Research & evaluation
Find research and evaluation projects exploring decision models and Jev-related approaches.
- 2346jev-projectsSmall demos of Jev (TypeSafe) through the Vercel AI Gateway: wiki race, town of agents, bullet chess, and more
az9713/jev-projects · JavaScript
00javascript - 2353jev-quiz-pilotPut Jev in the pilot's seat of a web quiz. A Python CLI that lets TypeSafe's Jev navigate quizzes in your Chrome and logs every pick, so you can measure how it does.
juanfabrega/jev-quiz-pilot · Python
00benchmarkbrowser-automationclillm-evaluationopenrouterplaywrightpython - Reproducible Chinese RAG reranking benchmark for Jev (TypeSafe System One) — private during build, protocol + scripts + full logs. EN/中文.
vicfei/jev-rag-zh-benchmark · Python
00benchmarkchineseragreproducible-researchrerankingt2ranking - 2358jev-ragcheckRAG evaluation with typed decisions: sentence-level hallucination verdicts with offsets and citations, passage and answer relevance, in one Jev call per answer. Benchmarked against Ragas, DeepEval, an LLM judge and HHEM.
gabazureus/jev-ragcheck · Python
00benchmarkfaithfulnesshallucination-detectionllm-as-a-judgellm-evaluationportuguesepython - 2363jev-replay-labLocal Jev evaluation workbench: datasets, typed questions, threshold simulation and run comparison
Tomdachs/jev-replay-lab · TypeScript
00typescript - 2368jev-researchJev-driven research engine for coding agents: query understanding, RRF reranking, shadow next-best-source, benchmarks
Yaro60/jev-research · JavaScript
00javascript - 2375jev-roastScore declared writing dimensions and cite only exact source spans for weak results.
gbesse/jev-roast · JavaScript
00content-qualityexplainable-ainodejstext-evaluationwriting-analysisjavascript - Probabilistic soft-constraint evaluation for volunteer scheduling using TypeSafe Jev, with deterministic application policy.
WINEEL/jev-scheduling-evaluator · Python
00decision-modelfastapillmnextjspythonscheduling - 2387jev-screenTitle and abstract screening for systematic reviews with Jev: explicit criteria, include/exclude/maybe with reasons, PRISMA counts, RIS export, recall against human screeners.
gbesse/jev-screen · Python
00evidence-synthesishuman-in-the-loopliterature-screeningprismapythonsystematic-review - Terminal-based Jev intent triage with typed decisions, explicit simulation mode, review policy and JSON exports.
suprkco/jev-serp-opportunity-lab · Python
00evaluationpythonseostructured-output - A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output.
blas0/jev-shadcn-lint-eval · JavaScript
00javascript - 2400jev-shadowTest whether TypeSafe Jev answers your questions correctly before you let it decide anything.
jonkthomas/jev-shadow · JavaScript
00javascript - 2402jev-shortlistA cached Jev prior for active learning: reusable rank fusion, matched ASReview controls, and a no-key evidence replay.
joaovaleri/jev-shortlist · Python
00active-learningasreviewpythonreciprocal-rank-fusionreproducible-researchsystematic-review - 2415jev-snakeHead-to-head Snake benchmark racing Jev against frontier LLMs from OpenRouter — same board seed, same 40-second clock, entirely in the browser.
TranBaVinhSon/jev-snake · JavaScript
00javascript - 2417jev-snap-labTiny inputs. Instant decisions. A small experimental playground for exploring fast, probabilistic decisions with Jev.
takafumikobayashi/jev-snap-lab · TypeScript
00typescript - 2428jev-studyHands-on measurements of TypeSafe's Jev via OpenRouter: integration, Chinese-language behaviour, and game loops. Every figure in the reports is reproducible by the scripts here. Reports in Chinese. ~1,430 API calls, ~$0.15.
