Provisional Patent · Sole Inventor · May 2026

A four-stage loop that makes agentic AI
cryptographically accountable.

Sense → Predict → Act → Verify → Sense. A domain-independent architecture in which each iteration emits a tamper-evident record binding Sense + Predict + Act + Observed-result, the next iteration can be optionally gated on that record, and the record is consumed as a Sense input by the next iteration. Twenty-two industry embodiments enumerated in the provisional. One architectural pattern.

See the architecture →
Filing-ready · 60 claims · 22 embodiments Parent over 63/986,305 · 63/995,754 · 63/996,139 · KORPI-001-NP Inventor Shelby Korpi · sole
The gap in the literature

Forty years of agent loops. None of them prove what they did.

OODA, MAPE-K, Sense-Plan-Act, ReAct, Reflexion — each treats verification as either internal reflection (ReAct, Reflexion) or as a passive operator-controlled log (audit pipelines, W3C PROV). None of these named frameworks binds the action to a tamper-evident cryptographic record, gates the next iteration on that record, AND consumes the record as the next Sense input. SPAV's contribution is the architectural integration of these three properties into a single loop. We are not aware of a prior published architecture that combines all three; a formal prior-art search is on the pre-non-provisional roadmap.

1976 · Boyd
OODA
Observe → Orient → Decide → Act. No verification stage. No record. No feedback to the next observation.
2003 · IBM
MAPE-K
Monitor → Analyze → Plan → Execute over Knowledge. Knowledge is internal, mutable, operator-controlled. Not cryptographically attested.
1980s · Brooks
Sense-Plan-Act
Classical robotics decomposition. No verification, no attestation, no closed feedback on the action's measured effect.
2022 · Yao et al.
ReAct
Interleaves reasoning + tool calls. Reflection lives inside the agent's cognition. Not externally verifiable. Cannot gate.
2023 · Shinn et al.
Reflexion
Self-criticism on outcomes. Self-graded. No cryptographic primitive. No external consumer. Trust the agent's own report.
Logging / SIEM / W3C PROV
Audit pipelines
Post-hoc, operator-controlled storage. Not part of the agent loop. Cannot gate the next iteration. Trivially mutable.

Prior-art citations: OODA — Boyd (USAF, 1976) · MAPE-K — Kephart & Chess, IBM (2003) · Sense-Plan-Act — Brooks (1986) · ReAct — Yao et al., ICLR 2023 (arXiv 2210.03629) · Reflexion — Shinn et al., NeurIPS 2023 (arXiv 2303.11366) · W3C PROV — W3C Provenance Working Group (2013).

The four practical failure modes that follow

Unverifiable action.
Regulators can't independently confirm the action was sound or authorized.
Silent model drift.
Without a record binding prediction → outcome, calibration becomes optional.
Cross-org composition fails.
Two agents can't compose without trust in operator-controlled logs.
Regulatory illegibility.
Modern regimes demand provable decisions; logs aren't proof.
The architecture

Four stages. One cycle. Two architectural inventions.

The SPAV architecture comprises four functional stages — Sense, Predict, Act, Verify — and a cycle controller. The novelty lives in two places: Verify-as-mandatory-gate (the next iteration cannot start until the prior verification record exists and validates) and Verify-feeds-Sense (the verification record from iteration N becomes a Sense input in iteration N+1). Click any stage to inspect.

SPAV Cycle Controller cycle 0 · gate OPEN
VERIFY GATE Sense INGEST · ANY MODALITY Predict INFER · CONFIDENCE Act ACTUATE · PHYS / DIGITAL Verify ATTEST · ANCHOR
0
cycle
cycle path verify → sense feedback cryptographic gate
STAGE 01 / 04

Sense

One or more processors ingest input data of any type and any source — physical sensors, APIs, databases, satellite imagery, biometric signals, market feeds, scientific instrumentation, human input, and the verification record from the prior iteration.
  • Modality-agnostic input interface
  • Optional cryptographic verification of inbound data
  • Prior-Verify-reference field carries forward
  • Emits structured Sense-input record
last verify hash:
The intelligence layer

SPAV doesn't just attest the action. It attests the model that produced it, the orchestration that called the model, and the training data that taught the model.

The Verify stage's hardware_attestation field signs the device. Its policy_attestation signs the rules. Its inference_attestation field cryptographically commits to the state of the inference system itself — the model, its version, its multi-agent topology, the prompt and retrieved context if it's a generative system, the simulation parameters if it's a digital twin, the execution-environment attestation if it ran on quantum or neuromorphic hardware. This is where the architecture's most sophisticated claims live.

What's attested at the intelligence layer — comparison
Existing on-orbit AI today
  • Hardware attested (TPM, HSM, HRAD)
  • Network identity attested (zero-trust auth)
  • Packet integrity verified (encryption + MAC)
  • Model state — operator-internal, not externally attested
  • Multi-agent topology — not exposed
  • Prompt + context (for LLMs) — not bound to output
  • Confidence threshold — operator can adjust without external proof
  • Model version that produced any decision — internal logs only
  • Training data lineage — not part of operational record
SPAV's intelligence-layer attestation
  • Hardware attested (inherited from substrate)
  • Network identity attested (inherited from substrate)
  • Packet integrity verified (inherited from substrate)
  • Model state cryptographically attested via inference_attestation
  • Multi-agent topology + intermediate outputs captured · Claim 22
  • LLM prompt + retrieved context + model version bound to synthesized output · Claim 21
  • Confidence threshold pre-registered, anchored T blocks before reliance · Claim 19
  • Model version of every prediction recorded; updates themselves Verify-recorded · Claim 34
  • Training-corpus subset that produced each model version cryptographically bound · Claims 71–80
Intelligence-layer claims · per-claim breakdown
inference_attestation field

Model state itself attested

Beyond the hardware that ran the inference, the Verify record cryptographically commits to the state of the inference system — model identifier, version, weights hash, configuration. An external party can verify that the prediction came from a specific, named model at a specific point in its life cycle.

