# Counterfactual Explanation Generation on MNIST (evaluation)

Source: [Counterfactual Explanation Generation on MNIST (evaluation)](<https://www.sota2.com/research/sota/counterfactual-explanation-generation-on-mnist-evaluation>)

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

Data updated: 2026-02-26T05:46:52.084Z

Evaluation of counterfactual explanation generation methods applied to the MNIST dataset, using metrics such as IM1, IM2, FID, and KID.

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 | Counterfactual Explanation Generation |
| Dataset (including any stated split) | MNIST (evaluation) |
| Metric | IM1 |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [IM1](<https://www.sota2.com/research/sota/counterfactual-explanation-generation-on-mnist-evaluation.md?metric=IM1>): Higher is better; unit: SCALAR.

- [IM2](<https://www.sota2.com/research/sota/counterfactual-explanation-generation-on-mnist-evaluation.md?metric=IM2>): Higher is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/counterfactual-explanation-generation-on-mnist-evaluation.md?metric=FID>): Lower is better; unit: SCALAR.

- [KID](<https://www.sota2.com/research/sota/counterfactual-explanation-generation-on-mnist-evaluation.md?metric=KID>): Lower is better; unit: SCALAR.

## Recorded results

| Method | IM1 | Result date | Report paper |
| --- | --- | --- | --- |
| CEM | 1.68 | Not recorded | 68fa6c161e209131cea320ac |
| CVE | 1.44 | Not recorded | 68fa6c161e209131cea320ac |
| Adv. Attack | 1.02 | Not recorded | 68fa6c161e209131cea320ac |
| ExpGAN | 0.72 | Not recorded | 68fa6c161e209131cea320ac |
| C3LT | 0.7 | Not recorded | 68fa6c161e209131cea320ac |
| Original Data | 0.47 | Not recorded | 68fa6c161e209131cea320ac |

### CEM

IM1: 1.68. Result ID: 698ecc85ffc3901de0a157d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c161e209131cea320ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64f91e209131cea0778c.md>)

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

### CVE

IM1: 1.44. Result ID: 698ecc85ffc3901de0a157d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c161e209131cea320ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e11e209131cea0d1df.md>)

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

### Adv. Attack

IM1: 1.02. Result ID: 698ecc85ffc3901de0a157d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c161e209131cea320ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa665a1e209131cea0fbae.md>)

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

### ExpGAN

IM1: 0.72. Result ID: 698ecc85ffc3901de0a157d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c161e209131cea320ac.md>)

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

### C3LT

IM1: 0.7. Result ID: 698ecc85ffc3901de0a157d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c161e209131cea320ac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c161e209131cea320ac.md>)

[Implementation](<https://github.com/IBM/Contrastive-Explanation-Method>)

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

### Original Data

IM1: 0.47. Result ID: 698ecc85ffc3901de0a157d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c161e209131cea320ac.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.