AI 中文总结
针对奇偶校验等确定性状态跟踪任务，提出仅传播隐藏状态的复状态传播器（CSP），结合Focal Loss在基准任务上实现100%准确率与完美F1分数。
AI 中文摘要
基于Transformer的架构在序列建模中占据主导地位，这很大程度上得益于注意力机制的表达能力。然而，对于一类确定性状态跟踪任务——如奇偶校验、模计数和括号匹配——注意力可能是大材小用。在本文中，我们证明仅状态传播就足够。我们提出了复状态传播器（Complex State Propagator, CSP），这是一种极简的循环架构，仅在层间传播隐藏状态，中间步骤无输出投影。状态表示为复值向量，通过复域中依赖输入的旋转进行更新。为实现深度传播而无梯度消失或退化，我们引入了块级跳跃连接，以及序列边界处的逐元素复归一化和SiLU激活。结合Focal Loss，CSP在基准任务上达到100%准确率和完美的F1分数。
英文摘要
Despite the dominance of massive language models, leading paradigms like Transformers and Mamba fundamentally falter at continuous deterministic state tracking, suffering from catastrophic out-of-distribution (OOD) collapse when generalizing to extended sequences. To shatter this bottleneck, we present the \textbf{Complex State Propagator (CSP)}, a radically minimalist recurrent paradigm that operates strictly on the complex phase manifold without intermediate output projections, amplitude modulations, or per-step non-linearities. Crucially, we unveil an unprecedented architectural marvel: \textbf{the phase signal survives extreme depth with absolute zero informational attenuation}. By implementing an exact four-quadrant \textbf{Coordinate-to-Phase (C-to-2)} transformation governed by the \(\text{atan2}(y, x)\) activation, CSP forces the continuous optimization landscape to seamlessly align with discrete cyclic groups. Remarkably, with a mere \textbf{3-layer hidden topology} trained on short inputs (length 16),CSP demonstrates absolute mathematical purity, achieving a nearly $100\%$ validation accuracy and F1-score when generalized to a $4\times$ prolonged OOD length of 64 on the canonical Mod-3 tracking task. Our work establishes complex-valued, pure-phase propagation not merely as a compact alternative, but as a dominant frontier that beats heavy networks at a fraction of their size.
