This article describes the semantics of the language of statecharts as implenented in the STATEMATE system [Harel et al. 1990; Harel and Politi 1996]. The initial version of this semantics was developed by a team about.10 years ago. With the added experience of the users of the system it has since been extended and modified. This executable semantics has been in operation in driving the simulation, dynamic tests, and code generation tDols of STATEMATE since 1987, and a technical report describing it has been available from i-Logix, Inc. since 1989. We have now decided to revise and publish the report so as to make it more widely accessible, to alleviate some of the confusion about the "official semantics of the language, and to counter a number of incorrect comments made in the literature about the way statecharts have been implemented. For example, the survey [yon der Beek 1994] does not mention the STATEMATE implementation of statecharts or the semantics adopted for it at all, although this semantics is different from the ones surveyed therein (and was developed earlier than all of them except for Harel et al. [1987]). As another example, Leveson et al. [1995] describe a case that exhibits an unacceptable kind of behavior in a statechart, which they say is what the "semantics of statecharts" leads to (pp. 695-697). Unfortunately, they base their discussion of statechart semantics on one of the many semantics proposed by various authors (that of Pnueli and Shalev [1991]) and give the reader the impression that this is the official semantics of the language