highly significantp < 0.001
3 , kappa values ranged from 0.79 to 0.95 across 1- to 5-shot examples, all with highly significant z-tests ( p < 0.001).
3 , kappa values ranged from 0.79 to 0.95 across 1- to 5-shot examples, all with highly significant z-tests ( p < 0.001).
0.729, p < 0.01), whereas differences in recall and F1-score did not reach statistical significance.