Is there anything you can do to say something is not a duplicate? I downloaded a series of PDFs that are year end summaries of an account. So they all have the same layout and text, but the dates/years mentioned are different as are the amounts.
There are 8 of them. Initially, it marked them all duplicates, so I did a little research and turned on the stricter matching setting. But for some reason, it still thinks 2 of the documents are duplicates of each other. I looked at them. They are not the same, and I am not sure why DT thinks these two are more matched than any of the others.
