# Failure Detection on LIBERO unseen

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

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

Data updated: 2026-04-23T10:49:52.061Z

Evaluation of Failure Detection performance on the LIBERO unseen dataset, measured using the Brier Score.

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 | Failure Detection |
| Dataset (including any stated split) | LIBERO unseen |
| Metric | Brier Score |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 37 of 37 |
| 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

- [Brier Score](<https://www.sota2.com/research/sota/failure-detection-on-libero-unseen.md?metric=Brier%20Score>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Brier Score | Result date | Report paper |
| --- | --- | --- | --- |
| SAFE-RNN-TDQC (Ours) | 0.097 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-RNN-TDQC (Ours) | 0.1 | Not recorded | 69e9a78555a3c32af89f6fea |
| RNN-TDQC (Ours) | 0.107 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-MLP-TDQC (Ours) | 0.128 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-MLP-TDQC (Ours) | 0.131 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-MLP BCE | 0.137 | Not recorded | 69e9a78555a3c32af89f6fea |
| RNN-TDQC (Ours) | 0.141 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-RNN | 0.148 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-MLP-TDQC (Ours) | 0.15 | Not recorded | 69e9a78555a3c32af89f6fea |
| RNN-BCE | 0.152 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-MLP BCE | 0.158 | Not recorded | 69e9a78555a3c32af89f6fea |
| RNN-BCE | 0.158 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-RNN | 0.162 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-MLP BCE | 0.162 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-RNN-TDQC (Ours) | 0.163 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-RNN | 0.172 | Not recorded | 69e9a78555a3c32af89f6fea |
| RNN-TDQC (Ours) | 0.197 | Not recorded | 69e9a78555a3c32af89f6fea |
| RNN-BCE | 0.206 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-RNN-TDQC (Ours) | 0.218 | Not recorded | 69e9a78555a3c32af89f6fea |
| Avg prob. | 0.218 | Not recorded | 69e9a78555a3c32af89f6fea |
| Avg entropy | 0.222 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-MLP-TDQC (Ours) | 0.229 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-MLP BCE | 0.231 | Not recorded | 69e9a78555a3c32af89f6fea |
| Running Avg prob. | 0.238 | Not recorded | 69e9a78555a3c32af89f6fea |
| SAFE-RNN | 0.255 | Not recorded | 69e9a78555a3c32af89f6fea |
| Running Avg entropy | 0.264 | Not recorded | 69e9a78555a3c32af89f6fea |
| Running Avg entropy | 0.273 | Not recorded | 69e9a78555a3c32af89f6fea |
| Avg entropy | 0.313 | Not recorded | 69e9a78555a3c32af89f6fea |
| Max prob. | 0.318 | Not recorded | 69e9a78555a3c32af89f6fea |
| Running Avg entropy | 0.33 | Not recorded | 69e9a78555a3c32af89f6fea |
| Running Avg prob. | 0.356 | Not recorded | 69e9a78555a3c32af89f6fea |
| Avg prob. | 0.364 | Not recorded | 69e9a78555a3c32af89f6fea |
| Max prob. | 0.39 | Not recorded | 69e9a78555a3c32af89f6fea |
| Avg entropy | 0.391 | Not recorded | 69e9a78555a3c32af89f6fea |
| Avg prob. | 0.532 | Not recorded | 69e9a78555a3c32af89f6fea |
| Running Avg prob. | 0.544 | Not recorded | 69e9a78555a3c32af89f6fea |
| Max prob. | 0.899 | Not recorded | 69e9a78555a3c32af89f6fea |

### SAFE-RNN-TDQC (Ours)

Brier Score: 0.097. Result ID: 69e9f93547f34ce924d1f465.

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

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

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

### SAFE-RNN-TDQC (Ours)

Brier Score: 0.1. Result ID: 69e9f93547f34ce924d1f454.

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

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

Recorded evaluation configuration: {"VLA Model":"UniVLA"}. This record does not assert independent reproduction.

### RNN-TDQC (Ours)

Brier Score: 0.107. Result ID: 69e9f93547f34ce924d1f458.

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

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

Recorded evaluation configuration: {"VLA Model":"UniVLA"}. This record does not assert independent reproduction.

### SAFE-MLP-TDQC (Ours)

Brier Score: 0.128. Result ID: 69e9f93547f34ce924d1f467.

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

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

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

### SAFE-MLP-TDQC (Ours)

Brier Score: 0.131. Result ID: 69e9f93547f34ce924d1f456.

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

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

Recorded evaluation configuration: {"VLA Model":"UniVLA"}. This record does not assert independent reproduction.

### SAFE-MLP BCE

Brier Score: 0.137. Result ID: 69e9f93547f34ce924d1f466.

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

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

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

### RNN-TDQC (Ours)

Brier Score: 0.141. Result ID: 69e9f93547f34ce924d1f463.

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

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

Recorded evaluation configuration: {"VLA Model":"π0-FAST"}. This record does not assert independent reproduction.

### SAFE-RNN

Brier Score: 0.148. Result ID: 69e9f93547f34ce924d1f45e.

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

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

Recorded evaluation configuration: {"VLA Model":"π0-FAST"}. This record does not assert independent reproduction.

### SAFE-MLP-TDQC (Ours)

Brier Score: 0.15. Result ID: 69e9f93547f34ce924d1f461.

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

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

Recorded evaluation configuration: {"VLA Model":"π0-FAST"}. This record does not assert independent reproduction.

