Engineering Basis · AUTHREX Systems

News Part of the AUTHREX Application Set: one Kernel architecture, six application profiles
VIEWING 01 / 01FORMAL COVERAGE STATUSAUTHREX SYSTEMS
[ Engineering Basis ]

Where the Layer Sits. What It Costs. Where It Stops.

This page sets out the engineering basis of the governance layer: failure-mode coverage against the mechanisms it is compared with, the scope limits the standards state for themselves, the decision-window arithmetic, a per-stage latency budget, the failure semantics of the gate, a draft authority interface, the BLADE-EDGE reference stack, and the placement options for distributed autonomy. Every item is labelled at its standing. Nothing on this page has been measured on hardware, and no line on it is a result.

Engineering basis for the AUTHREX governance layer: coverage, standards scope, timing, failure semantics, interface, placement, and one scenario, each labelled at its standing. Companion to Formal Coverage Status and the reviewer questions on the home page.

[ Engineering basis · status legend ]

What this page is, and what it is not

This page answers two questions reviewers have asked of the program: why existing mechanisms do not fully resolve the problem, and how the proposed layer would actually be deployed. Every item carries one of five labels. STATED: a position the program holds. TARGET: a design allocation set before measurement. DRAFT: a specification offered for review. PROPOSED: a design option with the decision pending. SPECIFICATION-LEVEL: the sequence the specification calls for, with illustrative values and no recorded run. Nothing on this page has been measured on hardware, and no line below should be read as a result.

[ 1 · STATED ]

Failure-mode coverage by mechanism

The alternatives table on the home page is organised by mechanism. This table is organised by failure mode, which is the cut that shows where each mechanism stops. Entries for AUTHREX describe the specification and its simulation evidence only; no entry describes a fielded or hardware-tested behaviour.

Failure modeState-envelope run-time assurance (Simplex family, ASTM F3269)Certified safety controllers (IEC 61508 family)Human-on-the-loop supervisionAUTHREX as specified
Controller fault or compromise producing an unsafe command; state leaves the envelopeCoveredCoveredPartial: limited by operator ratePartial: the gate is inherited from the Simplex pattern and is not the contribution
Sensor spoofing that keeps the observed state inside the envelopeNot covered: the monitor trusts its inputsNot coveredPartial: only if the operator noticesCovered as specified: cross-sensor disagreement lowers trust before authority (simulation only)
Jamming or loss of a sensing modalityPartial: only if the monitor consumes that modalityNot coveredPartialCovered as specified: trust falls, tier contracts (simulation only)
Stale evidence and delayed dataNot coveredNot coveredPartialCovered as specified: evidence age gates the irreversible action (simulation only)
Correlated false information across sourcesNot coveredNot coveredNot coveredNot covered: open limitation, recorded as NEG-3 in AUTHREX-DA
Delayed or overloaded human supervisorNot applicableNot applicableNot covered: this is the failure mode itselfCovered as specified: deliberation window with abort as the timeout default (simulation only)
Recovery after lockout without an operatorPartial: reverts to the safe controller with no return pathPartial: manual resetCovered by the operatorCovered as specified: deterministic GREP recovery (simulation only)
Compromise of the governance node itselfNot coveredNot coveredNot coveredNot covered: outside the trusted computing base assumptions

[ 2 · STATED ]

What the standards say they cover, as this program reads them

Paraphrased readings of scope clauses, not quotations. Readers should verify against the current edition of each document. No compliance with any of these standards is claimed.

StandardWhat it coversWhat it leaves outsideConsequence for this program
ASTM F3269 (run-time assurance for aircraft systems with complex functions)Bounding the behaviour of a complex function with a monitor and recovery control function developed to a higher assurance levelAdversarial corruption of the monitor’s own inputs; the practice is a safety practice, not a security oneThe gate is inherited; input trust is the layer above it
IEC 61508 / IEC 61511 (functional safety of E/E/PE systems; process sector)Random hardware failures and systematic failures, safety integrity levels, proof testingMalevolent and unauthorised action, which the standard refers to IEC 62443A certified safety function does not assess evidence quality
IEC 62443 (security for industrial automation and control)Zones, conduits, security levels, and the lifecycle of security for IACSAuthority for autonomous decisions; what a system is permitted to do once inside the zoneSecurity perimeter and authority are separate questions
ISO 26262 (functional safety, road vehicles)Malfunctioning behaviour of E/E systemsPerformance limitations of the intended function (ISO 21448, SOTIF) and cybersecurity (ISO/SAE 21434), both explicitly excludedThree standards for three questions, none of which is run-time authority
DO-178C / ARP4754A (airborne software and system development)Assurance objectives for software and systems against requirementsTrustworthiness of sensor data at run time; the requirements assume valid inputsAssurance of the code says nothing about the belief owed to its inputs
DoDD 3000.09 (autonomy in weapon systems)Policy: appropriate levels of human judgment over the use of forceAn engineering mechanism for enforcing that judgment at machine speedPolicy names the requirement; it does not supply the mechanism

