Training Witnesses proposes cheaply verifiable honesty certificates for ML data and evaluations

pratyusha_PS · x · 2026-10-02

Houjun Liu and co-authors launched Training Witnesses, arguing that trust in ML conference results is "utterly broken." The new system issues "honesty certificates" for datasets and evaluations, which a verifier can cheaply check and trust.

Related event: Stanford and NYU Unveil 'Training Witnesses' for Verifiable AI Training(3 posts)→

Original post →

More from Research

Research channel →