# Early Failure Detection on LIBERO Unseen

Source: [Early Failure Detection on LIBERO Unseen](<https://www.sota2.com/research/sota/early-failure-detection-on-libero-unseen>)

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

Data updated: 2026-06-09T08:53:40.627Z

Evaluation of Early Failure Detection performance on the LIBERO Unseen dataset, measured using ROC-AUC (q=0.25).

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 | Early Failure Detection |
| Dataset (including any stated split) | LIBERO Unseen |
| Metric | ROC-AUC (q=0.25) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [ROC-AUC (q=0.25)](<https://www.sota2.com/research/sota/early-failure-detection-on-libero-unseen.md?metric=ROC-AUC%20(q%3D0.25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ROC-AUC (q=0.25) | Result date | Report paper |
| --- | --- | --- | --- |
| ActProbe | 73.8 | Not recorded | 6a279e1f90966ade919bf751 |
| ActProbe | 71.4 | Not recorded | 6a279e1f90966ade919bf751 |
| SAFE-MLP | 67.9 | Not recorded | 6a279e1f90966ade919bf751 |
| STAC-Single | 65.2 | Not recorded | 6a279e1f90966ade919bf751 |
| SAFE-LSTM-TDQC | 62.8 | Not recorded | 6a279e1f90966ade919bf751 |
| SAFE-MLP-TDQC | 60.7 | Not recorded | 6a279e1f90966ade919bf751 |
| SAFE-LSTM | 59.2 | Not recorded | 6a279e1f90966ade919bf751 |
| SAFE-MLP | 58.9 | Not recorded | 6a279e1f90966ade919bf751 |
| LogpZO | 58.3 | Not recorded | 6a279e1f90966ade919bf751 |
| SAFE-LSTM-TDQC | 57.6 | Not recorded | 6a279e1f90966ade919bf751 |
| Cosine k-NN | 57.2 | Not recorded | 6a279e1f90966ade919bf751 |
| SAFE-LSTM | 55.9 | Not recorded | 6a279e1f90966ade919bf751 |
| SAFE-MLP-TDQC | 52.8 | Not recorded | 6a279e1f90966ade919bf751 |
| LogpZO | 52.6 | Not recorded | 6a279e1f90966ade919bf751 |
| Cosine k-NN | 42 | Not recorded | 6a279e1f90966ade919bf751 |

### ActProbe

ROC-AUC (q=0.25): 73.8. Result ID: 6a27d420fbc373592c24b098.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

Recorded evaluation configuration: {"Policy":"OpenVLA"}. This record does not assert independent reproduction.

### ActProbe

ROC-AUC (q=0.25): 71.4. Result ID: 6a27d420fbc373592c24b097.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

Recorded evaluation configuration: {"Policy":"π0"}. This record does not assert independent reproduction.

### SAFE-MLP

ROC-AUC (q=0.25): 67.9. Result ID: 6a27d420fbc373592c24b092.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d68e.md>)

Recorded evaluation configuration: {"Policy":"OpenVLA"}. This record does not assert independent reproduction.

### STAC-Single

ROC-AUC (q=0.25): 65.2. Result ID: 6a27d420fbc373592c24b08e.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa757c1e209131cea68461.md>)

Recorded evaluation configuration: {"Policy":"π0"}. This record does not assert independent reproduction.

### SAFE-LSTM-TDQC

ROC-AUC (q=0.25): 62.8. Result ID: 6a27d420fbc373592c24b093.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e9a78555a3c32af89f6fea.md>)

Recorded evaluation configuration: {"Policy":"π0"}. This record does not assert independent reproduction.

### SAFE-MLP-TDQC

ROC-AUC (q=0.25): 60.7. Result ID: 6a27d420fbc373592c24b095.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e9a78555a3c32af89f6fea.md>)

Recorded evaluation configuration: {"Policy":"π0"}. This record does not assert independent reproduction.

### SAFE-LSTM

ROC-AUC (q=0.25): 59.2. Result ID: 6a27d420fbc373592c24b08f.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d68e.md>)

Recorded evaluation configuration: {"Policy":"π0"}. This record does not assert independent reproduction.

### SAFE-MLP

ROC-AUC (q=0.25): 58.9. Result ID: 6a27d420fbc373592c24b091.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d68e.md>)

Recorded evaluation configuration: {"Policy":"π0"}. This record does not assert independent reproduction.

### LogpZO

ROC-AUC (q=0.25): 58.3. Result ID: 6a27d420fbc373592c24b08c.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79831e209131cea7de9c.md>)

Recorded evaluation configuration: {"Policy":"π0"}. This record does not assert independent reproduction.

### SAFE-LSTM-TDQC

ROC-AUC (q=0.25): 57.6. Result ID: 6a27d420fbc373592c24b094.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e9a78555a3c32af89f6fea.md>)

Recorded evaluation configuration: {"Policy":"OpenVLA"}. This record does not assert independent reproduction.

### Cosine k-NN

ROC-AUC (q=0.25): 57.2. Result ID: 6a27d420fbc373592c24b08a.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d68e.md>)

Recorded evaluation configuration: {"Policy":"π0"}. This record does not assert independent reproduction.

### SAFE-LSTM

ROC-AUC (q=0.25): 55.9. Result ID: 6a27d420fbc373592c24b090.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d68e.md>)

Recorded evaluation configuration: {"Policy":"OpenVLA"}. This record does not assert independent reproduction.

### SAFE-MLP-TDQC

ROC-AUC (q=0.25): 52.8. Result ID: 6a27d420fbc373592c24b096.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e9a78555a3c32af89f6fea.md>)

Recorded evaluation configuration: {"Policy":"OpenVLA"}. This record does not assert independent reproduction.

### LogpZO

ROC-AUC (q=0.25): 52.6. Result ID: 6a27d420fbc373592c24b08d.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79831e209131cea7de9c.md>)

Recorded evaluation configuration: {"Policy":"OpenVLA"}. This record does not assert independent reproduction.

### Cosine k-NN

ROC-AUC (q=0.25): 42. Result ID: 6a27d420fbc373592c24b08b.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e1f90966ade919bf751.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d68e.md>)

Recorded evaluation configuration: {"Policy":"OpenVLA"}. This record does not assert independent reproduction.

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