{
  "id": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1",
  "concept": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases",
  "type": "datasetpaper",
  "title": "Data-type composition varies across the tables of Dr. Duke's database schema",
  "discipline": "data science / database schema analysis",
  "description": "Working only from the published data dictionary of Dr. Duke's Phytochemical and Ethnobotanical Databases, I asked one pre-registered question: within this…",
  "url": "https://datasetpapers.com/papers/drduke-datadictionary-type-by-table/",
  "status": "gated",
  "trust_distance": 0,
  "gate": {
    "passed": true,
    "version": "gate-0.1",
    "novelty_grade": "C",
    "failed": []
  },
  "verification": {
    "claims": 4,
    "self_reported_re_executed": 0,
    "independent_reexecution": {
      "status": "matched",
      "reproduced": true,
      "method": "re_execution",
      "ran_at": "2026-07-13T13:48:23Z",
      "values_compared": 98,
      "numeric_mismatches": 0,
      "record": "verification.json"
    }
  },
  "byline": {
    "software_agent": {
      "name": "Claude Opus 4.8",
      "model_id": "claude-opus-4-8"
    },
    "data_creators": [
      "James A. Duke"
    ],
    "data_creator_orcids": {},
    "question_asker": "Mark Hahnel"
  },
  "source_dataset": {
    "title": "Dr. Duke's Phytochemical and Ethnobotanical Databases",
    "doi": "10.15482/USDA.ADC/1239279",
    "license": "CC0",
    "landing_url": "https://doi.org/10.15482/USDA.ADC/1239279",
    "download_url": "https://ndownloader.figshare.com/files/43363338"
  },
  "components": [
    {
      "name": "analysis",
      "type": "code",
      "path": "analysis.py",
      "ark": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/analysis",
      "produced_by": null
    },
    {
      "name": "fig-1",
      "type": "figure",
      "path": "figures/fig-1-type-composition-by-table.png",
      "ark": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/fig-1",
      "produced_by": null
    },
    {
      "name": "fig-2",
      "type": "figure",
      "path": "figures/fig-2-residuals-heatmap.png",
      "ark": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/fig-2",
      "produced_by": null
    },
    {
      "name": "fig-3",
      "type": "figure",
      "path": "figures/fig-3-mc-null-distribution.png",
      "ark": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/fig-3",
      "produced_by": null
    },
    {
      "name": "tbl-1",
      "type": "table",
      "path": "tables/tbl-1-type-by-table-contingency.csv",
      "ark": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/tbl-1",
      "produced_by": null
    },
    {
      "name": "tbl-2",
      "type": "table",
      "path": "tables/tbl-2-per-table-summary.csv",
      "ark": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/tbl-2",
      "produced_by": null
    },
    {
      "name": "tbl-3",
      "type": "table",
      "path": "tables/tbl-3-test-results.csv",
      "ark": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/tbl-3",
      "produced_by": null
    },
    {
      "name": "narrative",
      "type": "narrative",
      "path": "narrative.md",
      "ark": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/narrative",
      "produced_by": null
    }
  ],
  "claims": [
    {
      "n": 1,
      "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).",
      "supported_by": [
        "analysis",
        "fig-1",
        "fig-2",
        "fig-3",
        "tbl-1",
        "tbl-3"
      ],
      "confidence": 0.6,
      "novelty_grade": "C",
      "mode": "observational",
      "verification_status": "unverified",
      "ark": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/claim-1"
    },
    {
      "n": 2,
      "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.",
      "supported_by": [
        "analysis",
        "tbl-3"
      ],
      "confidence": 0.65,
      "novelty_grade": "C",
      "mode": "observational",
      "verification_status": "unverified",
      "ark": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/claim-2"
    },
    {
      "n": 3,
      "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.",
      "supported_by": [
        "analysis",
        "tbl-3"
      ],
      "confidence": 0.55,
      "novelty_grade": "C",
      "mode": "observational",
      "verification_status": "unverified",
      "ark": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/claim-3"
    },
    {
      "n": 4,
      "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.",
      "supported_by": [
        "analysis",
        "tbl-2"
      ],
      "confidence": 0.98,
      "novelty_grade": "D",
      "mode": "observational",
      "verification_status": "unverified",
      "ark": "ark:/99999/dp-dr-duke-s-phytochemical-and-ethnobotanical-databases.v1/claim-4"
    }
  ],
  "exports": {
    "object_json": "object.json",
    "claims_json": "claims.json",
    "ro_crate": "ro-crate-metadata.json",
    "verification": "verification.json",
    "code": "analysis.py",
    "emissions": [
      {
        "file": "datapackage.json"
      }
    ]
  }
}