Enrichment PlatformCreate a new session, or resume one in progress. Each session saves as you go.
Enter the admin access code to manage people and permissions for your institution.
The control plane: master-graph curation, the ontology, and the enrichment method. Staff only.
Kohēsis reads the full text and builds your enrichment interview. Nothing in the paper is changed.
Kohēsis read your paper. These are the places a current AI model would flatten your meaning. You'll set each one right, in your own words, before the enrichment begins.
Before the deeper enrichment, correct how today's AI reads the culturally loaded language in your paper. These are the terms a model would flatten. Put each one right in your own words — your corrections become the authoritative context that shapes every enrichment question that follows.
These seven layers are the parts of cultural context an AI model routinely misreads. Left to fill them in on its own, it guesses, and its guesses become hallucinations: confident, fluent claims about your community that no one in it would recognize. You are the authority that prevents that. Answer each layer in your own words, and the model works from your knowledge instead of its assumptions. A short note under each one explains what it is reaching for.
Your paper, with every contribution set in the margin beside the passage it deepens. The manuscript stays yours. Review it, then sign to lock.
I confirm these enrichments reflect my expertise and that I retain authorship of this contribution. I authorize Kohēsis to structure this enriched record for inclusion in the cultural knowledge graph.