TTG-Math

TTG-Math is a structured knowledge graph designed for mathematical reasoning. It abstracts mathematical problems into general problem templates and solution templates, and explicitly links reasoning steps to the corresponding mathematical theorems, forming a systematic knowledge network that connects problem types, reasoning chains, and theorems. The graph consists of automatically generated templates, reasoning steps, and theorem links, and is continuously enriched through difficulty-level expansion and template-variant generation. Reliability is ensured through mechanisms such as answer verification, theorem-consistency checking, and quality control of reasoning steps. Built upon this knowledge graph, models can retrieve similar problem types and relevant theorems for new problems, enabling structured knowledge transfer and analogy-based reasoning, thereby enhancing mathematical understanding and reasoning capabilities.