{
 "schema_version": "1.0",
 "generated": "2026-07-31",
 "public_origin": "https://magalia.wiki",
 "purpose": "Single source of truth for every public count. The site should READ this rather than hard-code numbers (the fix for count drift). Each count is typed (live/snapshot/source/curated/draft/ai-indexed/reference/teaching/generated) so source records, search rows, editions and AI-indexed items are never conflated.",
 "taxonomy": {
  "live": "queryable live index (DB/API rows)",
  "snapshot": "frozen point-in-time export",
  "source": "raw source records before dedup",
  "curated": "hand-edited scholarly editions",
  "draft": "not yet reviewed",
  "ai-indexed": "items in an AI/bridge index (NOT inscriptions)",
  "reference": "reference-work nodes (LCL/BNP/CIL/PIR)",
  "teaching": "course/teaching units",
  "generated": "derived/generated catalogue"
 },
 "counts": [
  {
   "key": "family_count",
   "label": {
    "en": "Top-level content families",
    "zh": "顶级内容门类"
   },
   "value": 11,
   "unit": "families",
   "type": "generated",
   "source": "schema/family-*.json (families/index.html card taxonomy)",
   "as_of": "2026-07-31",
   "where_used": [
    "home",
    "families index",
    "builds nav"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "SINGLE SOURCE OF TRUTH for the sitewide family count. Was drifting 8/8/9/10 across home.html (\"eight kingdoms\"), builds.html (\"eight families\") and families/index.html (\"nine kingdoms\", ten cards). stamp_counts.py syncs every surface; check_family_counts.py gates it. Per-family page counts live in doc[\"families\"]."
  },
  {
   "key": "list_rows",
   "label": {
    "en": "Unified inscription list",
    "zh": "统一铭文列表"
   },
   "value": 511973,
   "unit": "rows",
   "type": "live",
   "source": "list.sqlite (EDCS∪EDH∪TM metadata)",
   "as_of": "2026-06-08",
   "where_used": [
    "Discover",
    "Search",
    "browse"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "Search rows BEFORE cross-system dedup — NOT distinct inscriptions."
  },
  {
   "key": "edh_rows",
   "label": {
    "en": "EDH index",
    "zh": "EDH 索引"
   },
   "value": 81883,
   "unit": "rows",
   "type": "snapshot",
   "source": "edh.sqlite (Heidelberg, archival)",
   "as_of": "2026-06-08",
   "where_used": [
    "edh-corpus reader"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": ""
  },
  {
   "key": "papyri_rows",
   "label": {
    "en": "Papyri index",
    "zh": "纸草索引"
   },
   "value": 66079,
   "unit": "rows",
   "type": "snapshot",
   "source": "papyri.sqlite (TM-keyed)",
   "as_of": "2026-06-08",
   "where_used": [
    "papyri reader",
    "Symbolon bridge"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": ""
  },
  {
   "key": "kcl_snapshot",
   "label": {
    "en": "KCL Matrix-Hub inscriptions snapshot",
    "zh": "KCL 铭文快照"
   },
   "value": 5467,
   "unit": "records",
   "type": "snapshot",
   "source": "KCL IAph/IRT/IRCyr static snapshot",
   "as_of": "2026-06-08",
   "where_used": [
    "Matrix Hub catalogue"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": ""
  },
  {
   "key": "literature_works",
   "label": {
    "en": "Literature works (CTS)",
    "zh": "文学作品"
   },
   "value": 2248,
   "unit": "works",
   "type": "snapshot",
   "source": "canonical greekLit/latinLit TEI",
   "as_of": "2026-06-08",
   "where_used": [
    "literature reader",
    "Symbolon bridge"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": ""
  },
  {
   "key": "formula_shards",
   "label": {
    "en": "Formula-dossier decree shards",
    "zh": "套语法令切片"
   },
   "value": 6617,
   "unit": "normalised decree shards",
   "type": "generated",
   "source": "formula-dossier mining",
   "as_of": "2026-06-08",
   "where_used": [
    "Formula Dossier"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": ""
  },
  {
   "key": "formula_definitions",
   "label": {
    "en": "Formulae with corpus counts (dossier bank)",
    "zh": "有语料计数之套语（正典库）"
   },
   "value": 54,
   "unit": "formulae",
   "type": "curated",
   "source": "matrix-hub/formula-dossier/dossier.html \"F.x\" bank (corpus-counted subset of schema/formula-network.json, 58 uids)",
   "as_of": "2026-07-31",
   "where_used": [
    "Formula Dossier",
    "Governance Corpus",
    "formula-network.html",
    "syllabus",
    "week13 teaching"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "SINGLE SOURCE OF TRUTH for the sitewide \"N formulae\" claim — derived from the served dossier bank, all with corpus counts. schema/formula-network.json lists 58 uids: the closed-vocabulary superset incl. 4 Latin tier-2 formulae without corpus counts; only discovery.html / formula-browser.html (which display that artifact) cite 58. stamp_counts.py syncs every surface — was drifting 54/58/50."
