Reference Humans

Reference humans provide cohort-derived expectations for Twin initialization.

Reference humans are distributional models. They represent expected ranges, variance envelopes, trajectories, and priors for comparable human states.

Reference-human diagram #

INPUTCohort Context

Population fit · signal context · baseline assumptions

REFERENCE MODELDistributional Priors

Expected ranges · variance envelopes · trajectory priors

COMPARISONObserved Drift

Actual evidence compared against expected patterns

OUTPUTTwin Calibration

Reference-weighted model refinement

Reference model flow #

01

Expected ranges

Define expected values and ranges for comparable cohort contexts.

02

Variance envelopes

Represent normal variation instead of flattening populations into one average.

03

Trajectory priors

Help estimate how a state may move over time before enough individual history exists.

04

Initialization support

Provide priors for building the first usable version of the Twin.

05

Drift comparison

Allow DT4H to compare observed changes against expected cohort behavior.

06

Calibration anchor

Ground recalibration so updates remain interpretable and bounded.

Boundary principles #

ReferenceDistributional model

A reference human is a statistical construct, not a real person or avatar.

Expected rangeNot optimal claim

Expected values are contextual baselines, not universal health targets.

VarianceNot error

Variation is modeled explicitly so the system avoids false precision.

CalibrationEvidence-weighted

Reference assumptions should shift as individual evidence accumulates.

Implementation notes #

Model distributions, not avatars

Reference humans should represent ranges, variance, and priors rather than fictional people.

Expose assumptions

Expected ranges and priors should be explainable and traceable to cohort context.

Allow reference weighting to shift

Calibration should adjust reference influence as individual evidence grows.

LayerReference Modeling
StatusActive Draft
SystemDT4H / StateK / SETPOINT
BoundaryInfrastructure, not diagnosis
System lineageDT4HTwinStateKSETPOINTOutcomesRecalibration
Infrastructure boundaryDT4H models cohorts, Twins, calibration, and runtime state. It does not diagnose, prescribe, or replace licensed clinical judgment.
Document statusInfrastructure draft
Last updatedMay 2026
Applies toDT4H.ai / AvatarK.ai ecosystem