparison. We close by discussing potential trends and future applications, emphasizing the potential for machine learning and artificial intelligence to enhance the efficiency of sampling algorithms and comparison between theory and experiment, as well as collaboration and software development.

hep-ph↗

arXiv2025

Attention to the strengths of physical interactions: Transformer and graph-based event classification for particle physics experiments

A major task in particle physics is the measurement of rare signal processes. Even modest improvements in background rejection, at a fixed signal efficiency, can significantly enhance the measurement sensitivity. Building on prior research by others that incorporated physical symmetries into neural networks, this work extends those ideas to include additional physics-motivated features. Specifically, we introduce energy-dependent particle interaction strengths, derived from leading-order SM predictions, into modern deep learning architectures, including Transformer Architectures (Particle Transformer), and Graph Neural Networks (Particle Net). These interaction strengths, represented as the SM interaction matrix, are incorporated into the attention matrix (transformers) and edges (graphs). Our results in event classification show that the integration of all physics-motivated features improves background rejection by $10\%-40\%$ over baseline models, with an additional gain of up to $9\%$ due to the SM interaction matrix. This study also provides one of the broadest comparisons of event classifiers to date, demonstrating how various architectures perform across this task. A simplified statistical analysis demonstrates that these enhanced architectures yield significant improvements in signal significance compared to a graph network baseline.

hep-ph↗

arXiv2025

A Robust Determination of Antinuclei Production from Dark Matter via Weakly Decaying Beauty Hadrons

Recently, the Alpha Magnetic Spectrometer (AMS-02) Collaboration presented tentative evidence for the detection of cosmic antihelion-3 (${}^3\overline{\rm He}$) events, alongside a comparable number of antideuterons ($\overline{\rm D}$). If confirmed, these observations could revolutionize our understanding of cosmic-ray production and propagation and/or serve as compelling indirect evidence for dark matter. Given that the detection of cosmic $\overline{\rm D}$ is already at the limit of AMS-02 sensitivity, explaining the observation of ${}^3\overline{\rm He}$ even within the standard coalescence framework poses a significant challenge. It has recently been shown that a previously overlooked mechanism within the Standard Model of particle physics-namely, the production of antihelion via the displaced-vertex decay of $\barΛ_b^0$ baryons-could substantially enhance the ${}^3\overline{\rm He}$ flux arising from dark matter-induced processes. In light of these challenges, we present a tuning of Pythia that is consistent with LEP data on the fragmentation function of $b$ quarks into $b$-hadrons-a critical factor for determining the $\barΛ_b^0$ multiplicity-and with ALICE and ALEPH data for the $\overline{\rm D}$ and ${}^3\overline{\rm He}$ spectra, which we employ to determine our coalescence model. Our refined Pythia tuning, in conjunction with our coalescence model, results in a predicted branching ratio for the production of ${}^3\overline{\rm He}$ from $\barΛ_b^0$ decays that is consistent with the recent upper limit measured by LHCb. Furthermore, our prediction indicates that the contribution of $\overline{\rm D}$ and ${}^3\overline{\rm He}$ from beauty-hadron decays is negligible relative to the direct production from hadronization.

hep-ph↗

arXiv2025

Universal Anomaly Detection at the LHC: Transforming Optimal Classifiers and the DDD Method

In this work, we present a novel approach to transform supervised classifiers into effective unsupervised anomaly detectors. The method we have developed, termed Discriminatory Detection of Distortions (DDD), enhances anomaly detection by training a discriminator model on both original and artificially modified datasets. We conducted a comprehensive evaluation of our models on the Dark Machines Anomaly Score Challenge channels and a search for 4-top quark events, demonstrating the effectiveness of our approach across various final states and beyond the Standard Model scenarios. We compare the performance of the DDD method with the Deep Robust One-Class Classification method (DROCC), which incorporates signals in the training process, and the Deep Support Vector Data Description (DeepSVDD) method, a well-established and well-performing method for anomaly detection. Results show that the effectiveness of each model varies by signal and channel, with DDD proving to be a very effective anomaly detector. We recommend the combined use of DeepSVDD and DDD for purely unsupervised applications, with the addition of flow models for improved performance when resources allow. Findings suggest that network architectures that excel in supervised contexts, such as the particle transformer with standard model interactions, also perform well as unsupervised anomaly detectors. We also show that with these methods, it is likely possible to recognize 4-top quark production as an anomaly without prior knowledge of the process. We argue that the Large Hadron Collider community can transform supervised classifiers into anomaly detectors to uncover potential new physical phenomena in each search.