  },
  {
   "key": "formula_case_studies",
   "label": {
    "en": "Formula-dossier case studies",
    "zh": "套语案例研究"
   },
   "value": 21,
   "unit": "case studies",
   "type": "curated",
   "source": "matrix-hub/formula-dossier/case_studies/*.html minus index.html + TEMPLATE.html",
   "as_of": "2026-07-31",
   "where_used": [
    "Formula Dossier",
    "Governance Corpus",
    "syllabus"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "Standalone interpretive deep-dives (the dossier's most reader-facing artefact). stamp_counts.py syncs every surface — was drifting 20/21/22 (22 = a glob that wrongly counted the case_studies/index.html landing)."
  },
  {
   "key": "formula_periods",
   "label": {
    "en": "Formula-dossier periods",
    "zh": "套语涵盖时期"
   },
   "value": 4,
   "unit": "periods",
   "type": "curated",
   "source": "Classical Greek · Hellenistic Greek · Republican Latin · Imperial Latin",
   "as_of": "2026-07-31",
   "where_used": [
    "Formula Dossier"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "4 periods across 5 centuries. A \"5 periods\" surface was the drift — 5 is centuries."
  },
  {
   "key": "symbolon_bridge",
   "label": {
    "en": "Symbolon cross-evidence bridge",
    "zh": "Symbolon 跨证据桥"
   },
   "value": 669000,
   "unit": "indexed items",
   "type": "ai-indexed",
   "source": "bridge_*.jsonl (grc/lat/pap/lit/ed, concept+identity)",
   "as_of": "2026-06-08",
   "where_used": [
    "Symbolon app/browse"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "AI cross-evidence INDEX items across 5 streams — NOT inscriptions, NOT one vector space (identity/concept bridge; see Symbolon §0.5)."
  },
  {
   "key": "registry_artifacts",
   "label": {
    "en": "Identity-spine artifacts",
    "zh": "身份脊柱条目"
   },
   "value": 188,
   "unit": "artifacts",
   "type": "curated",
   "source": "registry.json (register.py harvest of #magalia-id blocks)",
   "as_of": "2026-07-31",
   "where_used": [
    "Symbolon",
    "subgraph",
    "edition back-links"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "By class: {'literary-passage': 94, 'edition-collection': 1, 'inscription': 92, 'section-landing': 1}."
  },
  {
   "key": "catalogue_records",
   "label": {
    "en": "Catalogue records",
    "zh": "编目记录"
   },
   "value": 186,
   "unit": "records",
   "type": "curated",
   "source": "catalogue.json",
   "as_of": "2026-07-31",
   "where_used": [
    "catalogue",
    "navigator"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": ""
  },
  {
   "key": "governance_curated",
   "label": {
    "en": "Governance curated editions",
    "zh": "治理类精编版本"
   },
   "value": 42,
   "unit": "curated editions",
   "type": "curated",
   "source": "governance-corpus.json",
   "as_of": "2026-07-31",
   "where_used": [
    "Governance Corpus",
    "Formula Dossier"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "Canonical curated count of the interlinked Greco-Roman public-documents core (17 BC–AD 247). A DIFFERENT categorisation from governance_stamped (all stamped pages sitewide); the Matrix Hub counts-explained note defines both subsets."
  },
  {
   "key": "governance_stamped",
   "label": {
    "en": "Governance stamped editions",
    "zh": "治理类盖印评注本"
   },
   "value": 81,
   "unit": "stamped editions",
   "type": "generated",
   "source": "matrix-hub/governance/*.html (pages with #magalia-id)",
   "as_of": "2026-07-31",
   "where_used": [
    "root sidebar",
    "Matrix Hub",
    "functions-manifest"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "SINGLE SOURCE OF TRUTH for the sitewide \"N stamped editions\" claim. stamp_counts.py syncs every surface to this; do not hand-edit those numbers."
