Hello! 

We use iKnow's GetSimilar for decision making. Right now we have a domain with both good and bad documents and using GetSimilar we want to see if a document is more similar to the good ones or the bad ones. To do this we simply compare the weighted average of the score from the good ones and the bad ones that GetSimilar returns.  

The problem is that GetSimilar doesn't always return the score to all other documents. Assuming we have 50 documents I would expect the following result:

DO ##class(%iKnow.Queries.SourceAPI).GetSimilar(.

Hello! 

My group and I are currently doing a research project on natural language processing and iKnow plays a big role in this project.  I am aware that the algorithms iKnow use aren't public, and I respect that.

My question is, are there any public documents/research that explains, at least part of, the algorthims iKnow uses and the motivations for using them?  

Here is a concrete example:  We are using GetSimilar() for many of our results and it works very well.