devwithjevReranks Code Retrieval Candidates
Ch3ngass experimented with using Jev as an attention layer over code retrieval. On 356 held-out SWE-Explore tasks, Jev reranking the same 100 zvec candidates improved core recall@1k lines from 11.96% to 22.95%.
Been experimenting with using jev as an attention layer over code retrieval.
On 356 held-out SWE-Explore tasks, adding Jev reranking to the same 100 zvec candidates improved core recall@1k lines from 11.96% โ 22.95%.
More here: https://t.co/ZNp3AnD8Bn
#jev #TypeScript
Also filed under Tools & apps
- Swift Client for TypeSafe Jev Judgments
swift-jev is a Swift client for TypeSafe Jev that uses typed judgments instead of generated text.
- Go SDK and CLI for Jev Decisions
go-jev provides a Go SDK and CLI for TypeSafe Jev typed yes/no, Choice, and Score decisions.
- Open-Model Semantic-If Engine
SemIf-OpenJev is an open-model semantic-if engine for local Jev-style decisions.
- Open-Weight Jev Decision Model
JevK5 is an open-weight Jev alternative that returns typed decisions with probabilities in one forward pass.