  },
  {
   "key": "scans_3d",
   "label": {
    "en": "3D inscription scans",
    "zh": "三维铭文扫描"
   },
   "value": 41,
   "unit": "photogrammetry captures",
   "type": "curated",
   "source": "models3d-identity.json + models3d-join.json",
   "as_of": "2026-07-31",
   "where_used": [
    "3D gallery",
    "inscription.html"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "8 fully spine-joined (EM⇄IG⇄PHI⇄edition); 17 carry the EM↔IG pair. The homepage '32 inscription + 9 sculpture' splits this same set — reconcile to 41."
  },
  {
   "key": "reference_nodes",
   "label": {
    "en": "Reference-work nodes (LCL/BNP/CIL/PIR)",
    "zh": "参考文献节点"
   },
   "value": 1674,
   "unit": "reference artifacts",
   "type": "reference",
   "source": "registry-references.json (build_reference_registry.py)",
   "as_of": "2026-07-31",
   "where_used": [
    "platform spine (mergeable)"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "LCL 28 · BNP 1504 · BNPSII 128 · CIL-vol 6 · PIR-vol 7."
  },
  {
   "key": "dh_tracker",
   "label": {
    "en": "DH database/project directory",
    "zh": "DH 数据库目录"
   },
   "value": 183,
   "unit": "databases/projects",
   "type": "curated",
   "source": "dh-tracker",
   "as_of": "2026-07-31",
   "where_used": [
    "DH Tracker"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "Homepage prose must read this number (was drifting 146 vs 183)."
  },
  {
   "key": "bundles",
   "label": {
    "en": "Live project bundles",
    "zh": "在线项目集"
   },
   "value": 11,
   "unit": "bundles",
   "type": "teaching",
   "source": "site sections (Happy Latin · Cicero · Pottery · Aesop · Periplus · Matrix Hub · Latin Exam Prep · DH Tracker · ML/AI · Greek Historians · Attic Orators)",
   "as_of": "2026-07-31",
   "where_used": [
    "homepage"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "Header chip + prose + meta must all read this. The homepage prose enumerates 11 live bundles: §IX Greek Historians and §X Attic Orators are SEPARATE sections (separate historiae/ and orators/ dirs). Reconciled 10→11 on 2026-06-16 — the source list previously omitted Attic Orators. To revert, fold Orators into Greek Historians."
  },
  {
   "key": "symbolon_validation",
   "label": {
    "en": "Symbolon/assistant honesty eval",
    "zh": "Symbolon 诚实性评测"
   },
   "value": 100,
   "unit": "gold items (abstention sample)",
   "type": "ai-indexed",
   "source": "eval/ harness (P2) — Qwen3.7-plus: abstain 1.00, 0 hallucinations",
   "as_of": "2026-07-31",
   "where_used": [
    "symbolon-validation.html (live)",
    "Symbolon workbench"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "From the own-ground-truth eval (eval/RESULTS.md). The validation page is SHIPPED and live at /symbolon-validation.html (HTTP 200, verified 2026-06-16) — was mislabelled \"(planned)\"."
  },
  {
   "key": "id_systems_linkable",
   "label": {
    "en": "Outbound ID systems (record-linkable)",
    "zh": "可直链外部标识系统"
   },
   "value": 6,
   "unit": "systems with verified deep-link templates",
   "type": "generated",
   "source": "schema/id-systems.json (build_id_systems.py)",
   "as_of": "2026-07-31",
   "where_used": [
    "edition Connections panel"
   ],
   "license": "—",
   "verified": true,
   "note": "Of 39 ID systems in registry.json equivalents; the remaining 33 are print corpora expanded via sigla-index (no fabricated URL)."
  },
  {
   "key": "federation_corpora",
   "label": {
    "en": "Cross-corpus federation (TM-partner)",
    "zh": "跨语料联邦（TM 合作语料）"
   },
   "value": 144,
   "unit": "partner corpora a TM-bearing text resolves across",
   "type": "reference",
   "source": "schema/id-systems.json federation (FAIR-epigraphy datasources)",
   "as_of": "2026-07-31",
   "where_used": [
    "matrix-hub/id-federation.html"
   ],
   "license": "CC-BY-SA 4.0",
   "verified": true,
   "note": "5 carry a live-verified per-id deep-link; the rest resolve through the Trismegistos relations hub (no fabricated URL)."
