Skip to content

Jev glossary

Patterns

Self-consistency

Repeatability across repeated evaluations: Jev's probability standard deviation measured at about 0.01 in the consistency cookbooks.
Category
Patterns
Also known as
None
Reading time
1 min
Related terms
4
Directory entries
2
Docs
docs.typesafe.ai
Added
2026-09-24

Definition

The Choice cookbook runs an 8-question moderation rubric 15 times per condition and measures a mean probability standard deviation of 0.0098, against 0.0245 to 0.0543 for five LLM distributions. The Noul cookbook measures 0.0102 on a 14-question claims rubric.

These are repeatability numbers, not accuracy numbers: Jev still flipped its top label on two questions across its own repeats, and a deterministic temperature-0 baseline can score perfect agreement by never abstaining.

Tagspatternsconsistencyevaluation

From the Jev directory

Directory entries that go deeper on this term.

A repeatability study: an 8-question moderation rubric run 15 times per condition shows a mean probability standard deviation of 0.0098, and a 0.60 uncertainty gate lifts agreement to 99.2%.
Jev CookbooksDocs#official#cookbook#consistency
Official
A 14-Noul claims-triage rubric over one insurance claim, repeated 15 times: mean probability standard deviation of 0.0102 at 111 ms per call, with a 0.30 to 0.70 band for human review.
Jev CookbooksDocs#official#cookbook#consistency
Official

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai