做物理信号预测或自回归模型长程展开的开发者，这篇论文用严谨的消融实验揭示了多 token 预测的关键作用，值得仔细看实验设计。
该研究以合成三分量地震图为例，探讨自回归序列模型在预测振荡物理信号（如地震波、引力波）时，长程展开的稳定性问题。研究发现，误差累积会导致相位漂移，而逐点指标无法检测。通过 SeismoGPT 模型的受控消融实验，多 token 预测是稳定展开的关键因素，几乎贡献了全部改进；地平线嵌入混合预测头和跨地平线 STFT 幅度相干损失可带来微小但一致的增益。性能严重依赖于上下文比率阈值接近1（约等于观测信号的 P-S 间隔），低于此阈值时展开泛化崩溃。主要的残留失败是极性反转，表明相位感知目标函数是下一步的自然方向。
When Do Autoregressive Sequence Models Forecast Physical Wavefields? A Controlled Study on Synthetic Seismograms
Long-horizon autoregressive forecasting of oscillatory physical signals, such as seismograms, gravitational-wave strain, and similar wavefields is limited by error accumulation: as a causal model is fed its own outputs over hundreds of steps, small per-step errors compound into phase drift that pointwise metrics fail to detect. We ask when such rollout stays stable, using synthetic three-component seismograms as a physically structured testbed and the \textsc{SeismoGPT} autoregressive forecaster as the model under study. Through controlled, intra-architecture ablations evaluated on free-running rollout with paired significance tests, we isolate the contribution of each design choice. Multi-token prediction is the dominant stabilizer, accounting for almost the entire improvement over a single-token baseline ($+0.040$ median NCC); a horizon-embedding hybrid prediction head and a cross-horizon STFT-magnitude coherence loss each add a small but consistent further gain. Performance depends sharply on a context-ratio threshold near one, roughly the full P-S interval of observed signal, below which rollout generalization collapses. The dominant residual failure is a polarity inversion that a magnitude-based spectral loss cannot, by construction, penalize, identifying phase-aware objectives as the natural next step. We frame this as a controlled study of rollout stability on oscillatory wavefields, not a benchmark of forecasting architectures.