Qubit-centric Transformer for Surface Code Decoding

Seong-Joon Park; Hee-Youl Kwak; Yongjune Kim

quant-phOct 13, 2025

Qubit-centric Transformer for Surface Code Decoding

Authors: Seong-Joon Park, Hee-Youl Kwak, Yongjune Kim

Organizations: Samsung Electronics Company, Ltd., Suwon 16677, South Korea · Institute of Artificial Intelligence, Pohang University of Science and Technology (POSTECH), Pohang 37673, South Korea · Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, South Korea · Department of Electrical Engineering, Pohang University of Science and Technology (POSTECH), Pohang 37673, South Korea

Abstract

For reliable large-scale quantum computation, quantum error correction (QEC) is essential to protect logical information distributed across multiple physical qubits. Taking advantage of recent advances in deep learning, neural network-based decoders have emerged as a promising approach to improve the reliability of QEC. We propose the qubit-centric transformer (QCT), a novel and universal QEC decoder based on a transformer architecture with a qubit-centric attention mechanism. Our decoder transforms input syndromes from the stabilizer domain into qubit-centric tokens via a specialized embedding strategy. These qubit-centric tokens are processed through attention layers to effectively identify the underlying logical error. Furthermore, we introduce a graph-based masking method that incorporates the topological structure of quantum codes, enforcing attention toward relevant qubit interactions. Across various code distances for surface codes, QCT achieves state-of-the-art decoding performance, significantly outperforming existing neural decoders and the belief propagation (BP) with ordered statistics decoding (OSD) baseline. Notably, QCT achieves a high threshold of 18.1% under depolarizing noise, which closely approaches the theoretical bound of 18.9% and surpasses both the BP+OSD and the minimum-weight perfect matching (MWPM) thresholds. This qubit-centric approach provides a scalable and robust framework for surface code decoding, advancing the path toward fault-tolerant quantum computing.

Figures & tables

Figure 1: Illustration of the topological structure of the surface code with distance $d=3$ (left) and the syndrome extraction circuits (right).

Figure 2: Illustration of the high-level decoding methodology treating decoding as a classification problem. An arbitrary physical error

E

can be decomposed into

E=S\cdot T\cdot L

Figure 3: The proposed QCT architecture. QCT processes the input syndrome vector $\mathbf{s}$ through the embedding layer and merging layer, followed by $N$ transformer blocks, to finally predict the logical operator.

Figure 4: Illustration of the embedding process for physical qubit $q_{5}$ in a $d=3$ surface code.

Figure 5: Illustration of the merging layer. The input consists of $n$ decoupled Z-tokens $\{\phi^{Z}_{i}\}_{i=1}^{n}$ (yellow) and $n$ decoupled X-tokens $\{\phi^{X}_{i}\}_{i=1}^{n}$ (blue) separately. This process fuses the decoupled embeddings into unified qubit tokens $\mathbf{x}^{(0)}$ .

Figure 6: Illustration of the structure-aware masks

M

for surface codes used in QCT. The left figure shows the mask for

d=3

surface code, and the right figure shows the mask for

d=5

surface code.

Panel of Figure 7 — Figure 7: Performance under the code-capacity noise model. Comparison of the proposed QCT decoder against MWPM, FFNN, and CNN decoders for code distances (a) $d=5$ , (b) $d=7$ , and (c) $d=9$ . The MWPM, FFNN, and CNN results are taken from [ 23 ] .

Figure 8: Performance under the code-capacity noise model. Comparison of the proposed QCT decoder against the BP+OSD baseline for code distances

d\in\{5,7,9,11,13\}

. At least

1000

logical errors are collected for

d\in\{5,7,9\}

and at least

500

for

d\in\{11,13\}

. Error bars indicate 95% Wilson confidence intervals. The values at

p=0.01

and

p=0.02

are obtained by extrapolation and are shown without markers.

Figure 9: Error suppression factor

\Lambda

under the code-capacity noise model, obtained from the LERs at

p=0.05

for QCT, BP+OSD, and MWPM. At least

1000

logical errors are collected for

d\in\{5,7,9\}

and at least

500

for

d\in\{11,13\}

. Error bars on the LER data indicate 95% Wilson confidence intervals.

Figure 10: Performance under the circuit-level noise model in terms of the LER normalized per round. At least

1000

logical errors are collected for each simulated data point, and error bars indicate 95% Wilson confidence intervals. The results at

p=0.001

are obtained by extrapolation and are shown without markers.

Figure 11: Error suppression factor

\Lambda_{5/7}

under the circuit-level noise model for QCT, standard MWPM, BP+OSD, and correlated MWPM. At least

1000

logical errors are collected for each simulated LER used to compute

\Lambda_{5/7}

; the values at

p=0.001

are based on extrapolated LERs and are shown without markers.

