Fig. B.1
Download original image
Recall confusion matrix of the bottom-level classifiers trained with the 176 features and the labeled set gathered in this work, only displaying the test set sources predicted with ≥50% probability. Generated using 20 random training and testing sets, we display a median, and the 5 and 95 percentiles for each class predictions.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.