Saved in:
Bibliographic Details
Main Authors: Visive, Ambre, de Austri, Roberto Ruiz, Moskvitina, Polina, Nellist, Clara, Caron, Sascha
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.21035
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908987879849984
author Visive, Ambre
de Austri, Roberto Ruiz
Moskvitina, Polina
Nellist, Clara
Caron, Sascha
author_facet Visive, Ambre
de Austri, Roberto Ruiz
Moskvitina, Polina
Nellist, Clara
Caron, Sascha
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_21035
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Masked-Token Prediction for Anomaly Detection at the Large Hadron Collider
Visive, Ambre
de Austri, Roberto Ruiz
Moskvitina, Polina
Nellist, Clara
Caron, Sascha
High Energy Physics - Phenomenology
High Energy Physics - Experiment
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.
title Masked-Token Prediction for Anomaly Detection at the Large Hadron Collider
topic High Energy Physics - Phenomenology
High Energy Physics - Experiment
url https://arxiv.org/abs/2604.21035