### RNN-BCE

Brier Score: 0.152. Result ID: 69e9f93547f34ce924d1f457.

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

Recorded evaluation configuration: {"VLA Model":"UniVLA"}. This record does not assert independent reproduction.

### SAFE-MLP BCE

Brier Score: 0.158. Result ID: 69e9f93547f34ce924d1f455.

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

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

Recorded evaluation configuration: {"VLA Model":"UniVLA"}. This record does not assert independent reproduction.

### RNN-BCE

Brier Score: 0.158. Result ID: 69e9f93547f34ce924d1f462.

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

Recorded evaluation configuration: {"VLA Model":"π0-FAST"}. This record does not assert independent reproduction.

### SAFE-RNN

Brier Score: 0.162. Result ID: 69e9f93547f34ce924d1f453.

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

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

Recorded evaluation configuration: {"VLA Model":"UniVLA"}. This record does not assert independent reproduction.

### SAFE-MLP BCE

Brier Score: 0.162. Result ID: 69e9f93547f34ce924d1f460.

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

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

Recorded evaluation configuration: {"VLA Model":"π0-FAST"}. This record does not assert independent reproduction.

### SAFE-RNN-TDQC (Ours)

Brier Score: 0.163. Result ID: 69e9f93547f34ce924d1f45f.

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

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

Recorded evaluation configuration: {"VLA Model":"π0-FAST"}. This record does not assert independent reproduction.

### SAFE-RNN

Brier Score: 0.172. Result ID: 69e9f93547f34ce924d1f464.

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

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

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

### RNN-TDQC (Ours)

Brier Score: 0.197. Result ID: 69e9f93547f34ce924d1f44d.

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

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

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

### RNN-BCE

Brier Score: 0.206. Result ID: 69e9f93547f34ce924d1f44c.

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

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

### SAFE-RNN-TDQC (Ours)

Brier Score: 0.218. Result ID: 69e9f93547f34ce924d1f449.

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

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

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

### Avg prob.

Brier Score: 0.218. Result ID: 69e9f93547f34ce924d1f45a.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a271e209131cea815f1.md>)

Recorded evaluation configuration: {"VLA Model":"π0-FAST"}. This record does not assert independent reproduction.

### Avg entropy

Brier Score: 0.222. Result ID: 69e9f93547f34ce924d1f45c.

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

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

Recorded evaluation configuration: {"VLA Model":"π0-FAST"}. This record does not assert independent reproduction.

### SAFE-MLP-TDQC (Ours)

Brier Score: 0.229. Result ID: 69e9f93547f34ce924d1f44b.

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

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

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

### SAFE-MLP BCE

Brier Score: 0.231. Result ID: 69e9f93547f34ce924d1f44a.

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

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

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

### Running Avg prob.

Brier Score: 0.238. Result ID: 69e9f93547f34ce924d1f45b.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a271e209131cea815f1.md>)

Recorded evaluation configuration: {"VLA Model":"π0-FAST"}. This record does not assert independent reproduction.

### SAFE-RNN

Brier Score: 0.255. Result ID: 69e9f93547f34ce924d1f448.

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

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

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

### Running Avg entropy

Brier Score: 0.264. Result ID: 69e9f93547f34ce924d1f45d.

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

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

Recorded evaluation configuration: {"VLA Model":"π0-FAST"}. This record does not assert independent reproduction.

### Running Avg entropy

Brier Score: 0.273. Result ID: 69e9f93547f34ce924d1f447.

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

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

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

### Avg entropy

Brier Score: 0.313. Result ID: 69e9f93547f34ce924d1f446.

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

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

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

### Max prob.

Brier Score: 0.318. Result ID: 69e9f93547f34ce924d1f459.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a271e209131cea815f1.md>)

Recorded evaluation configuration: {"VLA Model":"π0-FAST"}. This record does not assert independent reproduction.

### Running Avg entropy

Brier Score: 0.33. Result ID: 69e9f93547f34ce924d1f452.

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

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

Recorded evaluation configuration: {"VLA Model":"UniVLA"}. This record does not assert independent reproduction.

### Running Avg prob.

Brier Score: 0.356. Result ID: 69e9f93547f34ce924d1f445.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a271e209131cea815f1.md>)

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

### Avg prob.

Brier Score: 0.364. Result ID: 69e9f93547f34ce924d1f444.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a271e209131cea815f1.md>)

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

### Max prob.

Brier Score: 0.39. Result ID: 69e9f93547f34ce924d1f443.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a271e209131cea815f1.md>)

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

### Avg entropy

Brier Score: 0.391. Result ID: 69e9f93547f34ce924d1f451.

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

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

Recorded evaluation configuration: {"VLA Model":"UniVLA"}. This record does not assert independent reproduction.

### Avg prob.

Brier Score: 0.532. Result ID: 69e9f93547f34ce924d1f44f.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a271e209131cea815f1.md>)

Recorded evaluation configuration: {"VLA Model":"UniVLA"}. This record does not assert independent reproduction.

### Running Avg prob.

Brier Score: 0.544. Result ID: 69e9f93547f34ce924d1f450.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a271e209131cea815f1.md>)

Recorded evaluation configuration: {"VLA Model":"UniVLA"}. This record does not assert independent reproduction.

### Max prob.

Brier Score: 0.899. Result ID: 69e9f93547f34ce924d1f44e.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a271e209131cea815f1.md>)

Recorded evaluation configuration: {"VLA Model":"UniVLA"}. This record does not assert independent reproduction.

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