# Uncertainty Calibration on Tiny ImageNet OOD (test)

Source: [Uncertainty Calibration on Tiny ImageNet OOD (test)](<https://www.sota2.com/research/sota/uncertainty-calibration-on-tiny-imagenet-ood-test>)

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

Data updated: 2026-02-26T05:59:49.477Z

Evaluation of model uncertainty calibration performance on the Out-of-Distribution (OOD) test set of the Tiny ImageNet dataset, typically measured using metrics like RMS Calibration Error and MAD Calibration Error.

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) | Tiny ImageNet OOD (test) |
| Metric | RMS Calibration Error |
| Unit | PERCENT |
| 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

- [RMS Calibration Error](<https://www.sota2.com/research/sota/uncertainty-calibration-on-tiny-imagenet-ood-test.md?metric=RMS%20Calibration%20Error>): Lower is better; unit: PERCENT.

- [MAD Calibration Error](<https://www.sota2.com/research/sota/uncertainty-calibration-on-tiny-imagenet-ood-test.md?metric=MAD%20Calibration%20Error>): Lower is better; unit: PERCENT.

## Recorded results

| Method | RMS Calibration Error | Result date | Report paper |
| --- | --- | --- | --- |
| NAC-UE | 31.99 | Not recorded | 68fa72711e209131cea56542 |
| Temperature | 40.25 | Not recorded | 68fa72711e209131cea56542 |
| MSP | 48.01 | Not recorded | 68fa72711e209131cea56542 |

### NAC-UE

RMS Calibration Error: 31.99. Result ID: 6992380c3a6c3148490d6521.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56542.md>)

[Implementation](<https://github.com/BierOne/ood_coverage>)

Recorded evaluation configuration: {"Foundation Model":"CIFAR-10 Pre-trained"}. This record does not assert independent reproduction.

### Temperature

RMS Calibration Error: 40.25. Result ID: 6992380c3a6c3148490d6520.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa638b1e209131ce9ff6d1.md>)

Recorded evaluation configuration: {"Foundation Model":"CIFAR-10 Pre-trained"}. This record does not assert independent reproduction.

### MSP

RMS Calibration Error: 48.01. Result ID: 6992380c3a6c3148490d651f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56542.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e41e209131cea0731a.md>)

[Implementation](<https://www.sota2.com/github.com/hendrycks/error-detection>)

Recorded evaluation configuration: {"Foundation Model":"CIFAR-10 Pre-trained"}. This record does not assert independent reproduction.

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