Runtime Verification typically assumes a fixed alphabet of observable actions. This assumption becomes fragile in evolving software systems, where updates, reconfigurations, or architectural changes may rename, hide, split, or fuse actions while preserving the system’s high-level intent. In these cases, previously valid monitors and specifications may become misaligned with the running system. In this paper, we study runtime semantic discovery, namely the problem of identifying whether newly observed actions play the same monitoring-relevant role as previously known ones, without reconstructing a global behavioural model. To this end, we propose a local and runtime-computable notion of action similarity based on the neighbour contexts in which actions occur within execution traces. We define a family of k-neighbour equivalences together with an abstraction-based mechanism for comparing systems whose observable alphabets differ. Our approach is intentionally lightweight: it does not aim at fully characterising behavioural preservation, but at identifying candidate semantic correspondences between actions in evolving systems. We discuss the expressive power and limitations of neighbour-based equivalence and show how inferred correspondences can support monitor and specification adaptation in selected classes of alphabet evolution.