Claim 22

Multi-agent topology capture

When the Predict stage orchestrates multiple agentic-AI sub-agents, the Verify record captures sub-agent topology, intermediate outputs, and final decision. The graph of who-said-what-to-whom is bound to the action. Critical for autonomous-mission-management systems (Pit Boss-class) where one model's output is another's input.

Claims 18–20

Confidence-bounded actuation

Predict stage emits confidence representation. Act stage gates execution against a pre-registered threshold. The threshold itself is anchored to a tamper-evident substrate at least T blocks before reliance, where T is recorded in policy_attestation. Threshold updates are themselves Verify-recorded (Claim 20). Defeats post-hoc threshold adjustment as a justification mechanism.

Claim 21

Generative AI provenance binding

When Predict invokes a generative AI or LLM, the Verify record cryptographically binds the synthesized output to the input prompt, retrieved context, and model identifier+version. C2PA-aligned but architecturally tied to the agentic loop. For AI-generated mission planning, briefings, content moderation decisions, code generation — full prompt-to-output provenance.

Claim 34

Model-version provenance chain

When deviation metrics from recent Verify records drive model updates, recalibration, fine-tuning, or reweighting, the update operation is itself recorded as a Verify record. The result is a model life cycle expressed as a sub-chain within the verification chain — every model version points to its predecessor and to the training records that informed the transition.

Claim 23 / 24 / 47

Compute-substrate attestation

When Predict runs on high-performance, supercomputing, neuromorphic, or quantum infrastructure (Claim 23), or on a digital twin / simulation (Claim 24), or inside a confidential-computing / TEE environment (Claim 47), the Verify record incorporates an execution-environment attestation. Forward-looking for next-generation compute substrates.

What attesting the intelligence layer actually enables
Cross-operator model trust

Operator A's autonomous decisions can be consumed by Operator B's planning system with proof of which model produced them, what its training corpus was, and what confidence threshold it gated against. No "trust the operator's logs" required.

Multi-vendor satellite accountability

PWSA Tranche 2+ involves vendors from Northrop, Lockheed, York, Rocket Lab, etc. Each runs different models. inference_attestation lets each operator independently verify which vendor's model produced any given autonomous decision.

EU AI Act Article 10 compliance natively

Training-data governance, documentation, model lineage — all produced as a side-effect of normal operation, per Claim 79.

Defense AI rules-of-engagement audit

USSF, NRO, allied programs need to prove that an autonomous decision was made by a sanctioned model version against a pre-registered confidence threshold under a pre-registered ROE policy. SPAV produces the artifact natively.

Insurance underwriting input

Underwriters can price differently when they can prove which model made the decision, when it was last updated, and what its calibration history looks like — all from the Verify chain without operator self-report.

Post-incident model forensics

When an autonomous decision is later contested, the model version, training corpus subset, multi-agent topology, prompt/context (for generative), and confidence-vs-threshold can all be reconstructed from the verification chain. The black box becomes glass.

Why this is the deepest moat in the provisional: intelligence-layer attestation is harder to retrofit than network-layer authentication. Adding inference_attestation, multi-agent topology capture, and model-version provenance to a deployed AI system requires architectural changes to the inference pipeline, not just the network stack. SpiderOak's HAIPE / OrbitSecure ships zero-trust at the network layer; that's a one-cycle upgrade for any operator. SPAV's intelligence-layer attestation is a multi-cycle architectural commitment, which is exactly what makes it patentable AND defensible against fast-following.

Live demo · multi-domain

One architecture. Twenty-two industries. Pick any of seven — including space — to watch a real cycle execute.

The same four-stage loop runs in a poultry barn, a power substation, a hospital, a trading desk, a robotaxi, a factory line, and an autonomous spacecraft. Only the modalities of Sense, the model in Predict, the actuator in Act, and the regulator consuming Verify change. The architecture does not.

N.1 · COMMERCIAL POULTRY

Commercial layer poultry operation

EcoYield's flagship embodiment.

gating preference: joint hardware + smart contract
Sense
Predict
Act
Verify
Cycle telemetry
Cycle controller embodiment

Joint hardware-rooted + smart-contract gating

Actuator-side hardware attestation device verifies the on-chain Verify record before energizing the contactor. Both must agree: smart contract validates the prediction-to-outcome binding; hardware ensures the signed payload was not tampered with in transit.

