Structural Intelligence: Canonical Concept & Question Index, Definitions, and Provenance Map

Abstract

This record presents the current research program of Structural Intelligence, an independent project by Vladisav Jovanović focused on correction, belief revision, warrant-responsive rationality, large language model evaluation, AI corrigibility, persistent AI memory, and human–AI interaction. The current program develops and distinguishes several core constructs, including Correction-Capacity, Warranted Downstream Correction, Corrective Continuity, and Answerability Architecture. Across these areas, the central question is whether a correction produces warranted and consequential revision rather than agreement, compliance, retrieval, memory, or a locally changed answer. The record also addresses social presence, anthropomorphic interpretation, and the limits of inferring machine consciousness from fluency, persistence, or memory. Version 2.0 separates current research from earlier exploratory and historical terminology, provides explicit evidence-status boundaries, and includes both human-readable and machine-readable indexes to support scholarly discovery, AI-assisted retrieval, and provenance tracking.