jev-serp-opportunity-lab
suprkco/jev-serp-opportunity-lab
Terminal-based Jev intent triage with typed decisions, explicit simulation mode, review policy and JSON exports.
- 星标
- 0
- 派生
- 0
收录依据
搜索意图分类将 Jev 判断与代码路由分离,包含 API 连接器及离线策略模拟器;附带 SERP 示例是人为构造的测试数据。
suprkco/jev-serp-opportunity-lab
Terminal-based Jev intent triage with typed decisions, explicit simulation mode, review policy and JSON exports.
搜索意图分类将 Jev 判断与代码路由分离,包含 API 连接器及离线策略模拟器;附带 SERP 示例是人为构造的测试数据。
Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.
共同主题: evaluation
A 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.
共同主题: evaluation
Three measured experiments on RAG hallucination: quote-checking, TypeSafe's Jev, and IBM's STAIR. 850+ graded questions, raw responses included.
共同主题: evaluation