What Do Lorentz-Equivariant Jet Taggers Learn?
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 7 of its 13 references that are in the map. First posted on arXiv 19 Jun 2026.
Builds on
7 of 13 references.
References · 7
- 2019Similarity of Neural Network Representations Revisitedcited by 1,695
- 2022Particle Transformer for Jet Taggingcited by 95
- 2023Geometric Algebra Transformercited by 46
- 2024Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physicscited by 36
- 2025Lorentz Local Canonicalization: How to Make Any Network Lorentz-Equivariantcited by 12
- 2019Interpretability Study on Deep Learning for Jet Physics at the Large Hadron Collidercited by 3
- 2024Interpreting Transformers for Jet Taggingcited by 1
Built on by
Not cited yet.