{
  "schema_version": 1,
  "dataset": "Palmer Penguins, simplified penguins table",
  "observations": 344,
  "columns": [
    "species",
    "island",
    "bill_length_mm",
    "bill_depth_mm",
    "flipper_length_mm",
    "body_mass_g",
    "sex",
    "year"
  ],
  "study_years": [
    2007,
    2008,
    2009
  ],
  "retrieved_at_utc": "2026-10-22T13:57:31.974410+00:00",
  "upstream": {
    "repository": "https://github.com/allisonhorst/palmerpenguins",
    "commit": "8957207b78d6ccd1b4654a9dd9c9041b657478ab",
    "commit_url": "https://github.com/allisonhorst/palmerpenguins/commit/8957207b78d6ccd1b4654a9dd9c9041b657478ab",
    "source_csv_url": "https://raw.githubusercontent.com/allisonhorst/palmerpenguins/8957207b78d6ccd1b4654a9dd9c9041b657478ab/inst/extdata/penguins.csv",
    "license_url": "https://raw.githubusercontent.com/allisonhorst/palmerpenguins/8957207b78d6ccd1b4654a9dd9c9041b657478ab/LICENSE.md",
    "documentation_url": "https://allisonhorst.github.io/palmerpenguins/reference/penguins.html",
    "citation_url": "https://allisonhorst.github.io/palmerpenguins/authors.html"
  },
  "license": {
    "spdx": "CC0-1.0",
    "local_copy": "LICENSE_DATA.txt",
    "url": "https://creativecommons.org/publicdomain/zero/1.0/"
  },
  "package_citation": {
    "authors": [
      "Allison Marie Horst",
      "Alison Presmanes Hill",
      "Kristen B. Gorman"
    ],
    "year": 2020,
    "title": "palmerpenguins: Palmer Archipelago (Antarctica) penguin data",
    "doi": "10.5281/zenodo.3960218",
    "citation_version_note": "The upstream published citation names R package version 0.1.0; the pinned repository DESCRIPTION is version 0.1.1."
  },
  "original_study": {
    "authors": [
      "Gorman KB",
      "Williams TD",
      "Fraser WR"
    ],
    "year": 2014,
    "title": "Ecological Sexual Dimorphism and Environmental Variability within a Community of Antarctic Penguins (Genus Pygoscelis)",
    "journal": "PLoS ONE",
    "doi": "10.1371/journal.pone.0090081"
  },
  "underlying_data_dois": {
    "Adelie": "10.6073/pasta/98b16d7d563f265cb52372c8ca99e60f",
    "Gentoo": "10.6073/pasta/7fca67fb28d56ee2ffa3d9370ebda689",
    "Chinstrap": "10.6073/pasta/c14dfcfada8ea13a17536e73eb6fbe9e"
  },
  "missing_counts": {
    "species": 0,
    "island": 0,
    "bill_length_mm": 2,
    "bill_depth_mm": 2,
    "flipper_length_mm": 2,
    "body_mass_g": 2,
    "sex": 11,
    "year": 0
  },
  "preservation_policy": "All public-data derivatives retain all 344 source rows, their order, eight variable meanings, category spellings, numeric values, and missingness. No generated penguin observations, imputation, deduplication, sampling, or rounding are used.",
  "fixture_notice": "import_practice_semicolon.csv is a separate original fictional parsing exercise and must not be presented as real Palmer Penguins data.",
  "artifacts": {
    "penguins.csv": {
      "sha256": "f204db2c753b0937caac3cb35258562c14f073e4bbc76be24b4c51ce22767a93",
      "size_bytes": 15241,
      "transformations": [
        "Copied byte-for-byte from the pinned upstream inst/extdata/penguins.csv. This is the package simplified table, not its 17-column penguins_raw dataset."
      ],
      "source_csv_sha256": "f204db2c753b0937caac3cb35258562c14f073e4bbc76be24b4c51ce22767a93"
    },
    "penguins.tsv": {
      "sha256": "cda75e6d5943231ef1c59bb6829013e4925941e65e6e77b08c5cc7a36e5b698c",
      "size_bytes": 15241,
      "transformations": [
        "Read the upstream CSV with Python csv.DictReader as text, preserving field order, row order, spelling, numeric text, and NA tokens.",
        "Write the same header and 344 records with csv.DictWriter, delimiter tab and LF line endings. No index column."
      ],
      "source_csv_sha256": "f204db2c753b0937caac3cb35258562c14f073e4bbc76be24b4c51ce22767a93"
    },
    "penguins.txt": {
      "sha256": "23d79c843a611f80d5c6b6bd108818806f0239eaef8cd4d7f7fba4e105a08b31",
      "size_bytes": 15365,
      "transformations": [
        "Read the upstream CSV with Python csv.DictReader as text.",
        "Prepend two documented # comment lines. Write the identical header and 344 records with semicolon delimiters and LF line endings. No index column."
      ],
      "source_csv_sha256": "f204db2c753b0937caac3cb35258562c14f073e4bbc76be24b4c51ce22767a93"
    },
    "penguins.records.json": {
      "sha256": "f21d9654d95494c26e4fa72c112a6f9e593c368a01984cfb629a1a7ab5a0222d",
      "size_bytes": 70725,
      "transformations": [
        "Read the source CSV in original row and field order. Convert literal NA to JSON null.",
        "Parse bill_length_mm and bill_depth_mm as numbers; flipper_length_mm, body_mass_g, and year as integer numbers. Keep category spellings unchanged.",
        "Write an array of 344 record objects with eight fields per object, UTF-8, two-space indentation, and no nonstandard NaN tokens."
