# Skill Invocation Safety Auditing on SIA-Bench Locked in-distribution (test) Source: [Skill Invocation Safety Auditing on SIA-Bench Locked in-distribution (test)]() Collection index: [llms.txt]() Data updated: 2026-04-14T08:52:43.477Z Evaluation of model performance on the SIA-Bench Locked in-distribution test set, focusing on skill invocation safety auditing using metrics like HR-AUPRC, Rec@10%, and ECE. 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 | Skill Invocation Safety Auditing | | Dataset (including any stated split) | SIA-Bench Locked in-distribution (test) | | Metric | HR-AUPRC | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [HR-AUPRC](): Higher is better; unit: PERCENT. - [Recall@10%](): Higher is better; unit: PERCENT. - [Precision@10%](): Higher is better; unit: PERCENT. - [Spearman Correlation](): Higher is better; unit: SCALAR. - [ECE (Expected Calibration Error)](): Lower is better; unit: PERCENT. - [W-MAE (Weighted Mean Absolute Error)](): Lower is better; unit: PERCENT. ## Recorded results | Method | HR-AUPRC | Result date | Report paper | | --- | --- | --- | --- | | Fusion | 20.4 | Not recorded | 69ddca377d0172140ec79b88 | | Contextual | 19.5 | Not recorded | 69ddca377d0172140ec79b88 | | Text-Only | 18.9 | Not recorded | 69ddca377d0172140ec79b88 | | Static Prior | 18.8 | Not recorded | 69ddca377d0172140ec79b88 | | Denylist | 18.8 | Not recorded | 69ddca377d0172140ec79b88 | | No Audit | 16.9 | Not recorded | 69ddca377d0172140ec79b88 | | Agent-Audit | 16.9 | Not recorded | 69ddca377d0172140ec79b88 | ### Fusion HR-AUPRC: 20.4. Result ID: 69de005647f34ce924c58ca9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Contextual HR-AUPRC: 19.5. Result ID: 69de005647f34ce924c58ca8. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Text-Only HR-AUPRC: 18.9. Result ID: 69de005647f34ce924c58ca7. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Static Prior HR-AUPRC: 18.8. Result ID: 69de005647f34ce924c58ca4. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Denylist HR-AUPRC: 18.8. Result ID: 69de005647f34ce924c58ca5. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### No Audit HR-AUPRC: 16.9. Result ID: 69de005647f34ce924c58ca3. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Agent-Audit HR-AUPRC: 16.9. Result ID: 69de005647f34ce924c58ca6. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.