Pith. sign in

REVIEW 13 cited by

Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.14806 v3 pith:OV4USBFU submitted 2024-05-23 physics.data-an cs.LGhep-phstat.ML

Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics

classification physics.data-an cs.LGhep-phstat.ML
keywords l-gatralgebrageometrichigh-energyphysicsarchitecturedataexperiments
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Extracting scientific understanding from particle-physics experiments requires solving diverse learning problems with high precision and good data efficiency. We propose the Lorentz Geometric Algebra Transformer (L-GATr), a new multi-purpose architecture for high-energy physics. L-GATr represents high-energy data in a geometric algebra over four-dimensional space-time and is equivariant under Lorentz transformations, the symmetry group of relativistic kinematics. At the same time, the architecture is a Transformer, which makes it versatile and scalable to large systems. L-GATr is first demonstrated on regression and classification tasks from particle physics. We then construct the first Lorentz-equivariant generative model: a continuous normalizing flow based on an L-GATr network, trained with Riemannian flow matching. Across our experiments, L-GATr is on par with or outperforms strong domain-specific baselines.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Generative models on phase space

    hep-ph 2026-04 unverdicted novelty 8.0

    Generative diffusion and flow models are constructed to remain exactly on the Lorentz-invariant massless N-particle phase space manifold during sampling for particle physics applications.

  2. Neural Control Variates at LO and NLO

    hep-ph 2026-07 accept novelty 7.0

    Signed neural control variates from normalizing flows, combined with neural importance sampling, reduce weight ranges and negative weights for LO and NLO phase-space integration and event generation.

  3. Predict before you train: Scaling Laws for particle physics foundation models

    hep-ex 2026-07 conditional novelty 7.0

    A Chinchilla-style law fit on ParticleViT runs below 10^19 FLOPs predicts held-out pretraining loss within ~1% at >100× compute and tracks downstream jet-tagging rejection.

  4. Learning Standard Model structure from LHC data with Riemannian flow matching

    hep-ph 2026-07 conditional novelty 7.0

    ShellFlow, a Riemannian flow-matching transformer fed only on-shell and invariant-mass priors and ~8×10^8 recorded ATLAS events, reproduces the SM's dilepton resonances, Weinberg angle, and top/W mass peaks in a singl...

  5. Particle-Lund Multimodality in Jet Taggers

    hep-ph 2026-05 unverdicted novelty 7.0

    PLuM multimodal transformer improves top and H->bb jet tagging by jointly processing particle constituents and Lund plane splittings, yielding 25% higher background rejection at 25% di-Higgs efficiency.

  6. Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging

    hep-ex 2026-05 unverdicted novelty 7.0

    PHAT-JeT combines geometric message-passing with hierarchical patch attention to reach state-of-the-art accuracy and background rejection among resource-constrained jet tagging models on four benchmarks.

  7. Agentic Re-Casting using Agentic Re-Simulations

    hep-ph 2026-07 conditional novelty 6.0

    An agentic AI system with a physicist in the loop re-casts an ATLAS ttZ measurement into a global top-quark SMEFT fit and recovers injected coloron Wilson coefficients in a repeatable benchmark.

  8. Pointwise Metrics Mislead: An Evaluation Protocol for Multimodal Inverse Problems

    cs.LG 2026-05 unverdicted novelty 6.0

    Pointwise metrics compress marginal spectra in multimodal inverse problems, and a three-part protocol using CRPS, spectrum fidelity, and calibration reverses model rankings on synthetic and particle-physics benchmarks.

  9. Geometric algebra as the input language of collider foundation models

    hep-ph 2026-05 unverdicted novelty 6.0

    Collider events are represented as multivectors in Cl(1,3) ⊗ V_flav whose grade projections recover standard observables, intended as input for equivariant foundation models.

  10. What Do Lorentz-Equivariant Jet Taggers Learn?

    cs.LG 2026-06 unverdicted novelty 5.0

    Equivariant jet taggers suppress frame-dependent pseudorapidity while encoding jet mass and N-subjettiness strongly, with bivector channels negligible and vector channels dominant for top tagging.

  11. KIGNet: Physics-Motivated Multi-Graph Representation Learning for Explainable Jet Tagging

    hep-ph 2025-12 conditional novelty 5.0

    E-PCN reaches 94.67% macro-accuracy on 10-class jet tagging by weighting graphs with angular separation, transverse momentum, momentum fraction, and invariant mass, with Grad-CAM showing the first two account for 76% ...

  12. Amplitude Uncertainties Everywhere All at Once

    hep-ph 2025-08 unverdicted novelty 4.0

    Compares ensemble, Bayesian, and evidential regression approaches for uncertainty quantification in amplitude surrogates and shows they detect localized training data issues.

  13. Interpreting "Interpretability" and Explaining "Explainability" in Machine Learning in Physics

    physics.data-an 2026-06 unverdicted novelty 2.0

    The paper defines interpretability as model structural transparency and explainability as scientific content mapping, discusses their trade-offs, and frames both as deliberate modeling choices for ML in physics.