TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data
Abstract
Detecting phases of matter in general relies on identifying the correct order parameter - a task that remains notoriously difficult for unknown transitions and traditionally is guided by physical intuition and educated guess. Neural networks have recently offered an alternative route by locating phase transitions in known models without any a priori physical knowledge. Yet these approaches remain black boxes and only identify phases without elucidating their properties. Moreover, they often struggle when confronted with realistic, noisy experimental data, which constitute the ultimate testbed for automated methods in physics. Here, we bridge these perspectives by introducing TetrisCNN, a convolutional architecture with parallel branches of differently shaped filters, reminiscent of Tetris blocks, that learns sparse, interpretable latent representations directly in terms of spin correlators. Applied to experimental snapshots of two-dimensional Ising and XY quantum simulators measured in multiple bases, the network not only detects phase transitions and crossovers but also expresses its latent representation and decision boundaries as symbolic formulas built from experimentally measurable spin correlators. This framework opens the way to integrating interpretable neural networks with quantum simulators to uncover and understand new phases of matter.
Related
- Experimental observation of Higgs oscillations and their power-law decay across pairing regimes in a cavity QED quantum simulator
- Pseudogap in a Fermi–Hubbard quantum simulator
- Probing False Vacuum Decay on a Cold-Atom Gauge-Theory Quantum Simulator
- Trajectree - A quantum trajectory-based quantum circuit simulator
- Quantum Simulation of the Static Yukawa Model via Effective Particles on a Trapped-Ion Quantum Simulator
BibTeX
@misc{cybinski2026tetriscnn,
title = {{TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data}},
author = {Kacper Cybiński and Björn van Zwol and James Enouen and Guillaume Bornet and Thierry Lahaye and Antoine Browaeys and Antoine Georges and Anna Dawid},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.20693},
eprint = {2609.20693},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.20693},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data
AU - Kacper Cybiński
AU - Björn van Zwol
AU - James Enouen
AU - Guillaume Bornet
AU - Thierry Lahaye
AU - Antoine Browaeys
AU - Antoine Georges
AU - Anna Dawid
PY - 2026
DA - 2026/09/17
PB - arXiv
DO - 10.48550/arxiv.2609.20693
UR - https://arxiv.org/abs/2609.20693
AB - Detecting phases of matter in general relies on identifying the correct order parameter - a task that remains notoriously difficult for unknown transitions and traditionally is guided by physical intuition and educated guess. Neural networks have recently offered an alternative route by locating phase transitions in known models without any a priori physical knowledge. Yet these approaches remain black boxes and only identify phases without elucidating their properties. Moreover, they often struggle when confronted with realistic, noisy experimental data, which constitute the ultimate testbed for automated methods in physics. Here, we bridge these perspectives by introducing TetrisCNN, a convolutional architecture with parallel branches of differently shaped filters, reminiscent of Tetris blocks, that learns sparse, interpretable latent representations directly in terms of spin correlators. Applied to experimental snapshots of two-dimensional Ising and XY quantum simulators measured in multiple bases, the network not only detects phase transitions and crossovers but also expresses its latent representation and decision boundaries as symbolic formulas built from experimentally measurable spin correlators. This framework opens the way to integrating interpretable neural networks with quantum simulators to uncover and understand new phases of matter.
ER -