RICK: Certifying Transmission in Multi-Agent Credit Assignment via Worst-Regime Selection

A cooperative team trained from one shared reward learns exactly what its credit assignment tells it, so the kernel that decides which agent earned a delayed outcome is itself the training signal. However, that kernel is fitted to behaviour logs whose releases and arrivals share one exogenous driver, and every quantity that certifies it, the fit residual, the perturbation schedule and the conservation percentage, is read off those same logs, so the evidence certifies itself: a kernel can leave only $0.0261$ of the recorded variance unexplained while its coefficients sit $0.4541$ from the truth, and no reading inside the log separates the two. We propose the Regime-Invariant Credit Kernel (), which selects the kernel on intervention regimes the team manufactures and pays for. Regime-invariant kernel selection pins the kernel by its worst per-regime discrepancy instead of its aggregate fit. A regime scheduler commits the perturbation family under a bound on the return it costs, and a stop-gradient keeps team return out of the selection. Delayed backtracking and share accounting states the arrived mass a bounded window cannot reach as an unassigned share. Together, the three modules replace each self-certifying readout with one that can fail: a kernel propped up by the shared driver leaves a manufactured regime poorly explained, and the mass a window misses stays on the books. Scored against exact ground truth over ten draws per cell on three delayed environments, recovers the generating coefficients on the fan-in environments to a mean of $0.0935$, against $0.2186$ for the pooled aggregate fit at the same recording budget. On a structurally distinct held-out family it keeps that ordering, at $0.0539$ against $0.1151$ for the pooled aggregate fit.