🤖 AI Summary
This work addresses the longstanding challenge in AI and cognitive science of simultaneously achieving robust episodic memory storage and rigorous yet flexible logical reasoning. We propose a category-theoretic Cognitive Log framework, wherein actions serve as primitive semantic units; events—comprising actions, participants, and causal relations—are uniformly modeled using a relational graph database. This enables cross-event comparison, causal inference, and narrative abstraction. Our approach constitutes the first systematic application of category theory to event representation, yielding action-driven abstract reasoning and story generalization. It pioneers the “database-driven AI” paradigm, reconciling human-like cognitive flexibility with machine-level formal rigor. The framework scales to petabyte-scale knowledge bases, supporting high-precision event matching, interpretable causal reasoning, and verifiable cognitive architecture construction.
📝 Abstract
This research presents a computational framework for describing and recognizing episodes and for logical reasoning. This framework, named cognitive-logs, consists of a set of relational and graph databases. Cognitive-logs record knowledge, particularly in episodes that consist of"actions"represented by verbs in natural languages and"participants"who perform the actions. These objects are connected by arrows (morphisms) that link each action to its participant and link cause to effect. Operations based on category theory enable comparisons between episodes and deductive inferences, including abstractions of stories. One of the goals of this study is to develop a database-driven artificial intelligence. This artificial intelligence thinks like a human but possesses the accuracy and rigour of a machine. The vast capacities of databases (up to petabyte scales in current technologies) enable the artificial intelligence to store a greater volume of knowledge than neural-network based artificial intelligences. Cognitive-logs serve as a model of human cognition and designed with references to cognitive linguistics. Cognitive-logs also have the potential to model various human mind activities.