CIRCUMVENTION RESEARCH · STRUCTURED · LLM-CALLABLE

The field's literature, indexed.

A controlled-vocabulary corpus of censorship-circumvention research. Each paper is tagged against a shared taxonomy of censors, detection techniques, and defenses. An MCP server exposes it to any AI assistant.

papers
382
censors
15
techniques
22
defenses
36

§ I — WHY THIS EXISTS

A layer the field doesn't have yet.

The censorship-circumvention community has wonderful resources: net4people/bbs for discussion, gfw.report for original research, CensorBib as a maintained bibliography, OONI for measurement.

None of them are LLM-callable. None of them have a consistent structured-metadata schema. None of them let an AI assistant compose a corpus query with operational data in the same conversation.

This corpus adds that one missing layer.

The thing that compounds

The schema and the controlled vocabulary outlive whatever model you read it through. Frontier models change every six months. The taxonomy of censors / techniques / defenses doesn't.

§ II — CORE PAPERS

Hand-selected as load-bearing.

If a Lantern protocol designer hadn't read these, the team would expect them to be slowed down. Team consensus marks them as core: true; everyone using the corpus sees them surfaced first.

§ III — RECENT ADDITIONS

Plug it into your assistant.

One install. Your AI gains search_papers, get_paper, list_taxonomy, and find_related over the corpus.

How to install →