{
  "name": "GlioState data dictionary",
  "generated": "2026-10-15",
  "site": "https://gliostate.com",
  "license_note": "Content for research and education only; not medical advice.",
  "counts": {
    "items": 139,
    "topics": 8,
    "tags_total": 175,
    "tags_with_pages": 59,
    "graph_nodes": 212,
    "graph_edges": 536
  },
  "endpoints": {
    "/items.json": "all items, normalised (array)",
    "/items.csv": "original CSV",
    "/graph.json": "nodes + typed edges",
    "/graph.jsonld": "JSON-LD export of the same graph",
    "/api/items/<VCxxxx>.json": "one item with backlinks and related items",
    "/api/topics/<topic-id>.json": "one research topic (full record + resolved references)",
    "/data/graph/<file>.json": "raw research topic source records",
    "/schema.json": "this file",
    "/library/<VCxxxx>/": "paper HTML page",
    "/library/tag/<slug>/ · /library/type/<type>/ · /library/year/<year>/": "facet pages",
    "/library/facets/": "facet index"
  },
  "item": {
    "fields": {
      "id": "string — stable GlioState id (VC0001…)",
      "type": "enum — conference | dataset | interview | model | news | org | paper | preprint",
      "title": "string",
      "authors_or_org": "string — authors (papers) or organisation",
      "date": "string — YYYY-MM-DD, YYYY-MM or YYYY; may be empty",
      "year": "string|null — derived from date",
      "venue": "string",
      "url": "string — source URL (may equal the DOI URL)",
      "doi": "string — bare DOI, no URL prefix",
      "pmid": "string",
      "brain_tumor_focus": "enum — yes | partial | no",
      "topic_tags": "string — ORIGINAL semicolon-separated tags (items.json only; kept for backward compatibility)",
      "tags": "string[] — original tags split into an array (trimmed, composite ;-tags split)",
      "tag_slugs": "string[] — normalised tag slugs (case-folded, aliases merged, e.g. scRNA/scRNA-seq → scrna-seq)",
      "tag_labels": "string[] — display labels for tag_slugs",
      "one_line_summary_en": "string",
      "one_line_summary_zh": "string",
      "verified": "enum — yes | partial",
      "verification_source": "string — e.g. Europe PMC, PubMed, Crossref, official page",
      "page_url": "string — canonical HTML page /library/<id>/",
      "api_url": "string",
      "sameAs": "string[] — DOI / PubMed / source URLs",
      "is_preprint": "boolean",
      "facets": "object — type, year and tag facet page URLs",
      "cited_by": "object[] — research topics citing this item (backlinks)",
      "related": "object[] — up to 6 related items by shared tags (IDF-weighted)"
    },
    "enums": {
      "type": [
        "conference",
        "dataset",
        "interview",
        "model",
        "news",
        "org",
        "paper",
        "preprint"
      ],
      "brain_tumor_focus": [
        "yes",
        "partial",
        "no"
      ],
      "verified": [
        "partial",
        "yes"
      ]
    }
  },
  "tags": {
    "normalisation": [
      "split on \";\" (and \"/\")",
      "trim and de-duplicate per item",
      "case-fold to build the slug (non-alphanumerics → \"-\")",
      "alias map: scrna→scRNA-seq, scrna-seq→scRNA-seq, agent→agents, agents→agents, ai-agent→agents, tahoe-100m→Tahoe, aido.cell→AIDO, neurips2025→NeurIPS, idh-mutant→IDH, generative-ai→generative, drug-sensitivity→drug-response, latent-diffusion→diffusion",
      "facet pages only for tags used by ≥2 items"
    ],
    "facet_tags": [
      {
        "slug": "gbm",
        "label": "GBM",
        "count": 21
      },
      {
        "slug": "perturbation",
        "label": "perturbation",
        "count": 21
      },
      {
        "slug": "spatial",
        "label": "spatial",
        "count": 19
      },
      {
        "slug": "foundation-model",
        "label": "foundation-model",
        "count": 17
      },
      {
        "slug": "scrna-seq",
        "label": "scRNA-seq",
        "count": 12
      },
      {
        "slug": "benchmark",
        "label": "benchmark",
        "count": 11
      },
      {
        "slug": "aivc",
        "label": "AIVC",
        "count": 6
      },
      {
        "slug": "dataset",
        "label": "dataset",
        "count": 6
      },
      {
        "slug": "arc",
        "label": "Arc",
        "count": 5
      },
      {
        "slug": "challenge",
        "label": "challenge",
        "count": 5
      },
      {
        "slug": "critique",
        "label": "critique",
        "count": 5
      },
      {
        "slug": "organoid",
        "label": "organoid",
        "count": 5
      },
      {
        "slug": "perturb-seq",
        "label": "Perturb-seq",
        "count": 5
      },
      {
        "slug": "workshop",
        "label": "workshop",
        "count": 5
      },
      {
        "slug": "agents",
        "label": "agents",
        "count": 4
      },
      {
        "slug": "atlas",
        "label": "atlas",
        "count": 4
      },
      {
        "slug": "brain-metastasis",
        "label": "brain-metastasis",
        "count": 4
      },
      {
        "slug": "cross-species",
        "label": "cross-species",
        "count": 4
      },
      {
        "slug": "czi",
        "label": "CZI",
        "count": 4
      },
      {
        "slug": "definition",
        "label": "definition",