Panel of Figure 12 — Figure 12: Decoding performance of QCT under various configurations: (a) impact of the number of transformer blocks ( $N$ ), (b) effect of structure-aware masking, and (c) effect of the merging layer to decoding accuracy. At least $500$ logical errors are collected for each simulated data point, and error bars indicate 95% Wilson confidence intervals.

$d$	$3$	$5$	$7$	$9$	$11$	$13$
Code-capacity	–	1.61 M	1.61 M	1.62 M	1.63 M	1.64 M
Circuit-level	2.00 M	2.02 M	2.05 M	–	–	–

Table 1: Number of trainable parameters for the evaluated surface-code distances.

$d$	$3$	$5$	$7$
MWPM [ 10 ]	8.28%	10.36%	11.94%
FFNN [ 41 ]	9.77%	11.35%	12.49%
CNN [ 23 ]	9.80%	12.15%	13.26%
QCT (Proposed)	9.80%	13.27%	14.31%

Table 2: Comparison of the pseudo-thresholds for the proposed QCT against benchmark decoders (MWPM, FFNN, and CNN) on the surface code for distances

d=3,5,

and

7

under the code-capacity noise model. The results of MWPM, FFNN, CNN are from [ 23 ] .

Panel of Figure 13 — Figure 13: Threshold performance for surface codes with $d=5,7,9,11,13$ . (a) QCT. (b) BP+OSD. At least $1000$ logical errors are collected for $d\in\{5,7,9\}$ and at least $500$ for $d\in\{11,13\}$ . Error bars indicate 95% Wilson confidence intervals.

Explore similar work

Latency-Constrained Hardware-Aware Quantum Error Correction Co-Design with Adaptive Confidence-Gated Neural Decoding for the Rotated Surface Code
Jul 7, 2026Sumit ChongderQuantum Error Correction
Department of Physics, Quantum Information and Computation, Indian Institute of Technology Jodhpur, Jodhpur, Rajasthan 342037, India
Efficient foundation decoders for fault-tolerant quantum computing
Jun 25, 2026Ge Yan, Shanchuan Li, Shiyi Xiao +4Quantum Error Correction Post-Quantum Cryptography
College of Computing and Data Science, Nanyang Technological University, Singapore · Department of Electrical Engineering and Computer Science, Tokyo University of Agriculture and Technology, Koganei, Tokyo, Japan · School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China +2
Rethink the Role of Neural Decoders in Quantum Error Correction
May 12, 2026Ge Yan, Shanchuan Li, Yuxuan DuQuantum Error Correction Quantized
College of Computing and Data Science, Nanyang Technological University, Singapore 639798, Singapore · Department of Electrical Engineering and Computer Science, Tokyo University of Agriculture & Technology, Koganei, Tokyo, 184-8588, Japan · School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore 639798, Singapore

Jul 7, 2026, quant-phJ/K move · Enter open · S save

Latency-Constrained Hardware-Aware Quantum Error Correction Co-Design with Adaptive Confidence-Gated Neural Decoding for the Rotated Surface Code

Sumit Chongder

Department of Physics, Quantum Information and Computation, Indian Institute of Technology Jodhpur, Jodhpur, Rajasthan 342037, India

Quantum Error Correction

Open paper AskPDF arXiv

Real-time decoding is a major bottleneck in scaling quantum error correction (QEC) from noisy intermediate-scale quantum (NISQ) devices to fault-tolerant quantum computing. We present an adaptive confidence-gated decoding framework for the rotated surface code that treats decoding as a two-stage inference problem. A lightweight feed-forward neural network performs fast-path decoding for the majority of syndrome measurements, while only low-confidence predictions are escalated to a minimum-weight perfect matching (MWPM) refinement stage. We benchmark the framework on rotated surface codes with distances

d \in \{3,5,7,9,11\}

under circuit-level depolarising noise using the Stim stabiliser simulator. The evaluation characterises logical accuracy, confidence-controlled accuracy-latency trade-offs, decoding throughput, per-shot latency, and decoding-graph resource scaling. Routing only 3.3%-6.2% of syndromes to the refinement stage improves logical accuracy from 99.21% for the neural-only baseline to 99.81% at a confidence threshold of 0.95 while incurring only a bounded increase in average decoding cost. Neural-decoder throughput saturates near

4.6 \times 10^{5}

samples s

^{-1}

at batch size 512 on commodity CPU hardware, indicating that the neural fast path is not the dominant throughput bottleneck beyond code distance

d=7

. We release the complete benchmarking pipeline, trained models, raw benchmark data, and source code, and explicitly distinguish the experimentally validated contributions from the broader hardware-aware QEC co-design roadmap, including hardware-constrained code discovery, GPU-accelerated inference, and multi-noise optimisation, which remain directions for future work.

Abstract

Explore similar work

Latency-Constrained Hardware-Aware Quantum Error Correction Co-Design with Adaptive Confidence-Gated Neural Decoding for the Rotated Surface Code

Efficient foundation decoders for fault-tolerant quantum computing

Rethink the Role of Neural Decoders in Quantum Error Correction