AI RESEARCH
Deterministic Event-Graph Substrates as World Models for Counterfactual Reasoning
arXiv CS.AI
•
ArXi:2605.15967v1 Announce Type: new We study event-graph substrates: a class of world models that represent agent state as an append-only log of typed RDF triples and answer counterfactual queries by forking the log under a structured intervention vocabulary. Substrates are inspectable at the triple level, exact counterfactuals, and transfer across domains without learned components.