  },
  {
   "key": "sigla_expanded",
   "label": {
    "en": "Sigla with full attribution",
    "zh": "可展开著录的著录略语"
   },
   "value": 122,
   "unit": "sigla → full citation",
   "type": "reference",
   "source": "schema/sigla-index.json (EpiBib + supplement)",
   "as_of": "2026-07-31",
   "where_used": [
    "edition Connections panel",
    "portal"
   ],
   "license": "—",
   "verified": true,
   "note": "89 from EpiBib Heidelberg + 36 hand-curated (3 flagged uncertain)."
  },
  {
   "key": "restoration_audited",
   "label": {
    "en": "EDCS inscriptions audited for restoration",
    "zh": "已审计修复率的 EDCS 铭文"
   },
   "value": 537262,
   "unit": "Latin inscriptions scanned",
   "type": "generated",
   "source": "edcs-restoration-auditor → matrix-hub/restoration-atlas.json",
   "as_of": "2026-07-31",
   "where_used": [
    "restoration-atlas.html"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "Finding: 11.5% of legible letters are editorial restoration; 27.5% of inscriptions carry conjecture; 14,241 flagged. 'History from Square Brackets'."
  },
  {
   "key": "lire_geotemporal",
   "label": {
    "en": "Dated + located Latin inscriptions (LIRE)",
    "zh": "有纪年且定位之拉丁铭文"
   },
   "value": 132909,
   "unit": "geotemporal Latin inscriptions",
   "type": "generated",
   "source": "LIRE v1-2 (EDCS∪EDH merged) → matrix-hub/epigraphic-habit.json",
   "as_of": "2026-07-31",
   "where_used": [
    "epigraphic-habit.html"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "97.6% of LIRE's 136,190 features are dated+located. Epigraphic-habit peak 150–175 CE. A geotemporal VIEW of the merged record — overlaps the EDH/EDCS snapshots, not additive."
  },
  {
   "key": "pir_persons",
   "label": {
    "en": "Imperial prosopography persons (PIR²)",
    "zh": "帝国群体传记人物（PIR²）"
   },
   "value": 15061,
   "unit": "PIR² persons",
   "type": "reference",
   "source": "PIR-public export → schema/person-authority.json",
   "as_of": "2026-07-31",
   "where_used": [
    "prosopography.html"
   ],
   "license": "CC BY (PIR-public)",
   "verified": true,
   "note": "3,988 carry a cursus honorum; top attested office Consul (cos.) (n=1631). Citation+offices authority (names abbreviated in open export); DPRR Republican layer not yet ingested."
  },
  {
   "key": "fasti_consular_years",
   "label": {
    "en": "Consular fasti years (T1, DPRR)",
    "zh": "执政官名表年数（T1，DPRR）"
   },
   "value": 477,
   "unit": "years",
   "type": "reference",
   "source": "DPRR data.sql → build_fasti_republican.py → fasti/consular.json",
   "as_of": "2026-07-31",
   "where_used": [
    "fasti/index.html"
   ],
   "license": "open (KCL/DPRR)",
   "verified": true,
   "note": "-509..-20; 867 consul + 69 suffect attestations; 55 eponymy-exception years. T1 Republic data-driven; T2/T3 not yet built."
  },
  {
   "key": "fasti_figures_linked",
   "label": {
    "en": "Chronology figures linked to the fasti (DPRR)",
    "zh": "已连接执政官名表之编年人物（DPRR）"
   },
   "value": 8,
   "unit": "figures",
   "type": "reference",
   "source": "build_fasti_join.py → fasti/figures-backfill.json + figures-authority.json",
   "as_of": "2026-07-31",
   "where_used": [
    "fasti/index.html"
   ],
   "license": "CC BY 4.0 (metadata)",
   "verified": true,
   "note": "curated figures resolved to their exact DPRR person (homonym-safe); consular years backfilled into figures-authority.json; H7 round-trip clean."
