{
  "name": "BotanAI data dictionary",
  "description": "Every field in the bulk dumps: its meaning, its source dataset, and its licence.",
  "site": "https://botanai.app",
  "generated": "2026-07-20",
  "schema_version": 1,
  "datasets": {
    "wfo": {
      "name": "World Flora Online Plant List",
      "license": "CC0 1.0",
      "license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
      "attribution": "World Flora Online (2026). worldfloraonline.org",
      "url": "https://www.worldfloraonline.org/"
    },
    "kew_wcvp": {
      "name": "Kew, World Checklist of Vascular Plants (WCVP v16)",
      "license": "CC BY 3.0",
      "license_url": "https://creativecommons.org/licenses/by/3.0/",
      "attribution": "Govaerts R (ed.). 2026. WCVP. Facilitated by the Royal Botanic Gardens, Kew. doi.org/10.15468/6h8ucr",
      "url": "https://doi.org/10.15468/6h8ucr"
    },
    "chelsa": {
      "name": "CHELSA V2.1",
      "license": "CC0 1.0",
      "license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
      "attribution": "Karger, D.N. et al. (2017). Climatologies at high resolution for the earth's land surface areas. Scientific Data 4, 170122.",
      "url": "https://chelsa-climate.org/"
    },
    "kew_useful": {
      "name": "Kew, World Checklist of Useful Plant Species (2020)",
      "license": "CC BY 4.0",
      "license_url": "https://creativecommons.org/licenses/by/4.0/",
      "attribution": "Diazgranados M et al. (2020). World Checklist of Useful Plant Species. Royal Botanic Gardens, Kew. doi.org/10.5063/F1CV4G34",
      "url": "https://doi.org/10.5063/F1CV4G34"
    },
    "duke": {
      "name": "Dr. Duke's Phytochemical and Ethnobotanical Database",
      "license": "CC0 1.0",
      "license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
      "attribution": "U.S. Department of Agriculture, Agricultural Research Service. doi.org/10.15482/USDA.ADC/1239279",
      "url": "https://doi.org/10.15482/USDA.ADC/1239279"
    },
    "iucn_wikidata": {
      "name": "IUCN Red List category, via Wikidata (P141)",
      "license": "CC0 1.0 (Wikidata carrier; the category is a factual label)",
      "license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
      "attribution": "IUCN Red List category, carried through Wikidata (wikidata.org). Assessment: IUCN.",
      "url": "https://www.wikidata.org/"
    },
    "names": {
      "name": "Vernacular names, Wikidata (P1843) and GBIF",
      "license": "CC0 1.0 / per source",
      "license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
      "attribution": "Wikidata (wikidata.org, CC0) and GBIF vernacular names (gbif.org).",
      "url": "https://www.wikidata.org/"
    },
    "globi": {
      "name": "Global Biotic Interactions (GloBI)",
      "license": "CC BY 4.0 (aggregate)",
      "license_url": "https://creativecommons.org/licenses/by/4.0/",
      "attribution": "Poelen, J.H. et al. (2014). Global Biotic Interactions. globalbioticinteractions.org",
      "url": "https://www.globalbioticinteractions.org"
    },
    "ipni": {
      "name": "IPNI (International Plant Names Index)",
      "license": "CC BY 4.0",
      "license_url": "https://creativecommons.org/licenses/by/4.0/",
      "attribution": "International Plant Names Index (2026). ipni.org. The Royal Botanic Gardens Kew, Harvard University Herbaria & Australian National Botanic Gardens.",
      "url": "https://www.ipni.org"
    },
    "usda": {
      "name": "USDA PLANTS Database",
      "license": "Public domain (US Government work)",
      "license_url": "https://plants.usda.gov/",
      "attribution": "USDA, NRCS. The PLANTS Database. plants.usda.gov",
      "url": "https://plants.usda.gov/"
    },
    "gift": {
      "name": "GIFT (Global Inventory of Floras and Traits)",
      "license": "CC BY 4.0",
      "license_url": "https://creativecommons.org/licenses/by/4.0/",
      "attribution": "Weigelt P, Konig C, Kreft H (2020). GIFT, a Global Inventory of Floras and Traits. Journal of Biogeography 47.",
      "url": "https://gift.uni-goettingen.de/"
    },
    "wikidata_traits": {
      "name": "Wikidata structured plant traits (P4000, P2048)",
      "license": "CC0 1.0",
      "license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
      "attribution": "Wikidata (wikidata.org, CC0).",
      "url": "https://www.wikidata.org/"
    },
    "eol_traitbank": {
      "name": "EOL TraitBank (via Zenodo)",
      "license": "Per record: CC0 / CC BY 4.0 / public domain only",
      "license_url": "https://doi.org/10.5281/zenodo.17315431",
      "attribution": "Encyclopedia of Life TraitBank, via Zenodo (DOI 10.5281/zenodo.17315431). Only commercially-safe per-record licences retained.",
      "url": "https://doi.org/10.5281/zenodo.17315431"
    },
    "traits_mined": {
      "name": "Traits mined from USDA NRCS plant guides",
      "license": "Public domain (source documents)",
      "license_url": "https://plants.usda.gov/",
      "attribution": "Traits extracted from USDA NRCS plant guides and fact sheets (plants.usda.gov, public domain). Assembled by BotanAI.",
      "url": "https://plants.usda.gov/"
    },
    "inaturalist": {
      "name": "iNaturalist open data",
      "license": "Per photograph: CC0, CC BY or CC BY-SA only",
      "license_url": "https://www.inaturalist.org/pages/help#cc",
      "attribution": "iNaturalist contributors. Each photograph carries its own licence and photographer credit.",
      "url": "https://github.com/inaturalist/inaturalist-open-data"
    },
    "aiy": {
      "name": "Google AIY plants V1 + BotanAI measured confusion",
