Autonomous LLM agents can complete online surveys while passing conventional attention and logic checks at very high rates under tested conditions.

SocioLens project,

Claim LD07-HQ-C09 (v1.0)

Autonomous LLM agents can complete online surveys while passing conventional attention and logic checks at very high rates under tested conditions.

Research opportunities this claim motivates

What this claim leaves open for research. Each is a hypothesis about a gap, not a finding.

How much AI-assisted or agent responding reaches probability panels?Agents can pass conventional quality checks, so standard panel QA cannot be assumed to catch them.

Provenance and status

Claim type: Fact
Publication status: Eligible for publication
Verification state: Checked against the primary source. 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: Any field prevalence estimate
Limitations: Designed capability demonstration; not production-panel observation
Source (as cited): Sean J. Westwood, PNAS 122(47):e2518075122 (2025)
Source type: Peer-reviewed journal article (recorded as “Peer-reviewed journal article”)
Institutional position: Independent academic
Maturity of the evidence: Mature evidence (capability)
Recorded date: 25 September 2026
Currentness / correction: This is the current version. No correction or concern is recorded on its sources.

Sources this version cites

Westwood, “The potential existential threat of large language models to online survey research,” PNAS 122(47):e2518075122 (2025) (Peer-reviewed journal article)
Read the original

Version

This is the current version, v1.0. Earlier versions stay available, and their records never change.

Versions: v1.0 · current

Raw record: every recorded field, with its coded values

All 25 canonical Claim fields, verbatim, with the coded values derived from them. The plain-language labels above are read from these.

Claim type (coded): FACT (as printed: “FACT”)
Publication status (coded): ELIGIBLE (as printed: “ELIGIBLE”)
Verification state (coded): CONTENT_VERIFIED_PRIMARY
Source type (coded): PEER_REVIEWED_JOURNAL_ARTICLE
Maturity (coded): MATURE (CAPABILITY)

#	Canonical field	Canonical value (verbatim)	Normalized (Claim Value Vocabulary v1.0.2)
1	CLAIM ID	LD07-HQ-C09	—
2	PUBLIC-FACING CLAIM	Autonomous LLM agents can complete online surveys while passing conventional attention and logic checks at very high rates under tested conditions.	—
3	CLAIM TYPE	FACT	base_types: FACT
4	RESEARCH STRAND	D — Survey/trace contamination	—
5	MATURITY	CAPABILITY MATURE	states: MATURE · qualifiers: CAPABILITY
6	SOURCE	Sean J. Westwood, PNAS 122(47):e2518075122 (2025)	source_ids: SRC-LD07-WESTWOOD-SURVEY-THREAT-2025
7	SOURCE TYPE	Peer-reviewed journal article	classes: PEER_REVIEWED_JOURNAL_ARTICLE
8	INSTITUTIONAL POSITION	Independent academic	—
9	SCOPE	Online survey quality checks	—
10	DESIGN	Autonomous synthetic-respondent capability experiment	—
11	SAMPLE / DATASET	6,000 ACQ trials; broader 43,800 evaluations/139 questions	—
12	MODEL / TOOL / VERSION	o4-mini primary; key subset across nine LLMs	—
13	COMPARATOR	Conventional survey-quality checks / expected human constraints	—
14	MAIN RESULT	99.8% ACQ pass; perfect on 18/20 check types	—
15	INFERENTIAL TARGET	Capability to evade checks	—
16	DOES NOT LICENSE	Any field prevalence estimate	—
17	VERIFICATION STATE	CLEARED	state: CONTENT_VERIFIED_PRIMARY · verified_by: UNKNOWN
18	LIMITATIONS	Designed capability demonstration; not production-panel observation	—
19	CONTRADICTORY / SUPPORTING SOURCES	Later prevalence audits address different estimand	—
20	GEOGRAPHY / LANGUAGE	US / English	—
21	DISTRIBUTIONAL LEDGER	Not assessed	—
22	R01 / FIELD-MAP LINKS	T1, D9	—
23	WHAT WOULD CHANGE THIS CLAIM?	Robust checks that reliably separate capable agents from humans	—
24	PUBLICATION STATUS	ELIGIBLE	state: ELIGIBLE
25	RECORDED DATE	2026-09-25	—