hep-ph↗

arXiv2025

CosmiXs: Improved spectra for dark matter indirect detection

The spectra of stable particles produced from dark matter (DM) are one of the most important ingredients to calculate the fluxes for DM indirect detection experiments. At energies above a few GeV, most of the particles are produced following a complex sequence of phenomena including resonance decays, QED and QCD final-state radiation, radiation of weak gauge bosons, hadronization and hadron decays. In this contribution, we discuss improvements on the calculation of the energy spectra at the source using state-of-the-art tools that include effects that were not taken previously into account. We include helicity information of the particles produced in the annihilation channels, which leads to proper inclusion of electroweak radiation during the entire showering history. These effects are taken into account using the Vincia, which is based on the helicity-dependent antenna shower formalism. Off-shell contributions are also taken into account for annihilation channels into $WW$ and $ZZ$ through the four-body processes into fermions and for DM masses below the gauge boson mass. We also revisit the tune of the Lund fragmentation function parameters in Pythia using LEP data at the $Z$-boson pole. The spectra of cosmic messengers are provided for DM masses between 5 GeV and 100 GeV and are publicly distributed in this \href{https://github.com/ajueid/CosmiXs.git}{GitHub repository}.

hep-ph↗

arXiv2025

Insights into Dark Matter Direct Detection Experiments: Decision Trees versus Deep Learning

The detection of Dark Matter (DM) remains a significant challenge in particle physics. This study exploits advanced machine learning models to improve detection capabilities of liquid xenon time projection chamber experiments, utilizing state-of-the-art transformers alongside traditional methods like Multilayer Perceptrons and Convolutional Neural Networks. We evaluate various data representations and find that simplified feature representations, particularly corrected S1 and S2 signals as well as a few shape-related features including the time difference between signals, retain critical information for classification. Our results show that while transformers offer promising performance, simpler models like XGBoost can achieve comparable results with optimal data representations. We also derive exclusion limits in the cross-section versus DM mass parameter space, showing minimal differences between XGBoost and the best performing deep learning models. The comparative analysis of different machine learning approaches provides a valuable reference for future experiments by guiding the choice of models and data representations to maximize detection capabilities.

astro-ph.IM↗

arXiv2025

Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models

This paper explores ideas and provides a potential roadmap for the development and evaluation of physics-specific large-scale AI models, which we call Large Physics Models (LPMs). These models, based on foundation models such as Large Language Models (LLMs) - trained on broad data - are tailored to address the demands of physics research. LPMs can function independently or as part of an integrated framework. This framework can incorporate specialized tools, including symbolic reasoning modules for mathematical manipulations, frameworks to analyse specific experimental and simulated data, and mechanisms for synthesizing theories and scientific literature. We begin by examining whether the physics community should actively develop and refine dedicated models, rather than relying solely on commercial LLMs. We then outline how LPMs can be realized through interdisciplinary collaboration among experts in physics, computer science, and philosophy of science. To integrate these models effectively, we identify three key pillars: Development, Evaluation, and Philosophical Reflection. Development focuses on constructing models capable of processing physics texts, mathematical formulations, and diverse physical data. Evaluation assesses accuracy and reliability by testing and benchmarking. Finally, Philosophical Reflection encompasses the analysis of broader implications of LLMs in physics, including their potential to generate new scientific understanding and what novel collaboration dynamics might arise in research. Inspired by the organizational structure of experimental collaborations in particle physics, we propose a similarly interdisciplinary and collaborative approach to building and refining Large Physics Models. This roadmap provides specific objectives, defines pathways to achieve them, and identifies challenges that must be addressed to realise physics-specific large scale AI models.

physics.data-an↗

arXiv2024

A comparison of Bayesian sampling algorithms for high-dimensional particle physics and cosmology applications

For several decades now, Bayesian inference techniques have been applied to theories of particle physics, cosmology and astrophysics to obtain the probability density functions of their free parameters. In this study, we review and compare a wide range of Markov Chain Monte Carlo (MCMC) and nested sampling techniques to determine their relative efficacy on functions that resemble those encountered most frequently in the particle astrophysics literature. Our first series of tests explores a series of high-dimensional analytic test functions that exemplify particular challenges, for example highly multimodal posteriors or posteriors with curving degeneracies. We then investigate two real physics examples, the first being a global fit of the $Λ$CDM model using cosmic microwave background data from the Planck experiment, and the second being a global fit of the Minimal Supersymmetric Standard Model using a wide variety of collider and astrophysics data. We show that several examples widely thought to be most easily solved using nested sampling approaches can in fact be more efficiently solved using modern MCMC algorithms, but the details of the implementation matter. Furthermore, we also provide a series of useful insights for practitioners of particle astrophysics and cosmology.

