jev-paper-judge

Feedback on your paper in seconds.

How it uses Jev

That is what a System One model is for. Jev does not write an essay about the paper. It answers small, literal questions ("are the symbols in this passage defined when they first appear?") with a probability, in one pass, in well under a second. Three things follow:

Getting started

wrangler.jsonc also declares the rate limit and a TYPESAFE MODEL var that selects which Jev release answers. Set it to a versioned ID such as jev-1.13.0 if you tune thresholds and want them to stay put when jev-latest moves.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Keep exploring

Similar to jev-paper-judge

Browse all
jev-realtime-trading project preview
Benchmarks & research
Paper trading agents on a live tape, decided every second by TypeSafe's Jev (System One). Electron desktop app.
JEV-language project preview
Demos & playgrounds
Give your Jev language
harnessjudge project preview
Demos & playgrounds
Judge agent steps — ok / retry / escalate / stop via TypeSafe Jev
clarity-judge project preview
Demos & playgrounds
Multi-axis writing quality checker powered by TypeSafe AI's Jev model. Separate named checks, each with its own verdict and confidence.
mimicry project preview
Applications
Rewrite AI drafts in your own voice with a bounded TypeSafe feedback loop.
jev-shadcn-lint-eval project preview
Benchmarks & research
A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output.
jev-as-a-judge project preview
Benchmarks & research
Using Jev as an evaluator.
jev-for-chrome project preview
Browser & computer use
Jev for Chrome: drives the tab you are looking at with TypeSafe Jev, a sub-second decision model. Community port of browser-use/jev-ultrafast, not affiliated with TypeSafe.
skillranker project preview
Agent tooling
Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.