Just highlighting an overlap between the ideas expressed here and a stream that has recently been added to the MATS Summer 2024 Program.
This is not a direct extension of the work but something that shares some of intuitions and might help to formalise the ideas expressed in the post.
The grant proposal for the work is here. The proposal was submitted to Manifund (see here), where it was noticed by Ryan Kidd and subsequently added to the MATS program instead of receiving direct funding.
Do have a read and/or reach out if you're interested!
Here's a speculative correspondence that I hope might eventually have some applicability somewhere.
I view some of this as reflecting the difference between criminology and crime science. From what I understand criminology focuses more on the individual, using sociology, psychology, etc; it seems inherently internal, looking for deeper answers to why people commit crime. Crime science instead focuses more on a practical, "surface-level" approach, using a combination of empirical techniques to predict and prevent crime.
To my mind mech-interp seems more the former, and prosaic interp more the latter.
Here's a reference in case anyone's interested. Curious to hear if anyone has thought about this before of has any takes.