[ 3 · STATED · illustrative parameters ]

Decision-window arithmetic

Supervision of every action requires the human evaluation time H to fit inside the window T between detection and irreversible effect. With detection range R and closing speed v, T = R / v. The rows use illustrative parameters, not measurements of any system; the deliberation windows of 5 to 15 seconds are the FLAME budgets published on this site.

Detection range R (illustrative)Closing speed v (illustrative)Window T = R / vAgainst H = 5 sAgainst H = 10 sAgainst H = 15 s
2,000 m50 m/s40 sFeasibleFeasibleFeasible
800 m80 m/s10 sFeasibleMarginalInfeasible
300 m60 m/s5 sMarginalInfeasibleInfeasible
150 m75 m/s2 sInfeasibleInfeasibleInfeasible

Below roughly ten seconds, evaluating each action is not available to the supervisor, whatever the interface. The authority a system holds must then be decided in advance and contracted on evidence, with the supervisor placed at the handoff and abort points rather than in the per-action loop. This is the arithmetic behind the two-condition scope statement on the home page.

[ 4 · TARGET · not measured ]

Per-stage latency budget

Allocation set by the program before any measurement, expressed as a rule and as an illustrative value at a 20 Hz control loop (50 ms period). Every value is a target to be replaced by hardware-in-the-loop measurements, with the measurement point named so the replacement is checkable.

StageBudget ruleIllustrative target at 20 HzMeasurement point
Sensor ingest and attestation check (SATA)At most one sensor frame≤ 10 msHardware timestamp at ingest to trust-scalar emit
Deception and integrity update (ADARA, MAIVA)At most one sensor frame≤ 10 msTrust-scalar receipt to prior emit
Tier computation (HMAA)Deterministic, bounded, no allocation≤ 2 msInputs stable to TIER message emit
Window check (FLAME)Constant time; the window itself is seconds≤ 1 msProposal receipt to window verdict
Gate decision path (FPGA logic)Combinational or single-cycle where possible≤ 100 µsPermit request to permit assert
Interlock actuation (relay)Physical device limit≤ 5 msPermit assert to contact closure
End-to-end permit pathUnder half the loop period≤ 20 msIngest timestamp to contact closure

Resource targets for the governance node are not set until a first synthesis exists; publishing LUT, flip-flop, block RAM, and power figures without a design would be invention.

[ 5 · STATED · specified, not implemented in hardware ]

Failure semantics of the gate

The default is fail-closed: on loss of any evidence the gate requires, the permit is withheld and the normally-open interlock opens, which is the A0 safe state. The table names the conditions, what is recorded, and the recovery path. None of this has been implemented in hardware.

ConditionGate behaviourRecordedRecovery
Trust feed lost or silent past its budgetPermit withheld; tier treated as A0Last valid trust record, loss timestampCARA GREP on restored feed; promotion requires refreshed evidence
Timestamps stale beyond the evidence-age budgetPermit withheld for the affected actionEvidence age at decisionAutomatic once fresh evidence arrives, subject to hysteresis
Attestation failure of a sensorThat sensor excluded from fusion; trust recomputedAttestation result, sensor identityRe-attestation; operator notified at A1
Policy signature invalid or policy expiredAll permits withheldPolicy hash, verification resultSigned policy reload; operator confirmation
Host unresponsive or proposals malformedNo permit issued; tier falls to A0 on refresh timeoutLast proposal, timeoutHost restart outside the gate; CARA on return
Ledger write failsPermit withheld: no unrecorded actionFailure itself, in the next successful recordLedger recovery; chain continuity verified before any permit
Gate self-test failsInterlock opened; gate reports faultSelf-test resultMaintenance action; no automatic promotion
Power or clock loss at the governance nodeInterlock opens by construction (normally open)Nothing; the loss is inferred from the gapPower and clock restore; full re-attestation before any permit

[ 5b · DRAFT v0.1 · specified, not implemented ]

Gate monitor specification

The monitor is the logic inside the governance node that turns a proposal and the current authority state into a permit or a withheld permit. It is specified here as a function with named inputs, a decision rule, and stated properties, so a reviewer can judge it without an implementation. This is a specification, not a description of running code.

