JevCodenican2018/shade-arena-jev-monitor
The decision
README states: Strong per-action gate. Scoring each tool call before it runs, Jev ranked sabotage above almost all benign actions. Gemini Flash's scores piled up at 0 and 100.
Evidence
https://github.com/nican2018/shade-arena-jev-monitor/blob/main/llms/typesafe_llm.py#L20
Verification labels
call-site-verifiedPublic code that calls Jev and consumes its answer was located.
Labels describe the kind of evidence; they are not a score or a ranking.
Category
- Category
- Other lists
- Repository
- https://github.com/nican2018/shade-arena-jev-monitor
- Listed
- 2026-10-29
- Reviewed
- 2026-10-29
Keep going on this site
Try, docs, cases, and pricing link to each other. The next page is on this site.
- Site directoryThe full list of the pages above.
- EcosystemCommunity projects by category.
- Jev coverageEach entry names the decision and its evidence.
- Daily casesThe next batch of coverage cases, each day.
- CommunityPublic posts, each with its source.
- BuildsNotes on model and site updates.
- PrimitivesChoice, Noul, and Score together.
- PatternsRouting, fan-out, and composite scoring.
- SDKsHTTP, Python, and JavaScript.
Use clavue-jev
- Try a judgmentSend a state and read the answer.
- Live scenesTetris, six rapid judgments, and a sort. Copy the call and run it again.
- Judgment LabSupport triage, release review, compliance routing — edit and run on the spot.
- Compareclavue-jev and jev-1.13.0 answer the same question.
- DemosJudgment examples you can edit.
- PricingInput is $0.042 per million tokens. Output is free.
- APICall POST /v1/judge with a key.
Docs
- IntroductionWhat this model is for.
- Quick startThe smallest call that runs.
- System OneWritten here: a state plus one typed question. The model is clavue-jev.
- StateThe text you send in.
- ConfidenceHow sure the answer is, and when to act on it.
- ChoicePick one mutually exclusive option.
- NoulA yes/no question, returned as the probability of yes.
- ScoreRate along a scale.
- Intent routingOne Choice call dispatches the request.
- Confidence routingAct when confidence is high. Hand off when it is low.
- Fan-outAsk several questions of one state.
- Composite scoringFold several scores into one ranking.
- HTTP APIThe request shape without an SDK.
- Python SDKCall a judgment from Python.
- JavaScript SDKCall a judgment from JavaScript.
Cases
- Use-case mapWhich primitive people use for which job.
- GuardrailsA yes/no check before an action runs.
- Function callingPick which function to call.
- Classify with confidenceDo not act when the class is unsure.
- Semantic findFind the passages that match.
- Parallel questionsAsk the whole set in one call.
- Hierarchical classificationCoarse class first, then the fine one.
- Citation checkWhether a sentence is supported by the source.
- Entity alignmentWhether two names are the same thing.
- Skill suggestionChoose which skill fits the moment.