The Computational Assessment Stack: An Architecture for AI-Native Measurement
Abstract
Test development is shifting toward automation and agentic artificial intelligence (AI), in which autonomous systems draft items at scale, assemble test forms, administer adaptive assessments, score complex responses, and monitor test quality. As autonomous systems take on more of this work, the architecture underlying test development must change to preserve assessment quality under the new paradigm. This paper proposes the Computational Assessment Stack (CAS), a four-layer architecture for AI-native measurement where every stage of the assessment lifecycle shares a unifying computational construct representation as its base layer. This representation is a machine-readable, modular, and versioned knowledge graph. Three layers are built above it: computational content generation that builds on the knowledge graph; computational psychometrics that derives substantive structure directly from the knowledge graph; an orchestration layer in which agentic systems operationalize the stack under human governance. The paper's core contribution is architectural. Building on foundational psychometric frameworks, the CAS provides a persistent representation that unifies the four layers. Unlike the descriptive prose traditionally used to define constructs in test development, the proposed architecture renders measurement assumptions inspectable and their consequences empirically testable.
Related
- AI-Integrated Computational Framework for Pronunciation Error Analysis Through Native–Learner Speech Comparison
- Exactness as an Explanatory and Computational Target: A Reduction Architecture for First-Order ODEs, with a Higher-Order Outlook
- From Spectrum Regulation to Computational Enforcement: An Auditable Governance Architecture for Adaptive Spectrum Sharing
- Computational fluid dynamics assessment of upper airway morphology and flow dynamics in infants with Robin sequence treated with the Stanford Orthodontic Airway Plate
- Confidence Filtering in Video-Based Gait Assessment: Measurement Error versus Selection Shift
BibTeX
@misc{davier2026computational,
title = {{The Computational Assessment Stack: An Architecture for AI-Native Measurement}},
author = {Alina A. von Davier},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.33901},
eprint = {2610.33901},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.33901},
}
RIS
TY - UNPB
TI - The Computational Assessment Stack: An Architecture for AI-Native Measurement
AU - Alina A. von Davier
PY - 2026
DA - 2026/10/24
PB - arXiv
DO - 10.48550/arxiv.2610.33901
UR - https://arxiv.org/abs/2610.33901
AB - Test development is shifting toward automation and agentic artificial intelligence (AI), in which autonomous systems draft items at scale, assemble test forms, administer adaptive assessments, score complex responses, and monitor test quality. As autonomous systems take on more of this work, the architecture underlying test development must change to preserve assessment quality under the new paradigm. This paper proposes the Computational Assessment Stack (CAS), a four-layer architecture for AI-native measurement where every stage of the assessment lifecycle shares a unifying computational construct representation as its base layer. This representation is a machine-readable, modular, and versioned knowledge graph. Three layers are built above it: computational content generation that builds on the knowledge graph; computational psychometrics that derives substantive structure directly from the knowledge graph; an orchestration layer in which agentic systems operationalize the stack under human governance. The paper's core contribution is architectural. Building on foundational psychometric frameworks, the CAS provides a persistent representation that unifies the four layers. Unlike the descriptive prose traditionally used to define constructs in test development, the proposed architecture renders measurement assumptions inspectable and their consequences empirically testable.
ER -