Classify Document Scope with Intelligent Keyword Classifier

Hello,
I am having trouble to classify trained DocumentTypes the “Classify Document Scope” throws an error as below:

Classify Document Scope: Invalid character after parsing property name. Expected ‘:’ but got: }. Path ‘[3].FirstPageVector.TermsWithScores[105].Term’, line 1, position 319137.

I have tried the workaround suggested in this post: Issue With Training Classifiers
By reading the Learning File beforehand and assigning it to LearnData string variable. However the error persists.
I have 10 DocumentTypes each is from different brands but fields are same.

Anyone had similar error ?

Best Regards,
Onur