# Digit Classification on Shuffled MNIST (val)

Source: [Digit Classification on Shuffled MNIST (val)](<https://www.sota2.com/research/sota/digit-classification-on-shuffled-mnist-val>)

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

Data updated: 2026-02-26T05:34:18.411Z

Evaluation of Digit Classification performance on the validation split of the Shuffled MNIST dataset, measured using Kendall's tau.

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 | Digit Classification |
| Dataset (including any stated split) | Shuffled MNIST (val) |
| Metric | Accuracy (Kendall's tau) |
| 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

- [Accuracy (Kendall's tau)](<https://www.sota2.com/research/sota/digit-classification-on-shuffled-mnist-val.md?metric=Accuracy%20(Kendall%27s%20tau)>): Higher is better; unit: SCALAR.

- [Validation Accuracy](<https://www.sota2.com/research/sota/digit-classification-on-shuffled-mnist-val.md?metric=Validation%20Accuracy>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy (Kendall's tau) | Result date | Report paper |
| --- | --- | --- | --- |
| Mean Entropy | 1 | Not recorded | 68fa5b661e209131ce9c7f5b |
| Mean MI | 1 | Not recorded | 68fa5b661e209131ce9c7f5b |
| Frobenius-Norm | 1 | Not recorded | 68fa5b661e209131ce9c7f5b |
| Path-Norm | 1 | Not recorded | 68fa5b661e209131ce9c7f5b |
| 2-Norm | 0.8 | Not recorded | 68fa5b661e209131ce9c7f5b |

### Mean Entropy

Accuracy (Kendall's tau): 1. Result ID: 698c61ee37894ef7d9cdfcfe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5b661e209131ce9c7f5b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5b661e209131ce9c7f5b.md>)

[Implementation](<https://rachitbansal.github.io/information-measures>)

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

### Mean MI

Accuracy (Kendall's tau): 1. Result ID: 698c61ee37894ef7d9cdfcff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5b661e209131ce9c7f5b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5b661e209131ce9c7f5b.md>)

[Implementation](<https://rachitbansal.github.io/information-measures>)

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

### Frobenius-Norm

Accuracy (Kendall's tau): 1. Result ID: 698c61ee37894ef7d9cdfd01.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5b661e209131ce9c7f5b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66cd1e209131cea126b2.md>)

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

### Path-Norm

Accuracy (Kendall's tau): 1. Result ID: 698c61ee37894ef7d9cdfd02.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5b661e209131ce9c7f5b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66cd1e209131cea126b2.md>)

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

### 2-Norm

Accuracy (Kendall's tau): 0.8. Result ID: 698c61ee37894ef7d9cdfd00.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5b661e209131ce9c7f5b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66cd1e209131cea126b2.md>)

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

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