ResearchTasksDiscovering the cause of incorrect predictionsDiscovering the cause of incorrect predictionsFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedVGG-SoundLIMA26.56Avg Highest Confidence (Top 25%)8May 20, 2026LC25000 Lung (test)LIMA (w/ SLICO)62.15Average Highest Confidence (0-25%)6May 20, 2026