# Audit-endpoint disagreement on LIMO Source: [Audit-endpoint disagreement on LIMO]() Collection index: [llms.txt]() Data updated: 2026-06-09T10:34:17.825Z Evaluation of model performance on the LIMO dataset using audit-endpoint disagreement metrics, including L^A, R^M, and AEDS variants. 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 | Audit-endpoint disagreement | | Dataset (including any stated split) | LIMO | | Metric | L^A | | Unit | PERCENT | | Direction | Lower 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 - [L^A](): Lower is better; unit: PERCENT. - [R^M (Paper)](): Lower is better; unit: PERCENT. - [R^M (LiRA)](): Lower is better; unit: PERCENT. - [R^M](): Lower is better; unit: PERCENT. - [AEDS](): Lower is better; unit: PERCENT. - [AEDS (95% CI)](): Lower is better; unit: PERCENT. - [p-value](): Lower is better; unit: SCALAR. - [Endpoint-only Disagreement](): Lower is better; unit: SCALAR. - [AEDS Correlation](): Lower is better; unit: SCALAR. ## Recorded results | Method | L^A | Result date | Report paper | | --- | --- | --- | --- | | LaBraM | 30.6 | Not recorded | 6a279e5690966ade919bf9e7 | ### LaBraM L^A: 30.6. Result ID: 6a27eb58fbc373592c25620c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LaBraM"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.