QGrAT: Quantum Grade-Aware Transformer for Jet Tagging

Abstract

Lorentz symmetry and the three-prong structure of hadronic top decays provide physical guidance for designing compact quantum jet taggers. We introduce QGrAT (Quantum Grade-Aware Transformer), a quantum transformer that incorporates these structures into its interactions between constituent qubits. Geometric features constructed from the constituent four-momenta are organised by the grades of the spacetime Clifford algebra Cℓ(1,3), and their grade-specific inner products determine the pairwise attention couplings. For fixed constituents and co-transforming reference vectors, these couplings are Lorentz invariant, although the component-wise input encoding makes the complete classifier frame dependent. An auxiliary qubit introduces an explicit three-particle interaction through products of pairwise Minkowski inner products, while a trainable in-circuit readout converts the resulting quantum state into a classification score. We evaluate the architecture in state-vector simulation on the Top Tagging benchmarks. With ten constituents per jet, the configuration using grades 0−3 and the three-particle ancilla requires twelve qubits and $144$ trainable parameters, reaching AUC 0.944 ± 0.002 and background rejection 1/ε_B = 35.7 ± 2.4 (96.8 ± 7.7) at signal efficiency ε_S = 0.50 (0.30). This performance is competitive with the L-GATr-Slim baseline at matched constituent and parameter budgets. Adding the three-particle ancilla raises background rejection at 50% signal efficiency from $19.9$ to $35.7$, whereas extending the representation to the tested grade-$4$ feature gives no consistent improvement. The study establishes a framework for incorporating spacetime geometry into quantum attention and identifies explicit three-particle correlations as the principal source of improved background rejection among the architectural variations tested.

This is SParTA: A modular, efficient and scalable transformer architecture for jet-tagging
Rajneil Baruah, Subhadeep Mondal, Sunando Kumar Patra +1
arXiv19 Oct 2026PreprintCC BY 4.0Full textHigh-energy & particle physicsarXiv
Transformer fault diagnosis using an efficient simulation-driven variational quantum classifier with domain-aware feature encoding
Huy Hoang Le, Ba Tu Phung, Dai Huynh +1
arXiv1 Sep 2026PreprintarXiv licenceFull textQuantum physics & quantum informationarXiv
Quantum Graph Neural Networks for Jet Tagging on Quantum Hardware
Benjamin Jobilal, Jinghong Yang, Trevor Smith +3
arXiv3 Sep 2026PreprintarXiv licenceFull textHigh-energy & particle physics Quantum physics & quantum informationarXiv
Stackelberg Game with Multi-Agent Transformer for ISRS-Aware Resource Re-optimization in Multi-Band Optical Networks
Jiaxin Liu, Rentao Gu, Miao Zhu +3
arXiv10 Oct 2026PreprintarXiv licenceFull textComputational physics Optics & photonicsarXiv
Variational study of the magnetization plateaus in the spin-1/2 kagome Heisenberg antiferromagnet: An approach from vision transformer neural quantum states
Andreas Raikos, Sylvain Capponi, Fabien Alet
Physical Review B29 Sep 2026Peer-reviewedLicence not statedFull textCondensed matterHAL

Cite

BibTeX RIS

BibTeX

@misc{bhardwaj2026qgrat,
  title = {{QGrAT: Quantum Grade-Aware Transformer for Jet Tagging}},
  author = {Pallavi Bhardwaj and Michael Spannowsky},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.17351},
  eprint = {2610.17351},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.17351},
  note = {CC BY-NC-SA 4.0},
}

RIS

TY  - UNPB
TI  - QGrAT: Quantum Grade-Aware Transformer for Jet Tagging
AU  - Pallavi Bhardwaj
AU  - Michael Spannowsky
PY  - 2026
DA  - 2026/10/12
PB  - arXiv
DO  - 10.48550/arxiv.2610.17351
UR  - https://arxiv.org/abs/2610.17351
AB  - Lorentz symmetry and the three-prong structure of hadronic top decays provide physical guidance for designing compact quantum jet taggers. We introduce QGrAT (Quantum Grade-Aware Transformer), a quantum transformer that incorporates these structures into its interactions between constituent qubits. Geometric features constructed from the constituent four-momenta are organised by the grades of the spacetime Clifford algebra Cℓ(1,3), and their grade-specific inner products determine the pairwise attention couplings. For fixed constituents and co-transforming reference vectors, these couplings are Lorentz invariant, although the component-wise input encoding makes the complete classifier frame dependent. An auxiliary qubit introduces an explicit three-particle interaction through products of pairwise Minkowski inner products, while a trainable in-circuit readout converts the resulting quantum state into a classification score. We evaluate the architecture in state-vector simulation on the Top Tagging benchmarks. With ten constituents per jet, the configuration using grades 0−3 and the three-particle ancilla requires twelve qubits and $144$ trainable parameters, reaching AUC 0.944 ± 0.002 and background rejection 1/ε_B = 35.7 ± 2.4 (96.8 ± 7.7) at signal efficiency ε_S = 0.50 (0.30). This performance is competitive with the L-GATr-Slim baseline at matched constituent and parameter budgets. Adding the three-particle ancilla raises background rejection at 50% signal efficiency from $19.9$ to $35.7$, whereas extending the representation to the tested grade-$4$ feature gives no consistent improvement. The study establishes a framework for incorporating spacetime geometry into quantum attention and identifies explicit three-particle correlations as the principal source of improved background rejection among the architectural variations tested.
ER  -

Abstract

Related

Cite