      "license": "Apache 2.0 (model); BotanAI (measured confusion data)",
      "license_url": "https://www.apache.org/licenses/LICENSE-2.0",
      "attribution": "On-device identification model: Google AIY plants V1. Confusion measured by BotanAI over openly licensed photographs.",
      "url": "https://www.kaggle.com/models/google/aiy"
    }
  },
  "fields": [
    {
      "path": "id.slug",
      "type": "string",
      "description": "Stable BotanAI slug; the page is /plants/{slug}/.",
      "dataset": "wfo"
    },
    {
      "path": "id.wfo",
      "type": "string",
      "description": "World Flora Online identifier (the taxonomic spine key).",
      "dataset": "wfo"
    },
    {
      "path": "id.inat_taxon_id",
      "type": "number|null",
      "description": "iNaturalist taxon id.",
      "dataset": "inaturalist"
    },
    {
      "path": "url",
      "type": "string",
      "description": "Canonical page URL for this species.",
      "dataset": "wfo"
    },
    {
      "path": "last_modified",
      "type": "date",
      "description": "Real modification date of the underlying record.",
      "dataset": "wfo"
    },
    {
      "path": "name.scientific",
      "type": "string",
      "description": "Accepted binomial.",
      "dataset": "wfo"
    },
    {
      "path": "name.authorship",
      "type": "string",
      "description": "Naming authority abbreviation.",
      "dataset": "wfo"
    },
    {
      "path": "name.family",
      "type": "string",
      "description": "Accepted family.",
      "dataset": "wfo"
    },
    {
      "path": "name.taxonomic_status",
      "type": "string",
      "description": "Always \"accepted\" in this corpus.",
      "dataset": "wfo"
    },
    {
      "path": "name.synonyms",
      "type": "array",
      "description": "Heterotypic and homotypic synonyms with authorship.",
      "dataset": "wfo"
    },
    {
      "path": "name.common",
      "type": "object",
      "description": "Preferred and English common names, with their source.",
      "dataset": "names"
    },
    {
      "path": "name.wikipedia",
      "type": "string|null",
      "description": "Wikipedia article URL.",
      "dataset": "names"
    },
    {
      "path": "native_range",
      "type": "object|null",
      "description": "TDWG level-3 native distribution and regions; introduced/extinct/doubtful excluded.",
      "dataset": "kew_wcvp"
    },
    {
      "path": "traits.lifeform",
      "type": "string|null",
      "description": "Kew life form.",
      "dataset": "kew_wcvp"
    },
    {
      "path": "traits.climate",
      "type": "string|null",
      "description": "Kew climate class.",
      "dataset": "kew_wcvp"
    },
    {
      "path": "climate_envelope",
      "type": "object|null",
      "description": "CHELSA 5th to 95th percentile climate at georeferenced observations. NOT a hardiness zone.",
      "dataset": "chelsa"
    },
    {
      "path": "identification",
      "type": "object",
      "description": "On-device model coverage, benchmark membership, and measured lookalikes (confusion matrix).",
      "dataset": "aiy"
    },
    {
      "path": "photographs",
      "type": "object",
      "description": "Summary only in the bulk dump: counts, licences present, and a pointer to per-image metadata on the .json sibling.",
      "dataset": "inaturalist"
    },
    {
      "path": "uses",
      "type": "object|null",
      "description": "Documented use categories.",
      "dataset": "kew_useful"
    },
    {
      "path": "phytochemistry",
      "type": "object|null",
      "description": "Notable compounds and reported activities (snapshot 1992-2016).",
      "dataset": "duke"
    },
    {
      "path": "conservation",
      "type": "object|null",
      "description": "IUCN Red List category.",
      "dataset": "iucn_wikidata"
    },
    {
      "path": "vernacular_names",
      "type": "object|null",
      "description": "Names in other languages, grouped by language.",
      "dataset": "names"
    },
    {
      "path": "interactions",
      "type": "object|null",
      "description": "Recorded ecological interactions, grouped by type.",
      "dataset": "globi"
    },
    {
      "path": "growth_traits",
      "type": "object|null",
      "description": "Growth characteristics merged from USDA PLANTS, GIFT, Wikidata and EOL TraitBank, plus traits mined from public-domain USDA NRCS guides. Grouped by category; each value keeps every source that reported it. A value with extracted:true was read from prose (no structured source) and carries a verbatim quote and source_url.",
      "dataset": "gift"
    },
    {
      "path": "nomenclature",
      "type": "object|null",
      "description": "Protologue: author, work, year, IPNI record.",
      "dataset": "ipni"
    },
    {
      "path": "sources",
      "type": "array",
      "description": "The datasets actually used for THIS species, each with licence and retrieval date.",
      "dataset": "wfo"
    },
    {
      "path": "gaps",
      "type": "array",
      "description": "What is NOT published for this species, and why. A structured admission, not a disclaimer.",
      "dataset": "wfo"
    },
    {
      "path": "license",
      "type": "object",
      "description": "The licence of this record and a note on photograph licensing.",
      "dataset": "wfo"
    },
    {
      "path": "_meta (per-dimension files only)",
      "type": "object",
      "description": "First line of each dimension dump: that dimension source, licence, sync date, coverage and match method.",
      "dataset": "wfo"
    }
  ]
}