Generative Research
Institute for Truth

Measuring truth at machine scale.

We build open methods, benchmarks, and models for determining whether information can be trusted, whether a person or a model produced it.

Explore our research
NewAnnouncing the inaugural GRIFT Award for Journalism, presented to Brandy Zadrozny

Research areas

Provenance

Tracing where a claim originated and how it changed as it moved across platforms.

Model Evaluation

Benchmarks that test how reliably generative systems report facts.

Public Trust

Research on how people decide what to believe, and how to give them better signals.

Latest work

  • Paper, September 2026

    TruthBench: A Benchmark for Evaluating Factual Reliability in Generative Models

    Model Evaluation

  • Technical report, August 2026

    Signal Decay: Tracking Claim Mutation Across 4.1 Million Posts

    Provenance

  • Paper, July 2026

    Calibrated Confidence: Measuring When Audiences Should Trust a Source

    Public Trust

View all research

4.1M

posts analyzed in our provenance dataset

12

frontier models evaluated on TruthBench

100%

of methods published openly