The whole map

The Corpus

Every exploration is one question. The corpus is what happens when you merge them — a single weighted graph in which a chip-fab chokepoint connects to a social-security cliff connects to a fashion supply chain, because each exploration was built on top of everything already in the graph. That accumulated structure is where the cross-sector conclusions come from.

3,376
concepts
9,152
weighted connections
115
explorations live
27,468
cited sources

How it was built

Each exploration began as a single research question and was developed into a weighted knowledge graph: concepts as nodes, relationships as edges, every claim carrying its sources. Crucially, each new exploration was conditioned on the corpus that already existed — so the graph has cross-references a cold-start query cannot reproduce. The result was then read back as a whole, which is how the five cross-sector patterns were found: they live in the connections between explorations, not inside any one of them.

What's free here

All of it. PlexusGraph is a publication, not a product with a locked door. The point of view and the curation are the work; the data is meant to be used. So the merged graph is downloadable, and every exploration ships with an LLM-ready context pack you can drop straight into your own AI.

Download the corpus (.db)

The full merged SQLite graph — nodes, associations, weights, sources. ~13 MB gzipped; gunzip corpus.db.gz (or double-click on macOS) to open.

Download the context pack (.md)

An LLM-ready brief of the meta-analysis and top hub concepts. Paste or upload into any AI.

↓ .md Or discuss the whole corpus in — the full analysis + graph as markdown, ready to paste into ChatGPT, Claude, Gemini or any AI.

Tip: open corpus.db with any SQLite tool, or hand the context pack to ChatGPT, Claude, or Gemini and ask it to reason over the structure.