Conceptual Regression Depth (CReD): A Framework for Psychometric-Integrated Tutoring Systems that Preserve Critical Thinking

Patent Application: 63/878,038

Abstract

Current Intelligent Tutoring Systems (ITS) face a critical paradox: while they can improve immediate performance, they often promote cognitive off-loading that fosters dependency rather than independent learning. This paper introduces Conceptual Regression Depth (CReD), a framework that leverages prerequisite learning paths to guide remediation as an alternative to cognitive off-loading. CReD functions by parsing educator supplied instructional content into discrete concept units, constructing directed acyclic graphs of prerequisite relationships and classifying concepts by Bloom’s taxonomy cognitive levels. Learner errors are mapped onto this structure, and CReD scores are calculated as shortest path distances between observed difficulties and their prerequisite gaps. Patterns of learner interaction are then transformed into sparse matrices suitable for Item Response Theory (IRT) modeling, enabling precise diagnostics, targeted intervention, and validation of dependency pathways. CReD addresses two critical challenges: the dependency risks associated with AI tutoring and the need for individualized support in contexts where 74% of U.S. schools report teacher shortages. Through a human-in-the-loop design, CReD supplements rather than replaces educators, offering evidence-based diagnostics while maintaining teacher oversight. Its dual-metric approach distinguishes between internal prerequisite deficiencies and external knowledge gaps, providing particular value in identifying foundational skill deficits. CReD contributes a systematic method for quantifying remediation, extracting psychometric insights from natural learning conversations, and integrating with curricular structures while preserving educators’ pedagogical oversight.

Keywords: Measurement, Assessment, Artificial Intelligence (AI) Tutor, Intelligent Tutoring System (ITS), Bloom’s Taxonomy,