---
title: "The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.42066v1"
permalink: "https://feed.astralor.com/items/itm_817a8d958959f2ee99e4e744"
published: "2026-10-30T17:26:18.000Z"
score: 58
channel: "tech"
tags: ["推理效率","安全","The Knowledge Layer","Model","KLM","Evidence-Visible","Output","Routing Diagnostics"]
---

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

## At a glance

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 v…

## Key points

- 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.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_817a8d958959f2ee99e4e744