# Interpretability Evaluation on CUB-200-C 100-sample

Source: [Interpretability Evaluation on CUB-200-C 100-sample](<https://www.sota2.com/research/sota/interpretability-evaluation-on-cub-200-c-100-sample>)

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

Data updated: 2026-04-20T08:35:59.600Z

Evaluation of model interpretability methods on the specific 100-sample subset variant of the CUB-200 dataset, focusing on prototype relevance and overall quality scores.

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 | Interpretability Evaluation |
| Dataset (including any stated split) | CUB-200-C 100-sample |
| Metric | Focus Relevance |
| Unit | SCALAR |
| 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

- [Focus Relevance](<https://www.sota2.com/research/sota/interpretability-evaluation-on-cub-200-c-100-sample.md?metric=Focus%20Relevance>): Higher is better; unit: SCALAR.

- [Prototype Match](<https://www.sota2.com/research/sota/interpretability-evaluation-on-cub-200-c-100-sample.md?metric=Prototype%20Match>): Higher is better; unit: SCALAR.

- [Overall Quality](<https://www.sota2.com/research/sota/interpretability-evaluation-on-cub-200-c-100-sample.md?metric=Overall%20Quality>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Focus Relevance | Result date | Report paper |
| --- | --- | --- | --- |
| ProtoTTA | 4.3 | Not recorded | 69e5b30a7d0172140ec7df99 |
| EATA | 4.18 | Not recorded | 69e5b30a7d0172140ec7df99 |
| Unadapted | 4.14 | Not recorded | 69e5b30a7d0172140ec7df99 |
| Tent | 4.03 | Not recorded | 69e5b30a7d0172140ec7df99 |

### ProtoTTA

Focus Relevance: 4.3. Result ID: 69e5e56c47f34ce924cc1ac1.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7df99.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7df99.md>)

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

### EATA

Focus Relevance: 4.18. Result ID: 69e5e56c47f34ce924cc1ac0.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7df99.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea35123.md>)

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

### Unadapted

Focus Relevance: 4.14. Result ID: 69e5e56c47f34ce924cc1abe.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7df99.md>)

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

### Tent

Focus Relevance: 4.03. Result ID: 69e5e56c47f34ce924cc1abf.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b30a7d0172140ec7df99.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69941e209131cea22d2b.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.