# Uncertainty Mass Concentration on CIFAR-10

Source: [Uncertainty Mass Concentration on CIFAR-10](<https://www.sota2.com/research/sota/uncertainty-mass-concentration-on-cifar-10>)

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

Data updated: 2026-02-26T06:08:01.690Z

Evaluation of model uncertainty using Mass Concentration metrics (VGMU, EPJS, EPKL, EU) on the standard CIFAR-10 dataset.

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 Mass Concentration |
| Dataset (including any stated split) | CIFAR-10 |
| Metric | VGMU |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

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

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

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

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

## Recorded results

| Method | VGMU | Result date | Report paper |
| --- | --- | --- | --- |
| LLE | 0.885 | Not recorded | 698abbcac97a0b3e3b5de175 |
| MCD | 0.895 | Not recorded | 698abbcac97a0b3e3b5de175 |
| MCD-LLE | 0.907 | Not recorded | 698abbcac97a0b3e3b5de175 |

### LLE

VGMU: 0.885. Result ID: 6998dcc05698665ec440d070.

[Reporting paper](<https://www.sota2.com/research/paper/698abbcac97a0b3e3b5de175.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72eb1e209131cea59323.md>)

Recorded evaluation configuration: {"Ensemble Size (M)":"10"}. This record does not assert independent reproduction.

### MCD

VGMU: 0.895. Result ID: 6998dcc05698665ec440d06f.

[Reporting paper](<https://www.sota2.com/research/paper/698abbcac97a0b3e3b5de175.md>)

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

Recorded evaluation configuration: {"Ensemble Size (M)":"10"}. This record does not assert independent reproduction.

### MCD-LLE

VGMU: 0.907. Result ID: 6998dcc05698665ec440d071.

[Reporting paper](<https://www.sota2.com/research/paper/698abbcac97a0b3e3b5de175.md>)

Recorded evaluation configuration: {"Ensemble Size (M)":"100"}. This record does not assert independent reproduction.

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