Science
Build. Measure. Test. Publish.
Imagine All The People builds synthetic populations under explicit constraints, measures their coherence, tests the robustness of results and documents the methods used to examine them.
Method
The language model is involved in interactions with synthetic individuals. On its own, it does not define the statistical structure of the population.
Formulation
- p(x)probability of a complete individual configuration x
- fₖ(x)statistical constraint k (unary, binary or ternary)
- λₖmultiplier associated with constraint k
- Z(λ)normalization constant of the exponential family
Among the distributions compatible with the known constraints, the approach seeks the maximum-entropy one: the distribution that adds no further structure beyond what the retained data imposes.
SourceFrançois Pachet, Jean-Daniel Zucker — Maximum Entropy Relaxation of Multi-Way Cardinality Constraints for Synthetic Population Generation, Frontiers in Artificial Intelligence — DOI 10.3389/frai.2026.1840945 View
Peer-reviewed · Accepted for publication. Accepted on 30 September 2026.
Benchmark
Result
K ≥ 28
A threshold observed in this protocol, not universal superiority.
Protocol
- NPORS-derived · 4 to 40 attributes
- Unary, binary and ternary constraints
- Generalized raking vs Maximum Entropy Relaxation
Validation
Reference
Confront the model with the available external knowledge.
Deviation
Measure the differences between target and generated distributions.
Variation
Vary the structuring assumptions to identify robust and fragile results.
Auditability
Make it possible to trace a result back to the methodological conditions that produced it.
Limitations
- Not an individual prediction.
- Not a substitute for real-world data.
- Not certainty about the future.
- Not an automated decision.
Publications
Published
1 article peer-reviewed and accepted in Frontiers in Artificial Intelligence (DOI 10.3389/frai.2026.1840945).
Earlier preprint version on arXiv.
In preparation
Work described, not submitted.
Editorial contribution
Co-editing of the Synthetic Populations Research Topic, separate from the article.
Scientific team
François Pachet
Population synthesis · constrained generation
Jean-Christophe Baillie
Simulation · cognitive models · dynamic agents
Jean-Daniel Zucker
Complex systems · methodological robustness
AI agents
The method does not change with the interface.
Whether a population is questioned directly in Imagine All The People or from an agentic system, it is built on the same methods and the same constraints.
MCP access changes how the technology is used. It does not change the nature of the populations or the validation level of the results.
Your next decision
Which decision do you want to explore?
Describe your need. We can point you to the right level of support.
