Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2610.01683

A Code-Agnostic Graph Neural Network Decoder from the Detection Error Model

Federico Alberto Astolfi, Guido Pupillo

quant-phSubmitted Oct 1, 2026• Announced Oct 2, 2026• 1 citation
arXivHTMLPDF

Abstract

We present POLYMECHANON, a graph neural network (GNN) decoder for quantum error correction whose only input is the detection error model (DEM) of a quantum code under a given noise model. We represent the DEM as a tripartite graph of detectors, error mechanisms and logical observables, where every input feature is computed by using the quantum code as data rather than design choice. In this way, the same architecture decodes in principle any stabiliser code, under any noise model that can be expressed as a detection error model, once trained on the DEM. We test this approach along four directions. Firstly, on the rotated surface code the decoder outperforms correlated MWPM under both phenomenological and circuit-level noise, with up to $25\%$ fewer logical failures. Secondly, on a family of high-rate qLDPC codes it matches BP+OSD on the smaller codes and surpasses it on the larger ones, with up to $16\%$ fewer logical failures on $[\![130,4,6]\!]$. Thirdly, its decoding time does not depend on the physical error rate, whereas that of BP+OSD grows with it: on $[\![130,4,6]\!]$ its effective cost per shot is of the order of a few ms on a single GPU against a few tens of milliseconds for BP+OSD on a single CPU core, and its fixed computational graph makes it a candidate for real-time decoding on neutral-atom processors. Finally, a single model trained across codes of different families outperforms uncorrelated MWPM on the graph-like codes seen during training and stays within $10\%$ of BP+OSD on the others, while it tends to fail to generalize to unseen codes, particularly larger ones. Its probabilistic output enables confidence-based post-selection, lowering the logical error rate by more than an order of magnitude on the surface code while keeping more than $90\%$ of the shots. Since only the DEM changes, new codes and noise models can be decoded without redesigning the decoder.

AI Summary

The paper asks whether a neural quantum-error-correction decoder can use a common architecture across stabiliser-code families and noise models by operating directly on a detection error model (DEM). POLYMECHANON represents the DEM as a tripartite graph of detectors, error mechanisms and logical observables. A recurrent message-passing GNN uses syndromes, fault priors and DEM-derived features, including detector coordinates, to predict logical flips. Most benchmarks train separate weights for each code and noise model. Simulated memory-$Z$ experiments use $r=d$ syndrome rounds and compare decoders on identical shots. Against correlated MWPM, the GNN reduces logical failures by approximately $16$–$24\%$ on rotated surface codes with $d=3,5,7,9$ under phenomenological noise, and $10$–$25\%$ for $d=3,5,7$ under circuit-level noise. On phenomenological LaCross codes encoding four logical qubits, performance progresses from parity with BP+OSD at $[[34,4,3]]$ to $16\%$ fewer failures at $[[130,4,6]]$. It remains approximately $4\%$ worse on $[[65,9,4]]$. Confidence-based post-selection reduces surface-code logical errors by factors of $14$–$40$, retaining over $93\%$ of shots for $d\ge5$ at the reported operating point. Inference has fixed, syndrome-independent computation. For $[[130,4,6]]$, effective per-shot cost is $5.1$ ms on an H200 GPU versus $26$–$38$ ms for BP+OSD on one CPU core; this is not a hardware-matched comparison or a streaming demonstration. A shared model trained on fifteen codes approaches classical baselines on training codes, but transfer deteriorates on larger unseen graphs and fails from phenomenological to circuit-level noise. Real-time implementation and broader generalisation remain open.

Little sign of AI-generated textOverclaimsMissing comparison

Central claim may not hold: The claimed applicability to arbitrary DEMs exceeds the documented feature construction, which assumes coordinate and measurement-round conventions that arbitrary DEMs need not provide. Noise-independent forward-pass cost does not imply noise-independent average decoding cost when zero-syndrome shots bypass the network. The fitted low-noise exponents do not establish near-optimal decoding because they leave the logical-error prefactors and gap to maximum-likelihood decoding undetermined. The post-selection explanation incorrectly requires physical error weight at least d for logical failure, although failure can occur at weight ceil(d/2).

Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.

Comments
19 pages, 8 figures, 6 tables

Related papers

Code-Agnostic Graph Neural Network Decoding from Detection Error Models: A Reconciled Quantitative and Structural Assessment

Rowan Brad Quni-Gudzinas

Graph neural network (GNN) decoders for quantum error correction have historically been locked to specific code families. The POLYMECHANON preprint [1,2] proposes a decoder whose sole input is the detection error model (DEM) — a tripartite graph of detectors, error mechanisms, and logical observables — making the code data rather than an architectural design choice. This paper provides an independent, arithmetic-first assessment of that claim. We convert the reported headline numbers into concrete quantities: a 25% reduction in logical failures versus correlated MWPM on the rotated surface code corresponds to an improvement factor of 0.75, which under the standard scaling ansatz p_L ∝ (p/p_th)^⌈d/2⌉ is equivalent to a relative pseudo-threshold improvement of ≈10.06% at d = 5 and ≈7.46% at d = 7; a 16% reduction on the [[130,4,6]] qLDPC code corresponds to a factor of 0.84 and an equivalent threshold improvement of ≈5.98%. The reported latency advantage ("a few ms per shot on a single GPU" versus "a few tens of ms" for BP+OSD on a CPU core) would bound the speedup in [4×, 25×], midpoint ≈10×, with an explicit hardware-asymmetry caveat — but this latency analysis is conditional on claims not verifiable in the available abstract record of [1,2]. We derive DEM graph sizes for canonical cases (441 detectors, 1,337 mechanisms, 2,681 edges at d = 8, R = 8 under stated conventions), prove a cheap non-isomorphism certificate between surface-code and qLDPC DEMs via part-size vectors, and show that the claimed post-selection result (>10× error reduction at >90% shot retention) would arithmetically require discarded shots to fail at ≈9.1× the base rate — a strong, testable separability condition, conditional on a claim not verifiable in the available abstract record of [1,2]. We identify size-generalization, DEM fidelity, and hardware-fair latency comparison as the principal open risks, and propose falsification experiments for each. ## 1. Introduction Fault-tolerant quantum Full text and updates: papers.qnfo.org/papers/code-agnostic-graph-neural-network-decoding-from-detection-error-models-a-reconc/

•Oct 4, 2026•0 citations

Low Latency GNN Accelerator for Quantum Error Correction

Alessio Cicero, Luigi Altamura, Moritz Lange +2 more

Quantum computers can solve selected problems more efficiently than classical computers, but current devices are limited by high physical error rates. Quantum Error Correction (QEC) mitigates this by encoding many physical qubits into a logical qubit, with the surface code among the most widely studied approaches. Since syndrome measurements are produced continuously, the decoder must process them fast enough to avoid becoming a system bottleneck, making real-time decoding essential for fault-tolerant quantum computing. While most state-of-the-art real-time decoders rely on Minimum-Weight Perfect Matching (MWPM), we instead use a high-accuracy Graph Neural Network (GNN) that trades higher computational cost for lower logical error rates. To make this GNN practical for real-time decoding, we apply algorithm-hardware co-design. We reduce complexity through hardware-guided pruning and retraining, producing two hardware-friendly models that reduce parameter count by $3.1\times$ and $6.5\times$. These target, respectively, an average decoding latency of one syndrome cycle and a worst-case latency within one syndrome cycle. We further reduce hardware cost using input-graph filtering and post-training quantization. Based on these optimized models, we propose an FPGA-based architecture for low-latency inference and real-time decoding. Evaluated on surface codes up to distance 7 under circuit-level noise at physical error rate $p=10^{-3}$, our decoder outperforms MWPM in decoding accuracy for both average-latency and max-latency settings. It reduces logical error rate by 40% at $1μs$ average latency, and by 13% under a strict $1μs$ deadline.