        "count": 4
      },
      {
        "slug": "digital-twin",
        "label": "digital-twin",
        "count": 4
      },
      {
        "slug": "dmg",
        "label": "DMG",
        "count": 4
      },
      {
        "slug": "glioma",
        "label": "glioma",
        "count": 4
      },
      {
        "slug": "pathology",
        "label": "pathology",
        "count": 4
      },
      {
        "slug": "xaira",
        "label": "Xaira",
        "count": 4
      },
      {
        "slug": "drug",
        "label": "drug",
        "count": 3
      },
      {
        "slug": "generative",
        "label": "generative",
        "count": 3
      },
      {
        "slug": "in-silico-perturbation",
        "label": "in-silico-perturbation",
        "count": 3
      },
      {
        "slug": "llm",
        "label": "LLM",
        "count": 3
      },
      {
        "slug": "medulloblastoma",
        "label": "medulloblastoma",
        "count": 3
      },
      {
        "slug": "meningioma",
        "label": "meningioma",
        "count": 3
      },
      {
        "slug": "mri",
        "label": "MRI",
        "count": 3
      },
      {
        "slug": "news",
        "label": "news",
        "count": 3
      },
      {
        "slug": "noetik",
        "label": "Noetik",
        "count": 3
      },
      {
        "slug": "proteomics",
        "label": "proteomics",
        "count": 3
      },
      {
        "slug": "review",
        "label": "review",
        "count": 3
      },
      {
        "slug": "state",
        "label": "State",
        "count": 3
      },
      {
        "slug": "tahoe",
        "label": "Tahoe",
        "count": 3
      },
      {
        "slug": "world-model",
        "label": "world-model",
        "count": 3
      },
      {
        "slug": "zero-shot",
        "label": "zero-shot",
        "count": 3
      },
      {
        "slug": "agent-based",
        "label": "agent-based",
        "count": 2
      },
      {
        "slug": "aido",
        "label": "AIDO",
        "count": 2
      },
      {
        "slug": "bo-wang",
        "label": "Bo Wang",
        "count": 2
      },
      {
        "slug": "computational-biology",
        "label": "computational-biology",
        "count": 2
      },
      {
        "slug": "diffusion",
        "label": "diffusion",
        "count": 2
      },
      {
        "slug": "drug-response",
        "label": "drug-response",
        "count": 2
      },
      {
        "slug": "geneformer",
        "label": "Geneformer",
        "count": 2
      },
      {
        "slug": "grn",
        "label": "GRN",
        "count": 2
      },
      {
        "slug": "idh",
        "label": "IDH",
        "count": 2
      },
      {
        "slug": "interview",
        "label": "interview",
        "count": 2
      },
      {
        "slug": "multiscale",
        "label": "multiscale",
        "count": 2
      },
      {
        "slug": "neurips",
        "label": "NeurIPS",
        "count": 2
      },
      {
        "slug": "neuro-oncology",
        "label": "neuro-oncology",
        "count": 2
      },
      {
        "slug": "oncology",
        "label": "oncology",
        "count": 2
      },
      {
        "slug": "plasticity",
        "label": "plasticity",
        "count": 2
      },
      {
        "slug": "podcast",
        "label": "podcast",
        "count": 2
      },
      {
        "slug": "radiotherapy",
        "label": "radiotherapy",
        "count": 2
      },
      {
        "slug": "recursion",
        "label": "Recursion",
        "count": 2
      },
      {
        "slug": "scaling",
        "label": "scaling",
        "count": 2
      }
    ]
  },
  "topic": {
    "description": "Research-graph record, see /data/graph/*.json",
    "fields": {
      "id": "string",
      "type": "enum — cell_state | transition | model | dataset | perturbation | validation | topic",
      "url": "string — path",
      "title_en": "string",
      "title_zh": "string",
      "questions": "{en,zh}[]",
      "entities": "string[]",
      "evidenceRefs": "string[] — item ids",
      "evidence": "{primary[], models[], perturbation_validation[]}",
      "relatedTopics": "string[] — topic ids",
      "summary": "{en,zh}",
      "current_understanding": "{en,zh,refs[]}[]",
      "uncertainties": "{en,zh,refs[]}[]",
      "reviewStatus": "string",
      "publicationStatus": "string",
      "lastReviewed": "string|null",
      "version": "string",
      "analysis_files": "string[] — published analysis outputs only"
    }
  },
  "graph": {
    "node_kinds": {
      "item": "library item (id VCxxxx)",
      "topic": "research topic (id as in content/graph)",
      "hub": "research hub (id hub:<type>)",
      "tag": "facet tag (id tag:<slug>)"
    },
    "edge_kinds": {
      "cites": "topic → item: item listed in the topic evidenceRefs",
      "evidence": "topic → item: item placed in the topic evidence map (role = primary | models | perturbation_validation)",
      "uncertainty": "topic → item: item cited in the topic \"what remains uncertain\" section",
      "relatedTopic": "topic → topic: declared related topic",
      "inHub": "topic → hub: topic belongs to a research hub",
      "hasTag": "item → tag: normalised tag (only tags used ≥2 times)"
    }
  }
}