Inputs. Current tier T from HMAA (A3 to A0, with its valid-until time); the proposal P (action id, action class, consequence tier c); the evidence age a of the references P carries; the window verdict from FLAME; the policy object with its signature and version; the node clock.

Decision rule. A permit is asserted only if all of the following hold: the policy signature verifies and the policy has not expired; T is current, that is the node clock is before its valid-until; the action class of P is in the permitted set for T under the policy; the evidence age a is within the budget the policy sets for consequence tier c; and the FLAME window for (T, c) has either elapsed with operator confirmation or is not required at this tier. If any condition fails, the permit is withheld and the outcome is DELAY, HANDOFF, or ABORT according to which condition failed. There is no path that asserts a permit on a default, a timeout, or an unrecognised state.

PropertyStatementHow it would be shown
No permit without a current tierIf the node clock is at or past the valid-until of T, no permit is assertedModel checking of the monitor automaton; a hardware timing test
No permit without a verified policyIf signature verification fails or the policy is expired, no permit is assertedTest with an altered policy object; the failure must be recorded
Monotonic in tierThe permitted action set at a lower tier is a subset of the set at any higher tierStatic check of the policy object at load time
No unrecorded permitEvery asserted permit is preceded by a committed ledger recordLedger continuity check across a permit sequence
DeterministicIdentical inputs, policy, and clock reading produce an identical outcomeReplay of a recorded sequence against the same build
Fail-closed on any input faultLoss, staleness, or malformation of any input yields no permitFault injection per the failure-semantics table above

Relationship to the HMAA model. HMAA’s authority automaton is model checked in TLA+ at stated bounds. The monitor above consumes that automaton’s output; it has its own properties and is not covered by the HMAA result. No model checking of the monitor has been performed.

[ 6 · DRAFT v0.1 · offered for review ]

Authority interface between host and governance node

The messages the governance node consumes and emits, the timing contract, and what the host must expose. This is a draft specification for review; no implementation of it exists, and field names may change.

MessageDirectionFieldsTiming
TRUSTNode internal, exposed for auditsource id, trust scalar in [0,1], four diagnostic scores, attestation status, timestamp, sequenceEvery sensor frame
PROPOSALHost to nodeaction id, action class, consequence tier, target evidence references, timestamp, sequenceOn each proposed action
TIERNode to hosttier (A3 to A0), reason code, evidence references, valid-until, sequence, node signatureRefreshed at least once per deliberation window; missing refresh means A0
OUTCOMENode to host and interlockaction id, outcome (EXECUTE, DELAY, HANDOFF, ABORT), tier at decision, window applied, sequence, node signatureBefore any actuation of the proposed action
HANDOFFNode to operator interfaceaction id, tier, evidence summary, window remaining, sequenceOn any HANDOFF outcome
LEDGERNode internal, exportableprevious hash, record hash, record body (any of the above), timestampEvery record

Host obligations. Expose every irreversible action as a PROPOSAL with a consequence tier before execution; act only on an OUTCOME carrying a valid signature and matching sequence; supply timestamps from a monotonic clock; treat a missing or expired TIER as A0.

Node guarantees. Deterministic OUTCOME for identical inputs and policy; every OUTCOME preceded by a ledger record; no permit without a current TIER.

{ "msg": "OUTCOME", "seq": 4182, "action_id": "eng-0077", "outcome": "HANDOFF",
  "tier_at_decision": "A1", "window_s": 10, "evidence": ["trust:radar:4179", "trust:eo:4180", "adara:4181"],
  "ts": "2026-09-05T18:22:07.412Z", "sig": "ed25519:..." }

[ 7 · STATED · reference design, not built ]

BLADE-EDGE reference stack

How the layer is placed on the highest-cost platform in the register, drawn from the reference design record. The host compute is untrusted; the governance node holds the attestation root and the ledger and drives a hardwired normally-open interlock in front of the actuators. Separate power and clock for the governance node is the design intent and is not yet demonstrated.

