Governed Deduction: Policy-Grounded Premise Authorization Beyond Relevance

From an independently produced RBAC-augmented Spider benchmark, we construct 4,461 matched authorization pairs in which the same query premise and policy state support permitted and denied consuming transitions. It comes from a paper posted to arXiv on 28 September 2026. Reasoning systems usually treat premise use as a question of relevance: if a fact is available and useful, it may be selected for inference. Authorization imposes a different constraint: a premise may be represented and logically usable but not permitted for a particular local transition. We formalize this distinction as Governed Deduction (GD), with a transition-local admission predicate admit(p, tau, S). An initial joint controller reaches 99.19% held-out accuracy, but a transition-only control reaches 100%, exposing a role-name shortcut. After a frozen, label-independent context-local role permutation removes that shortcut, premise/state-only, transition-only, and joint linear controllers all score exactly 50% on 1,856 held-out edges, while a symbolic policy oracle remains at 100%. The result is a controlled negative finding: the benchmark instantiates policy-grounded authorization beyond relevance, but the frozen linear representation does not recover the relation. Matched one-sided controls and leakage audits are therefore essential for evaluating learned policy-sensitive reasoning.

Why it counts

From an independently produced RBAC-augmented Spider benchmark, we construct 4,461 matched authorization pairs in which the same query premise and policy state support permitted and denied consuming transitions.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.