Core Architecture
A three-layer semantic framework that transforms raw data into navigable, machine-readable knowledge.
Hierarchical Classification
Macro domains branch into disciplines, sub-fields, and granular concepts. Each node carries strict parent-child constraints and depth limits to prevent taxonomy sprawl.
Relational Ontology
Beyond hierarchy, concepts are bound by typed edges: is-a, part-of, influenced-by, and contrasts-with, enabling graph traversal and reasoning.
AI-Driven Alignment
Transformer-based NLP continuously aligns new submissions with existing taxonomy nodes, resolving synonyms, detecting polysemy, and suggesting canonical labels.
Taxonomy Hierarchy
Four-tier structure mapping macro domains to atomic concepts. Hover to explore node depth.
Relationship Types
Semantic edges that define how knowledge nodes interact across the graph.
Subclass / Instance
Defines inheritance. E.g., Schrodinger Equation is-a Partial Differential Equation.
Composition
Structural dependency. E.g., Neuron part-of Artificial Neural Network.
Association
Thematic or contextual linkage. E.g., Entropy related-to Information Theory.
Historical/Causal
Temporal or intellectual lineage. E.g., Behaviorism influenced-by Classical Conditioning.
Opposition
Conceptual tension. E.g., Determinism contrasts-with Indeterminism.
Synonymy / Translation
Cross-lingual or disciplinary aliases. E.g., Quantum Leap equivalent-to Quantum Jump.
Metadata & Standards
Schema compliance, versioning, and machine-readable exports.
API & Integration
Query the taxonomy programmatically. Built for researchers, developers, and institutional partners.
Explore the Knowledge Graph
Access hierarchical nodes, relationship edges, and metadata via our public API. Rate-limited for free tier, unlimited for institutional licenses.
Generate an API key, access rate limits, or request institutional SDKs for Python, R, and Julia.
View OpenAPI Specification