# ECG CR vs. Fidelity

This page summarizes how compression ratio (CR) trades off against signal- and physiology-level fidelity for the v1 RVQ goldens. The **Effective CR** column is populated when an entropy-prior run is available; otherwise, the codec CR is the release-facing operating point. CRs are reported alongside the [noise-aware metrics](https://ambiqai.github.io/compressionkit/validation-scorecard/) so it is easy to inspect the difference between waveform faithfulness, clean-reference fidelity, and physiological metric preservation.

## Headline summary (all samples)

## Noise-stratified detail (clean / median / noisy tertiles)

Tertiles are formed from a band-power noise estimate over each input recording; *clean* is the lowest-noise third, *noisy* is the highest.

## How to read these results

- **Faithful PRD** compares reconstruction with the recorded input; **Truth PRD** uses the fixture's clean reference. Their difference depends on the input noise and reference construction.
- **PRDN-noise** is a noise-normalized error measure. Interpret it with waveform and physiological errors, not as proof of denoising by itself.
- **HR MAE** and band error describe the measurements in this evaluation. Acceptance thresholds depend on your application.
- **Seam ratio** reports boundary energy relative to the window center. A missing value means no result was reported.
- Sample counts and noise-bucket composition can differ across ratios. Preserve that context when comparing candidates.

See the [validation scorecard](https://ambiqai.github.io/compressionkit/validation-scorecard/) for definitions and [customer evidence](https://ambiqai.github.io/compressionkit/customer-evidence/) for a compact comparison.