quant-pharXiv:2603.22149•Mar 24, 2026•4 citations

Decoding the surface code using graph neural networks

Moritz Lange

Quantum error correction is essential to achieve fault-tolerant quantum computation in the presence of noisy qubits. Among the most promising approaches to quantum error correction is the surface code, thanks to a scalable two-dimensional architecture, only nearest-neighbor interactions, and a high error threshold. Decoding the surface code, i.e. finding the most likely error chain given a syndrome measurement outcome is a computationally complex task. Traditional decoders rely on classical algorithms, which, especially for larger systems, can be slow and may not always converge to the optimal solution. This thesis presents a novel approach to decoding the surface code using graph neural networks. By mapping the syndrome measurements to a graph and performing graph classification, we find that the graph neural networks can predict the most likely error configuration with high accuracy. Our results show that the GNN-based decoder outperforms the classic minimum weight perfect matching (MWPM) decoder in terms of accuracy. With a phenomenological noise model with depolarizing noise and perfect syndrome measurements, our networks beat MWPM up to code-size 15 across all relevant error rates. Furthermore, the GNN is capable of surpassing MWPM under circuit-level noise up to code size 7. We also show that training the network on repetition code data from a recent experiment [Google Quantum AI, Nature 614, 676 (2023)] produces per-step error rates comparable to those achieved with a matching decoder specifically adapted to the error rates of the physical qubits. This indicates that graph neural network decoders are capable of learning the underlying error distribution on the qubits. Our findings advance the field of quantum error correction and provide a promising new direction for the development of efficient decoding algorithms.

•Oct 17, 2023•0 citations

Graph Neural Post-selection for Quantum Error Correction

Conor Carty, Tamas Noszko, Joschka Roffe +1 more

Post-selection improves the logical reliability of quantum computation by rejecting shots which are likely to result in logical failure. We introduce graph neural networks that predict decoder failure without additional decoder executions, using only syndromes, and for high-rate quantum low-density parity-check (qLDPC) codes, existing belief-propagation posteriors. We evaluate rotated surface and bivariate bicycle (BB) code memories under uniform depolarising circuit-level noise. Retaining 90% of shots gives approximately 3700x and 740x reductions in logical error rates for [[72,12,6]] and [[144,12,12]] BB codes at realistic physical error rates. For the distance 5 surface code at physical noise p=0.003, our neural post-selector achieves logical error suppression comparable to the leading complementary gap method without running the decoder.

quant-pharXiv:2610.00504•Oct 2, 2026•0 citations

Graph Neural Network Decoding of Surface Codes with Diagonally Correlated Two-Qubit Z Errors

Yinghui Ge, Shu Wang, Mengxin Li

Fault-tolerant quantum computing critically relies on quantum error correction. We study surface-code decoding with diagonally correlated two-qubit $\mathbf{Z}$ errors, a structured noise model that breaks assumptions leveraged by MinimumWeight Perfect Matching (MWPM). We develop a graph neural network (GNN) decoder based on learned message passing and benchmark it against a tuned MWPM baseline informed by the same noise statistics. In code-capacity simulations at code distances 3, 5, and 7, the GNN achieves consistently lower logical error rates than MWPM across the tested range of pair-error probabilities. The GNN correction threshold is about 2.5%, surpassing the 2.4% achieved by the MWPM baseline. These results indicate that data-driven message passing can adapt to complex, geometry-dependent noise without hand-crafted correlation models, thereby reducing reliance on manual model specification for quantum error correction.

