shade-arena-jev-monitor

What Jev does in shade-arena-jev-monitor

The project describes itself this way: Evaluating TypeSafe's Jev as a fast monitor and action gate for agent sabotage in SHADE-Arena, compared with Gemini 2.5 Flash/Pro. In the Benchmarks & research category, Jev typically decides labels and probabilities on fixed test sets, so accuracy, calibration and latency can be measured.

Verification

Verified. We confirmed this repository and its Jev relevance through the GitHub API and the source lists below. A specific file link has not been recorded yet.

How Benchmarks & research projects use Jev

Benchmarks and research projects test Jev rather than just use it. They compare it with language models and other classifiers, check whether its probabilities are well calibrated, and explore where the decision-model approach breaks down.

Also listed in: Games & simulations.

Related Jev projects in Benchmarks & research

1. jev-calibration-auditjujumilk3/jev-calibration-auditAudits Jev calibration, option-wording effects and Korean judgments through public APIs and datasets.★ 0
   Python
2. jev-transcript-screenerkeduseworku/jev-transcript-screenerDemo and evaluation harness that uses Jev to rank solver transcripts for review by a more costly judge.★ 0
   Python
3. jev-vs-clefrmax-ai/jev-vs-clefLaunch-window comparison harness for Jev and Cloudflare Clef decision models on synthetic decision tasks.★ 0
   Python
4. jev-comparewestsmith-open/jev-compareSide-by-side Jev and Gemini evaluation harness comparing typed decisions, requests, latency, cost and calibration.★ 0
   HTML
5. decision-benchHanno-Labs/decision-benchOpen benchmark runtime for document-grounded decision models.★ 1
   Python
6. jev-synergy-screeningPistachioAIHQ/jev-synergy-screeningA Jev title-and-abstract screening experiment compared with Cohen Abstract Triage labels for an ADHD review.★ 1
   Python

See all 107 Benchmarks & research projects →

Where we found it

• heyjunpenn/awesome-jev