# e-good arm identification on Caption 853 Source: [e-good arm identification on Caption 853]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:58:59.801Z Evaluation of e-good arm identification performance on the Caption 853 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 853 | | Metric | Probability of False Selection | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 18 of 18 | | 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 - [Probability of False Selection](): Lower is better; unit: SCALAR. ## Recorded results | Method | Probability of False Selection | Result date | Report paper | | --- | --- | --- | --- | | iKG | 0 | Not recorded | 68fa710a1e209131cea4ed72 | | TTEI | 0.01 | Not recorded | 68fa710a1e209131cea4ed72 | | KG | 0.01 | Not recorded | 68fa710a1e209131cea4ed72 | | iKG-ϵ | 0.02 | Not recorded | 68fa710a1e209131cea4ed72 | | iKG | 0.02 | Not recorded | 68fa710a1e209131cea4ed72 | | TTEI | 0.04 | Not recorded | 68fa710a1e209131cea4ed72 | | KG | 0.04 | Not recorded | 68fa710a1e209131cea4ed72 | | (ST)2 | 0.1 | Not recorded | 68fa710a1e209131cea4ed72 | | iKG-ϵ | 0.1 | Not recorded | 68fa710a1e209131cea4ed72 | | Equal Allocation | 0.11 | Not recorded | 68fa710a1e209131cea4ed72 | | EI | 0.12 | Not recorded | 68fa710a1e209131cea4ed72 | | EI | 0.14 | Not recorded | 68fa710a1e209131cea4ed72 | | Equal Allocation | 0.17 | Not recorded | 68fa710a1e209131cea4ed72 | | Equal Allocation | 0.19 | Not recorded | 68fa710a1e209131cea4ed72 | | (ST)2 | 0.21 | Not recorded | 68fa710a1e209131cea4ed72 | | Equal Allocation | 0.28 | Not recorded | 68fa710a1e209131cea4ed72 | | APT | 0.35 | Not recorded | 68fa710a1e209131cea4ed72 | | APT | 0.41 | Not recorded | 68fa710a1e209131cea4ed72 | ### iKG Probability of False Selection: 0. Result ID: 6991910f3a6c31484909072d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sample size":"3000"}. This record does not assert independent reproduction. ### TTEI Probability of False Selection: 0.01. Result ID: 6991910f3a6c314849090729. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sample size":"3000"}. This record does not assert independent reproduction. ### KG Probability of False Selection: 0.01. Result ID: 6991910f3a6c31484909072b. [Reporting paper]() Recorded evaluation configuration: {"Sample size":"3000"}. This record does not assert independent reproduction. ### iKG-ϵ Probability of False Selection: 0.02. Result ID: 6991910f3a6c3148490906e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sample size":10000}. This record does not assert independent reproduction. ### iKG Probability of False Selection: 0.02. Result ID: 6991910f3a6c31484909072c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sample size":"1600"}. This record does not assert independent reproduction. ### TTEI Probability of False Selection: 0.04. Result ID: 6991910f3a6c314849090728. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sample size":"1600"}. This record does not assert independent reproduction. ### KG Probability of False Selection: 0.04. Result ID: 6991910f3a6c31484909072a. [Reporting paper]() Recorded evaluation configuration: {"Sample size":"1600"}. This record does not assert independent reproduction. ### (ST)2 Probability of False Selection: 0.1. Result ID: 6991910f3a6c3148490906e7. [Reporting paper]() Recorded evaluation configuration: {"Sample size":10000}. This record does not assert independent reproduction. ### iKG-ϵ Probability of False Selection: 0.1. Result ID: 6991910f3a6c3148490906e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sample size":4000}. This record does not assert independent reproduction. ### Equal Allocation Probability of False Selection: 0.11. Result ID: 6991910f3a6c314849090725. [Reporting paper]() Recorded evaluation configuration: {"Sample size":"3000"}. This record does not assert independent reproduction. ### EI Probability of False Selection: 0.12. Result ID: 6991910f3a6c314849090727. [Reporting paper]() Recorded evaluation configuration: {"Sample size":"3000"}. This record does not assert independent reproduction. ### EI Probability of False Selection: 0.14. Result ID: 6991910f3a6c314849090726. [Reporting paper]() Recorded evaluation configuration: {"Sample size":"1600"}. This record does not assert independent reproduction. ### Equal Allocation Probability of False Selection: 0.17. Result ID: 6991910f3a6c314849090724. [Reporting paper]() Recorded evaluation configuration: {"Sample size":"1600"}. This record does not assert independent reproduction. ### Equal Allocation Probability of False Selection: 0.19. Result ID: 6991910f3a6c3148490906e3. [Reporting paper]() Recorded evaluation configuration: {"Sample size":10000}. This record does not assert independent reproduction. ### (ST)2 Probability of False Selection: 0.21. Result ID: 6991910f3a6c3148490906e6. [Reporting paper]() Recorded evaluation configuration: {"Sample size":4000}. This record does not assert independent reproduction. ### Equal Allocation Probability of False Selection: 0.28. Result ID: 6991910f3a6c3148490906e2. [Reporting paper]() Recorded evaluation configuration: {"Sample size":4000}. This record does not assert independent reproduction. ### APT Probability of False Selection: 0.35. Result ID: 6991910f3a6c3148490906e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sample size":10000}. This record does not assert independent reproduction. ### APT Probability of False Selection: 0.41. Result ID: 6991910f3a6c3148490906e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sample size":4000}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.