International Symposium on Computer and Information Processing Technology (ISCIPT)•Sep 12, 2025•0 citations

Neural Minimum Weight Perfect Matching for Quantum Error Codes

Yotam Peled, David Zenati, Eliya Nachmani

Realizing the full potential of quantum computation requires Quantum Error Correction (QEC). QEC reduces error rates by encoding logical information across redundant physical qubits, enabling errors to be detected and corrected. A common decoder used for this task is Minimum Weight Perfect Matching (MWPM) a graph-based algorithm that relies on edge weights to identify the most likely error chains. In this work, we propose a data-driven decoder named Neural Minimum Weight Perfect Matching (NMWPM). Our decoder utilizes a hybrid architecture that integrates Graph Neural Networks (GNNs) to extract local syndrome features and Transformers to capture long-range global dependencies, which are then used to predict dynamic edge weights for the MWPM decoder. To facilitate training through the non-differentiable MWPM algorithm, we formulate a novel proxy loss function that enables end-to-end optimization. Our findings on the toric code under depolarizing noise demonstrate thresholds of 17.9% and 10.95%, nearing the 18.9% and 11.0% maximum likelihood bounds, highlighting the advantage of hybrid decoders that combine the predictive capabilities of neural networks with the algorithmic structure of classical matching.

quant-pharXiv:2601.00242•Jan 2, 2026•3 citations
We present POLYMECHANON, a graph neural network (GNN) decoder for quantum error correction whose only input is the detection error model (DEM) of a quantum code under a given noise model. We represent the DEM as a tripartite graph of detectors, error mechanisms and logical observables, where every input feature is computed by using the quantum code as data rather than design choice. In this way, the same architecture decodes in principle any stabiliser code, under any noise model that can be expressed as a detection error model, once trained on the DEM. We test this approach along four directions. Firstly, on the rotated surface code the decoder outperforms correlated MWPM under both phenomenological and circuit-level noise, with up to 25%25\%25% fewer logical failures. Secondly, on a family of high-rate qLDPC codes it matches BP+OSD on the smaller codes and surpasses it on the larger ones, with up to 16%16\%16% fewer logical failures on [ ⁣[130,4,6] ⁣][\![130,4,6]\!][[130,4,6]]. Thirdly, its decoding time does not depend on the physical error rate, whereas that of BP+OSD grows with it: on [ ⁣[130,4,6] ⁣][\![130,4,6]\!][[130,4,6]] its effective cost per shot is of the order of a few ms on a single GPU against a few tens of milliseconds for BP+OSD on a single CPU core, and its fixed computational graph makes it a candidate for real-time decoding on neutral-atom processors. Finally, a single model trained across codes of different families outperforms uncorrelated MWPM on the graph-like codes seen during training and stays within 10%10\%10% of BP+OSD on the others, while it tends to fail to generalize to unseen codes, particularly larger ones. Its probabilistic output enables confidence-based post-selection, lowering the logical error rate by more than an order of magnitude on the surface code while keeping more than 90%90\%90% of the shots. Since only the DEM changes, new codes and noise models can be decoded without redesigning the decoder.
The paper asks whether a neural quantum-error-correction decoder can use a common architecture across stabiliser-code families and noise models by operating directly on a detection error model (DEM). POLYMECHANON represents the DEM as a tripartite graph of detectors, error mechanisms and logical observables. A recurrent message-passing GNN uses syndromes, fault priors and DEM-derived features, including detector coordinates, to predict logical flips. Most benchmarks train separate weights for each code and noise model.
Simulated memory-ZZZ experiments use r=dr=dr=d syndrome rounds and compare decoders on identical shots. Against correlated MWPM, the GNN reduces logical failures by approximately 161616–24%24\%24% on rotated surface codes with d=3,5,7,9d=3,5,7,9d=3,5,7,9 under phenomenological noise, and 101010–25%25\%25% for d=3,5,7d=3,5,7d=3,5,7 under circuit-level noise. On phenomenological LaCross codes encoding four logical qubits, performance progresses from parity with BP+OSD at [[34,4,3]][[34,4,3]][[34,4,3]] to 16%16\%16% fewer failures at [[130,4,6]][[130,4,6]][[130,4,6]]. It remains approximately 4%4\%4% worse on [[65,9,4]][[65,9,4]][[65,9,4]]. Confidence-based post-selection reduces surface-code logical errors by factors of 141414–404040, retaining over 93%93\%93% of shots for d≥5d\ge5d≥5 at the reported operating point.
