f1298750ed09618717f9c10ea8d1d3b0-AuthorFeedback.pdf

Samples corrected by self-training were (a) Synthetic source data: blondness perfectly (b) Synthetic target data: each gender mostly mistakenly predicted because of the correlates with the male gender. We thank the reviewers for the detailed and insightful feedback. The reviewers noted that the paper "target[s] a timely Clarification on why this is not provided or difficult to provide... would be useful." Instead, we focus on removing the spurious features. We respectfully and strongly disagree.