发表机构
University of Gothenburg; Chalmers University of Technology（哥德堡大学; 查尔姆斯理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出模块化图递归神经解码器，可跨硬件、噪声和逻辑操作迁移，在IBM和谷歌硬件上优于或接近MWPM，并支持稳定性实验和晶格手术解码。
AI 中文摘要
神经解码器在量子纠错表面码存储实验中已实现高精度，但实际容错计算要求解码器能够跨设备、噪声条件和逻辑操作进行迁移。我们引入了一种为这一场景设计的模块化图递归解码器。它由可复用的局部综合征编码器构建，在模拟中预训练，并通过通用流程微调到硬件，仅在不同实验之间适配轻量级空间聚合。该解码器在常规存储基准上表现优异，在IBM Nighthawk代处理器上距离3和5时优于最小权重完美匹配（MWPM），并在谷歌的低于阈值硬件数据上接近AlphaQubit。随后，我们在同一IBM设备上测试了该框架在存储解码之外的两种场景。首先，在$X$型稳定性实验中，我们通过可变预读出旋转连续调整有效测量错误率，并在所得噪声范围内联合训练单个解码器。在整个扫描范围内，它匹配或优于MWPM，无需为每种设置单独校准解码器。其次，我们解码了两个距离3表面码补丁之间的$ZZ$合并晶格手术实验，相对于MWPM，在真实硬件上改善了合并结果与最终$ZZ$奇偶性之间的解码相关性。总之，这些实验证明了神经解码不仅可跨硬件移植，还可跨定性不同的表面码可观测量和逻辑操作移植，且模型可在单GPU学术资源上训练。
英文摘要
Neural decoders for quantum error correction have achieved high accuracy on surface code memory experiments, but practical fault-tolerant computation requires decoders that transfer across devices, noise conditions, and logical operations. We introduce a modular graph-recurrent decoder designed for this setting. Built from reusable local syndrome encoders, it is pretrained in simulation and fine-tuned to hardware using a common pipeline, with only lightweight spatial aggregation adapted between experiments. The decoder performs competitively on conventional memory benchmarks, outperforming minimum-weight perfect matching (MWPM) at distances 3 and 5 on an IBM Nighthawk-generation processor and closely approaching AlphaQubit on Google's below-threshold hardware data. We then test the framework in two settings beyond memory decoding on the same IBM device. First, in an $X$-type stability experiment, we continuously tune the effective measurement error rate using a variable pre-readout rotation and train a single decoder jointly across the resulting noise range. It matches or outperforms MWPM across the sweep without requiring a separately calibrated decoder for each setting. Second, we decode a $ZZ$-merge lattice-surgery experiment between two distance-3 surface-code patches, improving the decoded correlation between the merge outcome and the final $ZZ$ parity relative to MWPM on real hardware. Together, these experiments demonstrate neural decoding that is portable not only across hardware, but also across qualitatively different surface code observables and logical operations, using models trainable on single-GPU academic resources.
