Taxonomy / Consociational codification / Compiling statutes into software

Compiling statutes into software

Official legal text goes in and a working piece of software comes out, sitting entirely outside the model: an act read clause by clause into measurable technical requirements with a suite that runs them, a generator that assembles a customized test environment from a shared library for the authority supervising a system, and a retrieval system over 242 regulatory documents from 68 jurisdictions that routes a question to the enacted law governing it and ranks legislation above commentary. The model's training and objectives are untouched; what changes is that written law becomes something a developer or a regulator can execute against a system or look up reliably. Every instance names one jurisdiction's law, because the move only works where the statute is specific enough to translate.

The method, against Consociational codification

Scroll the diagram sideways to see all of it.

Concept Analysis: Theoretical Foundations

Each concept is read twice: whether the approach carries it, and whether the approach's own sources claim it. A concept that is absent and was never claimed is a gap in the field rather than a failure of the work, and is marked out of scope.

Segmental autonomy

PartialClaimed · partial

Definition · Arend Lijphart, Democracy in Plural Societies (1977)

In a deeply divided society, each group governs its own internal affairs — its schools, its family law — within its own sphere, instead of everyone living under one uniform rule.

Analysis

Each body of law is taken on its own terms rather than melted into a single global standard: the retrieval corpus holds 242 documents from 68 jurisdictions, GoldCoin grounds its scenarios in named statutes such as HIPAA, and COMPL-AI interprets one Act. The segments are legal jurisdictions, which is autonomy by inheritance rather than by design. None of these systems changes how a model treats a user according to the segment the user belongs to, so what varies by sphere is the assessment, chosen by whoever runs the tool, not the rule the governed live under.

Choice-of-law rule

PartialClaimed · partial

Definition · Friedrich Carl von Savigny, System of the Modern Roman Law (1849)

When several bodies of rules could govern the same case, an explicit rule decides which one actually does — and states the reason. Without such a rule, "different rules for different groups" has no answer for the cases in between.

Analysis

The priority ranking that puts enacted legislation above policy and secondary sources is a rule of authority stated in advance, and entity detection routes a question to the right jurisdiction's material, which together are more of Savigny's machinery than anything else in this cell has built. But the rule orders sources within an answer rather than deciding whose law governs a person or a case, and the reason it gives is source hierarchy, not connection between case and jurisdiction. The system's own figures show where it breaks: answer relevancy falls from 0.92 on single-entity queries to 0.75 on multi-jurisdictional comparisons, weakest on the cases a choice-of-law rule exists for.

Mutual veto and proportionality

AbsentNot claimed · out of scope

Definition · Arend Lijphart, Democracy in Plural Societies (1977)

Decisions that affect all groups require every group's consent, and representation is proportional to each group's size — so no segment can simply be outvoted on what matters most to it.

Analysis

No jurisdiction consents to any of this, none can block a test or a technical reading it rejects, and a country appears in the corpus in proportion to how much it publishes rather than to anything about its people. The Sandbox Configurator points the opposite way from Lijphart, since its stated goal is cross-border standardization around a shared library, and an authority that disagrees with a test in that library has no veto over it, only the option of declining to select it for its own sandbox.

Papers