Research case
Simulating individuals from interviews and surveys (Park et al.)
Using data from 1,052 Americans, the study compares agents grounded in two-hour interviews, structured surveys or both on held-out survey and behavioral outcomes.
What is reported
The June 2026 revision reports GSS accuracy relative to human test–retest consistency of 83% for interview-only agents, 82% for survey-only and 86% for combined agents.
Before you use it
These percentages are relative to participants' own repeat answers, not raw accuracy. The findings concern this sample and raise consent questions about simulating individuals.
Sources and review
Source checked · Not tested by this site
Checked the public abstract and bibliographic record. Results describe the authors' study, not a replication by this site.
License and reuse
No license has been recorded. Check the source’s license before reusing code, models or data.
A license note is not a license audit. Open source does not guarantee free hosting, model access or commercial reuse.