Attenuation or Removal? Calibrated Reading of Usable Conditional Information

Cross-modal alignment trains a representation to match a description that is almost never complete. Does the alignment remove content the description omits, or merely make it harder to access? A finite probe cannot tell from a single operating point: its reading depends both on representation change and on where the target sits along its resolution curve. We separate representation-level conditional information from finite-resolution accessibility, and read usable information across Gaussian-noise resolution $\sigma$. Similarity transforms translate the resulting curve along $\log \sigma$, which is why the raw magnitude of a fixed-resolution diagnostic does not identify mechanism. Calibrating the probe with known invertible transforms then defines information-preserving nulls with an explicit floor and power region: a trajectory landing on such a null is not thereby shown invertible; it belongs to the instrument's observational equivalence class of information-preserving change. On fine-tuned CLIP checkpoints the Stanford Cars category channel contracts by $0.60$ nats of log-resolution while a construction-independent control does not, yet the trajectory remains indistinguishable from information-preserving attenuation; on CUB both targets expand instead, so we claim no universal sign. A local model of contrastive fine-tuning explains how this arises: alignment leaves the covariance-private block unchanged whereas the negative-sampling term contracts it, with an exactly preserving scalar regime and a perturbation bound around it. Synthetic ground truth separates attenuation from genuine removal, temperature interventions move contraction as predicted, and the calibrated pattern extends to DeepFashion, RSICD and COCO.