This project, which was published in NeurIPS workshop 2025, presents a machine learning framework for turning evidence from thousands of biomedical papers into a structured probabilistic model of scientific knowledge. We use an agentic LLM framework to extract relationships between biomedical entities, projects them into statistically meaningful covariance matrices, and clusters them using a custom hierarchical GMM (Gaussian Mixture Model) based on KL-divergence. Results on real biomedical literature and cancer benchmarks show that the model finds stable and biologically coherent clusters, enabling better organization of scientific knowledge at web scale and future prediction of unseen relationships.