The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results· KLM 模型：可见证据的 AI 输出及路由诊断
AI answers require more than apparent correctness: reviewers need to inspect their recorded basis. We introduce the Knowledge Layer Model (KLM), an open, implementation-neutral specification for inference records with versioned epistemic assessments, evidence relations, and explicit unknowns. SEDIM, the knowledge and evidence architecture of Nage AI OS, is a reference implementation. We reference KLM v0.3 (repository tag v0.3.0). Empirical material consists of separate internal experiments, not end-to-end validation. A historical platform-domain routing benchmark reports 137/150 classifications across 15 classes (91.3%; nominal 95% Wilson interval 85.7-94.9%); the numerator is recovered from a rounded summary, and historical example membership is unverified. A native-model weight-path conf
KLM模型提供可见证据的AI输出及路由诊断，提升审查透明度。
- 核心方法
- KLM通过记录推理过程中的知识版本、证据关系和显式未知信息，提供了一个开放且与实现无关的规范。
- 适合谁读
- 研究者
- 要解决的问题
- AI系统需要提高其输出审查的透明度，使得审查者能够检查其决策依据。
- 关键实验
- 论文包括历史平台域路由基准实验，报告了137/150的分类准确率，但未提供端到端验证。
- 主要贡献
- 提供了一个新的模型规范，使得AI的决策过程更加透明且可追溯。
- 意义与局限
- KLM模型增加了AI系统的可解释性和透明度，但其全面有效性仍需进一步验证。