From the paper: https://sci-hub.se/10.3847/1538-3881/ab570f

"We show that these objects are redder and have larger proper motions than typical USNO objects." -- Interesting, not sure what that'd imply.

"A particular focus is given to USNO objects that have several detections before vanishing" -- implies that these at least some of these objects are not just detector glitches or scratches or similar, although "Visual checks confirm that indeed the most interesting cases, about 100, are mostly one-time detections in the red band."

"In a separate paper by K. Pelckmans et al. (2019, in preparation). we propose a new tool for handling a large number of images using methods of machine learning." (since people were talking about ML in astronomy)