This paper develops provider-independent structural reference layers for AI and AGI environments. It addresses the risk that documents, roles, authority conditions, state histories, seal references, human discretion, economic references, preservation contexts, and propagation boundaries may become dependent on the provider, platform, model, cloud, agent framework, or workflow system that happens to generate or mediate an output. The framework separates implementation capability from structural reference. An AI or AGI implementation environment may generate, route, summarize, transform, assist, or mediate an output, but it does not thereby determine which document unit the output corresponds to, which role may refer to it, which authority-condition boundary applies, whether a state-history or seal-reference relation exists, whether human discretion has been preserved, whether an economic reference remains pre-effect, or how far a record may circulate. This paper follows Paper 11 and provides the general foundation for the second-phase infrastructure studies on government reference infrastructure, telecommunications edge reference nodes, distributed reference hardware, document-state layers, time-history and seal-reference structures, post-cloud preservation infrastructure, economic reference objects, domain design references, and institutional propagation boundaries.
The First Waters (2026) studied this question.