Why this gating choice

Layer-house actuators control bird life. Poultry-specific physical risk demands joint gating — cryptographic record AND tamper-evident hardware signature — before a ventilation command, a feed-line schedule change, or a vet-intervention dispatch.

regulator consumer: USDA · FDA · FSMA · OLPS-2029
All 22 embodied industries
Poultry Manufacturing Power Grid Algo Trading Clinical CDS Autonomous Vehicles Fraud / AML Generative Provenance Carbon Accounting Cyber IR Adaptive Credentialing Env. Compliance Legal / Contracts HR / Hiring Customer Service Scientific Discovery Warehouse Robotics Smart Building / HVAC Water Treatment Aerospace / UAS Identity / Biometrics Government Benefits
Frontier · the highest-leverage vertical

In space, autonomy is structurally required. SPAV provides the architectural pattern for making it externally auditable.

A signal from Mars takes 5–27 minutes one-way at varying orbital geometry. From cislunar, ~1.3 seconds. In a multi-thousand-satellite LEO constellation, a collision-avoidance burn must be authorized in seconds — orders of magnitude faster than a multi-hour human-in-the-loop conjunction-decision cycle. Ground oversight is structurally impossible at scale. Spacecraft already decide and act on their own. What's missing is a tamper-evident record of what they did, a gate that prevents un-attested maneuvers, and a feedback loop that confronts every prediction with its measured outcome. That's SPAV.

Constraint 01

Light-time forces autonomy

GEO round-trip ≈ 0.24 s. Cislunar ≈ 2.6 s. Mars 10–54 min round-trip depending on orbital geometry. Synchronous human oversight is physically impossible. Spacecraft must Sense, Predict, Act — and Verify what they did so a ground operator (or a regulator, or an insurer) can reconstruct it later.

Constraint 02

Constellations demand federation

Starlink, Kuiper, OneWeb, Iridium, government and partner constellations share the same orbital regime. A maneuver by one operator changes the conjunction map for every other. Federation requires a Verify record that is portable, signed, and consumable across organizations that don't trust each other.

Constraint 03

Regulators are catching up fast

FCC's 5-year deorbit rule (FCC 22-9, effective July 2024). FAA AST owns commercial spaceflight. USSF 18th Space Defense Squadron screens every conjunction. ESA's Zero Debris Charter (launched Nov 2023), EU Space Law (in draft, EU Commission proposal), DARPA LASSO for cislunar autonomy — all converging on the same demand: provable, externally consumable records of what your spacecraft did and why.

<10ms
SPAV verification overhead per cycle
HRAD signature onboard; compatible with sub-second autonomous CAM as Starlink runs today¹
7,560
Active satellites already in orbit
May 2023 snapshot; growing; UCS Satellite Database²
$1.8T
Total space economy projected by 2035
From $630B in 2023 · WEF & McKinsey, April 2024³ (SPAV addresses verification-layer infrastructure subset)
0
On-orbit S+P+A+Observed binding mandates identified
Per audit of public deployments. Cryptographic primitives exist (Cryptosat, SpaceChain, SDA HAIPE); none we identified mandate the four-way binding per iteration

¹ SpaceX Starlink performs ~275 autonomous CAMs/day (Aug 2024) · ² Union of Concerned Scientists Satellite Database · ³ WEF & McKinsey, "Space: The $1.8 Trillion Opportunity," April 2024

What SPAV uniquely brings to orbit

Spacecraft can act autonomously today. They cannot yet prove what they did in a format consumable across organizations.

The communications pipes are deployed in orbit (Starlink ISL mesh · SDA OISL Standard v2.1.2 · Iridium cross-links). The cryptographic primitives are deployed in orbit (Cryptosat TEE · SDA SpiderOak HAIPE). The autonomous decision/act loops are operational in orbit (Starlink ~275 CAMs/day · DARPA Pit Boss). The cross-organization trust artifact that binds Sense + Predict + Act + Observed-result into a single tamper-evident record portable across operators — has not, in our audit, been deployed in orbit. SPAV's claim is that artifact format.

Novelty 01 · the architectural mandate

One record. Four bindings. Per iteration. Always.

SPAV's claim is that each spacecraft iteration emit a single tamper-evident record cryptographically binding the Sense inputs, the Predict output and confidence, the Act decision, and the Observed outcome. The provisional positions this binding as a structural artifact the next iteration consumes — not as a passive log or operator-controlled telemetry. We have not identified a deployed on-orbit architecture that mandates this four-way binding per iteration.

Novelty 02 · gating-as-architecture

No verify, no next maneuver.

In the publicly-described space autonomy stacks (Starlink CAM, DARPA Pit Boss, ESA AOCS), verification is internal to each operator's stack and not externally attested. SPAV's claim positions the gate as structural: re-entry to Sense in iteration N+1 is conditioned on a valid Verify record from N. The provisional supports gated and ungated embodiments (FIG 5A–5F); the gating semantic is what is novel.

Novelty 03 · calibration-as-evidence

The Verify chain IS the audit trail. Forever.

Modern spacecraft GNC stacks already run Kalman filters and update models from residuals — internally, in proprietary state. SPAV's contribution is making the calibration chain cryptographically auditable end-to-end: a regulator, insurer, or partner constellation can independently verify the prediction-to-outcome history for the cycles in the cryptographic chain. Existing systems produce internal calibration logs; SPAV produces an externally-consumable equivalent.

Novelty 04 · trustless federation

A NASA orbiter can read an ESA satellite's record without trusting ESA's database.

