Causal Reasoning Using Conditional Causal Possibilities to Express Uncertainty of Causalities

This paper addresses an uncertain reasoning based on causal knowledge given by two layered network, where nodes in one layer express possible causes and those in the other are possible results. Uncertainties of the causalities are given by Conditional Causal Possibilities, which are proposed to express uncertainties of causalities we recognize in mind. The conventional Conditional Possibilities, on the other hand, are different from our cognition of possibilities for causalities, because they are a possibilistic evaluation including cases where the result is caused by other events than the one in the conditional part. The causal reasoning that the paper addresses uses the above Conditional Causal Possibilities, and derives conditional possibility distributions of arbitrarily chosen nodes, when some other nodes are instantiated.