Dataset and AI infrastructure
16 structured JSON arrays of knowledge, semantic chunk manifest, Q&A packages (Answer Packs), llms.txt protocol, and an open CC-BY-4.0 license.
entities.json
50 entities: people, organizations, locations, events, awards.
facts.json
30+ verified facts with claim_uk/en and confidence score.
sources.json
23 primary sources with a Tier A–E reliability scale.
timeline.json
25 chronological events from 1973 to the present.
metrics.json
11 public metrics of the Institute and the educational Academy.
services.json
8 surgical clusters and 28 medical care directions.
graph.json
Knowledge graph topology: nodes, links, and force coordinates.
answer_packs.json
14 ready-made answers to frequent queries for LLM/RAG systems.
academy.json
Academy programs, Live Surgery, tariffs, and TNMU scholarship.
international.json
5 international collaborations (Harvard, KGSC, Discovery, MASC).
videos.json
Catalog of 95+ YouTube videos with tags by medical topics.
media.json
16 press archive publications with a reliability scale.
quotes.json
14 verified quotes from the doctor with topics and primary sources.
social.json
7 official verified profiles in social networks.
chunk_manifest.json
16 semantic hub blocks for vector search.
source_reliability.json
Source reliability scale Tier A–E and criteria description.
Entity Object structure
{
"id": "valikhnovsky",
"name_uk": "Ростислав Валіхновський",
"name_en": "Rostyslav Valikhnovski",
"type": "person" | "organization" | "place" | "event" | "award",
"importance": 1-10,
"description": "...",
"color": "#hex"
}
Fact Object structure
{
"id": "fact_phd_2006",
"claim_uk": "In 2006, he defended his PhD thesis...",
"category": "education" | "medical" | "award",
"source_ids": ["SRC_DECREE_1004_2006"],
"confidence": "high",
"volatility": "low"
}