# Handwritten digit classification on MNIST non-i.i.d. partitioning, Regular graph 34 (test)

Source: [Handwritten digit classification on MNIST non-i.i.d. partitioning, Regular graph 34 (test)](<https://www.sota2.com/research/sota/handwritten-digit-classification-on-mnist-non-i-i-d-partitioning-regular-graph-34-test>)

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

Data updated: 2026-02-26T05:32:37.539Z

Evaluation of handwritten digit classification performance on a specific non-i.i.d. partitioning of the MNIST dataset defined by the Regular graph 34 structure, reporting accuracy.

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 | Handwritten digit classification |
| Dataset (including any stated split) | MNIST non-i.i.d. partitioning, Regular graph 34 (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher 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

- [Accuracy](<https://www.sota2.com/research/sota/handwritten-digit-classification-on-mnist-non-i-i-d-partitioning-regular-graph-34-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Standard SGD | 97.19 | Not recorded | 6965d1a46343fa78c8323807 |
| CIL | 96.11 | Not recorded | 6965d1a46343fa78c8323807 |
| CIL | 96.09 | Not recorded | 6965d1a46343fa78c8323807 |
| DeCaFork | 96.06 | Not recorded | 6965d1a46343fa78c8323807 |

### Standard SGD

Accuracy: 97.19. Result ID: 6999a8025698665ec41ecaef.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1a46343fa78c8323807.md>)

Recorded evaluation configuration: {"graph\_access":"full access to all nodes","Pac-Man node":"absent"}. This record does not assert independent reproduction.

### CIL

Accuracy: 96.11. Result ID: 6999a8025698665ec41ecaf0.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1a46343fa78c8323807.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6965d1a46343fa78c8323807.md>)

Recorded evaluation configuration: {"A (parameter)":"10 (small)"}. This record does not assert independent reproduction.

### CIL

Accuracy: 96.09. Result ID: 6999a8025698665ec41ecaf1.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1a46343fa78c8323807.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6965d1a46343fa78c8323807.md>)

Recorded evaluation configuration: {"A (parameter)":"350 (large)"}. This record does not assert independent reproduction.

### DeCaFork

Accuracy: 96.06. Result ID: 6999a8025698665ec41ecaf2.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1a46343fa78c8323807.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6965d1a46343fa78c8323807.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.