# Uncertainty Calibration on MN40

Source: [Uncertainty Calibration on MN40](<https://www.sota2.com/research/sota/uncertainty-calibration-on-mn40>)

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

Data updated: 2026-02-26T05:41:20.794Z

Evaluation of model uncertainty calibration performance on the MN40 dataset, typically measured using Expected Calibration Error (ECE).

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 Calibration |
| Dataset (including any stated split) | MN40 |
| Metric | ECE |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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

- [ECE](<https://www.sota2.com/research/sota/uncertainty-calibration-on-mn40.md?metric=ECE>): Lower is better; unit: PERCENT.

## Recorded results

| Method | ECE | Result date | Report paper |
| --- | --- | --- | --- |
| SageMix | 2.2 | Not recorded | 68fa6da11e209131cea3afab |
| PointMixup | 2.4 | Not recorded | 68fa6da11e209131cea3afab |
| Vanilla | 18.3 | Not recorded | 68fa6da11e209131cea3afab |
| RSMix | 24.2 | Not recorded | 68fa6da11e209131cea3afab |

### SageMix

ECE: 2.2. Result ID: 698fb0c13a6c314849fb25ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da11e209131cea3afab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da11e209131cea3afab.md>)

[Implementation](<https://github.com/mlvlab/SageMix>)

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

### PointMixup

ECE: 2.4. Result ID: 698fb0c13a6c314849fb25aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da11e209131cea3afab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68251e209131cea1a427.md>)

[Implementation](<https://github.com/yunlu-chen/PointMixup/>)

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

### Vanilla

ECE: 18.3. Result ID: 698fb0c13a6c314849fb25a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da11e209131cea3afab.md>)

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

### RSMix

ECE: 24.2. Result ID: 698fb0c13a6c314849fb25ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da11e209131cea3afab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697d1e209131cea2269c.md>)

[Implementation](<https://github.com/dogyoonlee/RSMix>)

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

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