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。
- jev-music-theory-1: TypeSafe Jev ecosystem repository.
adammichaelwood/jev-music-theory-1 · TypeScript
20typescript - Can a System One model steer music? Jev picks the plan (enums only); code renders sheet, audio and MIDI.
wustep/jev-playground · TypeScript
21typescript - Interactive playground for testing Jev model-routing decisions against OpenRouter models
hugo-alves/jev-router-playground · JavaScript
20javascriptmodel-routingopenrouter - Measures how well TypeSafe's RLCD-Jev model spots real secret credentials in file snippets
teyhouse/jev-secret-detection · Python
21python - Jev (TypeSafe System One) × ASReview SYNERGY abstract screening demo — Choice/Noul vs gold labels
PistachioAIHQ/jev-synergy-screening · Python
21python - Jev vs GPT-4.1 as synthetic survey respondents on Twin-2K-500. How you ask mattered more than which model you used.
jjd-lab/jev-synthetic-survey · Python
20behavioral-economicsbenchmarkcalibrationdigital-twindigital-twinsllmllm-evaluation - 1001jev-tradejev-trade: TypeSafe Jev ecosystem repository.
Waxmell114514/jev-trade · Python
20python - 1012jevcheckBehavioral contracts for TypeSafe Jev — pin production expectations, eval model upgrades, catch flips and confidence regressions.
sathariels/jevcheck · Python
21python - 1030let-jev-speakExperiment to trick Typesafe’s Jev, aka “the language model that won’t talk” into actually talking.
suidouble/let-jev-speak · JavaScript
20botchatbotllmjavascript - 1057RISC-jeVI tortured Jev into being a RISC-V CPU.
i2cjak/RISC-jeV · Python
20python - 1069Sys1Cal-v1A Benchmark for Calibration and Semantic Evaluation of System One Models
little-g-ai/Sys1Cal-v1 · Python
20python - 1070system-1-aiSmall reproducible experiments: System 1 decision models (basal, Jev-style) vs thinking LLMs on business decisions
agentGreg/system-1-ai · Python
20python - 1081typesafe-chessFUn little experiment with Typesafe AI Jev Model playing chess against stockfish :)
Dimesio/typesafe-chess · JavaScript
20javascript - Rebuilding the $1 Chevy Tahoe jailbreak, then stopping it: TypeSafe System One as a guardrail in an OpenAI Agents SDK agent, traced with Arize AX
jimbobbennett/typesafe-guardrails · Python
20python - 1096what-is-jevIndependent, source-linked research on TypeSafe AI's Jev (System One), with 947 rubric-scored public repositories, recurring patterns, datasets, and bilingual documentation.
g0runmezadam/what-is-jev · Python
20ai-agentsbenchmarkbilingualclassificationdatasetdecision-modelllm - 1108ask-jevUtilizing Jev, the RLCD-type model provided by TypeSafe AI, to independently and cheaply judge agentic coding sessions.
omni-/ask-jev · PowerShell
10powershell - 1109askjevA tree housing every closed question humans or machines ask, answered by Jev (TypeSafe System One): capabilities, defaults, and jaggedness. Not a benchmark.
brian-w-zhang/askjev · Python
10python - 1120BizzJevExperiments with TypeSafe/Jev semantic gates and a Semantic Operations Lab demo.
havietkok-sys/BizzJev · C#
10c# - 1142decisionopsJev thinks. Your code acts. The open-source lab for Choice, Score & Noul decisions.
mionax/decisionops · CSS
10ai-evaluationcalibrationdecision-intelligencellmlocal-first - 1149DoomSatF´ flight software → CCSDS/Yamcs → Open MCT, with jev (System One) and Claude Sonnet 5 (System Two) driving Doom over that real mission stack.
doom-satellite/DoomSat · Python
11ccsdsclaudefprimeopenmctyamcspython - 1154dsh-jev-verifyJev (TypeSafe System One) decision tools + live verification benchmark for DeepSeek Harness: jev_decision (choice/score/noul) and jev_verify, honest by design.
xienda/dsh-jev-verify · JavaScript
10javascript - 1162exquisite_evalsexquisite_evals: TypeSafe Jev ecosystem repository.
jamesward/exquisite_evals · Kotlin
10kotlin - 1180ghost-userghost-user: TypeSafe Jev ecosystem repository.
shauryajain07/ghost-user · TypeScript
10typescript - 1188gpt-vs-jevCompare GPT generated language with JEV structured Noul decisions on the same input.
