[Submitted on 19 Nov 2026]
View a PDF of the paper titled Who Moved My $Z$ Boson? Revealing Resonance Features Inside a Neural Network, by Kevin Alberto Urqu\’ia Calder\’on and 2 other authors
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 $Z$, $J/\psi$, and $\Upsilon$. 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 $Z$ boson: we change its mass between $\sim80$ and $105$ GeV, and removing such a feature from the neural network produces a broader $Z$ 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.
Submission history
From: Kevin A. Urquía-Calderón [view email]
[v1]
Thu, 19 Nov 2026 15:48:04 UTC (1,261 KB)
![[2611.26291] Who Moved My $Z$ Boson? Revealing Resonance Features Inside a Neural Network [2611.26291] Who Moved My $Z$ Boson? Revealing Resonance Features Inside a Neural Network](https://techwavedispatch.com/wp-content/uploads/2026/11/261126291-Who-Moved-My-Z-Boson-Revealing-Resonance-Features-Inside-1024x597.png)