# Concept Prediction on CUB-Incomp (test)

Source: [Concept Prediction on CUB-Incomp (test)](<https://www.sota2.com/research/sota/concept-prediction-on-cub-incomp-test>)

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

Data updated: 2026-02-26T05:51:58.408Z

Evaluation of Concept Prediction performance on the test split of the CUB-Incomp dataset, measured using AUC 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 | Concept Prediction |
| Dataset (including any stated split) | CUB-Incomp (test) |
| Metric | Mean Concept AUC |
| Unit | PERCENT |
| Direction | Higher 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

- [Mean Concept AUC](<https://www.sota2.com/research/sota/concept-prediction-on-cub-incomp-test.md?metric=Mean%20Concept%20AUC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Mean Concept AUC | Result date | Report paper |
| --- | --- | --- | --- |
| IntCEM | 94.5 | Not recorded | 68fa74fb1e209131cea650f6 |
| IntCEM | 94.42 | Not recorded | 68fa74fb1e209131cea650f6 |
| Ind. CBM | 93.65 | Not recorded | 68fa74fb1e209131cea650f6 |
| Seq. CBM | 93.65 | Not recorded | 68fa74fb1e209131cea650f6 |
| Joint CBM | 92.87 | Not recorded | 68fa74fb1e209131cea650f6 |
| IntCEM | 92.7 | Not recorded | 68fa74fb1e209131cea650f6 |
| CEM | 91.15 | Not recorded | 68fa74fb1e209131cea650f6 |
| Joint CBM | 90.88 | Not recorded | 68fa74fb1e209131cea650f6 |

### IntCEM

Mean Concept AUC: 94.5. Result ID: 699389083a6c31484916a7fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74fb1e209131cea650f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74fb1e209131cea650f6.md>)

[Implementation](<https://github.com/mateoespinosa/cem>)

Recorded evaluation configuration: {"lambda\_roll":"0.1"}. This record does not assert independent reproduction.

### IntCEM

Mean Concept AUC: 94.42. Result ID: 699389083a6c31484916a7fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74fb1e209131cea650f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74fb1e209131cea650f6.md>)

[Implementation](<https://github.com/mateoespinosa/cem>)

Recorded evaluation configuration: {"lambda\_roll":"1"}. This record does not assert independent reproduction.

### Ind. CBM

Mean Concept AUC: 93.65. Result ID: 699389083a6c31484916a801.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74fb1e209131cea650f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f231e209131cea43f55.md>)

[Implementation](<https://github.com/mateoespinosa/cem/>)

Recorded evaluation configuration: {"Training paradigm":"Independent"}. This record does not assert independent reproduction.

### Seq. CBM

Mean Concept AUC: 93.65. Result ID: 699389083a6c31484916a802.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74fb1e209131cea650f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f231e209131cea43f55.md>)

[Implementation](<https://github.com/mateoespinosa/cem/>)

Recorded evaluation configuration: {"Training paradigm":"Sequential"}. This record does not assert independent reproduction.

### Joint CBM

Mean Concept AUC: 92.87. Result ID: 699389083a6c31484916a800.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74fb1e209131cea650f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68f91e209131cea1f6a0.md>)

Recorded evaluation configuration: {"Bottleneck activation function":"Logit"}. This record does not assert independent reproduction.

### IntCEM

Mean Concept AUC: 92.7. Result ID: 699389083a6c31484916a7fb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74fb1e209131cea650f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74fb1e209131cea650f6.md>)

[Implementation](<https://github.com/mateoespinosa/cem>)

Recorded evaluation configuration: {"lambda\_roll":"5"}. This record does not assert independent reproduction.

### CEM

Mean Concept AUC: 91.15. Result ID: 699389083a6c31484916a7fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74fb1e209131cea650f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f231e209131cea43f55.md>)

[Implementation](<https://github.com/mateoespinosa/cem/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Joint CBM

Mean Concept AUC: 90.88. Result ID: 699389083a6c31484916a7ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74fb1e209131cea650f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68f91e209131cea1f6a0.md>)

Recorded evaluation configuration: {"Bottleneck activation function":"Sigmoid"}. This record does not assert independent reproduction.

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