I think this formulation is awkward. any more elegant way of stating it formally without the i and j stuff?

Why must it learn two mappings? maybe this statement is wrong

this could depend on settings. maybe for some settings the evidence mapping is very easy, but not a simple mapping from types. so make this less strong statements

I wonder whether we should motivate the paper with a big picture policy question (how to fight corruption) that requires understanding how it works and is organized. Knowing that we can better understand how the organizing responds to enforcement, what are signatures to look for (and which signatures are easily circumvented). Not sure exactly. But point is we must start with a very clear policy question. Then argue that existing literature comes short. Not just start with literature gap.