# Error Slice Discovery on Waterbirds Source: [Error Slice Discovery on Waterbirds]() Collection index: [llms.txt]() Data updated: 2026-05-29T10:15:19.065Z Evaluation of Error Slice Discovery performance on the Waterbirds dataset, reporting Precision@10 and MGF metrics. 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 | Error Slice Discovery | | Dataset (including any stated split) | Waterbirds | | Metric | Precision@10 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Precision@10](): Higher is better; unit: PERCENT. - [MGF](): Higher is better; unit: PERCENT. ## Recorded results | Method | Precision@10 | Result date | Report paper | | --- | --- | --- | --- | | CB-SLICE | 83 | Not recorded | 6a191dd6dbd7150506f82b04 | | CB-SLICE | 78 | Not recorded | 6a191dd6dbd7150506f82b04 | | DOMINO | 72 | Not recorded | 6a191dd6dbd7150506f82b04 | | DOMINO | 62 | Not recorded | 6a191dd6dbd7150506f82b04 | | DOMINO | 53 | Not recorded | 6a191dd6dbd7150506f82b04 | | GEORGE | 34 | Not recorded | 6a191dd6dbd7150506f82b04 | | HiBug2 | 25 | Not recorded | 6a191dd6dbd7150506f82b04 | | HiBug2 | 25 | Not recorded | 6a191dd6dbd7150506f82b04 | | GEORGE | 22 | Not recorded | 6a191dd6dbd7150506f82b04 | | HiBug2 | 20 | Not recorded | 6a191dd6dbd7150506f82b04 | | GEORGE | 18 | Not recorded | 6a191dd6dbd7150506f82b04 | | K-MEANS | 11 | Not recorded | 6a191dd6dbd7150506f82b04 | | K-MEANS | 9 | Not recorded | 6a191dd6dbd7150506f82b04 | | SPOTLIGHT | 5 | Not recorded | 6a191dd6dbd7150506f82b04 | | SPOTLIGHT | 5 | Not recorded | 6a191dd6dbd7150506f82b04 | | K-MEANS | 5 | Not recorded | 6a191dd6dbd7150506f82b04 | | SPOTLIGHT | 0 | Not recorded | 6a191dd6dbd7150506f82b04 | ### CB-SLICE Precision@10: 83. Result ID: 6a19671afbc373592c145300. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CBM + Joint"}. This record does not assert independent reproduction. ### CB-SLICE Precision@10: 78. Result ID: 6a19671afbc373592c1452ff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CBM + Seq"}. This record does not assert independent reproduction. ### DOMINO Precision@10: 72. Result ID: 6a19671afbc373592c1452f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CBM + Seq"}. This record does not assert independent reproduction. ### DOMINO Precision@10: 62. Result ID: 6a19671afbc373592c1452f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CBM + Joint"}. This record does not assert independent reproduction. ### DOMINO Precision@10: 53. Result ID: 6a19671afbc373592c1452f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Vanilla DNN"}. This record does not assert independent reproduction. ### GEORGE Precision@10: 34. Result ID: 6a19671afbc373592c1452f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Vanilla DNN"}. This record does not assert independent reproduction. ### HiBug2 Precision@10: 25. Result ID: 6a19671afbc373592c1452f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Vanilla DNN"}. This record does not assert independent reproduction. ### HiBug2 Precision@10: 25. Result ID: 6a19671afbc373592c1452f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CBM + Joint"}. This record does not assert independent reproduction. ### GEORGE Precision@10: 22. Result ID: 6a19671afbc373592c1452f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CBM + Seq"}. This record does not assert independent reproduction. ### HiBug2 Precision@10: 20. Result ID: 6a19671afbc373592c1452f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CBM + Seq"}. This record does not assert independent reproduction. ### GEORGE Precision@10: 18. Result ID: 6a19671afbc373592c1452f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CBM + Joint"}. This record does not assert independent reproduction. ### K-MEANS Precision@10: 11. Result ID: 6a19671afbc373592c1452fd. [Reporting paper]() Recorded evaluation configuration: {"Model":"CBM + Seq"}. This record does not assert independent reproduction. ### K-MEANS Precision@10: 9. Result ID: 6a19671afbc373592c1452fe. [Reporting paper]() Recorded evaluation configuration: {"Model":"CBM + Joint"}. This record does not assert independent reproduction. ### SPOTLIGHT Precision@10: 5. Result ID: 6a19671afbc373592c1452f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Vanilla DNN"}. This record does not assert independent reproduction. ### SPOTLIGHT Precision@10: 5. Result ID: 6a19671afbc373592c1452fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CBM + Seq"}. This record does not assert independent reproduction. ### K-MEANS Precision@10: 5. Result ID: 6a19671afbc373592c1452fc. [Reporting paper]() Recorded evaluation configuration: {"Model":"Vanilla DNN"}. This record does not assert independent reproduction. ### SPOTLIGHT Precision@10: 0. Result ID: 6a19671afbc373592c1452fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CBM + Joint"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.