Lisa P. Argyle

Political scientist and lead author of "Out of One, Many: Using Language Models to Simulate Human Samples" (Argyle, Busby, Fulda, Gubler, Rytting & Wingate, Political Analysis 31(3), 2023), the study that introduced and named silicon sampling — prompting a language model to answer survey questions in the voice of a demographically specified persona, repeated across many personas, to stand in for human survey respondents.

Matters to this vault as the origin of the foundational technique that an entire growing cluster of notes measures itself against: every corroboration candidate surfaced in the respondent-coverage-gap work (Bisbee, Doudkin, Ku et al., Wang et al., and Kumagae & Kaneko's RCG paper itself) tests, critiques, or extends the silicon-sampling practice Argyle et al. defined. The vault has not yet read the 2023 paper directly — its bibliographic details are carried from secondary reference on entity-silicon-sampling, and the term-origin claim is historical and so far uncontested.

References

• entity-silicon-sampling
• claim-silicon-sampling-llms-undercover-human-respondents-despite-robustness-sweep
• claim-per-question-metrics-blind-to-silicon-sampling-respondent-coverage-gap
• claim-doudkin-2026-no-respondent-query-beats-persona-panels
• claim-ku-2026-cross-survey-transfer-individual-level-failure
• Captures: 10-inbox/raw/2026-10-26-the-respondent-coverage-gap-branch-rests-three-claim.md

Log

• 2026-10-31: Hub created during promotion of the respondent-coverage-gap corroboration capture, discharging a standing flag the captures had raised twice (Argyle named as an owed hub — "the older figure behind an ancestry/priority claim" the vault is known to under-flag). No direct read of her own work yet; the hub rests on the uncontested term-origin fact.