First-hand information for everyone
Researchers show that a type of machine learning called graph neural networks (GNNs) can infer a global measure of quantum entanglement from only local projective measurement records in monitored quantum circuits. The task is to predict the half-chain von Neumann entanglement entropy — a standard way to quantify how strongly the left and right halves of a chain are quantum-mechanically correlated — using the classical outcomes of measurements that happen at specific qubits and times. The main finding is that prediction quality improves as the machine can integrate information over a larger spacetime region, and that different network designs give the same results when measured by a single effective spacetime scale.
The authors test this idea on one-dimensional monitored random quantum circuits. These circuits evolve a chain of N qubits for t_max = 30 layers of two-qubit random gates arranged in a brick-wall pattern. After each layer, every qubit is measured in the computational basis with probability p. Each simulated run produces a classical spacetime record of where and when measurements happened and what their outcomes were. The learning target is the final half-chain von Neumann entropy S_{N/2}, normalized by N/2 to remove the leading size dependence. For N up to 16 the dynamics were simulated with exact state vectors; for larger sizes the paper says they used matrix product states (MPS) to control errors.
To feed spacetime measurement records to the learner, each run is converted into a directed spacetime graph whose nodes are qubit–time events and whose edges follow causal connections: worldline edges from (i,t) to (i,t+1) and gate-induced diagonal edges between neighboring qubits across time layers. Node features include whether a measurement happened, the measurement outcome, a normalized time coordinate, and simple boundary-aware position flags. No raw qubit indices are included so the same model can be used across different system sizes. The authors compare two graph-based architectures. A single-scale directed GraphSAGE model stacks K message-passing layers so that information propagates only along paths of length up to K, making the reachable spacetime region grow roughly linearly with K. An RG-inspired hierarchical model repeatedly coarse-grains spacetime in 2×2 blocks so the effective receptive field grows much faster with the number of coarse-graining levels.
The central empirical result is that the ability to predict the normalized half-chain entropy rises as the network’s accessible spacetime scale grows. When the authors combine depth and coarse-graining into a single effective spacetime scale, prediction results from different architectures collapse onto a common curve. The paper interprets this as evidence that the classical measurement record contains the information needed to reconstruct global entanglement, but that this information is organized by spacetime scale: larger-scale correlations require aggregating measurement outcomes over larger spacetime regions. The authors also frame a finite-scale hypothesis linking prediction error to the ratio of the network’s effective scale and the circuit’s correlation length near the measurement-induced phase transition.
Important caveats are reported. The work studies a specific family of monitored random circuits in one dimension, with simulations up to modest sizes and with t_max = 30, so the results may not generalize immediately to other models, higher dimensions, or very large systems. The scaling relation the authors propose is empirical and tested numerically rather than proven. Measurements break unitary evolution, so standard locality theorems (Lieb–Robinson bounds) do not directly apply and propagation in monitored circuits can differ from purely unitary systems. Finally, the study is a supervised learning approach that reconstructs a particular entanglement observable from simulated measurement data; it does not claim to recover the full quantum state. Despite these limits, the work offers a concrete, operational framework to probe how global quantum correlations can be read out from local classical records and shows how graph-based models can control the spacetime scale of that readout.