This paper introduces a hybrid decoding architecture that serially couples a normalized min-sum (NMS) decoder with reinforced ordered statistics decoding (OSD) to achieve near-maximum likelihood (ML) performance for short linear block codes. The framework incorporates several key innovations: a decoding information aggregation model that employs a convolutional neural network to refine bit reliability estimates for OSD using the soft-output trajectory of the NMS decoder; an adaptive decoding path for OSD, initialized by the arranged list of the most a priori likely tests algorithm and dynamically updated with empirical data; and a sliding window assisted model that enables early termination of test error patterns' traversal, curbing complexity with minimal performance loss. For short high-rate codes, a dedicated undetected error detector identifies erroneous NMS outcomes that satisfy parity checks, ensuring they are forwarded to OSD for correction. Extensive simulations on LDPC, BCH, and RS codes demonstrate that the proposed hybrid decoder delivers a competitive trade-off, achieving near-ML frame error rate performance while maintaining advantages in throughput, latency, and complexity over state-of-the-art alternatives.

翻译：本文提出一种混合解码架构，通过将归一化最小和（NMS）解码器与增强型有序统计解码（OSD）串行级联，实现短线性分组码的近似最大似然（ML）性能。该框架包含多项关键创新：采用卷积神经网络构建解码信息聚合模型，利用NMS解码器的软输出轨迹优化OSD的比特可靠性估计；基于先验最可能测试算法排序列表初始化OSD的自适应解码路径，并利用经验数据动态更新；引入滑动窗口辅助模型，支持测试错误模式遍历的早期终止，在性能损失最小化的同时有效控制复杂度。针对短高码率码，专用未检错检测器可识别满足奇偶校验的错误NMS解码结果，确保其被传送至OSD进行纠错。在LDPC码、BCH码和RS码上的大量仿真表明，所提出的混合解码器实现了优越的权衡，在获得近似ML帧错误率性能的同时，在吞吐量、时延和复杂度方面均优于现有先进方案。