SPAV's Verify record is structured to be portable across organizations and across domains. A schema-translation operation between two systems is itself recorded as a Verify record (Claim 41), so end-to-end provenance survives the handoff. In the systems we audited, no on-orbit deployment provides cryptographically-attested cross-organization data exchange today: SDA's HAIPE works within the DoD ecosystem; Cryptosat operates as a standalone TEE service; SpaceChain payloads operate independently. SPAV is positioned as the inter-org artifact format that fits between them.

Why space, why now

The orbital economy is in a multi-year governance build-out. By 2031, tens of thousands of autonomous LEO satellites from dozens of operators across the US, China, EU, and emerging programs are projected to share crowded orbital regimes — Starlink alone is authorized for ~12,000 (filings for up to 42,000), with China's Guowang and Qianfan adding roughly 27,000 combined per filings, Kuiper ~3,200, plus Iridium, OneWeb, Spire, Planet, Capella, Kepler. Cislunar and lunar follow on a 2030s arc — Artemis-era stations, lunar PNT, NASA CLPS, ESA Moonlight, DARPA LASSO. The transport substrate to coordinate these spacecraft is operational today (Starlink ISL mesh, SDA OISL Standard with cross-vendor link demonstrated Jan 2025). The onboard autonomy to act inside them is operational today (Starlink ~275 autonomous CAMs/day). What does not yet exist as a single, externally-consumable, tamper-evident artifact format — one a regulator can audit, an insurer can use to price liability differently, a partner constellation can ingest without a trust dependency, a defense customer can use to prove rules-of-engagement compliance, and an on-orbit servicing mission can co-sign — is the trust layer. SDA's SpiderOak HAIPE is converging on a piece of this within the DoD ecosystem; NASA CARA shares conjunction data through a cooperative ground process. Neither is the cross-organization artifact format SPAV claims. The provisional was filed in May 2026; the priority window for the non-provisional and PCT filings closes in May 2027.

Verified substrate (existing on-orbit systems SPAV would build on, not replace): Starlink ISL mesh — 9,000+ sats, 42 PB/day · SDA OISL Standard v2.1.2 — first cross-vendor link demonstrated Jan 2025 · Cryptosat — 3 TEE-equipped CubeSats on orbit (Crypto1 May 2022, Crypto3 Nov 2023) · SpaceChain — 7+ blockchain payloads since 2018 · SDA SpiderOak HAIPE — zero-trust on-orbit, deployment in progress · Starlink autonomous CAM — ~275/day per SpaceX public reporting (Aug 2024).

Where SPAV sits in the stack

SPAV is the agentic-decision layer above the network-security stack — not in competition with it.

OrbitSecure / SDA HAIPE / SpiderOak authenticate who can send what packet to which subsystem. SPAV mandates the format and binding of the agentic decision artifact that flows over those authenticated pipes. Different layers, complementary functions.

LAYER 5
Federation
Cross-org Verify-record consumption

A NASA payload reads an ESA orbiter's record without trusting ESA's database. Schema-translation between domains is itself a Verify record (Claim 41).

SPAV claim space
LAYER 4
SPAV record + gate
Per-iteration four-way binding + verify-as-gate + verify-feeds-sense

Single record binds Sense + Predict + Confidence + ModelVersion + Act + Observed + Deviation. Doubly-linked chain (Claim 40). Pre-registered confidence thresholds (Claim 19). k-of-n witnesses (Claim 30). Per-action hybrid gating (Claim 12). Training-corpus duality (Claims 71–80).

SPAV claim space
LAYER 3
HRAD
Hardware root of trust on-orbit

Rad-hardened TPM / HSM / secure-element / TEE-equipped microcontroller. Signs Verify records, holds private keys whose private portion never leaves the device. Substrate examples: Collins Aerospace Apollo programmable crypto module, equivalent rad-hardened HRADs.

existing substrate
LAYER 2
Network security
Zero-trust authentication, encrypted comms, microsegmentation

Authenticates packets, identities, links. Decentralized identity-based authentication. Edge-based policy enforcement. Substrate examples: SpiderOak OrbitSecure / SDA HAIPE software-defined encryptor for PWSA; NSA Type 1 standards.

existing substrate
LAYER 1
Transport mesh
Inter-satellite optical/RF links

The physical pipes between satellites. Substrate examples: Starlink laser ISL mesh (9,000+ sats, 42 PB/day, 99%+ uptime); SDA OISL Standard v2.1.2 with cross-vendor link demonstrated Jan 2025; Iridium RF cross-links since 1998.

existing substrate
LAYER 0
Agent runtime
Autonomous Sense→Predict→Act loop execution

The runtime that executes the agent's perceive-decide-act loop onboard. Substrate examples: SpaceX Starlink autonomous CAM (~275/day per public reporting); DARPA Pit Boss / Blackjack autonomous mission management; ESA Aeolus-class onboard autonomy.

existing substrate
LAYER X
Intelligence
Models · multi-agent orchestration · model life cycle

The AI/ML models themselves: ML, deep learning, LLMs, generative AI, multi-agent systems, ensembles, neuro-symbolic reasoning, federated learning, foundation/multimodal models, simulation/digital-twin systems, quantum/neuromorphic compute. Models execute, get versioned, retrained, fine-tuned, orchestrated. Existing on-orbit substrate: per-operator, ad-hoc, no cross-vendor attestation standard. SPAV's claims attach here via inference_attestation, multi-agent topology capture (Claim 22), confidence-bounded actuation with pre-registered thresholds (Claims 18–20), model-version provenance chain (Claim 34), and the training-corpus duality (Claims 71–80).

substrate exists ·
SPAV attaches

Layers 0–3 exist on-orbit today. SPAV's claim space is layers 4 and 5: the format and binding mandates of the agentic-decision record, and the federation pattern that lets that record be consumed across organizations. SPAV runs on top of SDA HAIPE / OrbitSecure — they secure the packets, SPAV mandates the artifact format that flows in those packets. A natural deployment is SPAV-format Verify records flowing over OrbitSecure-authenticated SDA OISL links, signed by Collins Apollo HRADs, produced by Pit Boss-class onboard AI.

