Certify Uses Horn-Closure Certificates to Decide When Search Evidence Suffices, Hitting 80% Answer Accuracy vs 57%
_reachsumit · x · 2026-10-28
The Certify paper replaces holistic model judgment with a structural sufficiency test for search-augmented models: a per-query requirement hypergraph states which facts jointly yield others, and Horn closure over entity-checked links yields a certificate — the minimal sufficient passages and their derivation, or an abstention naming open requirements.
Pooled across three corpora with unanswerable twins, Certify decides significantly more accurately than search agents, graph retrieval and sufficiency judges in default configs, matching a proprietary model's sufficiency label with no extra model call. Over 21M Wikipedia passages, entity checks add 4–13 points of decision accuracy, and answers from its certificate are 80% correct versus 57% from all retrieved passages.
More from Research
- TTME beats test-time training on 5 math tasks while cutting FLOPs by 82.8-84.6% — UCSantaBarbara · 2026-10-28
- EnvLunch turns executable environments into free verifiable agent training data — KingsCollegeLondon · 2026-10-28
- Anthropic reveals it is developing its own experimental drugs using Claude — Polymarket · 2026-10-28
- Stanford launches TaskNet: 132 worker interviews build a large-scale occupational task inventory — soumitrashukla9 · 2026-10-28
- KAIST's Principia uses LLMs to construct and refine scientific principles at test time — coallaoh · 2026-10-28
- The AlphaFold Data Problem: Quantum Chemistry Models as Training Data for Larger Scales — TimothyDuignan · 2026-10-28