      ],
      "source_csv_sha256": "f204db2c753b0937caac3cb35258562c14f073e4bbc76be24b4c51ce22767a93"
    },
    "penguins.jsonl": {
      "sha256": "a675b15c29f3b4a9ba1f4dd2c1c42abf1acdfcf35c98723e8d669d16863e81c1",
      "size_bytes": 52146,
      "transformations": [
        "Use the same typed records and missing-value conversion as penguins.records.json.",
        "Write exactly one JSON object per line with original field order and LF endings."
      ],
      "source_csv_sha256": "f204db2c753b0937caac3cb35258562c14f073e4bbc76be24b4c51ce22767a93"
    },
    "penguins.nested.json": {
      "sha256": "a3e462b5cf6aed72d9c91c529ded78ba88d347ffe330628d43659f389faab5e3",
      "size_bytes": 83109,
      "transformations": [
        "Use the same typed records and missing-value conversion as penguins.records.json.",
        "Move the four measurement fields into a measurements object for each record. Keep species, island, sex, and year at the top level. Preserve original row order.",
        "This nesting is a teaching representation created for this course, not an upstream API response."
      ],
      "source_csv_sha256": "f204db2c753b0937caac3cb35258562c14f073e4bbc76be24b4c51ce22767a93"
    },
    "penguins.xlsx": {
      "sha256": "4f5515305590f36151bd58b2d01ca45fbcfa5534a09a58cb8b46871a6a5c62c5",
      "size_bytes": 17509,
      "transformations": [
        "Write the same 344 typed records into Penguins!A1:H345 with a single header row. Source NA values become genuinely blank cells. No index, formulas, filtering, imputation, sorting, or removed rows.",
        "Add Data_Dictionary!A1:D9 with original field names, plain-language descriptions, units, and observed missing counts. Source notes occupy F1:F8 outside the dictionary table.",
        "Export a two-sheet workbook with the bundled artifact-tool; formatting changes display only."
      ],
      "source_csv_sha256": "f204db2c753b0937caac3cb35258562c14f073e4bbc76be24b4c51ce22767a93"
    },
    "penguins.data_dictionary.json": {
      "sha256": "2b69a01ae0154f9d48c0797850deee6abe59de73cd060ada9b9dbad6c67e45c0",
      "size_bytes": 1071,
      "transformations": [
        "Create metadata for the eight original fields from the upstream field reference.",
        "Count source NA values per field. Descriptions are teaching paraphrases; measurements and field names are unmodified."
      ],
      "source_csv_sha256": "f204db2c753b0937caac3cb35258562c14f073e4bbc76be24b4c51ce22767a93"
    },
    "import_practice_semicolon.csv": {
      "sha256": "6204c0374b32b751489254f89105f13867f2d851986d19b7ac1e022a03f76876",
      "size_bytes": 280,
      "transformations": [
        "Create an ORIGINAL FICTIONAL three-record parsing fixture, unrelated to penguin observations.",
        "Encode as UTF-8 with BOM. Include two # comment lines, semicolon separators, a quoted embedded semicolon, leading-zero identifiers, a literal NA site code, comma-decimal amounts, and MISSING as an unavailable-amount token.",
        "NA means North Area; EU means East Unit in this invented fixture. None of its values represent real research data."
      ],
      "source_csv_sha256": null
    },
    "LICENSE_DATA.txt": {
      "sha256": "8e2c443dd9aea6fcd6c293dbf66935bd5ef502fc0ca9b466c773cf9316d5e04c",
      "size_bytes": 6966,
      "transformations": [
        "Copy the pinned upstream LICENSE.md byte-for-byte; only the local filename changes."
      ],
      "source_csv_sha256": null
    },
    "UPSTREAM_CITATION.txt": {
      "sha256": "5d408831f180a3cd1e4b5ca19f5614ebf3a59386650bcfd7c3b8fc4054dbdc01",
      "size_bytes": 638,
      "transformations": [
        "Copy the pinned upstream inst/CITATION byte-for-byte; only the local filename changes."
      ],
      "source_csv_sha256": null
    },
    "UPSTREAM_DESCRIPTION.txt": {
      "sha256": "71ffb68cb47285e2ea534da56b2e9af4532148542a063868c38646bd8c990a31",
      "size_bytes": 1454,
      "transformations": [
        "Copy the pinned upstream DESCRIPTION byte-for-byte; only the local filename changes."
      ],
      "source_csv_sha256": null
    },
    "source_retrieval.json": {
      "sha256": "1bdd45e16272dc68350dd6cbec4334e967536fb94ec4222ea88f5625c24dd036",
      "size_bytes": 1343,
      "transformations": [
        "Record the GitHub commit API response identifiers, retrieval timestamp, exact download URLs, and downloaded byte counts."
      ],
      "source_csv_sha256": null
    }
  },
  "created_with": {
    "python": "3.12.14",
    "csv_json_transformation": "Python standard-library csv and json; XLSX authored with bundled artifact-tool JavaScript library"
  },
  "prepared_by": {
    "name": "Dr. Ali Al Bataineh",
    "department": "Computer Information Science",
    "affiliation": "Higher Colleges of Technology, Ras Al Khaimah, United Arab Emirates",
    "github": "aalbata"
  }
}