# Online Physical Risk Defense on LIBERO Long (Seen Tasks) Source: [Online Physical Risk Defense on LIBERO Long (Seen Tasks)]() Collection index: [llms.txt]() Data updated: 2026-04-27T07:39:51.290Z Evaluation of Online Physical Risk Defense performance on the LIBERO Long (Seen Tasks) dataset, reporting success rates with and without guard mechanisms (ASR) and the change in benign success rate (ΔBenign SR). 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 | Online Physical Risk Defense | | Dataset (including any stated split) | LIBERO Long (Seen Tasks) | | Metric | ASR without Guard | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 1 of 1 | | 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 - [ASR without Guard](): Higher is better; unit: PERCENT. - [ASR with Guard](): Higher is better; unit: PERCENT. - [ΔBenign SR](): Higher is better; unit: PERCENT. ## Recorded results | Method | ASR without Guard | Result date | Report paper | | --- | --- | --- | --- | | SimpleVLA-Guard | 90.9 | Not recorded | 69eeed6a55a3c32af89f9657 | ### SimpleVLA-Guard ASR without Guard: 90.9. Result ID: 69ef115947f34ce924d4ef66. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"online intervention","threshold calibration":"Functional Conformal Prediction","alpha":"0.05"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.