  },
  {
   "key": "pleiades_places",
   "label": {
    "en": "Ancient places (Pleiades gazetteer)",
    "zh": "古代地名（Pleiades 地名辞典）"
   },
   "value": 42121,
   "unit": "ancient places profiled",
   "type": "reference",
   "source": "Pleiades v4.1 → matrix-hub/pleiades-atlas.json",
   "as_of": "2026-07-31",
   "where_used": [
    "pleiades-atlas.html"
   ],
   "license": "CC BY 3.0 (Pleiades)",
   "verified": true,
   "note": "34,563 located (82%); the spatial backbone beneath the site — 81 of these places carry Magalia editions (enriched with Pleiades type/precision). Spatial profile only."
  },
  {
   "key": "production_centers_scored",
   "label": {
    "en": "Roman production centers scored",
    "zh": "已评分之罗马生产中心"
   },
   "value": 23,
   "unit": "centers scored on the enclave rubric",
   "type": "finding",
   "source": "roman-economy-centers dossier (OXREP Mines v3.0 + CEIPAC + LIST/EDCS) -> matrix-hub/production-centers.html",
   "as_of": "2026-07-31",
   "where_used": [
    "production-centers.html"
   ],
   "license": "CC BY (OXREP, CEIPAC, EDCS)",
   "verified": true,
   "note": "1,399 attested OXREP mines mapped + dated; 23 centers scored on the 7-axis enclave rubric, 12 qualify as bounded fiscal-legal production enclaves. Citations P5-verified against EDCS."
  },
  {
   "key": "decree_formulae",
   "label": {
    "en": "Greek decree inscriptions (formula-traced)",
    "zh": "希腊政令铭文（套语追踪）"
   },
   "value": 6617,
   "unit": "decree inscriptions",
   "type": "generated",
   "source": "formula-dossier → matrix-hub/formula-diffusion.json",
   "as_of": "2026-07-31",
   "where_used": [
    "formula-diffusion.html"
   ],
   "license": "CC BY",
   "verified": true,
   "note": "4,370 dated; 22 commonest formulae traced across centuries/regions; peak century 2c_BCE (n=1691). Overwhelmingly Greek, Hellenistic-weighted, Attica-centric."
  },
  {
   "key": "latin_restoration_benchmark",
   "label": {
    "en": "Latin restoration benchmark (best exact)",
    "zh": "拉丁修复基准（最佳精确率）"
   },
   "value": 91.5,
   "unit": "% exact (Aeneas, leakage-free)",
   "type": "ai-indexed",
   "source": "eval/runs/*-metrics.json → matrix-hub/latin-restoration-eval.json",
   "as_of": "2026-07-31",
   "where_used": [
    "latin-restoration-eval.html"
   ],
   "license": "—",
   "verified": true,
   "note": "Specialist Aeneas 91.5% exact, ECE 0.0531 (calibrated); general LLM 5.5% exact at ECE 0.818 (confidently wrong). Surfaced from the existing eval/ harness; no model run by the page."
  },
  {
   "key": "sicily_inscriptions",
   "label": {
    "en": "Sicilian inscriptions profiled (I.Sicily)",
    "zh": "已剖析之西西里铭文（I.Sicily）"
   },
   "value": 4784,
   "unit": "EpiDoc inscriptions",
   "type": "reference",
   "source": "I.Sicily → matrix-hub/sicily-languages.json",
   "as_of": "2026-07-31",
   "where_used": [
    "sicily-languages.html"
   ],
   "license": "CC BY 4.0 (I.Sicily)",
   "verified": true,
   "note": "9 languages (Greek/Latin/Sikel/Elymian/Punic/Oscan/Hebrew), 3,813 dated, 19 bilingual — the multilingual contact zone across the centuries."
  },
  {
   "key": "ppret_inscriptions",
   "label": {
    "en": "Praetorian-prefecture inscriptions profiled (PPRET)",
    "zh": "已剖析之禁卫军长官铭文（PPRET）"
   },
   "value": 98,
   "unit": "EpiDoc inscriptions",
   "type": "reference",
   "source": "PPRET → matrix-hub/ppret-prefecture.json",
   "as_of": "2026-07-31",
   "where_used": [
    "ppret-prefecture.html"
   ],
   "license": "CC BY (PPRET, Porena dir. 2022)",
   "verified": true,
   "note": "76 dated (289–450 CE), 8 text-types (top Honorary 63.3%) — the late-antique administrative epigraphy of the empire's top civil officials."
