Skip to content
Technology How it works Breeder — Hyperion Burner — Aegis Burner — MetroVolt AI-Native Architecture Magnets Fuel cycle Safety Roadmap
Solutions AI & Data Centers Defense & Government Grid & Baseload Neutron Detection Quantum
Learn Technical Library
Proof Publications Whitepapers Technical Library Open Science & Reproducibility The Honest Gates
Company About / Mission Leadership Environment Health & Safety Investors Careers Press Contact
3D Model
AI Architecture › Physical Interfaces
Physical Interfaces

Interface Calibration and Provenance

A reading is only as trustworthy as its calibration record; this interface carries the traceable provenance every layer checks before acting.

STRATEGY / SLOW ▲ ▼ MICROSECOND REAL-TIMEL7Ecosystem & Strategytelemetry ▲ control ▼open ▸L6Experience & Visualizationtelemetry ▲ control ▼open ▸L5Applications & Copilotstelemetry ▲ control ▼open ▸L4Orchestrationtelemetry ▲ control ▼open ▸L3Twin Modeling & AItelemetry ▲ control ▼open ▸L2Data Fabrictelemetry ▲ control ▼open ▸L1Control Planetelemetry ▲ control ▼open ▸L0Foundationtelemetry ▲ control ▼open ▸PHYSICAL S.M.A.R.T. GENERATOR PLANTBREEDER · HYPERION1R0 1.2 m · A 2.5 · 16.84 T · δ −0.30BURNER · TANDEM MIRROR2317 T throat · 26.49 T plug · fₙ 5.44% · DEC1 center stack + plasma · 2 high-field plug · 3 expander → direct converterCOLOR GRAMMAR strategy AI-workflow infra/data models reactor/DECLINE SEMANTICStelemetry (µs)controlKRONOS FUSION ENERGYAI-NATIVE S.M.A.R.T. GENERATORMASTER BLUEPRINTSHEET 01REV. 2026-08L0-L7 · 2 MACHINES
The AI-Native S.M.A.R.T. Generator Master Blueprint — eight layers (L0→L7), one control stack, wired to both machines. Telemetry rises in microseconds; control descends the same path.

Trust travels with the number

Across both machines' 60+ ports, no layer is allowed to act on a bare number. Each engineering-unit value carries a provenance record: which calibration produced it, when, with what uncertainty, and whether the calibration is still valid. This interface defines and enforces that record.

Provenance fields

python
# provenance gate before any layer uses a value
def trusted(reading):
    p = reading.provenance
    return (p.status == 'valid'
            and age(p.cal_epoch) <= p.validity_window
            and reading.value == clip(reading.value, p.range))
# twin/MPC/copilot all call trusted() first
if not trusted(x): x = impute_or_mask(x)

When a calibration expires or a sensor drifts out of tolerance, the value is not silently used — it is marked suspect and either imputed (from the sensor-topology graph model) or masked so the reconstruction proceeds on trusted channels only. This is how a stale gauge never corrupts a strain margin, a heat-flux map, or an accountancy ledger.

Owner and scope

Owner: L2 for the calibration store and provenance record; every higher layer is a consumer that must check it. Accountancy-grade interfaces (tritium, helium-3) carry the strictest traceability; fast control channels carry the shortest validity windows because drift there is most damaging. This provenance is the same discipline the analog front end begins and the accountancy ledger ends with. Design-and-simulation specification.

Content reviewed August 2026 · design-and-simulation stage