Hi. A month ago I announced that my anti-plagiarism robot would start working but due to some complications in its code I decided to keep it off.
The robot is not yet ready to determine whether or not to mark the publication.
The robot uses its own API to search for matches on the web and due to the amount of information it can find, the data received is not exact. That is, once the robot compares the data obtained with the publication of the possible plagiarist the result will not always be correct given the extensive information that is in google. that is why the robot does not know at what point the publications are plagiarism or not.
What can be done?
For now I plan to automatically make a report about the publications that are possibly a plagiarism, the report will mention the possible plagiarized publications, "Title, link of the publication and link where the information may possibly be plagiarized". once the report is published, the moderators team will be able to obtain this information and verify by other tools if the publications shown by the report are a plagiarism or not. Finally, the team of moderators can take the decision to mark or not mark the publications.
When @Vital take this and other decisions?
I don't know for now.
I will keep you informed when you begin to make the reports. Thanks for reading this little information.