# Unconditional Generation on 2D Turbulence (test)

Source: [Unconditional Generation on 2D Turbulence (test)](<https://www.sota2.com/research/sota/unconditional-generation-on-2d-turbulence-test>)

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

Data updated: 2026-06-11T10:26:31.855Z

Evaluation of models performing unconditional generation on the test split of the 2D Turbulence dataset, assessed using metrics related to IR, DO, and DD biases/spreads/returns.

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 | Unconditional Generation |
| Dataset (including any stated split) | 2D Turbulence (test) |
| Metric | IR Bias |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| 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

- [IR Bias](<https://www.sota2.com/research/sota/unconditional-generation-on-2d-turbulence-test.md?metric=IR%20Bias>): Lower is better; unit: SCALAR.

- [IR Spread](<https://www.sota2.com/research/sota/unconditional-generation-on-2d-turbulence-test.md?metric=IR%20Spread>): Lower is better; unit: SCALAR.

- [IR Return](<https://www.sota2.com/research/sota/unconditional-generation-on-2d-turbulence-test.md?metric=IR%20Return>): Higher is better; unit: SCALAR.

- [DO Bias](<https://www.sota2.com/research/sota/unconditional-generation-on-2d-turbulence-test.md?metric=DO%20Bias>): Lower is better; unit: SCALAR.

- [DO Spread](<https://www.sota2.com/research/sota/unconditional-generation-on-2d-turbulence-test.md?metric=DO%20Spread>): Lower is better; unit: SCALAR.

- [DO Return](<https://www.sota2.com/research/sota/unconditional-generation-on-2d-turbulence-test.md?metric=DO%20Return>): Higher is better; unit: SCALAR.

- [DD Bias](<https://www.sota2.com/research/sota/unconditional-generation-on-2d-turbulence-test.md?metric=DD%20Bias>): Lower is better; unit: SCALAR.

- [DD Spread](<https://www.sota2.com/research/sota/unconditional-generation-on-2d-turbulence-test.md?metric=DD%20Spread>): Lower is better; unit: SCALAR.

- [DD Return](<https://www.sota2.com/research/sota/unconditional-generation-on-2d-turbulence-test.md?metric=DD%20Return>): Higher is better; unit: SCALAR.

## Recorded results

| Method | IR Bias | Result date | Report paper |
| --- | --- | --- | --- |
| Model A | -0.1 | Not recorded | 6a2a4137d33dfb23e7839446 |
| Model B | -0.03 | Not recorded | 6a2a4137d33dfb23e7839446 |

### Model A

IR Bias: -0.1. Result ID: 6a2a8ca3fbc373592c285a92.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a4137d33dfb23e7839446.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Model B

IR Bias: -0.03. Result ID: 6a2a8ca3fbc373592c285a93.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a4137d33dfb23e7839446.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2a4137d33dfb23e7839446.md>)

Recorded evaluation configuration: {"Description":"Spectrally Regularized Latent Flow Matching"}. This record does not assert independent reproduction.

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