Radar Update RADAR-LD07-PEW-SYNTHETIC-SURVEYS-2026

Version

Current version v1.0, resolved through the explicit current pointer RADAR_UPDATE--RADAR-LD07-PEW-SYNTHETIC-SURVEYS-2026.

Versions:v1.0 · current

What changed: Pew Research Center (30 September 2026) built an AI “digital twin” for each panelist analyzed from three 2026 waves of its American Trends Panel, a nationally representative panel of randomly selected U.S. adults. Each twin was conditioned on that person’s profile and earlier survey answers, and weighted synthetic and human results were compared on nearly 300 questions. With its best-performing configuration (Claude Opus 4.6), synthetic estimates differed from human estimates by an average of 12.4 percentage points. Error was substantial for every subgroup reported, reaching 16.1 points for Republicans and Republican leaners and 15.1 points for Black adults. On 47% of questions at least one answer choice was selected by no synthetic respondent, which happened on no question among humans. Results also differed systematically by AI model, although some toplines matched closely. This strengthens the evidence for LD07-HQ-C06 on selected-average agreement, real-world response variance and subgroup heterogeneity. The report contains no regression or treatment-effect analysis and no individual-level accuracy result for its final configuration, so those parts of the claim are unchanged. The claim wording is unchanged.
Recorded: 2026-10-07
Debate(s) moved: LD-07
Affected Claim versions: LD07-HQ-C06--v1.0
Affected / trigger Sources: SRC-LD07-PEW-SYNTHETIC-SURVEYS-2026
Movement semantic: NOT_APPLICABLE
Prior position effect: STRENGTHENED (LD-07 P2)
Durability: DURABLE
Canonical content changed: no — this update changes no debate standing and creates no claim

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 4ab7bfc671e6f5b2dde3491a8342789a96a36320ccfc1aa89caec99dc73e4ad7.

Frozen Drive-derived inputs

SocioLens — HQ Decision — Pew Radar Adjudication — sociolens-full-20261007T200039Z — Drive ID 16O6-3-Yw7M9iupjPxzwNxVV8uE5j_IRu; revision: NOT_EXPOSED_BY_DRIVE_TEXT_EXPORT; Drive modified 2026-10-07T22:26:55.921Z; block “SocioLens — HQ Decision — Pew Radar Adjudication — sociolens-full-20261007T200039Z FULL EXPORT” SHA-256 7846f929a1655b18ac2ae1d729242dff17b66672cec179b9663cf0e7c132ec72; SocioLens — Programme Status & Authority Register v0.8 status “Explicit non-Register basis: HQ decision HQ-ESC-sociolens-full-20261007T200039Z-02 (SHA-256 7846f929a1655b18ac2ae1d729242dff17b66672cec179b9663cf0e7c132ec72), issued under Programme Status & Authority Register v0.8 §5 and HQ decision HQ-BOOTSTRAP-sociolens-full-20261007T200039Z-01.”; frozen fixture fixtures/frozen/hq-decision-pew-radar-adjudication.

Builder decisions (not Drive data)

VERSION = v1.0 — basis: HQ decision HQ-ESC-sociolens-full-20261007T200039Z-02 item 5: version v1.0 with supersedes []; the first record of this Radar Update.
CURRENT_POINTER = true — basis: HQ decision HQ-ESC-sociolens-full-20261007T200039Z-02 item 5: the sole version of this Radar Update; the materialization manifest explicitly designates RADAR-LD07-PEW-SYNTHETIC-SURVEYS-2026--v1.0 current.
VISIBILITY = PUBLIC — basis: HQ decision HQ-ESC-sociolens-full-20261007T200039Z-02 item 5 records visibility PUBLIC.