English: ORES is a machine learning system for classifying edits to Wikipedia according to whether they are damaging or goodfaith. This plot compares model predicted probabilities for the damaging models to probabilities estimated from a sample of human labeled edits according to whether the subject of the article is in the global north or the global south. Results for the 26 Wikis on which ORES damaging models are deployed show no clear evidence of encoded bias along geographic lines.