Measure Before Reuse: Checkpoint Deltas as Post-Training Routing Signals

Open-model ecosystems increasingly require users to choose among post-training actions before the relevant evaluations are known: accept a new checkpoint or adapter, search over merges, run targeted regression tests, reuse a prior capability delta ${\Delta }_{\mathrm{cap}}$, or avoid reuse. Existing delta methods mainly consume checkpoint deltas as construction objects. We argue that they should first be measured as data-free routing signals. Our two-stage workflow compares a prior capability delta ${\Delta }_{\mathrm{cap}}$ with an update delta ${\Delta }_{\mathrm{task}}$: Stage I uses checkpoint geometry alone to route to an action family, while Stage II uses benchmark deltas and sample-wise forgetting/backward-transfer transitions to confirm, revise, or reject candidates within that family. The geometry combines a norm ratio $r=\Vert {\Delta }_{\mathrm{task}}\Vert /\Vert {\Delta }_{\mathrm{cap}}\Vert$ for displacement risk with module-level alignment for directional context. Across 20 post-training variants in our suite, norm ratio is the strongest coarse risk indicator, MLP and attention alignment add useful directionality, and global alignment does not. Case studies route a weak-conflict S1 regime to merge search, an adverse S2 regime away from prior reuse, and a statistically non-null but practically near-null SC LoRA case to targeted evaluation. In a fixed-candidate, branch-level routing study, geometry-guided action-family routing reaches mean Overall $\Delta =+0.041$ after Stage-II evaluation, compared with $-0.219$ for always-prior and $-0.137$ for never-prior. This is branch-level evidence over precomputed candidates, not prospective intervention selection or evaluation-cost reduction. Checkpoint deltas are evidence before they are ingredients.