Inference has fixed, syndrome-independent computation. For [[130,4,6]][[130,4,6]][[130,4,6]], effective per-shot cost is 5.15.15.1 ms on an H200 GPU versus 262626–383838 ms for BP+OSD on one CPU core; this is not a hardware-matched comparison or a streaming demonstration. A shared model trained on fifteen codes approaches classical baselines on training codes, but transfer deteriorates on larger unseen graphs and fails from phenomenological to circuit-level noise. Real-time implementation and broader generalisation remain open.
Graph neural network (GNN) decoders for quantum error correction have historically been locked to specific code families. The POLYMECHANON preprint [1,2] proposes a decoder whose sole input is the detection error model (DEM) — a tripartite graph of detectors, error mechanisms, and logical observables — making the code data rather than an architectural design choice. This paper provides an independent, arithmetic-first assessment of that claim. We convert the reported headline numbers into concrete quantities: a 25% reduction in logical failures versus correlated MWPM on the rotated surface code corresponds to an improvement factor of 0.75, which under the standard scaling ansatz p_L ∝ (p/p_th)^⌈d/2⌉ is equivalent to a relative pseudo-threshold improvement of ≈10.06% at d = 5 and ≈7.46% at d = 7; a 16% reduction on the [[130,4,6]] qLDPC code corresponds to a factor of 0.84 and an equivalent threshold improvement of ≈5.98%. The reported latency advantage ("a few ms per shot on a single GPU" versus "a few tens of ms" for BP+OSD on a CPU core) would bound the speedup in [4×, 25×], midpoint ≈10×, with an explicit hardware-asymmetry caveat — but this latency analysis is conditional on claims not verifiable in the available abstract record of [1,2]. We derive DEM graph sizes for canonical cases (441 detectors, 1,337 mechanisms, 2,681 edges at d = 8, R = 8 under stated conventions), prove a cheap non-isomorphism certificate between surface-code and qLDPC DEMs via part-size vectors, and show that the claimed post-selection result (>10× error reduction at >90% shot retention) would arithmetically require discarded shots to fail at ≈9.1× the base rate — a strong, testable separability condition, conditional on a claim not verifiable in the available abstract record of [1,2]. We identify size-generalization, DEM fidelity, and hardware-fair latency comparison as the principal open risks, and propose falsification experiments for each. ## 1. Introduction Fault-tolerant quantum Full text and updates: papers.qnfo.org/papers/code-agnostic-graph-neural-network-decoding-from-detection-error-models-a-reconc/
Quantum computers can solve selected problems more efficiently than classical computers, but current devices are limited by high physical error rates. Quantum Error Correction (QEC) mitigates this by encoding many physical qubits into a logical qubit, with the surface code among the most widely studied approaches. Since syndrome measurements are produced continuously, the decoder must process them fast enough to avoid becoming a system bottleneck, making real-time decoding essential for fault-tolerant quantum computing. While most state-of-the-art real-time decoders rely on Minimum-Weight Perfect Matching (MWPM), we instead use a high-accuracy Graph Neural Network (GNN) that trades higher computational cost for lower logical error rates. To make this GNN practical for real-time decoding, we apply algorithm-hardware co-design. We reduce complexity through hardware-guided pruning and retraining, producing two hardware-friendly models that reduce parameter count by 3.1×3.1\times3.1× and 6.5×6.5\times6.5×. These target, respectively, an average decoding latency of one syndrome cycle and a worst-case latency within one syndrome cycle. We further reduce hardware cost using input-graph filtering and post-training quantization. Based on these optimized models, we propose an FPGA-based architecture for low-latency inference and real-time decoding. Evaluated on surface codes up to distance 7 under circuit-level noise at physical error rate p=10−3p=10^{-3}p=10−3, our decoder outperforms MWPM in decoding accuracy for both average-latency and max-latency settings. It reduces logical error rate by 40% at 1μs1μs1μs average latency, and by 13% under a strict 1μs1μs1μs deadline.
