Skip to main content

Method and evidence for synthetic research you can inspect.

A synthetic panel is useful only when its origin, boundaries, and transformations remain visible. This guide follows the evidence into the panel, the questions asked of it, and the checks that help a researcher decide what an output can responsibly support.

Overhead view of a research desk covered with annotated transcripts, pinned photographs and a pin-linked thread map, with six small seated figures in blue, sage and cream deliberating on a round platform at the centre.

Scope

A synthetic output is a model-generated response from a defined panel. This page explains what enters the process, what the outputs mean, and where interpretation and validation apply.

Inputs

Target descriptions define the population. Interviews and surveys provide observed material. Briefs and existing research can frame the question. Exploratory panels can start before fieldwork; evidence-grounded panels use collected evidence.

Individual reconstruction

Source statements and responses are interpreted into individual cognitive representations. A Human Digital Twin is a synthetic participant, not an observed person.

Panel and deliberation

Twins form a defined population. They answer structured questions and deliberate through propositions, reasons, grouping, consensus, and disagreement.

What the panel returns

Outputs include individual responses, motivations, opinion groups, collective agreement, dissent, and traceability. They remain distinct from observations collected from real people.

Status

Observed material is collected from people; inferred structure is a model interpretation; synthetic output is generated by the panel. These labels describe information status, not a proof ranking.

Provenance

Keep the target, source material, question, panel configuration, and transformation path available for inspection.

Calibration

Compare panel behavior with reference evidence and a human control group where available. Adjust the setup when the panel deviates or the source changes.

Uncertainty

Confidence decreases as a question moves beyond the source material. A well-formed answer outside that perimeter is exploration, not an observation.

Privacy and governance

HDTwin is designed and hosted in Europe. Customer inputs are used to build their panel, remain their exclusive property, and are not stored on HDTwin infrastructure beyond strictly necessary processing.

Validation

Validation means comparing behavior with real-population evidence. It does not turn synthetic output into direct observation or guarantee future behavior.

Documentation

Read the working paper for the documented policy result and the Bodensee press release for the documented audience study. These are resources, not a separate Cases proof taxonomy.

Epistemic perspectives

Preserve minority reasons and disagreement instead of reducing every question to one average. Inspecting origins and transformations helps surface model and data imbalance.

Glossary

Use the glossary below as a descriptive reference, not a mandatory vocabulary.

Use the glossary below as a descriptive reference, not a mandatory vocabulary.
TermUsage
PlatformThe HDTwin system that constructs and interrogates panels.
Human Digital TwinOne synthetic participant representing relevant characteristics, attitudes, and information.
Synthetic panelThe defined population formed by Human Digital Twins.
EvidenceObserved material, such as interviews and surveys, used to inform or calibrate a panel.
InterrogationStructured questions or stimuli directed to a panel.
DeliberationIterative exchange in which panel members propose, comment on, judge, and group positions.
OutputResponses, reasons, groups, consensus, disagreement, and traceability generated by interrogation.
CalibrationAdjusting a panel against observed reference material.
ProvenanceThe visible relationship between input, panel, question, transformation, and output.
FieldworkResearch with real people.
Cultural InstitutionsThe sole initial Industry vertical.
Music & Performing ArtsThe first context within Cultural Institutions, not a route or taxonomy.
Discuss method and evidence for your project

30-minute online conversation; invite a methodological or governance reviewer and bring the evidence boundary you need to assess; next step is a focused technical walkthrough.