Fetching from the wire…
Research2026-08-12 · source-backed
Orr Paradise, Oliver Richardson, Yoshua Bengio and Shafi Goldwasser construct an interactive PCP protocol where a polynomial-time verifier certifies approximate consistency of predictions specified by circuits, even though those circuits implicitly define exponentially many claims (arXiv 2608.11181). For explicit claims (m conditional probabilities over n Boolean variables) they place ℓ2-approximate consistency in NP with certificates of length O(mn + log B). Motivation is stated as AI safety and honest uncertainty quantification: a theoretical basis for making a model prove its calibration rather than sampling it and hoping.
Each link below shares sources, entities, or timing with this story.
Shared entity: Boolean / Same source domain / Shared topic / Earlier coverage
Both cover Boolean; reported by the same outlet (arxiv.org); overlapping topics (boolean, claim).
Same source domain / Shared topic / Tension
Reported by the same outlet (arxiv.org); overlapping topics (calibration, claim); pushes against this story (vs).
Reported by the same outlet (arxiv.org); overlapping topics (even, explicit); pushes against this story (against).
Shared entity: Yoshua Bengio / Earlier coverage / Tension
Both cover Yoshua Bengio; earlier Yoshua Bengio coverage from 2026-02-26; pushes against this story (but).
Same source domain / Shared topic
Reported by the same outlet (arxiv.org); overlapping topics (circuit, even).
Reported by the same outlet (arxiv.org); overlapping topics (even, explicit).
Reported by the same outlet (arxiv.org); overlapping topics (certify, claim).
Reported by the same outlet (arxiv.org); overlapping topics (boolean, circuit).