aiqbench analysis
This research demonstrates how transformer-based generative models can learn the Standard Model's physical structure directly from raw LHC collision data without explicit parameter tuning, effectively capturing particle kinematics and resonances across five decades of mass. By utilizing Riemannian flow matching with minimal physics priors, the study proves that fundamental constants like the W boson mass emerge naturally from training on recorded events rather than being hard-coded into Monte Carlo simulations.
Learning Standard Model structure from LHC data with Riemannian flow matching
arXiv:2607.16144v1 Announce Type: cross Abstract: In this work we demonstrate that a single transformer-based generative model can capture Standard Model structure spanning five decades of invariant mass, from the sub-GeV regime to the TeV continuum, a range that no single Monte Carlo sample covers. To achieve this we design \textsc{ShellFlow}, a Riemannian conditional flow matching model that, given the recorded event composition, generates each particle on its on-shell manifold. Its only physics priors are the on-shell condition and the invariant-mass formula. The model is trained on $\sim 10^{9}$ real $pp$ collision events from the ATLAS Open Data 13~TeV release and told nothing else. From a single training run, the model learns to reproduce all of the following: intra-particle kinematics, the dilepton resonances ($J/\psi$, $\Upsilon$, $Z$) at their PDG positions, the leptonic Weinberg angle, the $W$ and top-quark masses, and inter-particle correlations that enter no training objective. A substantial fraction of the Standard Model is thus learnable directly from recorded collision data.
Abstract:In this work we demonstrate that a single transformer-based generative model can capture Standard Model structure spanning five decades of invariant mass, from the sub-GeV regime to the TeV continuum, a range that no single Monte Carlo sample covers. To achieve this we design \textsc{ShellFlow}, a Riemannian conditional flow matching model that, given the recorded event composition, generates each particle on its on-shell manifold. Its only physics priors are the on-shell condition and the invariant-mass formula. The model is trained on $\sim 10^{9}$ real $pp$ collision events from the ATLAS Open Data 13~TeV release and told nothing else. From a single training run, the model learns to reproduce all of the following: intra-particle kinematics, the dilepton resonances ($J/\psi$, $\Upsilon$, $Z$) at their PDG positions, the leptonic Weinberg angle, the $W$ and top-quark masses, and inter-particle correlations that enter no training objective. A substantial fraction of the Standard Model is thus learnable directly from recorded collision data.
High Energy Physics - Phenomenology (hep-ph); Machine Learning (cs.LG); High Energy Physics - Experiment (hep-ex)
arXiv:2607.16144 [hep-ph]
(or arXiv:2607.16144v1 [hep-ph] for this version)
https://doi.org/10.48550/arXiv.2607.16144 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 262 words
Related coverage
Riemannian Graph Tokenizer for Structural Knowledge Transfer
arXiv · Oct 14, 2026
Tensor network manifolds and Riemannian fundamental theorem for tensor networks
arXiv · Jun 15, 2026
Quantum Superposition Principle and Geometry
arXiv · Oct 16, 2026
Nonparametric Intensity Estimation for Covariate-Driven Poisson Processes Using Deep Learning
arXiv · Nov 3, 2026