# Out-of-scope Intent Detection on Banking77 (r=2.5% contamination, test) Source: [Out-of-scope Intent Detection on Banking77 (r=2.5% contamination, test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:25:33.033Z Evaluation of Out-of-scope Intent Detection performance on the test split of the Banking77 dataset, specifically focusing on results derived under 2.5% contamination conditions. 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 | Out-of-scope Intent Detection | | Dataset (including any stated split) | Banking77 (B77) r=2.5% contamination (test) | | Metric | AUC2 (10% Subset) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [AUC2 (10% Subset)](): Higher is better; unit: SCALAR. - [AUC2 (25% Subset)](): Higher is better; unit: SCALAR. - [AUC2 (50% Subset)](): Higher is better; unit: SCALAR. - [AUC2 (100% Subset)](): Higher is better; unit: SCALAR. ## Recorded results | Method | AUC2 (10% Subset) | Result date | Report paper | | --- | --- | --- | --- | | ZS | 0.818 | Not recorded | 68fa73601e209131cea5c0a8 | | ZS | 0.818 | Not recorded | 68fa73601e209131cea5c0a8 | | ColdFusion | 0.806 | Not recorded | 68fa73601e209131cea5c0a8 | | ColdFusion | 0.799 | Not recorded | 68fa73601e209131cea5c0a8 | | ColdFusion | 0.79 | Not recorded | 68fa73601e209131cea5c0a8 | | ZS | 0.789 | Not recorded | 68fa73601e209131cea5c0a8 | | ZS | 0.789 | Not recorded | 68fa73601e209131cea5c0a8 | | ColdFusion | 0.774 | Not recorded | 68fa73601e209131cea5c0a8 | | DN2 | 0.766 | Not recorded | 68fa73601e209131cea5c0a8 | | DN2 | 0.746 | Not recorded | 68fa73601e209131cea5c0a8 | | DN2 | 0.723 | Not recorded | 68fa73601e209131cea5c0a8 | | DN2 | 0.706 | Not recorded | 68fa73601e209131cea5c0a8 | ### ZS AUC2 (10% Subset): 0.818. Result ID: 6992d5e33a6c31484911d13e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoder":"MPNET","Contamination Ratio":"2.5%"}. This record does not assert independent reproduction. ### ZS AUC2 (10% Subset): 0.818. Result ID: 6992d5e33a6c31484911d150. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoder":"MPNET","Contamination Ratio":"7.5%"}. This record does not assert independent reproduction. ### ColdFusion AUC2 (10% Subset): 0.806. Result ID: 6992d5e33a6c31484911d140. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"MPNET","Contamination Ratio":"2.5%"}. This record does not assert independent reproduction. ### ColdFusion AUC2 (10% Subset): 0.799. Result ID: 6992d5e33a6c31484911d152. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"MPNET","Contamination Ratio":"7.5%"}. This record does not assert independent reproduction. ### ColdFusion AUC2 (10% Subset): 0.79. Result ID: 6992d5e33a6c31484911d13d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"GTE","Contamination Ratio":"2.5%"}. This record does not assert independent reproduction. ### ZS AUC2 (10% Subset): 0.789. Result ID: 6992d5e33a6c31484911d13b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoder":"GTE","Contamination Ratio":"2.5%"}. This record does not assert independent reproduction. ### ZS AUC2 (10% Subset): 0.789. Result ID: 6992d5e33a6c31484911d14d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Encoder":"GTE","Contamination Ratio":"7.5%"}. This record does not assert independent reproduction. ### ColdFusion AUC2 (10% Subset): 0.774. Result ID: 6992d5e33a6c31484911d14f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"GTE","Contamination Ratio":"7.5%"}. This record does not assert independent reproduction. ### DN2 AUC2 (10% Subset): 0.766. Result ID: 6992d5e33a6c31484911d13f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"MPNET","Contamination Ratio":"2.5%"}. This record does not assert independent reproduction. ### DN2 AUC2 (10% Subset): 0.746. Result ID: 6992d5e33a6c31484911d13c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"GTE","Contamination Ratio":"2.5%"}. This record does not assert independent reproduction. ### DN2 AUC2 (10% Subset): 0.723. Result ID: 6992d5e33a6c31484911d151. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"MPNET","Contamination Ratio":"7.5%"}. This record does not assert independent reproduction. ### DN2 AUC2 (10% Subset): 0.706. Result ID: 6992d5e33a6c31484911d14e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"GTE","Contamination Ratio":"7.5%"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.