# Uncertainty Quantification on CIFAR-10

Source: [Uncertainty Quantification on CIFAR-10](<https://www.sota2.com/research/sota/uncertainty-quantification-on-cifar-10>)

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

Data updated: 2026-06-01T08:06:05.433Z

Evaluation of model uncertainty quantification performance on the CIFAR-10 dataset, focusing on variance-based metrics (V-ID, V-OOD) and Mutual Information (MI) scores, alongside LPPD and computational overhead (Time/Memory).

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 | Uncertainty Quantification |
| Dataset (including any stated split) | CIFAR-10 |
| Metric | V-ID |
| Unit | SCALAR |
| Direction | Higher 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

- [V-ID](<https://www.sota2.com/research/sota/uncertainty-quantification-on-cifar-10.md?metric=V-ID>): Higher is better; unit: SCALAR.

- [V-OOD](<https://www.sota2.com/research/sota/uncertainty-quantification-on-cifar-10.md?metric=V-OOD>): Higher is better; unit: SCALAR.

- [MI-ID](<https://www.sota2.com/research/sota/uncertainty-quantification-on-cifar-10.md?metric=MI-ID>): Higher is better; unit: SCALAR.

- [MI-OOD](<https://www.sota2.com/research/sota/uncertainty-quantification-on-cifar-10.md?metric=MI-OOD>): Higher is better; unit: SCALAR.

- [LPPD](<https://www.sota2.com/research/sota/uncertainty-quantification-on-cifar-10.md?metric=LPPD>): Higher is better; unit: SCALAR.

- [Total Time](<https://www.sota2.com/research/sota/uncertainty-quantification-on-cifar-10.md?metric=Total%20Time>): Lower is better; unit: TIME.

- [Memory (GB)](<https://www.sota2.com/research/sota/uncertainty-quantification-on-cifar-10.md?metric=Memory%20(GB)>): Lower is better; unit: SIZE.

## Recorded results

| Method | V-ID | Result date | Report paper |
| --- | --- | --- | --- |
| LL-GLM | 0.9216 | Not recorded | 6a1d1214dbd7150506f84007 |
| DE | 0.9201 | Not recorded | 6a1d1214dbd7150506f84007 |
| LLA | 0.911 | Not recorded | 6a1d1214dbd7150506f84007 |
| MC | 0.9069 | Not recorded | 6a1d1214dbd7150506f84007 |
| DNN-GLM | 0.9063 | Not recorded | 6a1d1214dbd7150506f84007 |
| SMS-UBU | 0.5608 | Not recorded | 6a1d1214dbd7150506f84007 |
| SWAG | 0.4909 | Not recorded | 6a1d1214dbd7150506f84007 |

### LL-GLM

V-ID: 0.9216. Result ID: 6a1d3d5cfbc373592c1642b6.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### DE

V-ID: 0.9201. Result ID: 6a1d3d5cfbc373592c1642b7.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63bc1e209131cea0084f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### LLA

V-ID: 0.911. Result ID: 6a1d3d5cfbc373592c1642b8.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bfe1e209131cea31830.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### MC

V-ID: 0.9069. Result ID: 6a1d3d5cfbc373592c1642ba.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62d31e209131ce9fb5ff.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### DNN-GLM

V-ID: 0.9063. Result ID: 6a1d3d5cfbc373592c1642b5.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c2f1e209131cea8ce7f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### SMS-UBU

V-ID: 0.5608. Result ID: 6a1d3d5cfbc373592c1642bb.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5d1a1e209131ce9d7298.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### SWAG

V-ID: 0.4909. Result ID: 6a1d3d5cfbc373592c1642b9.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e71e209131cea130c6.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

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