DescriptionORES damaging calibration errors by newcomers and anons.png
English: ORES is a machine learning system for classifying edits to Wikipedia according to whether they are damaging or goodfaith. This plot shows that, for the 25 Wikis on which ORES damaging models are deployed, and when the prediction threshold is chosen to maximize overall accuracy, that the model tends to underestimate the incidence of damaging edits. However, the models are most conservative for editors that are neither newcomers nor anonymous. Compared to other editors, the models score edits by newcomers and anons are more likely to be damaging.
to share – to copy, distribute and transmit the work
to remix – to adapt the work
Under the following conditions:
attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
share alike – If you remix, transform, or build upon the material, you must distribute your contributions under the same or compatible license as the original.