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。
- 2664mars-gateA semantic-decision benchmark comparing Jev with general-purpose LLMs in a fictional Mars entry checkpoint.
komzweb/mars-gate · TypeScript
00benchmarkllmreacttypescript - 2676MiraveMirave: TypeSafe Jev ecosystem repository.
edoigtrd/Mirave · Python
00python - 2677miu-jevA formally constrained playground where a decision model chooses each legal move
dagfinndybvig/miu-jev · Python
00python - 2716open-system-oneAn independent, reproducible benchmark of TypeSafe's Jev against open, CPU-only alternatives — 10,000 decisions, all raw results published.
zhlei07/open-system-one · Python
00benchmarkcpu-inferencecross-encoderembeddingstext-classificationzero-shot-classification - 2727paper-siftClaude Code plugin: build a reading list for a research area from the Semantic Scholar citation graph, screened with TypeSafe's Jev
lucasddmc/paper-sift · Python
00python - Experiment to impute missing Polis votes (AGREE / DISAGREE / PASS) with TypeSafe's Jev
patcon/polis-jev-impute-simulation · TypeScript
00collective-intelligencedemocracypolispolisliketypescript - 2789reflex-jevTraining demonstration of Jev in a dispatch services command center scenario.
fullcolorcoder/reflex-jev · TypeScript
00typescript - 2801riverlineCan an LLM act as a poker policy? Exact exploitability measurement against CFR equilibria in Kuhn, Leduc and heads-up no-limit hold'em.
Lironktf/riverline · Python
00python - 2806roverlabA 3D planetary rover sandbox for experimenting with autonomous decisions using TypeSafe AI.
juancamiloqhz/roverlab · TypeScript
00typescript - POC de detecção de fraude em pedidos de compra no SAP S/4HANA: indicadores em CDS/RAP, app Fiori Elements e decisão tipada do TypeSafe Jev via OpenRouter, em modo sombra.
seccoit/sap-s4-antifraude-jev · JavaScript
00javascript - 2819scam-signal-lensscam-signal-lens: TypeSafe Jev ecosystem repository.
dannyliv/scam-signal-lens · TypeScript
00typescript - security-sandbox-jev: TypeSafe Jev ecosystem repository.
altanapps/security-sandbox-jev · Python
00python - 2830sem-topsem-top: TypeSafe Jev ecosystem repository.
OkThought/sem-top · TypeScript
00typescript - Label every sentence of a document with calibrated probabilities from Jev, rendered as a heatmap
abhishekmishragithub/semantic-microscope · Python
00llmpythonvisualization - Compile deterministic Vale candidates and narrow decision model judgments (Jev/Laya) into localized documentation style audits.
OpenScribbler/semantic-style-lab · HTML
00html - Evaluating TypeSafe's Jev as a fast monitor and action gate for agent sabotage in SHADE-Arena, compared with Gemini 2.5 Flash/Pro.
nican2018/shade-arena-jev-monitor · Python
01python - How many decisions can a model make in a minute, and what do they cost? Jev, a System One decision model, raced against six LLMs on the same Snake boards.
angelgalvisc/snake-arena-jev-vs-llms · Python
00anthropicbenchmarkcalibrationdecision-makinglatencyllmmoonshot - 2864snap-judgeAsk typed questions in TypeSafe Jev format (noul, choice, score) and run them on Jev or any LLM - probabilities, agreement and type violations side by side.
Arnav1771/snap-judge · JavaScript
00javascript - 2888system-one-benchBenchmark harness for System One decision models. Measures calibration, not just accuracy.
piyushpawar54/system-one-bench · Python
00python - 2889system-one-benchHands-on experiments with open-source System One (Jev-style) decision models on an Apple M5: a zero-shot tweet-sentiment benchmark against local LLMs, and a study of how they play Snake.
hgavert/system-one-bench · Python
01python - Jev vs Laya on Bulgarian: two System One models suggest a category for each blog post. A local BgGPT names new topics.
