arXiv subjects

Clara Nellist

Publications and source records attributed to Clara Nellist.

7 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

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

Physics Prospects for a near-term Proton-Proton Collider

Hadron colliders at the energy frontier offer significant discovery potential through precise measurements of Standard Model processes and direct searches for new particles and interactions. A future hadron collider would enhance the exploration of particle physics at the electroweak scale and beyond, potentially uniting the community around a common project. The LHC has already demonstrated precision measurement and new physics search capabilities well beyond its original design goals and the HL-LHC will continue to usher in new advancements. This document highlights the physics potential of an FCC-hh machine to directly follow the HL-LHC. In order to reduce the timeline and costs, the physics impact of lower collider energies, down to $\sim 50$~TeV, is evaluated. Lower centre-of-mass energy could leverage advanced magnet technology to reduce both the cost and time to the next hadron collider. Such a machine offers a breadth of physics potential and would make key advancements in Higgs measurements, direct particle production searches, and high-energy tests of Standard Model processes. Most projected results from such a hadron-hadron collider are superior to or competitive with other proposed accelerator projects and this option offers unparalleled physics breadth. The FCC program should lay out a decision-making process that evaluates in detail options for proceeding directly to a hadron collider, including the possibility of reducing energy targets and staging the magnet installation to spread out the cost profile.

hep-ex↗

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↗

arXiv2022

Activity Report of the Second African Conference on Fundamental and Applied Physics, ACP2021

The African School of Fundamental Physics and Applications, also known as the African School of Physics (ASP), was initiated in 2010, as a three-week biennial event, to offer additional training in fundamental and applied physics to African students with a minimum of three-year university education. Since its inception, ASP has grown to be much more than a school. ASP has become a series of activities and events with directed ethos towards physics as an engine for development in Africa. One such activity of ASP is the African Conference on Fundamental and Applied Physics (ACP). The first edition of ACP took place during the 2018 edition of ASP at the University of Namibia in Windhoek. In this paper, we report on the second edition of ACP, organized on March 7--11, 2022, as a virtual event.

physics.ed-ph↗

arXiv2019

Top SciComm: Communicating ATLAS Top Physics Results to the Public

An essential component of the long-term success of scientific research is communicating the methodology and significance of new results to the wider public. Utilising various social media platforms is a vital tool for this endeavour. Over the years, there have been a number of important results on top physics released by the ATLAS Collaboration. These have been communicated through audience-tailored content, including ATLAS physics briefings, videos, and press statements, amongst others. The ATLAS Collaboration has continued to adapt its communication strategy to match the social media evolution, producing content specifically targeting this emerging audience, the effect of which has been explored.

physics.pop-ph↗

arXiv2019

$t\bar{t}$ + $Z$ / $W$ / $t\bar{t}$ at ATLAS

The newest results from the ATLAS Collaboration for the production of a top-quark pair in association with a $Z$ or $W$ boson, and for the production of four top quarks, are summarised in these proceedings. The measurements were performed with 36.1 fb$^{-1}$ of proton-proton collision data from the Large Hadron Collider at a centre-of-mass energy of 13 TeV.

hep-ex↗