ResearchTasksCoder reliabilityFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedTransfer sample n = 400CSAF0.81Krippendorff's Alpha1Jun 4, 2026sample (n = 450) (val)CSAF0.86Krippendorff's Alpha1Jun 4, 2026Codebook sample (n = 250) (dev)CSAF0.85Krippendorff's Alpha1Jun 4, 2026