Evolution as Pillar
The fourth pillar was already there in the schema design. The _meta field says “hypothesis — designed to be deformed by the inference store.” That’s evolutionary epistemology. The word was already there; the pillar was unnamed.
What evolution means here. Hypotheses enter sparse. The inference store applies selection pressure. What doesn’t hold up against real data gets displaced — revised out of the schema, replaced by structure that actual inferences support. Schema versions, operator frameworks, author weights: all subject to that pressure. No special protection for any source or framework. Weak structure loses.
What this resolves about schema design. The RISC discipline — build sparse, resist premature complexity — can feel like excessive caution. Why not add Schütz, Goffman, Henrich, Bourdieu? The frameworks exist. The connections are plausible. The evolutionary framing gives the cleaner answer: the discipline isn’t “only add what’s proven,” it’s “add sparse hypotheses and let the data select.” The consequence of adding a framework too thickly — as a foundation rather than a hypothesis — is that it becomes harder for the data to dislodge. The RISC principle is about keeping the schema shapeable, not keeping it small.
The schema is the genome; inferences are selection pressure. Thin sourcing (Benedict at culture, Machin’s affective_field values) is intentional. These are hypotheses entering the coordinate space. _status: "stub" marks the parts not yet validated — processing code knows not to treat them as equivalent to validated dimensions.
Evolution applies to living theory, not just fixed code. Because the _src researcher names function as LLM query seeds at runtime, the theoretical layer also evolves. The LLM brings current scholarship — debates, extensions, critiques — to every inference run. The inference store validates whether theoretically-informed output holds up. Evolution selects across both the coded operator layer and the living theory layer simultaneously.
The velocity concern. Schemas are being generated faster than the inference store can validate them. Hypotheses entering faster than selection pressure can act. The risk: schemas depending on each other before any have been tested. The response: keep new schemas in input_ideas/ until the inference store has something to say about them — not to block input, but to maintain the distinction between hypothesis and validated structure. input_ideas/ is the holding pattern; validated structure earns its place in the main schema files.
The four pillars. Local-first. Privacy-preserving. No external taxonomies. Analogical orientation. Evolution is different in kind — not a constraint on behavior but a description of epistemology. How the system learns. How weak structure gets replaced without manual intervention. The inference store is not just the output of the pipeline — it is the selection environment.
Part of the Dimensional Fields project.