Gwet's AC1
A statistic for measuring inter-rater agreement, suited to categorical annotation tasks with imbalanced class distributions, and more robust than Cohen's Kappa in such settings.
Timeline (last 90 days)
The model judges' agreement with human adjudication labels on 1,860 elements (Gwet's AC1) was at least 0.894.
Gwet's AC1 is a statistic used to measure inter-rater agreement, applicable to classification annotation tasks with imbalanced category distributions, and is more robust than Cohen's Kappa when one category accounts for an extremely high proportion.
All Facts (2)
The model judges' agreement with human adjudication labels on 1,860 elements (Gwet's AC1) was at least 0.894.
50%UnverifiedGwet's AC1 is a statistic used to measure inter-rater agreement, applicable to classification annotation tasks with imbalanced category distributions, and is more robust than Cohen's Kappa when one category accounts for an extremely high proportion.
50%