Contribution to the handbook
Supporting · Assessed 2026-10-28
The data source and participant characteristics are relevant background for assessing whose preferences a system might reflect and how preference-prediction results should be interpreted. The packet identifies representativeness limits, but does not present a governance mechanism or evidence that the data represent all citizens.
Does this challenge the goal?
None identified
The question concerns the data source and participant data used in a study; it does not contest the handbook’s goal or scope.
The evidence identifies the source and data types but does not show that participants represent the broader public.
Why this category?
- useful data-provenance context
- consequential representativeness limitation
The supplied account does not establish sample representativeness, how omitted or more varied demographic responses were handled, or transfer to other populations.
This is an AI assessment of contribution to the goal, separate from whether the question has an answer.
Authority, accountability and resilience →
Tests, stop conditions and unresolved work →
Read the exploration goalNew evidence is being assessed. Any answer below is provisional; parts whose evidence changed or was withdrawn are withheld.
Identify the data-collection source and the types of participant data used.
What we can say so far
The model tests use participant data collected through Brazucracia, an online government-program builder used during Brazil’s 2022 presidential election. The data include participants’ paired choices between policy proposals and reported demographic details. The characteristics listed for prompt context were age, political ideology, urban or rural zone, education, sex, and city and state.
What remains open
- The evidence does not establish that participants represent people who did not take part.
Conditions and limits
- This describes data from participants in an online experiment, not a demonstrated representative sample of the Brazilian public.
- The source describes the recorded demographic categories; it does not establish how missing or more varied responses were handled.
Evidence and related ideas
Supporting evidence, qualifications and context play different roles in this answer.
supports
Where the data came from The study uses pairwise choices and demographic information collected through Brazucracia, an online government-program builder used during Brazil’s 2022 presidential election.
Directly identifies Brazucracia and the collected choices and demographic information.
Large Language Models (LLMs) as Agents for Augmented Democracy
Read full source: Large Language Models (LLMs) as Agents for Augmented Democracy (opens in a new tab) ↗Read source discussion: Large Language Models (LLMs) as Agents for Augmented Democracy →
context
Testing individual predictions The researchers test individual prediction by training models on some participants’ choices and checking predictions against choices from participants held out for testing.
Describes held-out participant choices used to test individual predictions; not needed to identify the data source or types.
Large Language Models (LLMs) as Agents for Augmented Democracy
Read full source ↗