The Marshall archive: making a hidden corpus navigable

The situation

Andrew Marshall ran the Office of Net Assessment for 42 years. The intellectual tradition around him (game theory, competitive strategies, the Revolution in Military Affairs debate, decades of thinking about long competitions) lives in scattered documents, oral histories, and the heads of people who worked with him. A graduate student writing about strategic assessment today has no way to ask the archive a question. A researcher building on Marshall-style net assessment has to know where to look before they can look.

The Andrew W. Marshall Foundation wanted to fix that.

What we built

A research console. The tool loads the archive as a knowledge graph. Documents, people, organizations, concepts, events, belief systems, and misconceptions live as connected nodes with named relationships between them. The graph is built from the archive itself. Documents are read, entities and relationships are extracted, communities are detected, and dates are tied to specific source material so a researcher can move through the tradition by era as well as by idea.

A researcher opens the console and asks a question in a chat panel. The answer arrives with numbered citations. A right-hand panel shows the evidence behind each citation as the reader scrolls. Click a badge in the response and the source passage opens in front of you. A timeline filters the graph and the conversation by era, so a researcher can ask the archive how a concept changed over four decades. The four eras are Early (1949 to 1973), ONA Founding (1973 to 1989), the RMA period (1990 to 2001), and GWOT (2001 to 2015).

A researcher can save an investigative thread (graph state, conversation, applied filters) and return to it.

Verified vs inferred

Every node and every edge in the graph carries a label. A verified label means the content came from an archive source. An inferred label means the model proposed the connection during reasoning. Verified nodes render as filled circles. Inferred nodes render as dashed outlines. The user always sees which is which.

The same discipline runs through the chat. Every assistant response uses numbered citations. Click one and a popover opens with the source document and the passage. Inferred claims carry a separate visual tag so a careful reader can distinguish what the archive says from what the model extrapolated. The console also runs Marshall-style net assessment diagnostics. Blind-spot detection, asymmetry surfacing, and second-order effect tracing all appear as auditable artifacts in their own right.

None of this requires the user to trust the model. If the answer says Marshall developed his RMA thesis in working papers with Wohlstetter during the late 1970s, the user can click and read the working paper.

What it replaced

A box of PDFs and an institutional memory that lived in a few people's heads and was eroding.

What a similar engagement looks like

Eight to fourteen weeks. We need the corpus (documents, oral histories, structured metadata), subject-matter-expert time to validate the entity schema and name the relationships that matter, and a hosting target. You get the deployed research console, the ingestion pipeline, the knowledge graph, and documentation for adding new material over time.

A specialist archive without a console is a private library. The few people who know it well can use it directly. Everyone else is asking the librarian, and the librarian is busy. A research console opens the archive to questions from researchers the original archivist never met, and makes the tradition portable in a way it never was when it lived in a few people's heads.

It's a fit for foundations, research institutes, agencies, and university programs that hold a specialist corpus and want researchers to interrogate it as a body of thought. It's not a fit if the corpus is already well-indexed by mainstream search. That problem is solved elsewhere.