Predicted Links as Messages: Separating Formation from Propagation in Temporal Graphs

Temporal graph models propagate information along recorded interactions. This convention leaves a plausible future relation unavailable as context until it appears, even when the observed history already supports it. Admitting the relation early can connect useful representations, but it can also transmit an irrelevant state. The missing decision is therefore not only which relation may form, but whether and how it should carry a message. We formalize future-relation message admission under a disjoint temporal protocol. Mechanism-Guided Graph Evolution (MGGE) uses historical formation evidence to freeze a sparse graph of schema-valid non-edges. A uniform residual channel then exposes this graph without writing predicted relations into temporal memory. At the common $K=8$ budget, paired 95% bootstrap confidence intervals for $\Delta$MRR lie above zero on Wiki, Enron, UCI, and GoogleLocal, with gains ranging from $0.00105$ to $0.01188$ MRR. Equal-budget controls show that utility depends on graph membership rather than edge count alone. Candidate-level analysis shows that formation rank is not a monotone ordering of message utility. On Wiki and GoogleLocal, two-sided exposure consistently exceeds source-only exposure across the tested budgets. A directional decomposition identifies an additional path through the destination representation. Predicted links are therefore candidate communication channels: formation constrains admission, while intervention and exposure determine utility.