Codebook-Anchored Prediction Across Physiological Views

Physiological sensors capture related but non-equivalent views of the same cardiovascular interval. Cross-view reconstruction is difficult because the inverse mapping is ambiguous and continuous latent spaces provide no stable correspondence across sensors. We introduce \method, a codebook-anchored predictor that learns a shared four-level residual-vector-quantized (RVQ) tokenizer and freezes its latent vocabulary during cross-view prediction. Modality-specific encoders and decoders retain view-specific signal structure, while nearest-codeword projection constrains predicted target latents before waveform decoding. We use a fixed subject-disjoint split of MIMIC-IV Waveform v0.1.0 with 138/20/40 train/validation/test subjects. Against the strongest evaluated external baseline, reduces subject-level PPG-to-ECG RMSE from $0.526$ to $0.493$ and increases R-peak F1 from $0.704$ to $0.739$. Under matched codebook parameter capacity, four-level RVQ reduces tokenizer RMSE from $0.171$ to $0.070$ relative to flat VQ. Using the same predictor checkpoint, nearest-codeword projection improves pooled-window F1 from $0.792$ to $0.827$. The same interface supports 25-to-250/500-Hz ECG reconstruction with R-peak F1 of $0.918/0.912$. In conclusion, these results show that our two-stage architecture supports both cross-sensor and cross-rate physiological reconstruction through a shared, frozen RVQ latent space within the evaluated MIMIC-IV cohort.