# Early Failure Detection on RoboCasa S (Unseen) Source: [Early Failure Detection on RoboCasa S (Unseen)]() Collection index: [llms.txt]() Data updated: 2026-06-09T08:53:40.762Z Evaluation of model performance on Early Failure Detection using the RoboCasa S (Unseen) subset, measured by 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) | RoboCasa S (Unseen) | | Metric | ROC-AUC (q=0.25) | | 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 - [ROC-AUC (q=0.25)](): Higher is better; unit: PERCENT. ## Recorded results | Method | ROC-AUC (q=0.25) | Result date | Report paper | | --- | --- | --- | --- | | ActProbe | 73.8 | Not recorded | 6a279e1f90966ade919bf751 | | SAFE-LSTM | 73.1 | Not recorded | 6a279e1f90966ade919bf751 | | SAFE-MLP | 71 | Not recorded | 6a279e1f90966ade919bf751 | | SAFE-MLP-TDQC | 70.4 | Not recorded | 6a279e1f90966ade919bf751 | | LogpZO | 67.2 | Not recorded | 6a279e1f90966ade919bf751 | | STAC-Single | 66 | Not recorded | 6a279e1f90966ade919bf751 | | SAFE-LSTM-TDQC | 62.4 | Not recorded | 6a279e1f90966ade919bf751 | | Cosine k-NN | 44.4 | Not recorded | 6a279e1f90966ade919bf751 | ### ActProbe ROC-AUC (q=0.25): 73.8. Result ID: 6a27d420fbc373592c24b0b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"π0.5"}. This record does not assert independent reproduction. ### SAFE-LSTM ROC-AUC (q=0.25): 73.1. Result ID: 6a27d420fbc373592c24b0b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"π0.5"}. This record does not assert independent reproduction. ### SAFE-MLP ROC-AUC (q=0.25): 71. Result ID: 6a27d420fbc373592c24b0b5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"π0.5"}. This record does not assert independent reproduction. ### SAFE-MLP-TDQC ROC-AUC (q=0.25): 70.4. Result ID: 6a27d420fbc373592c24b0b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"π0.5"}. This record does not assert independent reproduction. ### LogpZO ROC-AUC (q=0.25): 67.2. Result ID: 6a27d420fbc373592c24b0b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"π0.5"}. This record does not assert independent reproduction. ### STAC-Single ROC-AUC (q=0.25): 66. Result ID: 6a27d420fbc373592c24b0b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"π0.5"}. This record does not assert independent reproduction. ### SAFE-LSTM-TDQC ROC-AUC (q=0.25): 62.4. Result ID: 6a27d420fbc373592c24b0b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"π0.5"}. This record does not assert independent reproduction. ### Cosine k-NN ROC-AUC (q=0.25): 44.4. Result ID: 6a27d420fbc373592c24b0b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"π0.5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.