揭秘洛伦兹等变喷注分类器学到的物理特征。
What Do Lorentz-Equivariant Jet Taggers Learn?
- 用等变性测试和线性探针分析模型内部表征
- 抑制伪快度依赖性，强编码喷注质量与双子结构
- 多路径表示机制支持复杂判别任务，适合高能物理研究
我们研究了洛伦兹等变喷注分类器内部学习的内容，采用等变性测试、线性探针和等级消融方法，覆盖L-GATr、L-GATr-slim和LLoCa-T等五种模型。线性探针显示，等变模型将帧依赖的伪快度抑制为零，同时强烈编码喷注质量与N-亚喷注结构。对L-GATr的等级消融表明，双矢量通道在顶夸克标记中可忽略，而矢量类通道占主导但种子变量差异显著，说明网络利用多种表征路径。这些结果揭示了等变分类器中哪些物理特征与代数等级结构携带判别信息，有助于未来模型设计。
原文摘要 · Abstract (English)
We study what Lorentz-equivariant jet taggers learn internally, using equivariance tests, linear probes and grade ablations across five models including L-GATr, L-GATr-slim and LLoCa-T. Linear probes show that equivariant models suppress frame-dependent pseudorapidity to zero while encoding jet mass and N-subjettiness strongly. Grade ablations on L-GATr reveal that bivector channels are negligible for top-quark tagging while vector-like channels are dominant but seed variable, consistent with the network exploiting multiple representational pathways. These results characterize which physical features and algebraic grade structures carry discriminative information in equivariant taggers and may inform future development of such models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。