Capabilities SPAV unlocks for space

From conjunction avoidance to multi-nation lunar coordination — the same architecture, different actuator.

Capability 01
Verifiable autonomous CAM

Onboard HRAD signs the burn authorization against a pre-anchored envelope policy in <10 ms — adds verification to autonomous CAM workflows already operating today (e.g., Starlink ~275/day). Each burn produces an externally-consumable Verify record; ground-loop is decoupled from gate-time decisioning.

🌐
Capability 02
Cross-constellation coordination

Operator A's Verify record is consumable by Operator B's planning system without sharing proprietary state vectors — selective ZK disclosure preserves competitive secrecy.

📜
Capability 03
FCC / FAA-AST pre-clearance

Provable conjunction-avoidance compliance built into every burn. Maneuver records align with 47 CFR Part 25 orbital debris mitigation requirements (FCC 22-9, eff. July 2024).

💰
Capability 04
Insurance underwriting input

Verify-record-backed risk profile gives space-liability underwriters a provable maneuver-hygiene artifact. Today's space-insurance market relies heavily on operator self-reported data; an externally-verifiable artifact is the missing input.

🤝
Capability 05
On-orbit servicing chain-of-custody

Northrop MEV (operational since 2019), Astroscale ELSA-d demonstrations¹⁰, future cislunar refueling — every contact generates joint Verify records co-signed by both vehicles. Disputed-maneuver provenance becomes mathematical.

🌙
Capability 06
Cislunar / lunar federation

Artemis-era lunar surface ops, NRHO stations, lunar PNT. Multi-org, multi-nation. SPAV federation lets a NASA payload consume an ESA orbiter's Verify record without database trust.

🛡
Capability 07
Defense rules-of-engagement gating

USSF, NRO, allied programs. Actuator commands gated by ROE policy anchored to a tamper-evident substrate before reliance, per SPAV's confidence-bounded actuation embodiment (Claim 19). Aligns with the SDA PWSA zero-trust direction.

🔬
Capability 08
Post-mission anomaly forensics

When a satellite goes silent, the doubly-linked Verify chain is the black box. Reconstruct exactly what was sensed, predicted, acted on, and observed — independently verifiable.

Mission demo · live

SAT-217 · LEO 540 km · debris conjunction event with COSMOS-1408 fragment

LIVE MISSION: SAT-217 / NWHRZN-CONST-04 FRAME: ECI-J2000
T+ 00:00:00.00
SENSE 0
PREDICT 0
GATE 0
ACT 0
VERIFY 0
SAT-217-A DEBRIS · COS-1408 frag GS · LEDGER ANCHOR SAT-217
Orbit / Altitude
LEO · 540 km · 7.62 km/s
Conjunction Alert
TCA T+ —
Stage
IDLE
Verify record committed
0x…
Anchor block
⚠ CONJUNCTION RISK
0
Cycles completed
0
CAMs authorized
0
Verify records
Last miss distance
Last anchor hash
Speed
SOURCES (Frontier section):
¹ SpaceX Starlink ~275 autonomous CAMs/day (Aug 2024) · ² UCS Satellite Database (May 2023) · ³ WEF / McKinsey, "Space: The $1.8 Trillion Opportunity," April 2024 · ⁴ FCC 22-9 (Oct 2022, eff. July 2024) 5-year deorbit rule · ⁵ USSF 18th Space Defense Squadron · ⁶ ESA Zero Debris Charter (Nov 2023) · ⁷ DARPA LASSO (May 2025) · ⁸ NASA / JPL DSN light-time tables · ⁹ Northrop Grumman MEV-1 (operational 2019–) · ¹⁰ Astroscale ELSA-d (2021–2024)
PRIOR-ART SYSTEMS (honest comparison):
DARPA Blackjack / Pit Boss · SDA PWSA BMC3 fact sheet (Aug 2024) · SpiderOak HAIPE zero-trust on-orbit (SDA) · Cryptosat (TEE in orbit · Crypto1 2022, Crypto3 Nov 2023) · SpaceChain (7+ payloads since 2018) · Aerospace Corp SPARTA framework · NASA CARA process documentation
Scenario

SAT-217 ingests state from its own sensors and an ISL relay from companion SAT-217-A. The onboard model predicts a 142m conjunction with a tracked COSMOS-1408 fragment in T+382s. The Verify gate requires a rad-hardened HRAD signature and pre-registered burn-envelope compliance before the thruster will energize. Once authorized, a 0.42 m/s prograde burn executes. Post-burn, the observed miss distance is bound into a Verify record, signed, and downlinked to a permissioned ledger consumable by FCC, FAA AST, USSF, partner constellations, and the satellite's insurer.

