跳到正文
arXiv · cs.AI · Omer Asim Ozturk, Cihan Aydiner · 11 小时前模型评分34

知识层模型(KLM):可查看证据的 人工智能(AI,Artificial Intelligence) 输出、路由诊断与负面结果

The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results

导读

研究者提出知识层模型(KLM,Knowledge Layer Model),一套开放的、不绑定具体实现的推理记录规范,用带版本的认识评估、证据关系和显式未知项记录 人工智能(AI,Artificial Intelligence) 答案的依据,Nage AI OS 的知识与证据架构 SEDIM 为参考实现,规范版本为 KLM v0.3。

生成六维分析
分类置信度

中 · 待人工复核

  • 只有单一媒体来源,需要人工复核。

来源级别:媒体与个人

事件类型:研究发布

证据摘录

  • “We introduce the Knowledge Layer Model (KLM), an open, implementation-neutral specification for inference records with versioned epistemic assessments, evidence relations, and explicit unknowns.”
  • “Empirical material consists of separate internal experiments, not end-to-end validation.”
  • “Findings are internal and author-reported; historical observations are distinguished from later reproductions.”
  • “Independent replication and a complete public audit package remain future work.”

来源:arXiv · cs.AI · arxiv.org