In standard Transformer architectures, semantic importance is often conflated with activation magnitude, obscuring the geometric structure of latent representations. To disentangle these factors, we introduce PRISM, a complex-valued architecture designed to isolate the computational role of phase. By enforcing a strict unit-norm constraint (|z| = 1) and replacing attention with gated harmonic convolutions, the model is compelled to utilize subtractive interference in the frequency domain to suppress noise, rather than relying on magnitude-based gating. We utilize this constrained regime to demonstrate that a hybrid architecture - fusing phase-based routing with standard attention - achieves superior parameter efficiency and representation quality compared to unconstrained baselines. Mechanistically, we identify geometric phase clustering, where tokens naturally self-organize to resolve semantic ambiguities. This establishes an O(N log N) reasoning framework based on spectral interference, providing an algorithmic existence proof that subtractive logic is a sufficient primitive for deep reasoning.

翻译：在标准Transformer架构中，语义重要性常与激活幅度相混淆，从而模糊了潜在表示的几何结构。为厘清这些因素，我们提出了PRISM——一种专为分离相位计算作用而设计的复值架构。通过强制执行严格的单位范数约束（|z| = 1）并以门控谐波卷积替代注意力机制，该模型被迫利用频域中的相消干涉来抑制噪声，而非依赖基于幅度的门控机制。我们利用这一约束体系证明：融合相位路由与标准注意力的混合架构，在参数效率和表示质量上均优于无约束基线。从机制角度，我们发现了几何相位聚类现象——词元通过自组织方式自然消解语义歧义。这建立了一个基于频谱干涉的O(N log N)推理框架，从算法存在性层面证明相消逻辑足以作为深度推理的基本原语。