{
  "id": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1",
  "concept": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases",
  "url": "https://datasetpapers.com/papers/drduke-datadictionary-type-by-table/",
  "title": "Data-type composition varies across the tables of Dr. Duke's database schema",
  "source_dataset": {
    "title": "Dr. Duke's Phytochemical and Ethnobotanical Databases",
    "doi": "10.15482/USDA.ADC/1239279",
    "license": "CC0"
  },
  "verification": {
    "method": "re_execution",
    "status": "matched",
    "reproduced": true,
    "ran_at": "2026-07-13T13:48:23Z",
    "record": "verification.json"
  },
  "gate": {
    "passed": true,
    "version": "gate-0.1",
    "novelty_grade": "C",
    "failed": []
  },
  "claims": [
    {
      "id": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/claim-1",
      "n": 1,
      "triple": {
        "subject": "declared column data type",
        "predicate": "is associated with",
        "object": "which table a column belongs to"
      },
      "assertion_text": "Across the 15 tables and 199 column definitions of Dr. Duke's database schema, declared data type is associated with table membership (Monte-Carlo chi-square = 62.47, df = 42, p = 0.032, Cramer's V = 0.32, bias-corrected V = 0.19, n = 199); after Holm correction across the three-test family the primary test is at the significance boundary (p = 0.065).",
      "novelty_grade": "C",
      "mode": "observational",
      "confidence": 0.6,
      "self_reported_status": "unverified",
      "independent_reexecution": "matched",
      "entities": [],
      "relations": [
        {
          "predicate": "supportedByEvidence",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/analysis"
        },
        {
          "predicate": "supportedByEvidence",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/fig-1"
        },
        {
          "predicate": "supportedByEvidence",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/fig-2"
        },
        {
          "predicate": "supportedByEvidence",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/fig-3"
        },
        {
          "predicate": "supportedByEvidence",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/tbl-1"
        },
        {
          "predicate": "supportedByEvidence",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/tbl-3"
        },
        {
          "predicate": "wasDerivedFrom",
          "target": "https://doi.org/10.15482/USDA.ADC/1239279"
        },
        {
          "predicate": "isPartOf",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1"
        }
      ]
    },
    {
      "id": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/claim-2",
      "n": 2,
      "triple": {
        "subject": "the table-type association",
        "predicate": "is not an artefact of",
        "object": "the shared constant integer ID key"
      },
      "assertion_text": "Removing the structurally constant Long Integer ID key present in every table strengthens the association (Monte-Carlo chi-square = 52.48, df = 28, p = 0.011, Cramer's V = 0.38, n = 184; Holm p = 0.033), which is the only member of the three-test family to survive Holm correction.",
      "novelty_grade": "C",
      "mode": "observational",
      "confidence": 0.65,
      "self_reported_status": "unverified",
      "independent_reexecution": "matched",
      "entities": [],
      "relations": [
        {
          "predicate": "supportedByEvidence",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/analysis"
        },
        {
          "predicate": "supportedByEvidence",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/tbl-3"
        },
        {
          "predicate": "wasDerivedFrom",
          "target": "https://doi.org/10.15482/USDA.ADC/1239279"
        },
        {
          "predicate": "isPartOf",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1"
        }
      ]
    },
    {
      "id": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/claim-3",
      "n": 3,
      "triple": {
        "subject": "a binary Text vs Non-text contrast",
        "predicate": "retains",
        "object": "a moderate table-type association"
      },
      "assertion_text": "Collapsing declared type to Text vs Non-text preserves a moderate association (Monte-Carlo chi-square = 23.60, df = 14, p = 0.043, Cramer's V = 0.34, n = 199; Holm p = 0.065), landing at the corrected significance boundary like the primary test.",
      "novelty_grade": "C",
      "mode": "observational",
      "confidence": 0.55,
      "self_reported_status": "unverified",
      "independent_reexecution": "matched",
      "entities": [],
      "relations": [
        {
          "predicate": "supportedByEvidence",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/analysis"
        },
        {
          "predicate": "supportedByEvidence",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/tbl-3"
        },
        {
          "predicate": "wasDerivedFrom",
          "target": "https://doi.org/10.15482/USDA.ADC/1239279"
        },
        {
          "predicate": "isPartOf",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1"
        }
      ]
    },
    {
      "id": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/claim-4",
      "n": 4,
      "triple": {
        "subject": "the required and size dictionary fields",
        "predicate": "are degenerate and therefore",
        "object": "cannot support any statistical inference"
      },
      "assertion_text": "The 'required' field is FALSE for all 199 columns (zero variance) and 'size' takes exactly one value per declared type (within-type variance 0), so neither field can be tested and no inference about field requiredness or storage sizing is drawn from this dictionary.",
      "novelty_grade": "D",
      "mode": "observational",
      "confidence": 0.98,
      "self_reported_status": "unverified",
      "independent_reexecution": "matched",
      "entities": [],
      "relations": [
        {
          "predicate": "supportedByEvidence",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/analysis"
        },
        {
          "predicate": "supportedByEvidence",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/tbl-2"
        },
        {
          "predicate": "wasDerivedFrom",
          "target": "https://doi.org/10.15482/USDA.ADC/1239279"
        },
        {
          "predicate": "isPartOf",
          "target": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1"
        }
      ]
    }
  ]
}