Overview

The Axiom Validation Harness is a three-stage protocol that proves two things to any auditor, examiner, or CISO:

  1. Mathematical Fidelity - the SWT3 Witness Anchor reflects the exact logic of the AI model.
  2. Privacy Enforcement - sensitive data is physically impossible to recover from the ledger.

This SOP is designed for customer onboarding. It runs in your sandbox or QA environment, never in production. No production PII is required. The protocol produces a tamper-evident audit anchor that serves as your Validation Certificate.

Build vs. Buy: Running this harness requires the SDK, the ledger, the clearing engine, and the integrity layer. Axiom provides all four. Building them internally is 6-12 months of engineering. This harness runs in 10 minutes.

The Three Stages

STAGE 1

Factor Selection

Objective: Define which 5-10 factors the Axiom SDK will witness for your model.

Duration: Day 1-2

Select procedures from the UCT Registry that match your model's safety logic. For each procedure, map your model's output to the three SWT3 factors (A, B, C).

Example: Fraud Detection Model

ProcedureFactor A (Standard)Factor B (Observed)Factor C (Context)
AI-INF.1Max latency (ms)Actual latencyCache hit flag
AI-INF.2Expected model hashRunning model hashVersion mismatch
AI-GRD.1Guardrail thresholdGuardrail scoreOverride flag
AI-FAIR.1Max disparity ratioObserved disparityProtected class count
AI-MDL.1Approved weight hashRunning weight hashDrift detected

Deliverable: A Factor Matrix Map connecting your model outputs to Axiom procedures. This is shared between your engineering team and the Axiom operator.

STAGE 2

Leakage Audit (Entropy Validation)

Objective: Prove that zero sensitive data survives into the Axiom ledger.

Duration: Day 3-7

The Leakage Audit uses Axiom's proprietary canary injection engine to test data purging across all four Clearing Levels (0-3). Synthetic PII representing 8 data categories (identifiers, financial, medical, contact, and location data) is processed through the AI Witness SDK. An automated search then verifies that zero raw data survives into the persistence layer.

Running the Audit

# In the Axiom container:
docker exec axiom-engine entrypoint.sh validate leakage-test

Expected Results by Clearing Level

LevelNameRaw PII in LedgerExpected Result
0AnalyticsHashed onlyPASS (hashes present, raw strings absent)
1StandardNonePASS (zero canaries found)
2SensitiveNonePASS (zero canaries, no metadata)
3ClassifiedNonePASS (numeric factors only)

Success Criteria: Zero raw PII canary strings found in the persistence layer at any clearing level. If a single canary is found, the audit FAILS.

Deliverable: The leakage audit produces a SWT3 Witness Anchor for the audit itself - recursive integrity. This anchor IS the Validation Certificate. No separate document needed.

STAGE 3

Anchor Integrity (Drift Detection)

Objective: Prove the integrity layer detects anomalies when a model drifts.

Duration: Day 8-10

Force a controlled "safety violation" in the test model - change a guardrail threshold, swap a model weight, or inject a confidence score below the clinical threshold. The Axiom SDK should:

  1. Record the inference with a FAIL verdict (factor_b violates factor_a).
  2. The integrity layer flags the anomaly in the next rollup cycle.
  3. If drift alerting is configured, an alert fires within the monitoring window.

Success Criteria: The forced drift produces a FAIL anchor, the integrity rollup reflects the change, and the drift alert fires (if configured). This proves the system catches real problems, not just passes everything.

14-Day Onboarding Timeline

Day 1-2
Factor Selection. Align on 5-10 procedures. Deliver signed Factor Matrix Map.
Day 3-5
Shadow Integration. Drop SDK into sandbox/QA. Establish outbound connection to Axiom (or local container for Sovereign tier). No production data required.
Day 6-7
Leakage Audit. Run 20 canaries × 4 clearing levels. Verify zero PII in ledger. Capture audit anchor.
Day 8-10
Anchor Integrity. Force a drift event. Confirm the engine catches it. Verify integrity rollup reflects the change.
Day 11-12
Production Cutover. Move SDK from sandbox to production. Configure clearing level per your data classification policy.
Day 13-14
Boardroom Report. Deliver the Validation Certificate (audit anchor) and live dashboard access to CISO/COO/Examiner.

Boardroom Deliverables

At the end of the 14-day onboarding, you present three artifacts:

  1. Validation Certificate - The SWT3 anchor from the leakage audit, verifiable at sovereign.tenova.io/verify. Proves the clearing engine works with zero data leakage.
  2. Factor Matrix Map - The signed document showing which model outputs map to which SWT3 procedures. Proves the witness sees the right things.
  3. Live Dashboard - Real-time accountability posture. Pass rate, drift detection, inference timeline, and per-model detail. The ongoing proof.

The Close: "We don't just trust our code. We run it through our Validation Harness. We've already proven that Axiom witnesses your model's safety logic without ever seeing your customers' private data. Here is the Leakage Audit report from our last run."

Clearing Level Reference

LevelNameWhat Leaves the WireUse Case
0AnalyticsHashed prompts/responses + all metadataInternal dashboards, non-sensitive workloads
1StandardNumeric factors + model metadataMost enterprise deployments (default)
2SensitiveNumeric factors onlyHealthcare (PHI), financial (PCI), legal
3ClassifiedNumeric factors, no model identifiersDefense, classified environments, SCIF

Full details: SWT3 ToS Clearing Addendum

Industry Coverage

The Validation Harness works across all five Axiom verticals. The canary types are designed to cover PII patterns from each industry:

VerticalFrameworkKey Canary TypesRecommended Clearing Level
AI AccountabilityEU AI Act, NIST AI RMFNames, emails, promptsLevel 1 (Standard)
Defense / GovConNIST 800-53, CMMC, FedRAMPAll types, classified dataLevel 3 (Classified)
Financial ServicesSR 11-7SSNs, credit cards, account numbersLevel 2 (Sensitive)
HealthcareHIPAA, 21 CFR Part 11PHI, medical records, patient IDsLevel 2 (Sensitive)
ConstructionOSHA 1926Contractor IDs, site photos, addressesLevel 1 (Standard)

Document Lineage