xiaohuaxi/jev-study · Python
00python - 2443jev-testPlayground for TypeSafe's Jev System One model (Next.js)
Dillettant/jev-test · TypeScript
00typescript - 2445jev-testPruebita usando Jev: AI slop detector en Twitter
frontend-army/jev-test · JavaScript
00javascript - 2446jev-testEmpirical benchmarks, task telemetry, and engineering thesis for Jev (TypeSafe AI) System One in autonomous agentic organizations
shaifulshabuj/jev-test · Python
00python - 2447jev-testReproducible zero-shot Jev benchmark on all seven LexGLUE tasks
chepyle/jev-test · Python
00python - Reproducible Tetris decision benchmark comparing TypeSafe Jev with Claude Haiku
planstack-ai/jev-tetris-benchmark · TypeScript
00ai-evaluationnextjstetrisvercel-ai-gatewaytypescript - 2455jev-thuc-chienDemo tự chạy lại cho series Jev thực chiến (TypeSafe Jev)
thieung/jev-thuc-chien · JavaScript
00javascript - 2460jev-tool-callingApplying Jev to zero-shot tool calling on the Berkeley Function Calling Leaderboard (BFCL)
will-rice/jev-tool-calling · Python
01benchmarkbfclevaluationfunction-callingllm-agentstoken-classificationtool-calling - Application of TypeSafe Jev (noul judgment primitive) on the collusion.wiki corpus: agent vs human page authorship, head-to-head vs local Qwen3.8-Flash-Next
sypherin/jev-trace-classifier · Python
00python - 2470jev-traffic-raceLive demo showing why loop-speed classification matters: Jev vs LLMs on the same events, same clock, honest scorecard.
yshraj/jev-traffic-race · TypeScript
00typescript - Experimental PoC for Jev translation checking: bilingual benchmarks, prompt comparisons, re-verification, and MAGI voting.
mshk/jev-translation-checker · JavaScript
00javascript - Sample code for the Qualiteg Blog article: Jev (TypeSafe AI) hands-on, 244 API calls measured from Python
qualiteg/jev-typesafe-demo · Python
00python - jev-typesafe-spike: TypeSafe Jev ecosystem repository.
frquintero/jev-typesafe-spike · Python
00python - Testing TypesafeAI's "Jev" model using System One API
joaomloureiro-daredata/jev-typesafeai-test · Python
00python - 2477jev-uiUsing jev for intelligent UI list filtering
chrisyerga/jev-ui · TypeScript
00typescript - 2494jev-vs-cosineDo you need TypeSafe's Jev, or is cosine similarity enough? A $0, reproducible benchmark on Banking77 intent routing.
Madheshvivekanandan/jev-vs-cosine · Python
00python - jev-vs-llm-benchmark: TypeSafe Jev ecosystem repository.
sriram-um/jev-vs-llm-benchmark · Python
01python - Side-by-side showcase: traditional LLM vs TypeSafe Jev (System One) on stock order policy decisions
sheshisheri-hi/jev-vs-llm-stock-policy · Python
00python - Benchmark: TypeSafe Jev vs traditional LLM on support-ticket routing accuracy, latency, and cost
SarathChandraBellam/jev-vs-llm-ticket-router · Python
00python - 2499jev-vs-lunaReproducible Jev vs Luna review-classification benchmark with measured accuracy, latency, and costs.
mameli/jev-vs-luna · Python
00 - Does a System One model actually beat keyword matching? A reproducible benchmark on catching disguised duplicate thesis titles. 24 cases, real production baseline, raw data and charts included.
devnolife/jev-vs-tfidf-benchmark · TypeScript
00benchmarkindonesiainformation-retrievalllmplagiarism-detectionstructured-outputtf-idf - 2509jev-world-modelA frozen decision model (JEV) as an LLM agent's world model, compared with zero-shot and LoRA-fine-tuned generative LLMs in TextWorld. Code, logs, analysis and manuscript for KIIS 2026 Fall (oral). LLM 에이전트의 월드모델: 결정모델과 범용 LLM의 비교
thddydgnl/jev-world-model · Python
00decision-modelllm-agentsloraqwen3reproducible-researchresearch-papertextworld - 2523jevaljeval: open-source evaluations for AI outputs and agents, judged by Jev
vrash/jeval · TypeScript
00typescript - 2524JevalsJevals (jevals.com): independent benchmark of TypeSafe's Jev vs LLMs
Jevals/Jevals
00
301–350 of 389