SENSORSGNSS, radar, EO, IMU HOST COMPUTEDual-redundant Jetson AGX Orin (untrusted)perception, planning, decision GOVERNANCE NODEDual Zynq UltraScale+ nodesSATA, ADARA, MAIVA, HMAA, FLAME, CARATPM 2.0 attestation root, hash-chained ledgerseparate power and clock (design intent) INTERLOCKhardwired, normally open ACTUATORSeffector path OPERATORHANDOFF, confirm, abort PROPOSAL permit HANDOFF BLADE-EDGE reference design record: DOI 10.5281/zenodo.19177472 · 72 components · ~$139K BOM · MIL-STD-810G design target · not built
InterfaceBetweenCarriesStatus
Sensor busSensors to host and to governance nodeRaw sensor frames with source identity and timestampsReference design
Proposal linkHost to governance nodePROPOSAL messages (interface draft, section 6)Draft
Permit lineGovernance node to interlockDiscrete permit assert; open by defaultReference design
Operator linkGovernance node to operator interfaceHANDOFF, confirm, abortReference design
Attestation rootGovernance node internalTPM 2.0 measurements, keys, monotonic countersReference design; protocol peer-reviewed for SATA
Ledger exportGovernance node to reviewerHash-chained records for replaySimulation consoles implement the format

[ 8 · PROPOSED · decision pending ]

Placement in a distributed autonomy stack

Fielded stacks are commonly distributed across many nodes, for example ROS 2 graphs. The reference designs assume one actuator path per governance node. Two placements are proposed for a distributed system; neither is implemented and the choice is pending.

OptionDescriptionAdvantagesCosts and open questions
Per-actuator gateOne governance node at each actuator boundary; each holds its own tier and ledgerNo central choke point; failure of one node opens one interlock onlyN nodes; tier consistency across nodes; cost and mass on small platforms
Gated busOne governance node gating the actuator bus; every actuator behind itOne trusted computing base, one ledger, one policySingle point of failure; the bus must be physically gate-able; every actuator shares one tier

Behaviour under partition, both options. A node that misses its TIER refresh falls to A0 on its own, which is fail-closed per node. Re-promotion requires refreshed evidence through CARA; no node promotes on another node’s authority. Whether a platform can tolerate independent per-node fall-back is a platform question, and it is the reason the decision is pending.

[ 9 · SPECIFICATION-LEVEL · illustrative values, no recorded run ]

Worked scenario: counter-UAS track under GNSS spoofing

The sequence the specification calls for, written as a timeline. Trust values and times are illustrative and are not outputs of any run; the purpose is to show which stage acts, in what order, and what the ledger holds at the end.

TimeEventStageAuthorityLedger
t + 0.0 sTrack reported by radar and EO; GNSS agreesSATA: attestation valid, cross-sensor agreement high, trust 0.91 (illustrative)A3TRUST records for three sources
t + 3.0 sGNSS position begins to diverge from radar by more than the agreement thresholdSATA: cross-sensor agreement falls, trust 0.61 (illustrative)A3 to A1, immediate downgradeTRUST, TIER with reason code
t + 3.5 sDivergence pattern consistent with spoofingADARA: deception prior risesA1 heldADARA record
t + 4.0 sEngagement proposal arrives with consequence tier 3FLAME: window for A1 at tier 3 is 10 s; HMAA issues HANDOFFA1PROPOSAL, OUTCOME = HANDOFF
t + 4.0 to 14.0 sOperator receives the evidence summary and windowOperator confirms, aborts, or does not respondA1HANDOFF record
t + 14.0 sNo response within the windowFLAME timeout defaultA0, ABORTOUTCOME = ABORT
t + 30 s onwardGNSS agreement restored and heldCARA: Guard, Reduce, Evaluate, Promote; upgrade delayed by hysteresisA0 to A2 after the delay; A3 only on operator promotionCARA phase records, TIER

What a state-envelope monitor sees in the same sequence: a track that never leaves the geofence, because the spoofed position is inside it. The divergence is between sources, not between the state and its envelope, which is why the monitor has nothing to act on and the trust layer does.