Field 22 references resolved against Field Map v0.2: T1 (TENSION); D9 (DOMAIN)

The sources as recorded, with their record IDs and coded source types:

Pinned Sources (field 6, version-specific)

“Sean J. Westwood, PNAS 122(47):e2518075122 (2025)” → Westwood (2025), “The potential existential threat of…” (SRC-LD07-WESTWOOD-SURVEY-THREAT-2025--v1.0) — Westwood, “The potential existential threat of large language models to online survey research,” PNAS 122(47):e2518075122 (2025); class PEER_REVIEWED_JOURNAL_ARTICLE (explicit public provenance pin)

Cited by Living Debate versions

AI in the research apparatus (v0.1) LD-07
AI in the research apparatus (v0.2) LD-07

Cite this page

SocioLens project. (2026, September 25). Autonomous LLM agents can complete online surveys while passing conventional attention and logic checks at very high rates under tested conditions [Claim LD07-HQ-C09, version v1.0]. SocioLens. https://sociolens-web.pages.dev/claims/ld07-hq-c09/v1.0/

@misc{sociolens_ld07_hq_c09_v1_0,
  author = {{SocioLens project}},
  title = {Autonomous LLM agents can complete online surveys while passing conventional attention and logic checks at very high rates under tested conditions.},
  year = {2026},
  date = {2026-09-25},
  howpublished = {\url{https://sociolens-web.pages.dev/claims/ld07-hq-c09/v1.0/}},
  note = {Claim LD07-HQ-C09, version v1.0}
}

The link points to this version, whose record never changes. For a finding, cite the original study as well: SocioLens summarizes research and does not replace it.

Research-of-record provenance

Materialized by sociolens-materializer 0.6.0 at 2026-09-28T20:00:00.000Z; normalization contract SocioLens — Claim Value Vocabulary v1.0.2 — Pre-Spike Materialization Contract (v1.0.2). Content seal SHA-256 2495ad73d1553002b0cda712a856ccf6f9b9056d99ee7a7160a5aed46ba1944a.

Frozen Drive-derived inputs

R03 — LD-07 Canonical Claim Ledger v1.0 — LOCKED (v1.0) — Drive ID 1xVz_LrQAA8EA1tPhVWIrDgOUU3Zidlg9; revision: NOT_EXPOSED_BY_DRIVE_TEXT_EXPORT; Drive modified 2026-09-29T04:31:14.120Z; block “ENTRY 09 — LD07-HQ-C09” SHA-256 9cca63585480e85526d69f464287a27db8b934aba686e9e299e5b1c1e51e022d; SocioLens — Programme Status & Authority Register v0.6 status “CURRENT.”; frozen fixture fixtures/frozen/r03-ld07-claim-ledger-v1.0-canonical.

Builder decisions (not Drive data)

VERSION = v1.0 — basis: Claim version taken from the canonical ledger artifact version (R03 — LD-07 Canonical Claim Ledger v1.0); Implementation Architecture Selection §5
CURRENT_POINTER = true — basis: SocioLens — Programme Status & Authority Register v0.6 status for "R03 — LD-07 Canonical Claim Ledger v1.0 — LOCKED": "CURRENT."
FIELD_6_SOURCE_REFERENCE = SRC-LD07-WESTWOOD-SURVEY-THREAT-2025--v1.0 — basis: field 6 of ENTRY 09 — LD07-HQ-C09 cites "Sean J. Westwood, PNAS 122(47):e2518075122 (2025)"; the frozen field-6 segment of this ClaimVersion's ledger block; Drive-derived identity authority (Issue #39 Source inventory): Batch 03 §1; ledger C09; KEY EVIDENCE.
SOURCE_PROVENANCE_PIN = SRC-LD07-WESTWOOD-SURVEY-THREAT-2025--v1.0 — basis: Issue #5 proof rendering (Architecture Proof Protocol v0.1 AP-08 / Amendment v1.2 §6): explicit version-pinned public provenance of this ClaimVersion — the pinned field-6 Source record "Sean J. Westwood, PNAS 122(47):e2518075122 (2025)"; Drive-derived identity authority (Issue #39 Source inventory): Batch 03 §1; ledger C09; KEY EVIDENCE.