Primary technical disclosure

Positive Abstention: Withholding as a First-Class, Non-Convertible Outcome Positive abstention makes withholding a first-class, non-convertible outcome for autonomous agents: a per-stage degradation map, a type-level conversion bar, and a signed non-execution attestation carrying a recorded abstention across the agent boundary.

Secondary technical

Relay Non-Execution Attestation With Depth and Cycle Bounds How a relay non-execution attestation lets a middle semantic agent disclose a withholding it did not itself write, deriving the withheld action-class enumeration from a failing dispatch-authority predicate and bounding chain depth and cycles while preserving the abstention type.The Anti-Amplification Bound on Propagated Determinations How the Adaptive Query architecture bounds the movement of an admitting agent's scoped integrity vector on a propagated conduct determination at a declared sub-unity fraction of a locally computed reference, so judgments do not amplify across a chain of autonomous agents.The Attestation Revocation Object How a disclosing agent retracts its own non-execution attestation in the Adaptive Query architecture, releasing a carried abstention entry per action class on successor-epoch verification while incrementing no counter and producing no determination about either party.Empty-Intersection Mutual Positive Abstention How a semantic agent handles an empty co-residency intersection between two conflicting signed policy objects on a stateless node: a mutual positive abstention that produces no denial, no determination, and no counter increment under the conversion bar.Curing Counterparty Absence by Introduction Protocol How a persistent semantic agent cures an absent admissible counterparty class through a signed introduction protocol, admitting an introduction record from a second agent by signature verification and policy-object class membership testing.

Applications · general

Safety-Critical Autonomy: Recording a Refusal to Act as a First-Class Outcome How safety-critical autonomous systems can record a refusal to act as a first-class, non-convertible outcome using a degradation map, a type-level conversion bar that forecloses defaults and sentinel substitution, and signed cross-party non-execution attestations.

Terminology

abstention outcome an outcome of a recorded class emitted by a determination stage where an input required by that stage is unavailable, incomplete, or unresolvable, and adverse to no party..conversion bar the property by which a consuming determination is foreclosed from converting an abstention outcome into a scalar value, a default value, an operand of a threshold comparison, or a consequence adverse to any party..non-execution attestation a signed governed observation emitted responsive to writing an authorization gate to a withheld state, whose payload comprises at least an enumeration of the withheld action classes and a typed marker of the recorded abstention class..positive abstention a recorded, governed withholding of an action, the semantic agent appending a determination naming the withheld action and the ground relied upon, and withholding dispatch of the action..