# Learning latent dynamics on M-SP+F (mass-spring with friction) (test)

Source: [Learning latent dynamics on M-SP+F (mass-spring with friction) (test)](<https://www.sota2.com/research/sota/learning-latent-dynamics-on-m-sp-plus-f-mass-spring-with-friction-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:59:58.582Z

Evaluation of model performance on learning the latent dynamics associated with the M-SP+F system (mass-spring with friction), using the test split, measured by RMSE, PSNR, and SSIM.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Learning latent dynamics |
| Dataset (including any stated split) | M-SP+F (mass-spring with friction) (test) |
| Metric | RMSE |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 7 of 7 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [RMSE](<https://www.sota2.com/research/sota/learning-latent-dynamics-on-m-sp-plus-f-mass-spring-with-friction-test.md?metric=RMSE>): Lower is better; unit: PERCENT.

- [PSNR](<https://www.sota2.com/research/sota/learning-latent-dynamics-on-m-sp-plus-f-mass-spring-with-friction-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/learning-latent-dynamics-on-m-sp-plus-f-mass-spring-with-friction-test.md?metric=SSIM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | RMSE | Result date | Report paper |
| --- | --- | --- | --- |
| NODE | 2.64 | Not recorded | 68fa75391e209131cea668c6 |
| coRNN | 2.65 | Not recorded | 68fa75391e209131cea668c6 |
| GRU | 2.67 | Not recorded | 68fa75391e209131cea668c6 |
| CON | 3.03 | Not recorded | 68fa75391e209131cea668c6 |
| CFA-CON | 3.13 | Not recorded | 68fa75391e209131cea668c6 |
| MECH-NODE | 3.28 | Not recorded | 68fa75391e209131cea668c6 |
| RNN | 27.39 | Not recorded | 68fa75391e209131cea668c6 |

### NODE

RMSE: 2.64. Result ID: 699395293a6c314849170545.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66cb1e209131cea12502.md>)

[Implementation](<https://www.sota2.com/github.com/rtqichen/torchdiffeq>)

Recorded evaluation configuration: {"latent dimension":"4","input mapping":"removed","# Parameters":"3368"}. This record does not assert independent reproduction.

### coRNN

RMSE: 2.65. Result ID: 699395293a6c314849170544.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea22495.md>)

Recorded evaluation configuration: {"latent dimension":"4","input mapping":"removed","# Parameters":"40"}. This record does not assert independent reproduction.

### GRU

RMSE: 2.67. Result ID: 699395293a6c314849170543.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa617b1e209131ce9f462d.md>)

Recorded evaluation configuration: {"latent dimension":"4","input mapping":"removed","# Parameters":"248"}. This record does not assert independent reproduction.

### CON

RMSE: 3.03. Result ID: 699395293a6c314849170547.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

Recorded evaluation configuration: {"latent dimension":"4","input mapping":"removed","# Parameters":"34"}. This record does not assert independent reproduction.

### CFA-CON

RMSE: 3.13. Result ID: 699395293a6c314849170548.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

Recorded evaluation configuration: {"latent dimension":"4","input mapping":"removed","# Parameters":"34"}. This record does not assert independent reproduction.

### MECH-NODE

RMSE: 3.28. Result ID: 699395293a6c314849170546.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

Recorded evaluation configuration: {"latent dimension":"4","mechanical structure prior knowledge":"true","# Parameters":"3244"}. This record does not assert independent reproduction.

### RNN

RMSE: 27.39. Result ID: 699395293a6c314849170542.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75391e209131cea668c6.md>)

Recorded evaluation configuration: {"latent dimension":"4","input mapping":"removed","# Parameters":"88"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
