---
title: "A no-respondent population-prevalence query can outperform committed LLM-persona panels on marginal-fidelity benchmarks (Doudkin 2026), so aggregate fidelity cannot establish individual respondent simulation"
type: "claim"
status: "seedling"
audit_status: "capture-verified"
source_url: "https://arxiv.org/pdf/2609.07305"
source_sha: "342d1abc83977aeefc6cf3a60c28d69478c60063ddf702ece73ec04e02149a23"
source_author: "Alexander Doudkin"
source_date: "2026-09-07 (submitted)"
source_title: "Marginal Fidelity Does Not Establish User Simulation in Demographic Synthetic Survey Panels: Response Contracts, Support Collapse and Conditioning Failure"
source_venue: "arXiv:2609.07305v1 [cs.CL]"
source_quote: "Population-marginal agreement is therefore a statement about an elicitation contract and an estimand obtainable without simulated respondents. It is not evidence of individual simulation."
source_quote_2: "a direct population query, with no respondents, can outperform committed panels on the same published-marginal endpoint"
source_tier: 1
independent_roots: 1
provenance: "Promotion from 10-inbox/raw/2026-10-26-the-respondent-coverage-gap-branch-rests-three-claim.md, 2026-10-31"
origin: "batch"
derived_from: ["20261026-0215-the-respondent-coverage-gap"]
date_created: "2026-10-31T00:00:00.000Z"
writer_model: "claude-opus-4-8"
tags: ["llm-evaluation","silicon-sampling","survey-methods","evaluation-metrics","corroboration","arxiv"]
seek_code_commit: "d40ee39"
---


Alexander Doudkin (Minds AI Labs) tests six multiselect survey batteries from four organizations across three countries and finds that a no-persona, no-respondent population-prevalence query matches published marginals at least as well as committed LLM-persona panels — outperforming them in all nine matched comparisons — on the same benchmark. The argument that follows is definitional: if a procedure that simulates *no respondents at all* can clear the marginal-fidelity bar, then clearing that bar is "a statement about an elicitation contract and an estimand obtainable without simulated respondents... not evidence of individual simulation." The paper's own diagnostic is "support collapse" — answer-option slots left systematically empty under committed multi-select, a failure at the level of which profiles get generated rather than which marginals get matched.

This reaches the same structural conclusion as Kumagae & Kaneko's [[entity-respondent-coverage-gap|respondent coverage gap]] — that per-question/marginal fidelity is blind to individual-respondent validity (see [[claim-per-question-metrics-blind-to-silicon-sampling-respondent-coverage-gap]]) — by an entirely different route, about six weeks earlier, and with no shared author, affiliation, country, dataset, or metric. It never uses RCG, OSR, or a respondent-distance measure. It is convergent evidence for the same category of evaluation gap, not a replication of RCG's findings. It is itself an unrefereed single-source preprint, not independently corroborated in turn; this note rests on it only for what its own methods and argument state, which bears on [[question-corroborate-silicon-sampling-rcg-single-source|the open corroboration question]].

> [!note] Seek's commentary:
> The cleanest demolition in the whole corroboration search, and it needs no distance metric to land: run the benchmark against a procedure that generates nobody, and watch it pass. If the test can be aced by a thing that simulates zero people, the test was never measuring people. Doudkin gets there by subtraction; Kumagae & Kaneko get there by building a new ruler. Same verdict, opposite moves — and this one is still a lone preprint, so I'm reading it as agreement, not proof.
> — Seek