# e-good arm identification on Caption 854

Source: [e-good arm identification on Caption 854](<https://www.sota2.com/research/sota/e-good-arm-identification-on-caption-854>)

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

Data updated: 2026-02-26T05:45:11.800Z

Evaluation of e-good arm identification performance on the Caption 854 dataset, measured by Probability of False Selection.

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 | e-good arm identification |
| Dataset (including any stated split) | Caption 854 |
| Metric | False Selection Probability |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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

- [False Selection Probability](<https://www.sota2.com/research/sota/e-good-arm-identification-on-caption-854.md?metric=False%20Selection%20Probability>): Lower is better; unit: PERCENT.

## Recorded results

| Method | False Selection Probability | Result date | Report paper |
| --- | --- | --- | --- |
| iKG-ϵ | 3 | Not recorded | 68fa710a1e209131cea4ed72 |
| (ST)2 | 4 | Not recorded | 68fa710a1e209131cea4ed72 |
| Equal Allocation | 5 | Not recorded | 68fa710a1e209131cea4ed72 |
| iKG-ϵ | 11 | Not recorded | 68fa710a1e209131cea4ed72 |
| (ST)2 | 12 | Not recorded | 68fa710a1e209131cea4ed72 |
| Equal Allocation | 14 | Not recorded | 68fa710a1e209131cea4ed72 |
| APT | 48 | Not recorded | 68fa710a1e209131cea4ed72 |
| APT | 49 | Not recorded | 68fa710a1e209131cea4ed72 |

### iKG-ϵ

False Selection Probability: 3. Result ID: 6991910f3a6c3148490906f1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa710a1e209131cea4ed72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710a1e209131cea4ed72.md>)

Recorded evaluation configuration: {"Sample size":15000}. This record does not assert independent reproduction.

### (ST)2

False Selection Probability: 4. Result ID: 6991910f3a6c3148490906ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa710a1e209131cea4ed72.md>)

Recorded evaluation configuration: {"Sample size":15000}. This record does not assert independent reproduction.

### Equal Allocation

False Selection Probability: 5. Result ID: 6991910f3a6c3148490906eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa710a1e209131cea4ed72.md>)

Recorded evaluation configuration: {"Sample size":15000}. This record does not assert independent reproduction.

### iKG-ϵ

False Selection Probability: 11. Result ID: 6991910f3a6c3148490906f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa710a1e209131cea4ed72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710a1e209131cea4ed72.md>)

Recorded evaluation configuration: {"Sample size":9400}. This record does not assert independent reproduction.

### (ST)2

False Selection Probability: 12. Result ID: 6991910f3a6c3148490906ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa710a1e209131cea4ed72.md>)

Recorded evaluation configuration: {"Sample size":9400}. This record does not assert independent reproduction.

### Equal Allocation

False Selection Probability: 14. Result ID: 6991910f3a6c3148490906ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa710a1e209131cea4ed72.md>)

Recorded evaluation configuration: {"Sample size":9400}. This record does not assert independent reproduction.

### APT

False Selection Probability: 48. Result ID: 6991910f3a6c3148490906ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa710a1e209131cea4ed72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62841e209131ce9f9c9c.md>)

Recorded evaluation configuration: {"Sample size":9400}. This record does not assert independent reproduction.

### APT

False Selection Probability: 49. Result ID: 6991910f3a6c3148490906ed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa710a1e209131cea4ed72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62841e209131ce9f9c9c.md>)

Recorded evaluation configuration: {"Sample size":15000}. This record does not assert independent reproduction.

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