# Local Feature Importance on AND Gate Simulation

Source: [Local Feature Importance on AND Gate Simulation](<https://www.sota2.com/research/sota/local-feature-importance-on-and-gate-simulation>)

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

Data updated: 2026-03-12T06:53:24.687Z

Evaluation of local feature importance methods using the AND Gate Simulation dataset, measured by FP-MAE (False Positive Mean Absolute 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 | Local Feature Importance |
| Dataset (including any stated split) | AND Gate Simulation |
| Metric | FP-MAE |
| Unit | SCALAR |
| Direction | Lower 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

- [FP-MAE](<https://www.sota2.com/research/sota/local-feature-importance-on-and-gate-simulation.md?metric=FP-MAE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | FP-MAE | Result date | Report paper |
| --- | --- | --- | --- |
| CLIQUE | 0.005 | Not recorded | 68fa77101e209131cea70e57 |
| SHAP | 0.216 | Not recorded | 68fa77101e209131cea70e57 |
| LIME | 0.405 | Not recorded | 68fa77101e209131cea70e57 |
| ICI | 0.466 | Not recorded | 68fa77101e209131cea70e57 |

### CLIQUE

FP-MAE: 0.005. Result ID: 69b2626e6dbb7075b95c68b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77101e209131cea70e57.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77101e209131cea70e57.md>)

Recorded evaluation configuration: {"Base Model":"Random Forest"}. This record does not assert independent reproduction.

### SHAP

FP-MAE: 0.216. Result ID: 69b2626e6dbb7075b95c68b3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77101e209131cea70e57.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d01e209131cea00e17.md>)

Recorded evaluation configuration: {"Base Model":"Random Forest"}. This record does not assert independent reproduction.

### LIME

FP-MAE: 0.405. Result ID: 69b2626e6dbb7075b95c68b2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77101e209131cea70e57.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62a11e209131ce9fa620.md>)

[Implementation](<https://github.com/marcotcr/lime-experiments>)

Recorded evaluation configuration: {"Base Model":"Random Forest"}. This record does not assert independent reproduction.

### ICI

FP-MAE: 0.466. Result ID: 69b2626e6dbb7075b95c68b4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77101e209131cea70e57.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67e81e209131cea190b9.md>)

Recorded evaluation configuration: {"Base Model":"Random Forest"}. This record does not assert independent reproduction.

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