arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.21035hep-phhep-ex
收藏

基于掩码词预测的大型强子对撞机异常检测

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

NIKHEF(荷兰国家核子和亚原子物理研究所)

Ambre Visive, Roberto Ruiz de Austri, Polina Moskvitina, Clara Nellist, Sascha Caron

AI总结:

本文首次将大语言模型的掩码词预测技术应用于高能物理异常检测,通过轻量级编码器架构捕捉标准模型物理结构,识别偏离该结构的异常事件,展示了其在四顶夸克生产和超对称胶子对产生等场景中的有效性。

摘要:

在高能物理中,异常检测需要在 overwhelming 背景中识别稀有信号,而无先验知识。我们首次将掩码词预测技术应用于此问题。一个仅在背景事件上训练的轻量级编码器架构捕捉标准模型(SM)物理结构;在推理阶段,偏离该学习结构的序列被标记为异常。我们评估了该方法在四顶夸克生产和超对称胶子对产生搜索中的表现,两者均具有丰富的顶夸克最终状态和显著的缺失横向能量,涵盖SM和超越SM(BSM)场景。在四顶夸克签名上表现出色,证明了方法对细微偏差的敏感性。我们进一步表明,tokenization策略显著影响性能:通过向量量化变分自编码器(VQ-VAE)学习的tokenization优于查表tokenization。与已建立的异常检测基线比较确认了方法的鲁棒性。这些结果突显了基于token的对撞机数据表示与transformer架构结合在新物理发现中的潜力。一旦在SM背景上训练,模型可跨不同BSM搜索转移,实现计算成本降低的可扩展、模型无关的异常检测。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