At the beginning of July the test data will be released.Given the information available we know that a portion of data will come from one of the known sites while the remaining portion will come from an unkown/unseen site.

Is it possible to know a little more in detail the format and the kind of data that will be released for the test phase? For example, will be available a phenotypic file? What kind of attributes/columns will be hidden and what will be available? Will the information on site be available as input data to prediction or part of the inference task? What about gender, age, handedness, ... ?

Thanks in advance.
Paolo A.