FILE 02 / V0.1 BUILD CONTRACT SUMMARY

Numbers to test, not performance to advertise.

Revision 03 replaces the working hypothesis register with a summary of the project's controlled v0.1 build contract (August 2026). Every value carries a requirement state. None has been measured on Norysr hardware, because there is no Norysr hardware.

Not a prescription, safety envelope or regulatory determination. The complete contract with equations, schemas and requirement identifiers lives in the project workspace.

00 / REQUIREMENT STATES

Four words separate what is fixed from what is not yet known.

The contract also rejects the earlier public stimulation, ramp, burst, refractory, charge-cap and gait-window values as controlling requirements; some were mutually incompatible and none was established as a safe pediatric envelope. Literature values are never promoted to requirements automatically.

Locked

Implement and verify now. Changing it creates a new model or controller generation.

Provisional

The current internal target. Clinical, statistical or regulatory review may change it before formal design-input freeze.

TBD-gated

No value is invented. A named owner must approve it before the dependent stage.

Excluded

Not part of v0.1. Surface EMG, online learning, home use and every energized output are in this state.

01 / SENSING

One sensor, one leg, one prediction every ten milliseconds.

ItemValueState
SensorOne 6-axis inertial sensor on the affected distal shankLocked
Sampling100 Hz nominal; one prediction per accepted frameLocked
Units and framem/s² and rad/s in a calibrated affected-shank frame recorded in the session manifestLocked
Window32 frames (nominal 310 ms span), no look-ahead; a gap, reset or invalid frame restarts itLocked
Surface EMGLater collection and ablation onlyExcluded as a v0.1 dependency
EnvironmentTherapist-supervised straight, indoor, level walkingLocked for first validation

02 / MODEL 1 CONTRACT

Three probabilities from 1,603 parameters, with a rule-based comparator beside it.

ItemValueState
Input tensor[32, 6]: ax, ay, az, gx, gy, gz, standardized with training-only constantsLocked
OutputsP(toe-off within 80 ms), P(heel strike within 80 ms), P(stance now, auxiliary)Locked; the 80 ms horizon is a versioned first choice
ArchitectureCausal temporal convolutional network: stem Conv1D 6→16 (kernel 2), four 16-channel residual depthwise-separable blocks at dilations 1, 2, 4, 8, linear head 16→3Locked reference; 1,603 parameters
CalibrationBound probability-calibration transform fitted on validation participants onlyLocked
AdaptationFixed weights; no online, federated or runtime learningLocked
Target formatSigned INT8 weights and activations, artifact-owned quantization, parity-tested against floatProvisional
ComparatorCausal angular-velocity gait-event state machine; ML is adopted only if it passes every absolute gate and the paired baseline gatesLocked policy

The model reports probabilities. It cannot emit charge, current, voltage, pulse width, frequency, ramp, duration, electrode selection or an actuator command.

03 / SUPERVISOR AND SAFETY

No public value is a safe-use instruction, and no learned value has actuator authority.

Frequency, pulse width, current, electrode placement, command duration and stimulation timing are TBD-gated to qualified electrical, clinical, safety and regulatory owners. They are not on this page because they do not exist as requirements.

Default state

No output after startup, reset, brownout, communication loss, watchdog expiry, sensor fault, stale data or low confidence.

Explicit states

Boot-safe, not-ready, stance tracking, pre-swing armed, assist window, terminating, fault terminating, swing tracking and fault latched. Every state and input combination has a row; a missing row is a fault.

Invalid transitions

Zero, at every stage. Any observed unsafe allow is a release blocker even if the aggregate rate rounds to zero.

Identity

Model, thresholds and configuration are content-identified, and an authenticated release manifest is required before shadow-target work.

04 / PROVISIONAL ACCEPTANCE GATES

Event detection on independent data, judged per participant.

GateThresholdState
Toe-off and heel-strike sensitivity and precisionat least 0.95 eachProvisional
Equal-participant median absolute timing error, each eventat most 20 msProvisional
Equal-participant p95 absolute timing error, each eventat most 50 msProvisional
Absolute median signed bias, each eventat most 10 msProvisional
False eventsat most 1 per 100 reference stridesProvisional
Expected calibration error, 10 binsat most 0.05Provisional
Valid runtime fractionat least 95 percentProvisional
Paired baseline gatessensitivity difference lower bound at least −0.02; false-event difference upper bound at most +0.5 per 100 strides; a material timing or coverage advantage for each event typeProvisional

Ground truth must be an independent synchronized reference such as pressure insoles, an instrumented walkway or motion capture. Events derived from the same shank signal are development labels only. These gates validate event detection; they do not establish assist timing or benefit.

05 / TIMING AND RESOURCE GATES

Freshness is measured end to end. The old 23 ms subtotal is retired.

ItemGateState
Update periodone accepted frame per 10 ms nominalLocked
Model inference execution, p99at most 5 msProvisional
Newest sample to supervisor decision, p99at most 30 msProvisional
Maximum newest-source to decision age50 ms; older results inhibited; no catch-up processingProvisional hard freshness gate
Model weightsexpected under 4 KiB INT8; actual reportedProvisional
Model constants plus tensor arenaat most 16 KiBProvisional
Firmware memory, current, runtime, temperaturemeasured after hardware selectionTBD-gated

No timing value has been measured on Norysr hardware, because none has been selected.

06 / DATA TIERS

Five tiers, and the workspace is at the first.

TierPurposeClaims allowed
D0 syntheticschema, timing, state, metric and fault testssoftware correctness only
D1 development-derivedpipeline feasibility, pretraining, debuggingno independent performance claim
D2 independent retrospectivealgorithm selection and internal generalizationinternal development performance
D3 prospective externallocked validationpreclinical validation within declared scope
D4 clinicalbiomechanical and clinical safety and benefitprespecified regulated or peer-reviewed claims only

Participant ID is the split unit. No session, trial or overlapping window may cross partitions. Random row or window cross-validation is prohibited for product evidence.

07 / STAGE GATES

Eight ordered exits. Two are in progress; none is closed.

S0

Specification

In progress; sufficient to seed implementation, not formally closed.

S1

Replay and schema

In progress; first increment exists with 281 passing synthetic tests.

S2

Rule baseline

Code exists; exit blocked on a licensed participant-grouped dataset.

S3

Model 1 offline

Blocked; no dataset at the required tier, so no gait model has been trained.

S4

Shadow target

Blocked; depends on S3 and hardware selection.

H

Hardware-in-the-loop

Blocked; non-energized simulator only.

E

Energized bench

Blocked; separate electrical and safety gate, approved loads only.

C

Human feasibility

Blocked; separate clinical, ethics and regulatory gate.