Why this mission demo matters

Every step you see is what the patent claims: Sense ingests including the prior Verify record; Predict emits with confidence; Verify gate blocks unauthorized actuation; Verify-feeds-Sense closes the calibration loop without ground intervention.

🛰 Jump to Space tab in live demo →
The verify record

A single tamper-evident artifact binds Sense + Predict + Act + Outcome.

The Verify record is what makes SPAV externally consumable. Every iteration emits one. It binds the Sense inputs, Predict output and confidence, Act decision, and observed outcome under a single cryptographic commitment so the record cannot be modified without detection. Anchored to a permissioned ledger. Optionally selectively-disclosed via zero-knowledge proofs. Doubly-linked to the prior iteration's record.

// VERIFY-RECORD schema · per provisional Section F
VerifyRecord {
  version:                 protocol_version_identifier
  domain:                  domain_identifier
  iteration_id:            unique_iteration_identifier
  prior_record_pointer:    hash_or_ledger_anchor_of_prior_VerifyRecord
  prior_binding_receipt:   // HMAC over prior record w/ fresh nonce — Claim 40
                            HMAC(prior_record, nonce_from_present_Sense)

  sense_binding:           CryptographicCommitment(SenseInput)
  predict_binding:         CryptographicCommitment(
                              PredictOutput,
                              Confidence,
                              InferenceSystemId+Version
                            )
  act_binding:             CryptographicCommitment(
                              ActDecision,
                              ExecutionMetadata
                            )
  observed_result:         CryptographicCommitment(ObservedResult)

  deviation_metric:        Quantification(PredictOutput, ObservedResult)
                            // fed back into next Sense — Claim 33

  hardware_attestation:    SignatureByHRAD(record_hash, certificate_chain)
                            // HRAD root → manufacturer → CA

  policy_attestation:      CryptographicAttestation(
                              PolicyRegistryState,
                              registration_time   // pre-registered, anchored T blocks
                            )                          // before reliance — Claim 19

  inference_attestation:   CryptographicAttestation(InferenceSystemState)
                            // model state itself, not just hardware

  witness_attestation:     ThresholdSignature(k_of_n_observers, ObservedResult)
                            // k-of-n distributed observation — Claim 30

  optional_zk_proof:       ZeroKnowledgeProof(PolicyCompliance)
  optional_explanation:    HumanReadableExplanation
                            cryptographically bound to record_hash

  integrity: {
    record_hash:           hash of all preceding fields
    signature:             system signature over record_hash
    ledger_anchor:         optional transaction_id or block_reference
    smart_contract_event:  optional event_emission_reference
    timestamp_proof:       optional trusted_timestamp_attestation
                           // RFC 3161 or equivalent
  }

  selective_disclosure_map: per-field disclosure markers
                            // reveal in plaintext to authorized,
                            // reveal as ZK proof to others — Claim 38
}
Cryptographic primitives — pick any combination
SHA3 hash chain Merkle proofs Distributed ledger anchor Smart-contract event Ed25519 signatures Threshold / multi-party sigs Verifiable credentials DIDs RFC 3161 timestamping Hardware-rooted attestation Post-quantum primitives Zero-knowledge proofs

Claimed in the alternative. Any single primitive or any combination satisfies the architecture. Future post-quantum migration is a deployment decision, not a re-invention.

Six gating embodiments
FIG 5A · Smart-contract gating
FIG 5B · Hardware-rooted gating
FIG 5C · Joint smart-contract + HW
FIG 5D · TEE-enforced gating
FIG 5E · Software-enforced gating
FIG 5F · Ungated (record-only)

The choice of gating is a deployment-time decision matched to risk. The architectural pattern itself does not require any specific one.

Named novel mechanisms · per-claim

Specific cryptographic constructions, not generic primitive lists. Each is a named claim element with a non-obvious mechanism.

Claim 40

Doubly-linked Verify chain

Each record contains BOTH a prior_record_pointer AND a prior_binding_receipt — an HMAC over the prior record using a fresh nonce known only to the present iteration's Sense module. Tampering with any single record requires simultaneous compromise of multiple records and signatures from independent points in time.

Claim 19

Pre-registered confidence threshold

The confidence threshold the Act stage gates against is anchored on a tamper-evident substrate at least T blocks before reliance — where T is itself a policy parameter recorded in policy_attestation of every record. Defeats post-hoc adjustment to retroactively justify an action.

Claim 30

k-of-n witness attestation

The Verify record can incorporate a threshold attestation requiring agreement among k of n independent witnesses regarding the observed result. For an on-orbit conjunction outcome: USSF + commercial SSA + partner constellation must independently agree on what actually happened.

Claim 22

Multi-agent topology capture

When the Predict stage orchestrates multiple agentic-AI sub-agents, the Verify record captures sub-agent topology, intermediate outputs, and final decision — not just the top-level output. Critical for accountability of agentic-mission-management systems (e.g., DARPA Pit Boss-class).

Claim 12

Per-action hybrid gating

Different actions or action classes within the same SPAV system are subject to different gating regimes. A spacecraft applies joint hardware+smart-contract gating to a maneuver burn while applying software-enforced gating to a payload data downlink — all within the same Verify chain.

Claim 21

LLM/generative provenance binding

When Predict invokes a generative AI or LLM, the Verify record cryptographically binds the synthesized output to the input prompt, retrieved context, AND model identifier+version. Architecturally analogous to C2PA but tied to the agentic loop, not bolted on after content publication.

