hep-phNov 19, 2026

Who Moved My ZZ Boson? Revealing Resonance Features Inside a Neural Network

Authors: Kevin Alberto Urquía Calderón, Midori Kato, Inar Timiryasov, Oleg Ruchayskiy

Organizations: Niels Bohr Institute, University of Copenhagen, Jagtvej 155A, DK-2200, Copenhagen, Denmark.

Abstract

Methods used in mechanistic interpretability have revealed human-aligned concepts inside language and image models. In this paper, we search for physics concepts inside a neural a generative collider physics model trained on real LHC data (ShellFlow). We discover features inside ShellFlow that represent resonances, such as the ZZ, J/ψJ/ψ, and ΥΥ. The network was never told which muons come from a resonance, it was only trained to generate the kinematics of the final-state particles. We use these features to alter aspects of the ZZ boson: we change its mass between ∼80\sim80 and 105105 GeV, and removing such a feature from the neural network produces a broader ZZ peak. In both cases the rest of the invariant mass spectrum remains mostly unchanged. The feature was built from the gradients of the neural network, and its selectivity was built using pattern recognition methods. A generative particle physics model trained on unlabeled data can be modified internally to change a physical quantity.

Figures & tables

Appendix figures & tables21 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

May 11, 2026

Dissecting Jet-Tagger Through Mechanistic Interpretability

Mechanistic interpretability seeks to reverse engineer a trained neural network by identifying the minimal subset of internal components. We perform a mechanistic interpretability analysis of the Particle Transformer architecture, trained on the Top Quark Tagging reference dataset, with the goal of identifying the computational circuit responsible for jet classification and characterizing the physical content of its internal representations. Combining zero ablation, path patching with two complementary on-manifold corruption strategies and linear probing of the residual stream, we identify a sparse six-head circuit that recovers the great majority of the full model performance while admitting a clean source-relay-readout interpretation. In this circuit, a single early layer head serves as the primary causal source, a cluster of middle-layer heads acts as relays selectively attending to hard pairwise substructure and a single late-layer head reads out the aggregated signal. Linear probes show that the residual stream is preferentially aligned with the energy correlator basis over the NN-subjettiness basis. Within the energy correlator basis, the model preferentially encodes 2-prong substructure observables over the 3-prong observables. A per-layer trained probe further reveals that the apparent single step commitment of the model to a classification decision in the first class attention block is in fact a basis rotation, with the discriminating signal already saturating in the particle attention stack. These results demonstrate that mechanistic interpretability methods developed for natural language models can be used for jet physics classifiers and indicate that gradient descent may rediscover physically meaningful aspects of jet tagging without supervision.
Jul 17, 2026

Learning Standard Model structure from LHC data with Riemannian flow matching

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 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 ∼109\sim 10^{9} real pppp 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/ψJ/ψ, ΥΥ, ZZ) at their PDG positions, the leptonic Weinberg angle, the WW 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.
May 8, 2026

Uncovering Hidden Systematics in Neural Network Models for High Energy Physics

Neural networks (NNs) are inherently multidimensional classifiers that learn complex, non-linear relationships among input observables. While their flexibility enables unprecedented performance in high-energy physics (HEP) analyses, it also makes them sensitive to small variations in their inputs. Consequently, the propagation and estimation of systematic uncertainties in NN-based models remain an open challenge. There are indications that uncertainties derived in control regions or from nominal variations of input features can underestimate the true model uncertainty, potentially leaving biases unaccounted for. Inspired by insights from adversarial-attack studies in machine learning, we explore how subtle perturbations, fully consistent with the experimental uncertainties on the input observables, can lead to substantial changes in NN outputs, while keeping the one-dimensional and correlated input distributions nearly unchanged. Using a set of representative HEP tasks, including event classification and object identification, and testing across a variety of network architectures, we demonstrate that networks can be systematically "fooled" at significant rates within the allowed uncertainty envelopes. Building on this observation, we introduce a quantitative framework to probe and measure the hidden sensitivity of neural networks to realistic experimental variations, providing a practical path to evaluate and control their systematic uncertainty in physics analyses.