hep-ph↗

arXiv2024

Nailing down the theoretical uncertainties of $\overline{\rm D}$ spectrum produced from dark matter

The detection of cosmic antideuterons ($\overline{\rm D}$) at kinetic energies below a few GeV/n could provide a smoking gun signature for dark matter (DM). However, the theoretical uncertainties of coalescence models have represented so far one of the main limiting factors for precise predictions of the $\overline{\rm D}$ flux. In this Letter we present a novel calculation of the $\overline{\rm D}$ source spectra, based on the Wigner formalism, for which we implement the Argonne $v_{18}$ antideuteron wavefunction that does not have any free parameters related to the coalescence process. We show that the Argonne Wigner model excellently reproduces the $\overline{\rm D}$ multiplicity measured by ALEPH at the $Z$-boson pole, which is usually adopted to tune the coalescence models based on different approaches. Our analysis is based on Pythia~8 Monte Carlo event generator and the state-of-the-art Vincia shower algorithm. We succeed, with our model, to reduce the current theoretical uncertainty on the prediction of the $\overline{\rm D}$ source spectra to a few percent, for $\overline{\rm D}$ kinetic energies relevant to DM searches with GAPS and AMS, and for DM masses above a few tens of GeV. This result implies that the theoretical uncertainties due to the coalescence process are no longer the main limiting factor in the predictions. We provide the tabulated source spectra for all the relevant DM annihilation/decay channels and DM masses between 5 GeV and 100 TeV, on the CosmiXs github repository (https://github.com/ajueid/CosmiXs.git).

astro-ph.HE↗

arXiv2023

CosmiXs: Cosmic messenger spectra for indirect dark matter searches

The energy spectra of particles produced from dark matter (DM) annihilation or decay are one of the fundamental ingredients to calculate the predicted fluxes of cosmic rays and radiation searched for in indirect DM detection. We revisit the calculation of the source spectra for annihilating and decaying DM using the Vincia shower algorithm in Pythia to include QED and QCD final state radiation and diagrams for the Electroweak (EW) corrections with massive bosons, not present in the default Pythia shower model. We take into account the spin information of the particles during the entire EW shower and the off-shell contributions from massive gauge bosons. Furthermore, we perform a dedicated tuning of the Vincia and Pythia parameters to LEP data on the production of pions, photons, and hyperons at the $Z$ resonance and discuss the underlying uncertainties. To enable the use of our results in DM studies, we provide the tabulated source spectra for the most relevant cosmic messenger particles, namely antiprotons, positrons, $γ$ rays and the three neutrino flavors, for all the fermionic and bosonic channels and DM masses between 5 GeV and 100 TeV, on https://github.com/ajueid/CosmiXs.git.

astro-ph.HE↗

arXiv2023

New energy spectra in neutrino and photon detectors to reveal hidden dark matter signals

Neutral particles capable of travelling cosmic distances from a source to detectors on Earth are limited to photons and neutrinos. Examination of the Dark Matter annihilation/decay spectra for these particles reveals the presence of continuum spectra (e.g. due to fragmentation and W or Z decay) and peaks (due to direct annihilations/decays). However, when one explores extensions of the Standard Model (BSM), unexplored spectra emerge that differ significantly from those of the Standard Model (SM) for both neutrinos and photons. In this paper, we argue for the inclusion of important spectra that include peaks as well as previously largely unexplored entities such as boxes and combinations of box, peak and continuum decay spectra.

hep-ph↗

arXiv2023

Progress in End-to-End Optimization of Detectors for Fundamental Physics with Differentiable Programming

In this article we examine recent developments in the research area concerning the creation of end-to-end models for the complete optimization of measuring instruments. The models we consider rely on differentiable programming methods and on the specification of a software pipeline including all factors impacting performance -- from the data-generating processes to their reconstruction and the extraction of inference on the parameters of interest of a measuring instrument -- along with the careful specification of a utility function well aligned with the end goals of the experiment. Building on previous studies originated within the MODE Collaboration, we focus specifically on applications involving instruments for particle physics experimentation, as well as industrial and medical applications that share the detection of radiation as their data-generating mechanism.

physics.ins-det↗