The sampling-algorithm cybernetics conjecture

Consider the subcategory of $\mathbf{BayesLens}$ spanned by finite-dimensional smooth manifolds, with morphisms generated under sequential and parallel composition by the generalized autoencoder and inference games. Sampling-algorithm cybernetics conjecture. Sampling algorithms, such as Markov chain Monte Carlo, should supply a corresponding category of open cybernetic systems of interest. The conjecture extends the paper's variational-Bayesian cybernetic realizations to other families of approximate inference methods, but the source does not state whether it has been proved or refuted.