# Concept Prediction on CUB (test) Source: [Concept Prediction on CUB (test)]() Collection index: [llms.txt]() Data updated: 2026-03-04T18:32:44.358Z Evaluation of Concept Prediction performance on the test split of the Caltech-UCSD Birds (CUB) dataset, measured using Mean Concept AUC. 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 | Concept Prediction | | Dataset (including any stated split) | CUB (test) | | Metric | Mean Concept AUC | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [Mean Concept AUC](): Higher is better; unit: PERCENT. - [Concept Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Mean Concept AUC | Result date | Report paper | | --- | --- | --- | --- | | SCBM | 98.6 | Not recorded | 68fa7c071e209131cea8bf9f | | PSCBM | 98.59 | Not recorded | 68fa7c071e209131cea8bf9f | | CBM | 98.25 | Not recorded | 68fa7c071e209131cea8bf9f | | Joint CBM | 94.65 | Not recorded | 68fa74fb1e209131cea650f6 | | IntCEM | 94.46 | Not recorded | 68fa74fb1e209131cea650f6 | | CEM | 94.46 | Not recorded | 68fa74fb1e209131cea650f6 | | Joint CBM | 93.76 | Not recorded | 68fa74fb1e209131cea650f6 | | Seq. CBM | 93.68 | Not recorded | 68fa74fb1e209131cea650f6 | | Ind. CBM | 93.58 | Not recorded | 68fa74fb1e209131cea650f6 | | IntCEM | 93.39 | Not recorded | 68fa74fb1e209131cea650f6 | | IntCEM | 89.63 | Not recorded | 68fa74fb1e209131cea650f6 | ### SCBM Mean Concept AUC: 98.6. Result ID: 69a87ab56dbb7075b950a5dc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Covariance":"Amortized","Intervention Policy":"probability uncertainty"}. This record does not assert independent reproduction. ### PSCBM Mean Concept AUC: 98.59. Result ID: 69a87ab56dbb7075b950a5dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Covariance":"Amortized","Intervention Policy":"probability uncertainty"}. This record does not assert independent reproduction. ### CBM Mean Concept AUC: 98.25. Result ID: 69a87ab56dbb7075b950a5db. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Covariance":"Amortized","Intervention Policy":"probability uncertainty"}. This record does not assert independent reproduction. ### Joint CBM Mean Concept AUC: 94.65. Result ID: 699389083a6c31484916a7f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Bottleneck activation function":"Sigmoid"}. This record does not assert independent reproduction. ### IntCEM Mean Concept AUC: 94.46. Result ID: 699389083a6c31484916a7f5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"lambda\_roll":"0.1"}. This record does not assert independent reproduction. ### CEM Mean Concept AUC: 94.46. Result ID: 699389083a6c31484916a7f6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Joint CBM Mean Concept AUC: 93.76. Result ID: 699389083a6c31484916a7f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Bottleneck activation function":"Logit"}. This record does not assert independent reproduction. ### Seq. CBM Mean Concept AUC: 93.68. Result ID: 699389083a6c31484916a7fa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training paradigm":"Sequential"}. This record does not assert independent reproduction. ### Ind. CBM Mean Concept AUC: 93.58. Result ID: 699389083a6c31484916a7f9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training paradigm":"Independent"}. This record does not assert independent reproduction. ### IntCEM Mean Concept AUC: 93.39. Result ID: 699389083a6c31484916a7f4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"lambda\_roll":"1"}. This record does not assert independent reproduction. ### IntCEM Mean Concept AUC: 89.63. Result ID: 699389083a6c31484916a7f3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"lambda\_roll":"5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.