Tumbug: A pictorial, universal knowledge representation method

TL;DR

Tumbug introduces a pictorial, temporal knowledge representation method designed as a universal semantic base across languages and domains. Built on the SCOVA five-building-block foundation ($O$, $A$, $V$, $C$, $S$), it emphasizes image-like diagrams and motion with time arrows to capture objects, attributes, values, changes, and system states. The work argues that knowledge representations in AI should prioritize explicit structures over purely statistical learning, grounding the approach in physics and mathematics while offering a rich set of building blocks (e.g., State Diagrams, Correlation Boxes, XOR Boxes) and rules for composition. If developed into software, Tumbug could provide a scalable, visual CSR-enabled pathway toward AGI by enabling intuitive reasoning, generalization, and cross-domain semantics. The framework aims to unify semantic representation across languages and real-world systems, potentially advancing CSR-driven AI beyond current neural network-centric paradigms.

Abstract

Since the key to artificial general intelligence (AGI) is commonly believed to be commonsense reasoning (CSR) or, roughly equivalently, discovery of a knowledge representation method (KRM) that is particularly suitable for CSR, the author developed a custom KRM for CSR. This novel KRM called Tumbug was designed to be pictorial in nature because there exists increasing evidence that the human brain uses some pictorial type of KRM, and no well-known prior research in AGI has researched this KRM possibility. Tumbug is somewhat similar to Roger Schank's Conceptual Dependency (CD) theory, but Tumbug is pictorial and uses about 30 components based on fundamental concepts from the sciences and human life, in contrast to CD theory, which is textual and uses about 17 components (= 6 Primitive Conceptual Categories + 11 Primitive Acts) based mainly on human-oriented activities. All the Building Blocks of Tumbug were found to generalize to only five Basic Building Blocks that exactly correspond to the three components {O, A, V} of traditional Object-Attribute-Value representation plus two new components {C, S}, which are Change and System. Collectively this set of five components, called "SCOVA," seems to be a universal foundation for all knowledge representation.

Figures (334)

• Figure 1: First alternative for language translation: This strategy uses one universal representation, and would need only two programs for three languages.
• Figure 2: Second alternative for language translation: This strategy uses no universal representation, and would need six programs for three languages.
• Figure 3: The field of AI is divided into ANI and AGI, and in turn the field of AGI contains CSR. There is currently little or no overlap between ANI and AGI except in trivial ways such as hierarchies or the massive training of large language models (LLMs).
• Figure 4: A summary of knowledge-based approaches to CSR. Tumbug is so unique that it has its own category.
• Figure 5: Examples of two KRMs for chess: The shown chess move can be represented as "e4" in algebraic notation, based on the indices on the left, or as "P-K4" in descriptive notation, based on the indices on the right. Which is "best" depends on the type of information elicited.