  },
  {
   "key": "cretan_inscriptions",
   "label": {
    "en": "Cretan institutional inscriptions profiled (I.Cret)",
    "zh": "已剖析之克里特制度铭文（I.Cret）"
   },
   "value": 397,
   "unit": "EpiDoc inscriptions",
   "type": "reference",
   "source": "I.Cret → matrix-hub/cretan-institutions.json",
   "as_of": "2026-07-31",
   "where_used": [
    "cretan-institutions.html"
   ],
   "license": "CC BY (Cretan Institutional Inscriptions)",
   "verified": true,
   "note": "373 dated (700 BCE–212 CE), 271 distinct institutions named 3,149 times (top kosmos 554) — the civic vocabulary of the Cretan poleis."
  },
  {
   "key": "papyri_distribution",
   "label": {
    "en": "Papyri profiled by century & findspot",
    "zh": "已剖析之纸草（分世纪与出土地）"
   },
   "value": 66079,
   "unit": "papyri & ostraca",
   "type": "snapshot",
   "source": "papyri.sqlite → matrix-hub/papyri-distribution.json",
   "as_of": "2026-07-31",
   "where_used": [
    "papyri-distribution.html"
   ],
   "license": "CC BY 4.0 (Trismegistos)",
   "verified": true,
   "note": "65,077 dated across 1,974 findspots; peak 2nd c. CE (n=15619). The documentary habit — the everyday twin of the inscribed record (Oxyrhynchus, the Fayum, Thebes)."
  },
  {
   "key": "funerary_epitaphs",
   "label": {
    "en": "Latin epitaphs profiled (Dis Manibus)",
    "zh": "已剖析之拉丁墓志（Dis Manibus）"
   },
   "value": 27953,
   "unit": "epitaphs",
   "type": "snapshot",
   "source": "EDH dis_manibus → matrix-hub/funerary-formula.json",
   "as_of": "2026-07-31",
   "where_used": [
    "funerary-formula.html"
   ],
   "license": "CC BY 4.0 (EDH)",
   "verified": true,
   "note": "25,191 dated; the Sacrum variant (D M S) is a western/African signature — Baetica 96% vs the Danube/Rhine ~1%. Filtered to EDH's epitaph class; Sacrum over legible-formula subset."
  },
  {
   "key": "embedding_outlier_leads",
   "label": {
    "en": "Embedding-outlier discovery leads",
    "zh": "嵌入离群点发现线索"
   },
   "value": 100,
   "unit": "leads",
   "type": "ai-indexed",
   "source": "phase-16 semantic index → matrix-hub/embedding-outliers.json",
   "as_of": "2026-07-31",
   "where_used": [
    "embedding-outliers.html"
   ],
   "license": "CC BY 4.0 (derived; model-only signal)",
   "verified": true,
   "note": "model-only, unreviewed queue: 18,387 of 30,000 sampled Greek texts scored across 222 (region × century) cells; high score = locally isolated in embedding space, NOT a proven error."
  },
  {
   "key": "formula_discovery_candidates",
   "label": {
    "en": "Candidate formulae (open-vocabulary discovery)",
    "zh": "候选套语（开放词表发现）"
   },
   "value": 80,
   "unit": "candidate clusters",
   "type": "generated",
   "source": "I.PHI register mining → schema/formula-discovery.json",
   "as_of": "2026-07-31",
   "where_used": [
    "formula-discovery.html"
   ],
   "license": "CC BY 4.0 (derived)",
   "verified": true,
   "note": "REVIEW-ONLY curator queue over 4,434 register decrees vs background; nothing is auto-promoted into the 58-formula bank; every stored attestation offset re-slices or the build fails."
  },
  {
   "key": "word_order_texts",
   "label": {
    "en": "Treebank texts profiled for word order",
    "zh": "已剖析语序之树库文本"
   },
   "value": 12,
   "unit": "PROIEL texts",
   "type": "generated",
   "source": "PROIEL treebank → matrix-hub/word-order.json",
   "as_of": "2026-07-31",
   "where_used": [
    "word-order.html"
   ],
   "license": "CC BY-NC-SA (PROIEL)",
   "verified": true,
   "note": "Object-before-verb share: classical Latin 85% (verb-final) vs Greek 40%; the Vulgate 37% calques Greek order. One construction (obj↔verb), no model."