TanayPadar/gpt-vs-jev · TypeScript
10typescript - 1199here-we-go-jevLocal playground and test bench for TypeSafe's Jev System One model: typed questions, calibrated-probability answers, and side-by-side comparison with an LLM baseline.
creativoma/here-we-go-jev · TypeScript
10buncalibrationclassificationevaluationllmopenrouter - jev-and-cartesia-experiment: TypeSafe Jev ecosystem repository.
zeuslawyer/jev-and-cartesia-experiment · Python
10python - 1232jev-battleshipBattleship against Jev, a model that answers in probabilities instead of text. Web game plus a CLI arena that plays it against general-purpose LLMs on identical fleets.
sah1l/jev-battleship · JavaScript
10battleshipbenchmarkllmprompt-engineeringverceljavascript - 1233jev-benchBenchmark TypeSafe's Jev (System One model) vs Claude on structured decisions: accuracy, latency, calibration, cost
stern9/jev-bench · Python
10anthropicbenchmarkclaudeevaluationllmpython - 1234jev-benchDoes the cited source actually say it? A 42-claim benchmark: Jev (TypeSafe System One) against GPT-5.4, Claude Sonnet 5 and Gemini 3.1 Pro.
TheWayWithin/jev-bench · Python
10python - 1235jev-bias-benchA benchmark for Jev's biases, built from people who differ in one attribute at a time.
Fox-Islam/jev-bias-bench · PHP
10ai-fairnessalgorithmic-biasaudit-studybenchmarkbias-detectioncounterfactualdiscrimination - 1242jev-certifyFinite-sample guarantees for Jev (TypeSafe's System One). Conformal risk control turns calibrated probabilities into certified routing thresholds; prediction-powered inference audits them. 2,412 decisions on CLINC150 for $0.23 — including the shift and prevalence cases where the guarantee breaks.
nikkoxgonzales/jev-certify · Python
10clinc150conformal-predictiondecision-modelintent-classificationllm-routingopenrouterprediction-powered-inference - Tacet: a marketing decision layer that knows when to stay silent. Next best action and budget steering, built with Jev and jev-state.
suranjaychandra/jev-decision-layer · TypeScript
10typescript - 1270jev-demojev-demo: TypeSafe Jev ecosystem repository.
aoprisan/jev-demo · Rust
10rust - 1278jev-doomWatch Jev play Freedoom in a local dashboard. TypeSafe direct and Vercel AI Gateway, inspectable decisions, and bounded spending.
olivier-motium/jev-doom · Python
11ai-agentsdoomfreedoomvercel-ai-gatewaypython - Survey of the open-source ecosystem around TypeSafe Jev: use-case classification of 16,128 GitHub repositories, verified integrations, replicas, and evaluations (English and Simplified Chinese)
cl-victor1/jev-ecosystem-survey
11 - 1287jev-evalBenchmark TypeSafe Jev against any OpenRouter model on your own data.
4esv/jev-eval · Python
10python - 1289jev-experimentsexperiments with system one model jev
naveenreddy61/jev-experiments · Python
10python - 975 PLC tag Expressions in Under a Quarter of a Second
jakeashcraft/jev-expression-benchmark · TypeScript
10typescript - 1299jev-graph-walkContext-carrying graph retrieval with Jev: branching walks, reproducible ablations, and a visual replay.
timsamart/jev-graph-walk · Python
10graphraginformation-retrievalknowledge-graphpython
389 件中 101–150 件