Object-Spatial Programming

Abstract: The evolution of programming languages from low-level assembly to high-level abstractions demonstrates a fundamental principle: by constraining how programmers express computation and enriching semantic information at the language level, we can make previously undecidable program properties tractable for optimization. Building on the insight of this undecidability-lessening effect, we introduce Object-Spatial Programming (OSP), a novel programming model that extends Object-Oriented Programming by introducing topologically-aware class constructs called archetypes. OSP fundamentally inverts the traditional relationship between data and computation, enabling computation to move to data through four specialized archetypes: object classes, node classes (discrete data locations), edge classes (first-class relationships), and walker classes (mobile computational entities). By making topological relationships and traversal patterns explicit at the language level, OSP transforms previously opaque program behaviors into observable, optimizable patterns. This semantic enhancement enables runtime systems to make informed decisions about data locality, parallel execution, and distribution strategies based on explicit topology, while providing programmers with intuitive abstractions for modeling complex systems where connection topology is central to the computational model. The paradigm addresses fundamental limitations in traditional programming models when representing agent-based systems, social networks, neural networks, distributed systems, finite state machines, and other spatially-oriented computational problems, demonstrating how thoughtful abstraction design can simultaneously enhance programmer expressiveness and enable sophisticated system-level optimizations across the computing stack.