Taxonomy / Contestatory constitutionalism / Reading the written spec the way a court reads a statute

Reading the written spec the way a court reads a statute

Takes a specification that already exists and disciplines what its words mean: it names the interpretive choices the text leaves open, shows that several equally defensible readings of one principle drive model behavior apart, and imports the machinery courts and agencies use to contain that — a pipeline that rewrites ambiguous rules the way an agency reworks a regulation, and prompt-level canons that constrain how the remaining ambiguity gets applied, tested across 5,000 real user scenarios. The strand's internal argument is the old jurisprudential one: bind a powerful decider with rules, or with accumulated cases. This is drafting and reading hygiene on the developer's side; nothing in it touches who wrote the text or who authorized it.

The method, against Contestatory constitutionalism

Scroll the diagram sideways to see all of it.

Also places in

  • Divergent precedent — Its jurisprudence half reads alignment as the choice between deciding from written rules and deciding from accumulated cases, and asks how a line of readings should be allowed to diverge and be revised openly — the divergent-precedent question, argued from the specification side.

Counts and the concept reading below use the primary regime only.

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.

Contestability

PartialClaimed · partial

Definition · Philip Pettit, On the People's Terms (2012)

Anyone subject to a decision must have a real route to challenge it — to inspect the grounds it was made on, to contest the outcome, and to have that challenge answered. Legitimacy is not settled once by an election or an act of consent; it is held open by that route staying available. The test of a free system is not that its rulers are kind, but that their decisions can be contested by the people they affect.

Analysis

The route these papers argue for is Pettit's: a reading of the specification should be challengeable, and answered by someone other than whoever made it. They go further than argument on two of law's three interpretive stages — ambiguity is reduced when the rule is written, and constrained when it is applied — and both interventions measurably work. The third stage is the one this cell is named for, and it is untouched: nothing lets a person subject to a reading contest it, and a panel of reasonable interpreters is an evaluation instrument, not a forum.

Non-domination

PartialClaimed · partial

Definition · Philip Pettit, Republicanism (1997)

Freedom here is not the absence of interference. You are unfree if someone holds unchecked power over you — even if they never misuse it and mean well. A benevolent master is still a master, and so is an authority whose workings you cannot see. Legitimacy requires that power be checked, not merely well-intentioned.

Analysis

The domination worry is stated in its sharpest form: whoever fixes the reading of an ambiguous principle holds unchecked power over everyone it governs, and at present nobody can see that reading being fixed. The interpretive constraints are a real check — discretion is narrowed by a rule stated in advance rather than by the interpreter's restraint, which is exactly Pettit's structural move. But the check is held by the developer over the model, not by the governed over the developer.

Public decision record

PartialClaimed · partial

Definition · Common-law practice

Rulings on challenges are written down, published and citable, so the system's interpretation of its own rules accumulates in the open, where it can be studied, invoked and criticized. The record is what makes the system predictable as well as legitimate: nothing is settled in private, and every decision leaves its reasoning behind it.

Analysis

A record of readings is the concrete ask, and the jurisprudence essay makes the case from Dworkin and Sunstein for why a line of construction has to accumulate in the open. What is built instead points the other way: the rule-refinement pipeline removes ambiguity by rewriting the rule, so the disagreement is erased upstream rather than recorded and cited. Nothing is written down that a later case could invoke.

Concept Analysis: Newly Introduced

Ambiguity measured, not argued

Added

Jurisprudence has always known that principles underdetermine cases. What is new is measuring it: showing empirically that different defensible readings of the same written principle produce systematically different model behavior. That turns an old theoretical claim into a quantity, and makes the absence of a review institution an empirical finding rather than a structural observation.

Papers

Statutory Construction and Interpretation for Artificial Intelligence

Luxi He et al., Sep 2025

arXiv:2509.01186MethodBuilt

Shows that the same natural-language principle admits several defensible readings that push model behavior apart, then builds two mechanisms borrowed from law — a pipeline that revises ambiguous rules, the way an agency reworks a regulation, and prompt-based interpretive constraints that play the role legal canons play in guiding discretion — and shows on 5,000 WildChat scenarios that both raise agreement across a panel of reasonable interpreters.

Argued for, not built

These make the case for this approach, or sketch a design for it, but leave nothing built and tested behind.

Alignment as Jurisprudence

Nicholas Caputo, May 2026

arXiv:2605.08416ProposalGap

Reads the alignment problem as the jurisprudential one: both fields try to fix in language how a powerful decider will act in situations nobody has yet seen, and both split over whether to bind the decider to rules or to accumulated cases.