CORPUS
A governed AI research database for teams that need discovery, provenance, rights controls, and editorial dossiers in one subscription workspace.
Five-point mandate
The public surface stays simple: paid users sign in, non-members request access, and the product remains aligned to the legal and architectural guardrails in the CORPUS corpus.
Metadata-first ingestion with persistent identifiers and source provenance.
Rights-aware connector policies before full-text storage or downstream use.
Hybrid lexical and semantic search over documents, versions, and dossiers.
Editorial dossier workspaces for watchlists, citations, exports, and briefs.
Organization-scoped access for paid research teams and compliance-sensitive work.
Paywalled by default
Search, watchlists, dossier creation, and exports are reserved for authenticated subscriber organizations. Public dossier URLs can still be enabled intentionally when a team decides to publish.
OpenAlex, Crossref, DataCite, ORCID, ROR
arXiv, HAL, PubMed Central, Zenodo
EUR-Lex, CNIL, AI Office, OECD.AI
Elsevier, Springer Nature, IEEE, ProQuest