- Open Access
Probing the fundamental limit of jet tagging with surrogate reference models
Phys. Rev. D 114, 092012 – Published 16 November, 2026
DOI: https://doi.org/10.1103/rcpy-nr72
Abstract
Beyond the practical goal of improving search and measurement sensitivity through better jet tagging algorithms, there is a deeper question: what are their upper performance limits? Generative surrogate models with learned likelihood functions offer a new approach to this problem, provided the surrogate correctly captures the underlying data distribution. In this work, we introduce the SUrrogate ReFerence (SURF) method, a new approach to validating generative models. This framework enables exact Neyman-Pearson tests by training the target model on samples from another tractable surrogate, which is itself trained on real data. We argue that the EPiC-FM generative model is a valid surrogate reference for jetclass jets and apply SURF to show that modern jet taggers may already be operating close to the true statistical limit. By contrast, we find that autoregressive generative pretrained transformer models unphysically exaggerate top vs QCD separation power encoded in the surrogate reference, implying that they are giving a misleading picture of the fundamental limit.
Physics Subject Headings (PhySH)
Article Text
References (47)
- H. Qu and L. Gouskos, ParticleNet: Jet tagging via particle clouds, Phys. Rev. D 101, 056019 (2020).
- A. Butter et al., The machine learning landscape of top taggers, SciPost Phys. 7, 014 (2019).
- A. M. Sirunyan et al. (CMS), Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques, J. Instrum. 15, P06005 (2020).
- S. Gong, Q. Meng, J. Zhang, H. Qu, C. Li, S. Qian, W. Du, Z.-M. Ma, and T.-Y. Liu, An efficient Lorentz equivariant graph neural network for jet tagging, J. High Energy Phys. 07 (2022) 030.
- A. Bogatskiy, T. Hoffman, D. W. Miller, J. T. Offermann, and X. Liu, Explainable equivariant neural networks for particle physics: PELICAN, J. High Energy Phys. 03 (2024) 113.
- H. Qu, C. Li, and S. Qian, Particle transformer for jet tagging, arXiv:2202.03772.
- J. Brehmer, V. Bresó, P. de Haan, T. Plehn, H. Qu, J. Spinner, and J. Thaler, A Lorentz-equivariant transformer for all of the LHC, SciPost Phys. 19, 108 (2025).
- V. Mikuni and B. Nachman, Solving key challenges in collider physics with foundation models, Phys. Rev. D 111, L051504 (2025).
- V. Mikuni and B. Nachman, A method to simultaneously facilitate all jet physics tasks, Phys. Rev. D 111, 054015 (2025).
- ATLAS Collaboration, Accuracy versus precision in boosted top tagging with the ATLAS detector, J. Instrum. 19, P08018 (2024).
- L. Favaro, G. Gerhartz, F. A. Hamprecht, P. Lippmann, S. Pitz, T. Plehn, H. Qu, and J. Spinner, Lorentz-equivariance without limitations, arXiv:2508.14898.
- W. Bhimji, C. Harris, V. Mikuni, and B. Nachman, OmniLearned: A foundation model framework for all tasks involving jet physics, Phys. Rev. D 113, 032020 (2026).
- J. Neyman and E. S. Pearson, On the problem of the most efficient tests of statistical hypotheses, Phil. Trans. R. Soc. A 231, 289 (1933).
- J. Geuskens, N. Gite, M. Krämer, V. Mikuni, A. Mück, B. Nachman, and H. Reyes-González, The fundamental limit of jet tagging, Phys. Rev. D 112, L091901 (2025).
- H. Qu, C. Li, and S. Qian, JetClass: A large-scale dataset for deep learning in jet physics, 10.5281/zenodo.6619768 (2022).
- T. Finke, M. Krämer, A. Mück, and J. Tönshoff, Learning the language of QCD jets with transformers, J. High Energy Phys. 06 (2023) 184.
- M. S. Albergo and E. Vanden-Eijnden, Building normalizing flows with stochastic interpolants, arXiv:2209.15571.
- Y. Lipman, R. T. Chen, H. Ben-Hamu, M. Nickel, and M. Le, Flow matching for generative modeling, arXiv:2210.02747.
- A. Tong, K. Fatras, N. Malkin, G. Huguet, Y. Zhang, J. Rector-Brooks, G. Wolf, and Y. Bengio, Improving and generalizing flow-based generative models with minibatch optimal transport, arXiv:2302.00482.
- E. Buhmann, C. Ewen, D. A. Faroughy, T. Golling, G. Kasieczka, M. Leigh, G. Quétant, J. A. Raine, D. Sengupta, and D. Shih, EPiC-ly fast particle cloud generation with flow-matching and diffusion, arXiv:2310.00049.
