Abstract. This paper discusses the relationship between incidence calculus and the ATMS. It shows that managing labels for statements in an ATMS is similar to producing the incidence sets of these statements in incidence calculus. We will prove that a probabilistic ATMS can be implemented using incidence calculus. In this way, we can not only produce labels for all nodes in the system automatically, but also calculate the probability of any of such nodes in it. The reasoning results in incidence calculus can provide justi cations for an ATMS automatically.