Training-corpus provenance · Claims 71–80

Operational data IS training data — with cryptographic provenance per example.

A defining property of the SPAV architecture is that each Verify record simultaneously fulfills four functional roles: an audit record, a calibration feedback artifact, a labeled training example, and a model-lineage anchor. The chain of Verify records produced by repeated cycles constitutes a tamper-evident, per-example-attested training corpus. There is no separation between "production traffic" and "training data" — they are the same artifacts viewed from different perspectives.

How a Verify record functions as a labeled training example
sense_binding
Input features

The cryptographic commitment to the Sense input data becomes the X (features) of the training example.

predict_binding
Prior model output

The model's prior prediction (with confidence + version) becomes the prior-output for residual-based learning.

act_binding
Action taken

The action becomes the A in (S,P,A,O) — the intervention whose effect is being measured.

observed_result
Ground-truth label

The measured outcome becomes the Y (label). The integrity field makes the example individually tamper-evident.

Together with the integrity field, the Verify record produces a labeled training example whose authenticity is independently verifiable without trusting the operator. This is Claim 71. The chain of records is the corpus.

Property · Claim 73

Model-lineage attestation

When an inference system is updated, retrained, or fine-tuned using Verify records as training data, the update operation is itself recorded as a Verify record. The resulting model version is cryptographically bound to the specific subset of Verify records that informed it. An external party can verify the precise training-corpus subset that produced any deployed model — without operator disclosure beyond cryptographic openings of the lineage attestation (Claim 74).

Property · Claim 77

Dataset-poisoning resistance

Under the SPAV architecture, training data IS the verification chain. An adversary wishing to poison a future model must compromise records that may already be ledger-anchored, hardware-attested, or witnessed by k-of-n independent observers. The threat surface for dataset poisoning becomes equivalent to the threat surface for the audit chain itself — substantially harder than poisoning an operator-controlled dataset.

Property · Claim 75

Continuous learning is itself verifiable

Online learning, periodic fine-tuning, scheduled retraining, and reinforcement-from-deviation-metric updates are all triggered by Verify records and themselves recorded as Verify records. The model life cycle is expressed as a sub-chain within the verification chain: each model version points to its predecessor, to the training-record set that informed the transition, and (in confidential-computing embodiments) to the attestation of the training-execution environment.

Property · Claim 76

Federated training preserves provenance

When Verify records produced by one organization's SPAV system are consumed by another organization for training, every example crossing the organizational boundary retains its cryptographic provenance. Federated learning under SPAV produces models with auditable per-example provenance back to the originating organization — without requiring either party to expose underlying confidential data, when selective-disclosure or zero-knowledge embodiments are used.

Regulatory addressability · Claim 79

SPAV produces the training-data transparency artifact emerging regulatory regimes already demand.

The Verify chain natively satisfies training-data documentation requirements imposed by:

EU AI Act · Article 10

Training-data quality and governance requirements for high-risk AI systems. SPAV's per-example-attested chain is the artifact that demonstrates compliance.

U.S. Federal Reserve SR 11-7

Model risk management guidance for banking. Model lineage attestation directly addresses validation, monitoring, and documentation requirements.

FDA AI/ML SaMD guidance

AI/ML-based Software as a Medical Device documentation. Training-data provenance and model-version control built into the operational record.

Emerging algorithmic-accountability frameworks

NIST AI RMF, sector-specific algorithmic-accountability rules, EU Digital Services Act audit requirements — all converge on per-example training-data attestation.

Per the inventor's appendix, the training-corpus continuation (Claims 71–80) is identified as likely the most commercially valuable continuation given the EU AI Act enforcement timeline and the SR 11-7 / FDA AI guidance regimes.

Federation · multi-system composition

Verify records are portable. Two SPAV systems can compose without trusting each other's logs.

Because the Verify record is tamper-evident and carries its own provenance, one system's verified outcome can be consumed as another system's Sense input — across organizations and across domains. The schema-translation operation is itself recorded as a Verify record. The architecture enables cryptographically-attested multi-agent and multi-domain composition without dependence on the counterparty's operator-controlled database.

System A · Energy Grid Operator DOMAIN: power.iso-ne Sense Predict Act Verify VERIFY RECORD 0x91ae…02bc portable · selectively disclosed System B · Carbon Accounting DOMAIN: carbon.disclosure Sense Predict Act Verify SCHEMA-TRANSLATION OP IS ITSELF A VERIFY RECORD · END-TO-END PROVENANCE PRESERVED

Cross-organization

An OEM's Verify records are tamper-evident and externally consumable by its supplier's regulator — without either party trusting the other's database.

Cross-domain

The architecture supports use cases where a Verify record from one domain (e.g., autonomous-vehicle telematics) could be consumed as a Sense input by a system in a different domain (e.g., insurance pricing) via a recorded schema-translation. Such cross-domain consumption is enabled architecturally; commercial adoption is a separate question.

Cross-iteration training

Verify records are training data with provenance. Model retraining is itself recorded — closing the calibration loop with audit.

The transport substrate already exists

SPAV federation is an artifact format on top of pipes that are already in orbit.