  },
  {
   "key": "smyth_sections",
   "label": {
    "en": "Smyth's Greek Grammar sections",
    "zh": "Smyth 希腊语法节数"
   },
   "value": 3048,
   "unit": "numbered §§",
   "type": "reference",
   "source": "neelsmith/smyth (Perseus-derived TEI) → greek-grammar/smyth.html",
   "as_of": "2026-07-31",
   "where_used": [
    "greek-grammar/smyth.html",
    "historiae readers"
   ],
   "license": "CC BY-SA (Perseus)",
   "verified": true,
   "note": "All 3048 canonical sections (§1–§3048) + 213 dialect notes; betacode converted to Unicode polytonic, cross-source-verified vs the 1920 Textkit edition. The Greek companion to Woodcock's Latin syntax reference."
  },
  {
   "key": "comparative_comparanda",
   "label": {
    "en": "Comparative Greek–Latin comparanda",
    "zh": "希腊-拉丁比较项"
   },
   "value": 129,
   "unit": "comparanda",
   "type": "reference",
   "source": "Whiton/Sihler/Pinkster/Mason/Oniga → comparative-grammar/comparative.html",
   "as_of": "2026-07-31",
   "where_used": [
    "comparative-grammar/comparative.html"
   ],
   "license": "source works as cited (Whiton PD; Sihler/Pinkster/Mason/Oniga quoted, page-cited)",
   "verified": true,
   "note": "Across syntax 81 (Whiton's parallel rules), morphology 12 (Sihler), semantics 10 + pragmatics 12 (Pinkster/Oniga), vocabulary 14 (Mason). Anchored on Smyth (Greek) + Woodcock (Latin) §§; the four sampled dimensions are page-cited, not bulk-OCR'd."
  },
  {
   "key": "bibliography_works",
   "label": {
    "en": "Secondary-literature works cited",
    "zh": "所引二手学术著作"
   },
   "value": 29,
   "unit": "works",
   "type": "reference",
   "source": "bibliography.json (scholarship + dataset authorities + reference grammars)",
   "as_of": "2026-07-31",
   "where_used": [
    "matrix-hub/bibliography.html"
   ],
   "license": "works as cited",
   "verified": true,
   "note": "Grounds 13 pages; each work linked to a page only where that page genuinely relies on it (MacMullen 1982→epigraphic habit, Badian 1989→restoration, Whiton/Sihler/Pinkster/Mason/Oniga→comparative grammar, LIRE/EDH/PROIEL/I.Sicily/Pleiades/PIR→the data findings). Distinct from registry-references.json (Loeb/Pauly/CIL/PIR series)."
  }
 ],
 "families": [
  {
   "slug": "library",
   "label_en": "The Library · Greek & Latin editions",
   "label_zh": "",
   "hub": "/families/library.html",
   "count": 66
  },
  {
   "slug": "epigraphy",
   "label_en": "Epigraphy & Editions",
   "label_zh": "",
   "hub": "/families/epigraphy.html",
   "count": 107
  },
  {
   "slug": "governance",
   "label_en": "Governance & Public Documents",
   "label_zh": "治理与公共文书",
   "hub": "/families/governance.html",
   "count": 200
  },
  {
   "slug": "history_time",
   "label_en": "History & Time",
   "label_zh": "",
   "hub": "/families/history_time.html",
   "count": 45
  },
  {
   "slug": "prosopography",
   "label_en": "Prosopography & Encyclopedia",
   "label_zh": "",
   "hub": "/families/prosopography.html",
   "count": 2879
  },
  {
   "slug": "material",
   "label_en": "Material Culture",
   "label_zh": "",
   "hub": "/families/material.html",
   "count": 54
  },
  {
   "slug": "computational",
   "label_en": "Computational · prediction & findings",
   "label_zh": "",
   "hub": "/families/computational.html",
   "count": 55
  },
  {
   "slug": "learn",
   "label_en": "Learn · graded reading",
   "label_zh": "",
   "hub": "/families/learn.html",
   "count": 73
  },
  {
   "slug": "grammar",
   "label_en": "Grammar & Syntax",
   "label_zh": "",
   "hub": "/families/grammar.html",
   "count": 9
  },
  {
   "slug": "composition",
   "label_en": "Prose Composition · graded exercises",
   "label_zh": "",
   "hub": "/families/composition.html",
   "count": 7
  },
  {
   "slug": "ancient-ecology",
   "label_en": "Ancient Ecology · maritime geography & exploration",
   "label_zh": "古代生态 · 海洋地理与探索",
   "hub": "/families/ancient-ecology.html",
   "count": 65
  }
 ]
}