研究と評価
判断モデルや Jev 関連の手法を扱う研究・評価プロジェクトを探せます。
- ecommerce-classifier: TypeSafe Jev ecosystem repository.
ferreirase/ecommerce-classifier · HTML
00html - 1799english-2-sqlenglish-2-sql: TypeSafe Jev ecosystem repository.
trivektor/english-2-sql · JavaScript
00javascript - estudo-system-one: TypeSafe Jev ecosystem repository.
gutoportelaa/estudo-system-one · Python
00python - Evidence-aware semiconductor alert triage research demo with TypeSafe Jev, policy guards, and reproducible evaluation
hongdroid94/fab-evidence-gate · TypeScript
00typescript - Using Jev to test how well it predicts financial markets(just like most llms as of september 2026, it doesnt do that good)
thodoh1/FinancialPredictionJev · Python
00python - JEV evaluation (FM-JEV-01): replay-only, advisory-only evaluation of Foreman-style supervision with TypeSafe Jev. Measures how much safety comes from the model versus a deterministic evidence gate. No worker authority.
MahdiHedhli/foreman-jev-evaluation · Python
00agent-supervisionai-safetyevaluation-harnessllm-evaluationpython - Experimental design harness: a small decision model (Jev) picks the design in about a second, a traditional LLM (Luna) only writes the words. With and without it.
LamplighterPaul/forma-system1-experiment · TypeScript
00 - 1840fraud-jevfraud-jev: TypeSafe Jev ecosystem repository.
frankied003/fraud-jev · TypeScript
00typescript - 1855ground-zeroDecision library to detect and classify AI hallucinations, powered by Jev AI.
wmcbtech30/ground-zero · Python
00 - 1856gsd-jev-demoJev recognizes glycogen storage disease patterns in synthetic USMLE-style vignettes: one Choice question, full option distributions, 14 preserved runs.
bioarchitectonic/gsd-jev-demo · Python
00clinical-reasoningmedical-educationpython - heavenideas.github.io: TypeSafe Jev ecosystem repository.
heavenideas/heavenideas.github.io · HTML
00html - 1866hellow-jevhellow-jev: TypeSafe Jev ecosystem repository.
TakuM-M/hellow-jev · Python
00python - 1879i-shoot-rockjev-based rock paper scissors, to test jev pre-trained model.
Ewen2015/i-shoot-rock · Python
00python - 1888jaggedA pre-registered test of which parts of TypeSafe's advice for its Jev model change the answer.
zkousama/jagged · HTML
00html - 1896jevIndependent research notes toward an open Jev-like decision model: public facts, API contract, training and eval plan.
WiredMind2/jev · Python
00python - 1915jev_experimentsExperiments with TypeSafe's Jev System One model
xavierforge/jev_experiments · JavaScript
00javascript - 1918jev_practiceJev (TypeSafe System One) と LLM に同じゲームを打たせて、レイテンシ・コスト・判断の質を比べる練習台
ryuchan00/jev_practice · Python
00python - 1924Jev-2048Jev-2048: TypeSafe Jev ecosystem repository.
scavin/Jev-2048 · Python
00python - 1928jev-access-dayA learning scaffold for TypeSafe AI's System One models: eval harness plus a measured, plain-language comparison of the Jev decision model vs an LLM stand-in on 24 real operational decisions. All numbers reproducible from committed run files.
andreaserradev-gbj/jev-access-day · TypeScript
00benchmarkdecision-supportevaluationllmtype-safety - 1929jev-acento¿Jev entiende tu acento? Pre-registered audit of TypeSafe AI's Jev on Spanish — accuracy, calibration and token cost — plus a CLI to run the same comparison on your own labelled data.
marcosmartinez/jev-acento · Python
01benchmarkcalibrationexpected-calibration-errorllm-evaluationnlppre-registrationreproducible-research - 1936jev-agent-demojev-agent-demo: TypeSafe Jev ecosystem repository.
calvingit/jev-agent-demo · TypeScript
00typescript - 1940jev-agent-safetyjev-agent-safety: TypeSafe Jev ecosystem repository.
justinfrevert/jev-agent-safety · Python
00python - 1950jev-alpha-benchDoes Jev predict stock returns from news? It reads the news well; there is no tradeable alpha. Three arms separate reading from recall.
Gaurav-Gosain/jev-alpha-bench · Go
00go - Jev (TypeSafe) vs. Gemini 3.8 Flash vs. GPT-5.6 Luna na anotação estruturada de sentenças do TJSP: qualidade, tempo e custo
lab-dados/jev-anotacao-sentencas · Python
00python - Empirical experiments and API research for TypeSafe's Jev System One model trained using RLCD
BipinRajC/Jev-api-experiments · Python
00apiexperimentalrlcdpython - 1956jev-applicationSInce Jev model is popular, let's try some interesting.
lichin1/jev-application · Python
01python - 1960jev-arcadeCan a System One model play arcade games? TypeSafe's Jev plays Tetris, Snake and 2048 — benchmarked against random and heuristic baselines.
CankatSarac/jev-arcade · Python
00python - 1963jev-as-llmTypeSafe's Jev, a judgment model that was never trained to write, made to chat one word at a time. Browser-only, bring your own OpenRouter key.
damienen/jev-as-llm · TypeScript
00experimentllmnextjsopenroutertypescript - 1967jev-atari-labChallenge Atari with Jev: structured decisions, value questions, and replayable experiments
memorysaver/jev-atari-lab · Python
00 - Reproducible citation-attribution benchmarks for Jev using AttributionBench, ContractNLI, and human-review experiments.
0x471/jev-attribution-bench · TypeScript
00typescript - Evaluate typed AI decisions on labeled French-language cases.
gbesse/jev-banc-francais · JavaScript
00calibrationevaluationfrancejavascript - 1976jev-baseballTesting TypeSafe Jev (a decision-only model) on MLB judgement tasks against simple baselines
yasumorishima/jev-baseball · Python
00baseballevaluationllmmlbpython - 1977jev-benchMeasure accuracy and calibration of Jev (TypeSafe AI's decision model) on public datasets: 12 business-like tasks, 7 experiments, one Python file.
Running-Dolphins/jev-bench · Python
00benchmarkcalibrationllmpython - 1978jev-benchmarkjev-benchmark: TypeSafe Jev ecosystem repository.
haxudev/jev-benchmark · Jupyter Notebook
00jupyter-notebook - 1987jev-box-studyFindings from building an AI-image hallucination detector on TypeSafe Jev 1.14 Box + image input: what worked, what didn't, why
RINNECODER/jev-box-study · JavaScript
01javascript - 2000jev-calibrationIs TypeSafe AI's Jev calibrated? Reliability diagram, ECE and saturation split on 240 hand-labelled agent tool calls.
themsquared/jev-calibration · Python
00agentevalsagentgatewayai-agentsbenchmarkcalibrationllmpython - Independent calibration audit of TypeSafe AI's Jev: when it says 80%, is it right 80% of the time? Tested on EIA weekly petroleum reports against an LLM classifier via LangChain, with exact ground truth from EIA data.
n9omi/jev-calibration-audit · Python
00calibrationcommoditieseiaenergy-marketsforecast-verificationlangchainllm-evaluation - 2011jev-chessJev (TypeSafe AI's System One model) playing chess against itself, graded by Stockfish
DevItaliya22/jev-chess · TypeScript
00typescript - Reproducible experiments on prompting criteria in TypeSafe's Jev — how much of a classifier's behaviour is yours to define
RastislavDujava/jev-classification-prompting · Python
00python
389 件中 201–250 件