We introduce ChainRF, a Bayesian prior that links RF burst timings to on-chain mempool
dynamics and protocol heartbeats. ChainRF conditions a GM-PHD tracker (bearings + GhostRF delay) on mempool windows and fee-pressure regimes, yielding closed-form MI bounds that
price dwell K under temporal alignment. A depth-2 NBV planner maximizes information per
second while ActionGate prunes unsafe branches (I1–I12/E1–E4). We provide stubs for live
mempool feeds, a simulator for RF↔chain alignment jitter, and a results blurb that auto-injects
NBV choices + TLC PASS.