Why it is a question
A110 §IX.5: “For composed reconstruction kernels, characterize the evolution of (D_obs(n), D_struct(n), D_dec(n)). Determine when these quantities converge together, diverge, or evolve independently. This includes the possibility that a chain becomes conventionally interpretable while losing ancestral pragmatic structure.”
Where it stands
Manuscript §8: “We propose observing how selected invariants, decision risks, and compatibility structures evolve together; their trajectories need not coincide.” Narrower forms are already filed: sufficiency along a chain (QUESTION-016), and one task family kept while another is lost (QUESTION-010). CLAIM-081 gives one case of divergence.
Note of 2026-10-11: material in the record that may bear on this
A synthesis review of 2026-10-11 found these entries bearing on this
question without being linked to it. Each is listed for what its title
says; none has yet been assessed as an answer, and none is linked by
answers.
- CLAIM-031: A reconstruction chain reorganizes observational constraints rather than only accumulating metric error: a…
- CLAIM-114: Drift along a reconstruction chain can be marked by a pragmatic phase change, the first generation at…
- CLAIM-128: Transports whose distortion profiles trade off are incomparable until a task fixes weights, so no single…
- TERM-043: fidelity, as a profile of directed distortions compared component by component
- THEORY-155: Iterated learning by Bayesian agents who sample from the posterior converges to the shared prior
- CLAIM-177: An argument developed with collaborators who keep no memory fails at identity, not at structure: concepts…