# Peak prediction (Task 1) on CMI-PB (test)

Source: [Peak prediction (Task 1) on CMI-PB (test)](<https://www.sota2.com/research/sota/peak-prediction-task-1-on-cmi-pb-test>)

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

Data updated: 2026-05-14T07:35:15.549Z

Evaluation of Peak prediction (Task 1) performance on the test split of the CMI-PB dataset, measured using AUROC and 95% CI.

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 | Peak prediction (Task 1) |
| Dataset (including any stated split) | CMI-PB (test) |
| Metric | AUROC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [AUROC](<https://www.sota2.com/research/sota/peak-prediction-task-1-on-cmi-pb-test.md?metric=AUROC>): Higher is better; unit: SCALAR.

- [95% CI (Lower Bound)](<https://www.sota2.com/research/sota/peak-prediction-task-1-on-cmi-pb-test.md?metric=95%25%20CI%20(Lower%20Bound)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| Logistic regression | 0.816 | Not recorded | 6a0556e7dbc836b87d828adf |
| multi-task contrastive multimodal fusion architecture | 0.797 | Not recorded | 6a0556e7dbc836b87d828adf |
| TabMLP | 0.785 | Not recorded | 6a0556e7dbc836b87d828adf |
| XGBoost | 0.781 | Not recorded | 6a0556e7dbc836b87d828adf |
| Logistic regression | 0.699 | Not recorded | 6a0556e7dbc836b87d828adf |
| TabMLP | 0.594 | Not recorded | 6a0556e7dbc836b87d828adf |
| XGBoost | 0.5 | Not recorded | 6a0556e7dbc836b87d828adf |

### Logistic regression

AUROC: 0.816. Result ID: 6a057ab947f34ce924ec2216.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828adf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa646e1e209131cea04ae5.md>)

Recorded evaluation configuration: {"Input features":"TabPFN-v2 embeddings (concatenation)","Embedding dimensions":"6,144"}. This record does not assert independent reproduction.

### multi-task contrastive multimodal fusion architecture

AUROC: 0.797. Result ID: 6a057ab947f34ce924ec2219.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828adf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828adf.md>)

Recorded evaluation configuration: {"Input features":"TabPFN-v2 embeddings (concatenation)","Method Label":"Preferred (ours)"}. This record does not assert independent reproduction.

### TabMLP

AUROC: 0.785. Result ID: 6a057ab947f34ce924ec2218.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828adf.md>)

Recorded evaluation configuration: {"Input features":"TabPFN-v2 embeddings (concatenation)","Embedding dimensions":"6,144"}. This record does not assert independent reproduction.

### XGBoost

AUROC: 0.781. Result ID: 6a057ab947f34ce924ec2214.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828adf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62821e209131ce9f9b56.md>)

[Implementation](<https://github.com/dmlc/xgboost>)

Recorded evaluation configuration: {"Input features":"Raw features (mean-imputed concatenation)","Imputation method":"per-feature training-set mean imputation"}. This record does not assert independent reproduction.

### Logistic regression

AUROC: 0.699. Result ID: 6a057ab947f34ce924ec2213.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828adf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa646e1e209131cea04ae5.md>)

Recorded evaluation configuration: {"Input features":"Raw features (mean-imputed concatenation)","Imputation method":"per-feature training-set mean imputation"}. This record does not assert independent reproduction.

### TabMLP

AUROC: 0.594. Result ID: 6a057ab947f34ce924ec2215.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828adf.md>)

Recorded evaluation configuration: {"Input features":"Raw features (mean-imputed concatenation)","Imputation method":"per-feature training-set mean imputation"}. This record does not assert independent reproduction.

### XGBoost

AUROC: 0.5. Result ID: 6a057ab947f34ce924ec2217.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828adf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62821e209131ce9f9b56.md>)

[Implementation](<https://github.com/dmlc/xgboost>)

Recorded evaluation configuration: {"Input features":"TabPFN-v2 embeddings (concatenation)","Embedding dimensions":"6,144"}. This record does not assert independent reproduction.

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