KLM 规范发布：让 AI 输出附带可审查的证据记录
The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results
arXiv 上的 KLM 规范，让 AI 回答能带着证据记录供人审查，还把失败实验也写出来了，这种坦诚不多见。
KLM（Knowledge Layer Model）是一个开放的、实现中立的知识层规范（v0.3），用于记录带版本标注的证据关系和显式未知项，参考实现为 Nage AI OS 的 SEDIM 架构。历史路由基准在 15 类共 150 条上报告 137 条正确（91.3%，Wilson 区间 85.7%-94.9%）。论文同时公开了负面结果：词法和范围诊断在静默与矛盾样本上的 AUC 仅 0.008，低于预注册的 0.65 下限；旧版打包在 221 个案例中 118 个丢失了含金标文本，修复后为 221/221。作者明确说明这些为内部结果，独立复现和完整公开审计包仍是待完成工作。
The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results
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 configuration yielded 0/15 successful answers in a corrected two-source test. A capacity-growth comparison could not establish a reliable effect because of a defective legacy scorer and missing original outputs. Lexical and scoped diagnostics each yielded AUC 0.008 for silent-versus-contradicted examples, below the registered minimum of 0.65. Legacy packing lost gold-containing text in 118/221 selected cases; repaired packing retained it in 221/221. These measure text presence, not answer quality. Python and TypeScript verifiers reportedly agreed on six checks per synthetic fixture; a separate production disclosure was not accepted. Restoration, re-derivation, human-rubric support, boundary isolation, and bounded-response evaluations remain proposed. Findings are internal and author-reported; historical observations are distinguished from later reproductions. Evidence visibility does not establish correctness, causal reliance, security, or regulatory compliance. Independent replication and a complete public audit package remain future work.