Quantum error correction is essential to achieve fault-tolerant quantum computation in the presence of noisy qubits. Among the most promising approaches to quantum error correction is the surface code, thanks to a scalable two-dimensional architecture, only nearest-neighbor interactions, and a high error threshold. Decoding the surface code, i.e. finding the most likely error chain given a syndrome measurement outcome is a computationally complex task. Traditional decoders rely on classical algorithms, which, especially for larger systems, can be slow and may not always converge to the optimal solution. This thesis presents a novel approach to decoding the surface code using graph neural networks. By mapping the syndrome measurements to a graph and performing graph classification, we find that the graph neural networks can predict the most likely error configuration with high accuracy. Our results show that the GNN-based decoder outperforms the classic minimum weight perfect matching (MWPM) decoder in terms of accuracy. With a phenomenological noise model with depolarizing noise and perfect syndrome measurements, our networks beat MWPM up to code-size 15 across all relevant error rates. Furthermore, the GNN is capable of surpassing MWPM under circuit-level noise up to code size 7. We also show that training the network on repetition code data from a recent experiment [Google Quantum AI, Nature 614, 676 (2023)] produces per-step error rates comparable to those achieved with a matching decoder specifically adapted to the error rates of the physical qubits. This indicates that graph neural network decoders are capable of learning the underlying error distribution on the qubits. Our findings advance the field of quantum error correction and provide a promising new direction for the development of efficient decoding algorithms.
Post-selection improves the logical reliability of quantum computation by rejecting shots which are likely to result in logical failure. We introduce graph neural networks that predict decoder failure without additional decoder executions, using only syndromes, and for high-rate quantum low-density parity-check (qLDPC) codes, existing belief-propagation posteriors. We evaluate rotated surface and bivariate bicycle (BB) code memories under uniform depolarising circuit-level noise. Retaining 90% of shots gives approximately 3700x and 740x reductions in logical error rates for [[72,12,6]] and [[144,12,12]] BB codes at realistic physical error rates. For the distance 5 surface code at physical noise p=0.003, our neural post-selector achieves logical error suppression comparable to the leading complementary gap method without running the decoder.
Fault-tolerant quantum computing critically relies on quantum error correction. We study surface-code decoding with diagonally correlated two-qubit Z\mathbf{Z}Z errors, a structured noise model that breaks assumptions leveraged by MinimumWeight Perfect Matching (MWPM). We develop a graph neural network (GNN) decoder based on learned message passing and benchmark it against a tuned MWPM baseline informed by the same noise statistics. In code-capacity simulations at code distances 3, 5, and 7, the GNN achieves consistently lower logical error rates than MWPM across the tested range of pair-error probabilities. The GNN correction threshold is about 2.5%, surpassing the 2.4% achieved by the MWPM baseline. These results indicate that data-driven message passing can adapt to complex, geometry-dependent noise without hand-crafted correlation models, thereby reducing reliance on manual model specification for quantum error correction.
Realizing the full potential of quantum computation requires Quantum Error Correction (QEC). QEC reduces error rates by encoding logical information across redundant physical qubits, enabling errors to be detected and corrected. A common decoder used for this task is Minimum Weight Perfect Matching (MWPM) a graph-based algorithm that relies on edge weights to identify the most likely error chains. In this work, we propose a data-driven decoder named Neural Minimum Weight Perfect Matching (NMWPM). Our decoder utilizes a hybrid architecture that integrates Graph Neural Networks (GNNs) to extract local syndrome features and Transformers to capture long-range global dependencies, which are then used to predict dynamic edge weights for the MWPM decoder. To facilitate training through the non-differentiable MWPM algorithm, we formulate a novel proxy loss function that enables end-to-end optimization. Our findings on the toric code under depolarizing noise demonstrate thresholds of 17.9% and 10.95%, nearing the 18.9% and 11.0% maximum likelihood bounds, highlighting the advantage of hybrid decoders that combine the predictive capabilities of neural networks with the algorithmic structure of classical matching.