Abstract: In a method for extracting, transforming and loading legal information onto autonomous agents, large language models are used to extract decision paths from legal data, a transform method converts the decision paths into a computation graph database known as a factor graph document database, a load method loads factual data onto the factor graph document database using read and write operations, and a decision method infers the decision to be performed by the agent using the mathematical, statistical, and logical capabilities of the factor graph document database.

Abstract: In a method of generating a user interface, a user query is submitted to an encoder LLM which provides variable elements used to infer novel variable elements using a factor graph document database, which are in turn passed to a decoder LLM to generate user interface elements.

Abstract: Disclosed herein are various combinations of pneumococcal polypeptides for use in immunisation. Also disclosed herein are pneumococcal polypeptides that may be useful as single antigens. These polypeptides may optionally be used in combination with pneumococcal saccharides. The antigens may be used in pneumococcal vaccines, but may also be used as components in vaccines for immunising against multiple pathogens.