Thanks for the link, Benjamin. Can one give a Hasekll type to a particle filter? In the arxiv paper you linked, I found this quite unnerving sentence: "The divergence between the true conditioned distribution on execution traces and the distribution encoded by the program may depend strongly on what inference instructions are chosen and how they are interleaved with the incorporation of data." Does this mean: Here is a programming language that may or may not compute what you meant it to do? --Olaf