# Autonomous rollout classification on Dataset F expanding

Source: [Autonomous rollout classification on Dataset F expanding](<https://www.sota2.com/research/sota/autonomous-rollout-classification-on-dataset-f-expanding>)

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

Data updated: 2026-03-31T07:52:23.222Z

Evaluation of Autonomous rollout classification performance on Dataset F expanding, utilizing metrics related to training accuracy, Koopman analysis, and dynamical complexity (dCor/TE).

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 | Autonomous rollout classification |
| Dataset (including any stated split) | Dataset F expanding |
| Metric | Mean Training Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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 Training Accuracy](<https://www.sota2.com/research/sota/autonomous-rollout-classification-on-dataset-f-expanding.md?metric=Mean%20Training%20Accuracy>): Higher is better; unit: PERCENT.

- [Minimum Training Accuracy](<https://www.sota2.com/research/sota/autonomous-rollout-classification-on-dataset-f-expanding.md?metric=Minimum%20Training%20Accuracy>): Higher is better; unit: PERCENT.

- [Koopman Mean Accuracy](<https://www.sota2.com/research/sota/autonomous-rollout-classification-on-dataset-f-expanding.md?metric=Koopman%20Mean%20Accuracy>): Higher is better; unit: PERCENT.

- [Koopman Minimum Accuracy](<https://www.sota2.com/research/sota/autonomous-rollout-classification-on-dataset-f-expanding.md?metric=Koopman%20Minimum%20Accuracy>): Higher is better; unit: PERCENT.

- [Steps Below 90% Threshold (Auto)](<https://www.sota2.com/research/sota/autonomous-rollout-classification-on-dataset-f-expanding.md?metric=Steps%20Below%2090%25%20Threshold%20(Auto)>): Lower is better; unit: SCALAR.

- [Retrained Upper Bound Score](<https://www.sota2.com/research/sota/autonomous-rollout-classification-on-dataset-f-expanding.md?metric=Retrained%20Upper%20Bound%20Score>): Higher is better; unit: SCALAR.

- [Frozen Mean Accuracy](<https://www.sota2.com/research/sota/autonomous-rollout-classification-on-dataset-f-expanding.md?metric=Frozen%20Mean%20Accuracy>): Higher is better; unit: PERCENT.

- [Frozen Steps Below 90% Threshold](<https://www.sota2.com/research/sota/autonomous-rollout-classification-on-dataset-f-expanding.md?metric=Frozen%20Steps%20Below%2090%25%20Threshold>): Lower is better; unit: SCALAR.

- [Mean dCor (Off-Diagonal)](<https://www.sota2.com/research/sota/autonomous-rollout-classification-on-dataset-f-expanding.md?metric=Mean%20dCor%20(Off-Diagonal)>): Lower is better; unit: SCALAR.

- [dCor Pairs Above 0.5 Threshold](<https://www.sota2.com/research/sota/autonomous-rollout-classification-on-dataset-f-expanding.md?metric=dCor%20Pairs%20Above%200.5%20Threshold>): Lower is better; unit: SCALAR.

- [Transfer Entropy Ratio (L1/L2)](<https://www.sota2.com/research/sota/autonomous-rollout-classification-on-dataset-f-expanding.md?metric=Transfer%20Entropy%20Ratio%20(L1%2FL2)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Mean Training Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| KOMET | 1 | Not recorded | 69cb55240636e5bf4afc9fd0 |

### KOMET

Mean Training Accuracy: 1. Result ID: 69cb7d2e47f34ce924b390e5.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55240636e5bf4afc9fd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cb55240636e5bf4afc9fd0.md>)

Recorded evaluation configuration: {"Drift type":"expanding","Classes / nθ":"3/27","Koopman basis":"Detrend+Fourier","PCs / nθ":"5/27","Spectral radius ρ(A)":"1.000","Rollout steps":"100","Zero retraining":"true"}. This record does not assert independent reproduction.

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