Claim LD07-SL-C01 (v1.1)

Provenance and status

Claim type

Estimate

Publication status

Eligible for publication, with qualifiers: version

Verification state

Checked against the primary source; the source is a preprint. Who checked this claim is not recorded for it; claim checks so far were AI-led, and no person has checked claims against their sources.

Does not license

Replacing a population or sample with synthetic respondents; inference about variables outside the conditioning backstory; fidelity in other countries, domains or models; treatment effects or regression coefficients

Limitations

The published version is Political Analysis 31(3):337–351, 2023 (doi:10.1017/pan.2023.2); it was read only in its abstract, and its figures may differ from the preprint figures given here; backstories include party identification and ideology, which predict vote choice; the headline results use one model, GPT-3 (an appendix compares five model families on vote choice only); one country and one domain; for the associations among 2016 survey answers the authors did not evaluate correspondence at the individual level

Source (as cited)

Argyle, Busby, Fulda, Gubler, Rytting & Wingate, “Out of One, Many: Using Language Models to Simulate Human Samples,” arXiv:2209.06899 v1, September 2022

Source type

Preprint (recorded as “Preprint”)

Institutional position

Independent academic

Maturity of the evidence

Contested evidence

Recorded date

22 October 2026

Currentness / correction

This is the current version. No correction or concern is recorded on its sources.

Sources this version cites

• Argyle, Busby, Fulda, Gubler, Rytting & Wingate, “Out of One, Many: Using Language Models to Simulate Human Samples,” arXiv:2209.06899 v1, September 2022 (Preprint)
  Read the original

Version

This page shows version v1.1. Its record never changes, even when newer evidence arrives; the site may add a note to the page or withhold a figure not cleared for public use.

This pinned version is also the current version.

Versions: v1.0, v1.1 · current

What changed in this version

This version supersedes version v1.0 (LD07-SL-C01--v1.0), which stays available with its record unchanged.

Changed fields

2 PUBLIC-FACING CLAIM; 14 MAIN RESULT; 25 RECORDED DATE

What changed

The public-facing claim now says, beside the correlations, that the backstories included each respondent’s party identification and ideology, and that the figures are correlations, not shares of votes predicted correctly. The main result adds the proportion agreement from the same table (0.85, 0.87 and 0.89), names Table 1, and says that the preprint does not report how many respondents each year’s figures rest on. The figures, the source and the other fields are unchanged.

Why

An external research-integrity review of the site on 22 October 2026 (an AI reviewer, not a person) found the figures correct but asked that the party-identification caveat sit beside the headline correlations, that Table 1 be cited and that the per-year sample sizes be given. SocioLens re-read arXiv:2209.06899 v1 on 22 October 2026. Study 2 lists “(5) party identification” and ideological self-placement among the variables used to condition GPT-3, and Table 1 gives whole-sample tetrachoric correlations of 0.90, 0.92 and 0.94 with proportion agreement of 0.85, 0.87 and 0.89. Neither Table 1 nor the appendix tables for Study 2 state how many respondents each year’s comparison uses, so this version says that rather than give a number. The check and this revision were done by an AI agent reading the preprint, not by a person.