SciScend/system-one-categorizer-demo · Python
00ai-agentsbenchmarkbggptbulgarianlayallmmodel-comparison - Compare System One decision models (Laya & Jev) on the same evidence: one contract, per-engine confidence gates, every decision stored with the engine that made it.
elixirautomation/system-one-decision-lab · TypeScript
00decision-modelflaky-testskevlayallm-evaluationplaywrightpostgresql - TypeSafe's System One launch claims, each as a runnable experiment: Jev vs Claude vs keyword rules through one typed interface. Calibration, parallel questions, Wikiracing. Offline in CI; --live for the real thing.
gsaini/system-one-models-getting-started · Python
00ai-agentscalibrationclaudellm-evaluationpythonstructured-outputs - Run the new wave of decision models (Laya, Decider, Kev, Jev) side by side on your Mac. Structured input in, calibrated probabilities out, with honest accuracy, calibration, latency and memory numbers.
jeffclimbsbikes/system-one-playground · TypeScript
01apple-siliconbenchmarkcalibrationclassificationdecision-modelevaluationlaya - 2896System1DoomSystem One models (TypeSafe Jev, Laya) play DOOM via ViZDoom: typed decisions + deterministic controller
PanikParty/System1Doom · Python
00python - 2902systemone-probeConformance and behaviour test harness for Jev / System One decision models (POST /v1/systemone)
mokko/systemone-probe · Python
00python - 2915terrariumA sandbox where a TypeSafe System One model presses the controls of a small creature. Code runs the world.
TheGali/terrarium · JavaScript
00javascript - Charts: TypeSafe Jev evaluated on Thai standardized exams vs 110 other models
vehas/thaiexam-jev-charts · HTML
00html - 2930tiny-jevTypeSafe / Jev community project: karimatayuta/tiny-jev.
karimatayuta/tiny-jev · HTML
00 - 2931tiny-llm2tiny-llm2: TypeSafe Jev ecosystem repository.
Kwetng/tiny-llm2 · HTML
00python - Large typed decision model evaluation benchmark and novel calibration standard (`calibration.json`) for any typed decision inference system, covering 275 distinct use-cases and 27,598 individual decisions for Jev-like open typed decision models.
kyr0/typed-decision-bench · Python
00benchmarkbenchmark-frameworkcalibrationjev-alternativejev-api - Bench of typed decision models: Jev vs OpenJev vs Laya, small local LLMs and cheap hosted LLMs on the same zero-shot classification tasks, in English and French.
4nt0ineB/typed-decision-bench · Python
00benchmarkcalibrationenglishfrenchlayallm-evaluationmassive-dataset - An evaluation of typesafe AI chess. As it turns out, the AI isn't doing really well even though chess is not a particularly open-ended game. Still, it's only a prototype and this probably wasn't optimzied for games.
AliceRoselia/Typesafe_chess_eval · Python
00python - 2963typesafe-aiTypeSafe AI: structured AI judgments as programming primitives
bulldozer2003/typesafe-ai · JavaScript
00javascript - Live Python demos and model comparisons for TypeSafe Jev.
niralikhoda/typesafe-jev-demos · Python
00python - A live, graphical dojo for TypeSafe's Jev (System One) typed decision model — routing, a Tetris-playing agent, parallel swarms, and an honest Jev-vs-Claude gauntlet.
lafollett-labs/typesafe-jev-dojo · TypeScript
01ai-agentscanvasdecision-modelopenroutertetris - UiPath Maestro Flow x TypeSafe Jev - a card dispute triage bench comparing a calibrated typed-decision model against an inline AI agent on identical work, with latency and cost measured at runtime.
1aifanatic/uipath-maestroflow-jev
00 - Score TypeSafe's Jev on water-supply triage reports: a zero-dependency Python benchmark that answers urgency, scope, cause, priority and escalation questions and checks them against your team's expected policy.
hariprasad2512/water-supply-prioritizer · Python
00benchmarkllm-evaluationpythonwater-supply - 3035WHAT-s-Up-jevWHAT-s-Up-jev: TypeSafe Jev ecosystem repository.
Pragyan330/WHAT-s-Up-jev · Python
00python
389 件中 351–389 件