- J. Birk, E. Buhmann, C. Ewen, G. Kasieczka, and D. Shih, Flow matching beyond kinematics: Generating jets with particle identification and trajectory displacement information, Phys. Rev. D 111, 052008 (2025).
- T. Golling, L. Heinrich, M. Kagan, S. Klein, M. Leigh, M. Osadchy, and J. A. Raine, Masked particle modeling on sets: towards self-supervised high energy physics foundation models, Mach. Learn. Sci. Tech. 5, 035074 (2024).
- J. Birk, A. Hallin, and G. Kasieczka, OmniJet-: The first cross-task foundation model for particle physics, Mach. Learn. Sci. Tech. 5, 035031 (2024).
- T. Wolf et al., Transformers: State-of-the-art natural language processing, in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (Association for Computational Linguistics, 2020), pp. 38–45.
- O. Press and L. Wolf, Using the output embedding to improve language models, Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (2017).
- H. Inan, K. Khosravi, and R. Socher, Tying word vectors and word classifiers: A loss framework for language modeling, in International Conference on Learning Representations (ICLR) (2017).
- C. Krause and D. Shih, CaloFlow: Fast and accurate generation of calorimeter showers with normalizing flows, Phys. Rev. D 107, 113003 (2021).
- O. Amram et al., CaloChallenge 2022: A community challenge for fast calorimeter simulation, Rep. Prog. Phys. 88, 116201 (2025).
- S. H. Lim, K. A. Raman, M. R. Buckley, and D. Shih, GalaxyFlow: Upsampling hydrodynamical simulations for realistic mock stellar catalogues, Mon. Not. R. Astron. Soc. 533, 143 (2024).
- R. Kansal, A. Li, J. Duarte, N. Chernyavskaya, M. Pierini, B. Orzari, and T. Tomei, Evaluating generative models in high energy physics, Phys. Rev. D 107, 076017 (2023).
- R. Das, L. Favaro, T. Heimel, C. Krause, T. Plehn, and D. Shih, How to understand limitations of generative networks, SciPost Phys. 16, 031 (2023).
- P. Cappelli, G. Grosso, M. Letizia, H. Reyes-González, and M. Zanetti, Learning to validate generative models: A goodness-of-fit approach, Mach. Learn. Sci. Tech. 7, 045011 (2026).
- H. Reyes-Gonzalez, M. Krämer, A. Mück, B. Nachman, V. Mikuni, J. Geuskens, and N. Gite, Resources for the fundamental limit of jet tagging, 10.5281/zenodo.14023638 (2024).
- A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sutskever, Language models are unsupervised multitask learners (2019).
- Z. Kadkhodaie, F. Guth, E. P. Simoncelli, and S. Mallat, Generalization in diffusion models arises from geometry-adaptive harmonic representations, arXiv:2310.02557.
- J. J. Vastola, Generalization through variance: How noise shapes inductive biases in diffusion models, arXiv:2504.12532.
- Q. Bertrand, A. Gagneux, M. Massias, and R. Emonet, On the closed-form of flow matching: Generalization does not arise from target stochasticity, arXiv:2506.03719.
- N. Rahaman, A. Baratin, D. Arpit, F. Draxler, M. Lin, F. Hamprecht, Y. Bengio, and A. Courville, On the spectral bias of neural networks, in International Conference on Machine Learning (PMLR, 2019), pp. 5301–5310.
- B. Ronen, D. Jacobs, Y. Kasten, and S. Kritchman, The convergence rate of neural networks for learned functions of different frequencies, Adv. Neural Inf. Process. Syst. 32 (2019).
- Y. Zhang and X. Xu, Diffusion noise feature: Accurate and fast generated image detection, arXiv:2312.02625.
- A. J. Larkoski, Systematic interpretability and the likelihood for boosted top quark identification, arXiv:2411.00104.
- D. Faroughy, JetSequences, GitHub repository (2025), https://github.com/dfaroughy/JetSequences.
- I. Pang, jet_cfm, GitHub repository (2025), https://github.com/Ian-Pang/jet_cfm.
- E. Buhmann, G. Kasieczka, and J. Thaler, EPiC-GAN: Equivariant point cloud generation for particle jets, SciPost Phys. 15, 130 (2023).
- M. Zaheer, S. Kottur, S. Ravanbakhsh, B. Poczos, R. R. Salakhutdinov, and A. J. Smola, Deep sets, Adv. Neural Inf. Process. Syst. 30 (2017).
- P. T. Komiske, E. M. Metodiev, and J. Thaler, Energy flow networks: Deep sets for particle jets, J. High Energy Phys. 01 (2019) 121.
- D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980.