The Noosphere corpus
Noosphere does not search the internet: it answers from a document base of its own. This page states exactly what that base contains, where each part came from and how it was built, so anyone can judge the worth of an answer before trusting it.
Public records with stable URLs: references from public sources to find and cite, without full text.
The four figures above are read from the graph itself as the page loads. The breakdown below could not be read just now: these are figures from October 2026, rounded down.
Where it comes from
No single source dominates, and that is deliberate. Biomedical literature brings experimental rigour; the project's own archive brings what rarely reaches an indexed journal — risk-reduction reports, conference proceedings, dissertations, specialist press; OpenAlex brings the fields a biomedical search never reaches, such as anthropology or law.
| Origin | Documents | What it contributes |
|---|---|---|
| Crossref | 50,000+ | Everything with a DOI: humanities, law, botany |
| OpenAlex | 25,000+ | Social sciences, botany, law |
| PubMed / Europe PMC | 5,000+ | Peer-reviewed biomedical literature |
| Own library | 1,800+ | Reference books and monographs |
| Document archive | 1,100+ | Reports, proceedings, theses and grey literature |
| Cannabis Magazine | 650+ | Own back catalogue, 1997 onwards |
| Open and reference web | 200+ | Public bodies and organisations |
Scope
How it is built
Automated harvesters query PubMed, Europe PMC and OpenAlex every week across forty-four thematic axes, from receptor pharmacology to botanical taxonomy and drug policy. What they find is filtered for relevance, dropped if already held, and anything new is split into passages, indexed by meaning and by word, and analysed to extract the concepts it mentions and the relations between them. That graph is what lets a question about a receptor also surface what has been written about the plant that activates it.
Retrieval combines semantic and literal matching, merges candidates and uses local reranking to select relevant passages. This helps find sources but does not check that every generated claim is supported by them. Verify the passage and the original publication.
What you can and cannot read here
The public catalogue provides bibliographic references and links, without full texts or abstracts. Answers show retrieved passages so citations can be checked. Coverage and open-access flags are document metadata: they do not certify a licence or reuse rights for each work.
How to cite it
Cite the original publications you consulted to support each claim, with their authors, title, year and DOI or URL. When describing the tool, identify Noosphere, Psiconáutica, its link and your access date. A question link does not preserve the answer, its sources or a corpus version. A stable bibliographic-record URL does not guarantee immutable metadata either. See the recommended record for documenting a search.
Psiconáutica (2026). Corpus documental multidisciplinar sobre sustancias psicoactivas (Noosphere). https://brain.psiconautica.org/corpus.html
Contributing documents
The corpus grows mainly by contribution. If you hold relevant literature — theses, agency reports, conference proceedings, risk-reduction material, back catalogue — write to noosphere@psiconautica.org and we will review it before taking it in. We are especially interested in what is indexed nowhere and gets lost: the grey, the local, and what was not published in English.
Ask it something you already know
It is the only honest way to measure a corpus: ask a question whose answer you already know, and check where it says it got it.
Noosphere is a document research tool by Psiconáutica. References let you check an answer; they do not guarantee correctness or exhaustive coverage.
How to verify and cite · Corpus fact sheet · Method and limitations