It is inconceivable how chaotic the world would look to hu-mans, faced with innumerable decisions a day to be made un-der uncertainty, had they been lacking the capacity to distin-guish the relevant from the irrelevant—a capacity which com-putationally amounts to handling probabilistic independencerelations. The highly parallel and distributed computationalmachinery of the brain suggests that a satisfying process-levelaccount of human independence judgment should also mimicthese features. In this work, we present the first rational, dis-tributed, message-passing, process-level account of indepen-dence judgment, called D∗. Interestingly, D∗ shows a curi-ous, but normatively justified tendency for quick detection ofdependencies, whenever they hold. Furthermore, D∗ outper-forms all the previously proposed algorithms in the AI litera-ture in terms of worst-case running time, and a salient aspectof it is supported by recent work in neuroscience investigatingpossible implementations of Bayes nets at the neural level. D∗exemplifies how the pursuit of cognitive plausibility can leadto the discovery of state-of-the-art algorithms with appealingproperties, and its simplicity makes D∗ potentially a good can-didate as a teaching tool.

The Frame Problem (FP) is a puzzle in philosophy of mindand epistemology, articulated by the Stanford Encyclopedia ofPhilosophy as follows: “How do we account for our apparentability to make decisions on the basis only of what is relevantto an ongoing situation without having explicitly to considerall that is not relevant?” In this work, we focus on the causalvariant of the FP, the Causal Frame Problem (CFP). Assumingthat a reasoner’s mental causal model can be (implicitly) repre-sented by a causal Bayes net, we first introduce a notion calledPotential Level (PL). PL, in essence, encodes the relative po-sition of a node with respect to its neighbors in a causal Bayesnet. Drawing on the psychological literature on causal judg-ment, we substantiate the claim that PL may bear on how timeis encoded in the mind. Using PL, we propose an inferenceframework, called the PL-based Inference Framework (PLIF),which permits a boundedly-rational approach to the CFP, for-mally articulated at Marr’s algorithmic level of analysis. Weshow that our proposed framework, PLIF, is consistent withseveral findings in the causal judgment literature, and that PLand PLIF make a number of predictions, some of which arealready supported by existing findings.