# Machine Unlearning Accuracy on MNIST Forget Set (class 7)

Source: [Machine Unlearning Accuracy on MNIST Forget Set (class 7)](<https://www.sota2.com/research/sota/machine-unlearning-accuracy-on-mnist-forget-set-class-7>)

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

Data updated: 2026-06-12T08:09:22.835Z

Evaluation of Machine Unlearning performance specifically on the subset of MNIST data corresponding to class 7 (the forget set), measured using standard accuracy metrics.

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 | Machine Unlearning |
| Dataset (including any stated split) | MNIST Forget Set (class 7) |
| Metric | Accuracy (Forget Set) |
| 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 (Forget Set)](<https://www.sota2.com/research/sota/machine-unlearning-accuracy-on-mnist-forget-set-class-7.md?metric=Accuracy%20(Forget%20Set)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Forget Set) | Result date | Report paper |
| --- | --- | --- | --- |
| Original Model | 89.55 | Not recorded | 6a2b929ed33dfb23e783b0ae |
| Original Model | 89.55 | Not recorded | 6a2b929ed33dfb23e783b0ae |
| Modified Model | 0.06 | Not recorded | 6a2b929ed33dfb23e783b0ae |
| Modified Model | 0 | Not recorded | 6a2b929ed33dfb23e783b0ae |

### Original Model

Accuracy (Forget Set): 89.55. Result ID: 6a2bbe9efbc373592c2a1588.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b929ed33dfb23e783b0ae.md>)

Recorded evaluation configuration: {"Environment":"MaskWorld"}. This record does not assert independent reproduction.

### Original Model

Accuracy (Forget Set): 89.55. Result ID: 6a2bbe9efbc373592c2a158a.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b929ed33dfb23e783b0ae.md>)

Recorded evaluation configuration: {"Environment":"ShiftWorld"}. This record does not assert independent reproduction.

### Modified Model

Accuracy (Forget Set): 0.06. Result ID: 6a2bbe9efbc373592c2a158b.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b929ed33dfb23e783b0ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2b929ed33dfb23e783b0ae.md>)

Recorded evaluation configuration: {"Environment":"ShiftWorld"}. This record does not assert independent reproduction.

### Modified Model

Accuracy (Forget Set): 0. Result ID: 6a2bbe9efbc373592c2a1589.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b929ed33dfb23e783b0ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2b929ed33dfb23e783b0ae.md>)

Recorded evaluation configuration: {"Environment":"MaskWorld"}. This record does not assert independent reproduction.

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