G.13:2 - Problem

External sources publish claim‑adjacent signals (citations, concept graphs, “task/method” tags, replication links, dataset usage, disruption‑style indicators, benchmark metadata). These are useful for generation (palette building, declared set-result exploration, candidate bridge discovery), not only for audit. But typical interop practices create predictable failure modes:

• CN/CG spec-ref leakage. External numeric signals get treated as if they were lawful “scores” without explicit binding to CHR/CAL/CG surfaces.
• Implicit crossings. Cross‑context and cross‑plane reuse happens through opaque transformations, without explicit exposure of the crossing bundle pins needed downstream.
• Edition drift + refresh brittleness. Snapshots change, schemas drift, indicator definitions get revised; without edition‑pinned interop surfaces and typed trigger causes, parity and dashboard stability degrade.
• Evidence disconnect. “Derived features” are produced without explicit EvidenceGraph anchoring, making later refutation/repair expensive.
• Format‑as‑norm. A convenient serialisation (KG export, JSON schema, RO‑Crate, etc.) becomes treated as the specification, undermining notation independence.