SPAV's federation does not require new inter-satellite communications infrastructure. The peer-to-peer mesh substrate is operational at industrial scale today:

  • Starlink laser ISL mesh — 9,000+ satellites · 42 PB/day · 5.6 Tbps · 99%+ uptime · third-party access publicly planned¹¹
  • SDA OISL Standard v2.1.2 — first cross-vendor laser link demonstrated Jan 2025 (York + SpaceX); mesh operationalized Jan 2026 across Northrop, Lockheed, York, Kepler¹²
  • Iridium cross-links — operational since 1998 (first commercial sat-to-sat ever)

What's missing is not the pipe — it's the artifact format that flows through it. Cross-organization, cryptographically-attested data exchange between satellites operated by different parties is essentially undeployed. SPAV's Verify record is that artifact format. Real-time P2P transmission isn't required for most federation value — ground-side ledger anchoring with hours-to-days latency satisfies regulator audit, insurance underwriting, and multi-nation program coordination. Where real-time on-orbit federation is desired (e.g., joint conjunction planning across constellations), the Starlink/SDA mesh is the available physical layer.

Note on commercial reality: vertically-integrated constellations (SpaceX, Kuiper, OneWeb) have weak voluntary-federation incentives. The high-value federation cases are DoD/SDA ecosystem (where interoperability is mandated), multi-nation programs (Artemis, lunar PNT), regulator-mandated transparency (FCC, FAA AST), and insurance underwriting.

¹¹ Starlink laser ISL operational scale (Feb 2024) · ¹² First SDA cross-vendor laser link · York + SpaceX (Jan 2025) · SDA OISL Standard v2.1.2 (Dec 2023)

IP positioning

Parent over a portfolio. Defensible novelty cluster. §101 mitigations baked in.

SPAV is positioned as a universal parent pattern above the inventor's existing portfolio of three hardware-gated provisionals and one non-provisional. Hardware gating was deliberately removed from the parent so the architecture covers software, smart-contract, TEE, and joint embodiments — every industry, not just poultry hardware.

Patent family hierarchy
SPAV (this filing) · 2026
Parent universal architecture. Domain-independent. 60 claims. 22 industry embodiments. Six gating modes claimed in the alternative.
63/986,305
Earlier provisional · poultry-specific embodiment of three-layer enforcement stack.
63/995,754
Earlier provisional · hardware-gated actuator authorization.
63/996,139
Earlier provisional · ledger-anchored compliance binding.
KORPI-001-NP
Pending non-provisional · vertical implementation in commercial layer poultry.

Continuation strategy: 3–4 narrower non-provisionals from this parent within 12 months (broad SPAV / calibration loop / smart-contract gating / cross-domain federation). PCT decision at 12-month mark for international protection.

Novelty 01 · Claims 1(d), 5

Verify-as-mandatory-gate

Re-entry to Sense in iteration N+1 is conditioned on a valid Verify record from iteration N. Six alternative gating mechanisms claimed. Distinguishes SPAV from every prior agent loop.

Novelty 02 · Claims 6, 22, 26-28

Verify-feeds-Sense feedback

The Verify record is consumed as a structured Sense input by the next iteration. Standard control systems already feed residuals back internally (Kalman filters, online learning); SPAV's contribution is making that feedback chain tamper-evidently auditable end-to-end, so a regulator/insurer/partner can prove the calibration history rather than trust an operator self-report.

Novelty 03 · Claims 41, 44, 54

Cross-domain federation

Verify records carry cryptographic provenance across organizations and domains. Schema-translation operations are themselves Verify records. End-to-end provenance survives composition.

§101 abstract-idea mitigations (already baked in)
Cryptographic apparatus tangibility — primitives produce concrete artifacts
Gating-as-apparatus — six enumerated cycle-controller embodiments
22 industry embodiments — practical-application lifeboats (Claims 29-50)
18 worked Detailed-Description embodiments — concrete reduction to practice across domains
Why this matters · investor frame

SPAV positions as a foundational architectural-IP layer for verifiable autonomous decisions.

22
industry embodiments
60
claims drafted
6
gating modes claimed
12mo
window for continuations + PCT

The wedge

EcoYield's commercial poultry pilot is the first vertical instantiation: 14+ years of historical data (5,843 barn-weeks across 75 flock cycles, 4 breeds), live deployment at an 800K-hen pilot operation. Validates the architecture in a regulated, multi-stakeholder environment before broader licensing.

The platform

The architecture is enumerated across 22 industry embodiments in the provisional. Adoption in any one of them is a separate go-to-market motion; the patent positioning supports licensing or operating models per vertical.

The moat

Provisional filed May 2026 as parent over an existing 4-application portfolio. The novelty cluster (Claims 1(d), 5, 6, 22, 26-28, 41, 44, 54) covers gating, verify-feeds-sense, and federation. A formal prior-art search is on the pre-non-provisional roadmap.

The architectural pattern as regulated AI scales.

As agentic AI deployments scale and regulatory regimes around automated-decision accountability tighten (EU AI Act, FDA AI/ML SaMD guidance, FCC/FAA orbital reporting, Federal Reserve SR 11-7, and analogous regimes), externally-verifiable artifacts of automated decisions become the relevant compliance asset. SPAV is an architectural pattern for producing such artifacts: a tamper-evident record of what each iteration sensed, predicted, acted on, and observed, optionally gated, and consumable across organizations. The provisional positions this pattern as a parent over the inventor's existing portfolio, with 22 enumerated industry embodiments and an initial vertical instantiation in commercial poultry.