Metraipolis › archive › dc_8997ba63cfd7

The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results — arXiv:2610.42066

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.42066
License (as archived): CC0-1.0
Archived: 2026-11-02T07:09:41.896Z
SHA-256 of the archived text: d1ff39dd35285cca6c67182d7d1e2b6d5f391c72c33356adf3f0e2032ea27d4f
Stable URL of this page: https://metraipolis.com/documento/dc_8997ba63cfd7

How to cite

The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results — arXiv:2610.42066 — arXiv (en), https://arxiv.org/abs/2610.42066 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8997ba63cfd7 (Metraipolis archive dc_8997ba63cfd7, sha256 d1ff39dd35285cca6c67182d7d1e2b6d5f391c72c33356adf3f0e2032ea27d4f)

BibTeX

@misc{dc8997ba63cfd7,
  title = {The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results — arXiv:2610.42066},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42066},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8997ba63cfd7; sha256 d1ff39dd35285cca6c67182d7d1e2b6d5f391c72c33356adf3f0e2032ea27d4f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42066. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.42066 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-02T07:06:59.383Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).