SDC in brief¶

PlateLanguage describes; judgement decides. The gap is the architecture.

One sentence¶

Split-Domain Cognition is a principle that keeps language work (descriptive, generative, interpretive) and judgement work (evaluative, verdictive, categorical) structurally apart, because fusing them in a single call produces reliably the same failures — unauditable verdicts, descriptions that smuggle evaluation, rubrics that cannot be taught, drift under pressure, sycophancy in machines.

One paragraph¶

Split-Domain Cognition is the observation that, whenever a single agent — a person, a model, an institution, a form — is asked to do two unlike kinds of thinking in the same breath, a predictable pattern of failure appears. The first kind of thinking is descriptive: it attends to what is there. The second is verdictive: it closes on an outcome. The two can look similar from outside and feel like one continuous act from inside. They are not one continuous act. Their criteria are different in kind: language work goes right by coverage-under-interpretation, judgement work by reproducibility-under-rule. Optimised in the same channel, they contaminate each other. SDC is the architecture that refuses the contamination — keep the two domains structurally apart, let each be answerable to the criteria proper to itself.

The AI-pipeline instance¶

In software, SDC is most commonly expressed as a three-stage pipeline.

Stage 1 — Language work. A language model reads unstructured input (concept statement, transcript, sketch description, menu, brief) and produces structured signals: classifications, embeddings, extracted features.
Stage 2 — Judgement work. Deterministic code applies thresholds, priorities, and rules to those signals and produces a verdict: a score, a ranking, a surfacing decision.
Stage 3 — Language work (again). A language model narrates the verdict in readable prose.

The three stages are held apart on principle. Language models are good at pattern recognition across language but unreliable at verdicts that must be consistent, auditable, and reproducible. Code is good at verdicts but cannot generate fluent narration without overwhelming the user. Each stage does what it is good at. None borrows the criteria of another.

Why this is a principle, not only a pipeline¶

The pipeline is the most compact expression of SDC. It is not the whole of SDC. The same move shows up in teaching (rubric-bound critique separated from generative making), curation (description separated from curatorial thesis), animal ethics (rights-grounded judgement separated from welfare-language description), editorial work, and many other places.

The AI instance makes the move precise because software forces precision. But the move is older than the software and will outlast any particular implementation. See principle-not-pattern in the repository for the longer argument. ¹

When does SDC apply?¶

All three must hold:

Two kinds of cognition are in play. Generative/interpretive and evaluative/verdictive activity, both present.
They are at risk of collapsing. In current practice the two are being done in the same call — same person, model, form, moment.
The collapse produces a measurable cost. Trust eroding, decisions indefensible, learners cannot learn the criteria, stakeholders cannot re-enter the argument.

If all three hold, SDC is appropriate. If fewer, it is probably not.

When does SDC not apply?¶

Generative-only work (a painting, a poem, an improvisation).
Judgement-only work with no language component (a tax calculation, a chess move).
Domains where the fusion is the point (oratory, advertising, evangelism).
Decisions where speed matters more than auditability (emergency triage).

A principle with a clear scope is a principle with teeth. SDC declines to be everything.

The long-form articulation lives in the project repository as sdc.md and principle-not-pattern.md. A public rendering of the long-form is forthcoming; for now, read the condensation above and follow the derivation protocol for your own domain. ↩