HyperKnowledge

"a Web of Knowledge... see how any idea is connected with other ideas in debates, through evidence, citations, influence, consequences...an interoperable mesh of knowledge where everyone can contribute... [that allow] knowledge applications that consume and expose knowledge on this mesh."

At the heart, a protocol to "support interoperability of knowledge at personal and organisational levels and federation of knowledge sources so that knowledge can be synthesised to augment our ability to learn, understand, to be understood, solve problems and achieve goals."

The page has a pretty nice video explaining the high-level vision, but the whole subject badly needs primers for those not already immersed in the field, with graphical explanations supported by examples.

From https://hyperknowledge.org/pages/approach.html : "The aim of HyperKnowledge is to define a data represention for the individual and collective understanding of complex issues... should enable:

• an ecosystem of collective intelligence tools
• visualization of and interaction with nuances of meaning
• [social use] on a massive scale"

This will require presenting "conversations as event streams of statements... maintained by individual or collectives ... decentralized and federated". Statements can simply be natural language, but can be evolved into "frame-based formalizations... [by] identifying concept references".

There's a "high-level similarity with IdeaLoom... to connect conversation through the identification of ideas and idea patterns in those conversations... but a global conversation is too complex to fit into a single data structure visualization ... [so] we need a way to compare and unify curated partial views... [see also] SenseCraft (with TopicQuests), a conversation game which in which people can learn skills for thoughtful civil conversations.. learn to listen for the patterns in other player's contributions, so they can read and contribute to conversation maps, and eventually HyperKnowledge maps of diverse viewpoints."

Also related:

• helping "people extract concepts and concept structures from natural language ... [using] (OpenSherlock, also with TopicQuests), and ClaimMiner using prompt engineering (with SocietyLibrary.)
• discussing the structure of argument maps with colleagues at the Canonical Debate Lab.