Inspectable Learning Governance A Forensic Architecture for Safe AI Systems

Fuente: Zenodo
Enregistré dans:
Détails bibliographiques
Auteur principal: Jaspers, Koen
Format: Recurso digital
Langue:anglais
Publié: Zenodo 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866901541824233472
author Jaspers, Koen
author_facet Jaspers, Koen
contents <p>Contemporary AI systems increasingly incorporate adaptive or learning components, yet most provide limited or no means for independent verification of how, when, or under whose authority learning occurs. This opacity complicates oversight, accountability, and trust—particularly in safety-critical, regulatory, or research contexts.</p> <p>This paper presents an architectural approach to <em>inspectable learning governance</em>: a system in which learning-relevant state changes—whether deliberate, authorized updates or detected unintended adaptations—are constrained, recorded, cryptographically anchored, and optionally human-attested. The architecture emphasizes metadata-only logging, immutable integrity chains, external verification, and explicit human responsibility, without reliance on access to model internals.</p> <p>Rather than making claims about intelligence, alignment, or correctness, the proposed design focuses on enabling post-hoc inspection and evidentiary review of learning activity. Safety and accountability are treated not as assumed properties of the system, but as matters that can be evaluated through verifiable records.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18172389
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Inspectable Learning Governance A Forensic Architecture for Safe AI Systems
Jaspers, Koen
AI safety
Learning governance
Inspectable AI
Auditable systems
AI accountability
Learning traceability
Cryptographic integrity
Forensic system design
<p>Contemporary AI systems increasingly incorporate adaptive or learning components, yet most provide limited or no means for independent verification of how, when, or under whose authority learning occurs. This opacity complicates oversight, accountability, and trust—particularly in safety-critical, regulatory, or research contexts.</p> <p>This paper presents an architectural approach to <em>inspectable learning governance</em>: a system in which learning-relevant state changes—whether deliberate, authorized updates or detected unintended adaptations—are constrained, recorded, cryptographically anchored, and optionally human-attested. The architecture emphasizes metadata-only logging, immutable integrity chains, external verification, and explicit human responsibility, without reliance on access to model internals.</p> <p>Rather than making claims about intelligence, alignment, or correctness, the proposed design focuses on enabling post-hoc inspection and evidentiary review of learning activity. Safety and accountability are treated not as assumed properties of the system, but as matters that can be evaluated through verifiable records.</p>
title Inspectable Learning Governance A Forensic Architecture for Safe AI Systems
topic AI safety
Learning governance
Inspectable AI
Auditable systems
AI accountability
Learning traceability
Cryptographic integrity
Forensic system design
url https://doi.org/10.5281/zenodo.18172389