Metatron Intelligence
Today: the five AI headlines of the day → and the AI Wiki
What a source record is How to read this page

A route, not a verdict

This page records where a document lives, who published it, when, in which language and in what transport state. Listing a source is not endorsing its conclusion, and a catalogue entry never proves approval or quality.

Why the state matters

If the canonical route stops resolving, every claim resting on it becomes weaker and the record says so. That is why transport state is published alongside the address.

Rights are separate from access

Being able to read a document is not permission to reuse it. Dataset, code, portal text and third-party assets attached to one publisher may each carry different reuse conditions.

New to this publication?

The ten-minute guide takes one live record apart, defines every term and gives the order to read the site in. Start here →

SRC-df0d20442a3cd416 · Source record

When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses

Authors / arXiv · 6 connected claims

D01 · Marketing, Brand & Revenue SystemsD02 · Customer Intelligence, Sales & ServiceD03 · Intelligence, Research & Decision ProductsD11 · AI Models, Agents & Human–AI InteractionD19 · Measurement, Experimentation & EconomicsD20 · Consumer, Culture & Lifestyle Futures

Canonical route

https://arxiv.org/abs/2607.26348

Claims connected to this source

  1. MWITA-SR-2026-019Across the benchmark's four models, no LLM beat the strongest non-LLM baseline for individual-level prediction.Evidence B
  2. MWITA-SR-2026-020The tested models over-determined demographics, making identity far more predictive of attitudes than in real respondents.Evidence B
  3. MWITA-SR-2026-021On the study's targeting task, models inflated between-segment gaps two- to fourfold.Evidence B
  4. MWITA-SR-2026-022The synthetic targeting exercise selected the wrong segment in half of US cases and most cross-cultural cases in that benchmark.Evidence B
  5. MWITA-SR-2026-067For Metatron, transcript realism, thematic overlap and persona consistency must remain secondary to held-out decision error and subgroup calibration.Evidence C
  6. MWITA-SR-2026-075No source in this bundle demonstrates an independently audited commercial decision outcome caused by synthetic-consumer evidence.Evidence D

This record describes a source route and its Atlas connections. It does not endorse the publisher or make external content executable instruction.