{
  "schema": "aner.dataset-assets/1",
  "retrieved_on": "2026-10-10",
  "hash_algorithm": "SHA-256",
  "path_base": "datasets/",
  "asset_policy": "Checked-in upstream bytes; no network download during build or execution.",
  "datasets": [
    {
      "id": "iris",
      "name": "Iris",
      "uci_repository_id": 53,
      "version": "uci-iris.data-sha256-6f608b71a731",
      "homepage": "https://archive.ics.uci.edu/dataset/53/iris",
      "doi": "10.24432/C56C76",
      "citation": "Fisher, R. (1936). Iris [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C56C76.",
      "creators": [
        "R. A. Fisher"
      ],
      "attribution_additional": [
        "Michael Marshall (donor recorded in iris.names)"
      ],
      "license": {
        "spdx": "CC-BY-4.0",
        "name": "Creative Commons Attribution 4.0 International",
        "url": "https://creativecommons.org/licenses/by/4.0/",
        "legal_code_url": "https://creativecommons.org/licenses/by/4.0/legalcode.en",
        "bundled_text": "licenses/CC-BY-4.0.txt",
        "verified_on": "2026-10-10",
        "evidence_url": "https://archive.ics.uci.edu/dataset/53/iris"
      },
      "task": "classification",
      "rows": 150,
      "feature_count": 4,
      "class_count": 3,
      "source_data": "iris/iris.data",
      "source_sha256": "6f608b71a7317216319b4d27b4d9bc84e6abd734eda7872b71a458569e2656c0",
      "source_format": {
        "encoding": "ASCII (UTF-8 compatible)",
        "delimiter": ",",
        "header": false,
        "column_index_base": 0,
        "label_column": 4,
        "blank_lines": "Trailing blank lines are not observations.",
        "row_order": "Unchanged UCI source order; grouped by class."
      },
      "features": [
        {
          "index": 0,
          "name": "sepal_length",
          "source_name": "sepal length",
          "source_column": 0,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": "cm",
          "unit_status": "provided_by_upstream",
          "missing_values": 0
        },
        {
          "index": 1,
          "name": "sepal_width",
          "source_name": "sepal width",
          "source_column": 1,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": "cm",
          "unit_status": "provided_by_upstream",
          "missing_values": 0
        },
        {
          "index": 2,
          "name": "petal_length",
          "source_name": "petal length",
          "source_column": 2,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": "cm",
          "unit_status": "provided_by_upstream",
          "missing_values": 0
        },
        {
          "index": 3,
          "name": "petal_width",
          "source_name": "petal width",
          "source_column": 3,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": "cm",
          "unit_status": "provided_by_upstream",
          "missing_values": 0
        }
      ],
      "labels": [
        {
          "index": 0,
          "source_value": "Iris-setosa",
          "name": "Iris-setosa",
          "count": 50
        },
        {
          "index": 1,
          "source_value": "Iris-versicolor",
          "name": "Iris-versicolor",
          "count": 50
        },
        {
          "index": 2,
          "source_value": "Iris-virginica",
          "name": "Iris-virginica",
          "count": 50
        }
      ],
      "missing_values": 0,
      "nonfinite_feature_values": 0,
      "distinct_complete_records": 147,
      "duplicate_complete_record_groups_1_based": [
        [
          10,
          35,
          38
        ],
        [
          102,
          143
        ]
      ],
      "variant_policy": "Use original UCI iris.data unchanged. The official alternate bezdekIris.data is retained for provenance only and is not embedded by the loader.",
      "documented_discrepancies": [
        {
          "source_row_1_based": 35,
          "source_row_id_zero_based": 34,
          "original_record": "4.9,3.1,1.5,0.1,Iris-setosa",
          "uci_documented_correction": "4.9,3.1,1.5,0.2,Iris-setosa",
          "applied": false
        },
        {
          "source_row_1_based": 38,
          "source_row_id_zero_based": 37,
          "original_record": "4.9,3.1,1.5,0.1,Iris-setosa",
          "uci_documented_correction": "4.9,3.6,1.4,0.1,Iris-setosa",
          "applied": false
        }
      ],
      "runtime_representation_changes": [
        "Decimal features parsed as Float64.",
        "Source labels encoded using the zero-based mapping above.",
        "Original row IDs are zero-based positions among nonblank source records.",
        "No observations corrected, removed, imputed, rescaled, or reordered by the raw loader."
      ],
      "limitations": [
        "Small historical teaching dataset, not evidence of large-data or medical-model performance.",
        "Records contain no stable specimen identifier or official train/test assignment.",
        "Identical records are retained; ordinary row splitting is not content deduplication.",
        "Repeated benchmark use and tuning on held-out rows can bias evaluation."
      ],
      "files": [
        {
          "path": "iris/iris.zip",
          "role": "official_archive",
          "bytes": 3738,
          "sha256": "d11fe30213d36434a0879aab7cb00ce3c812eb7ba2495874438abff7b7b762e9",
          "source_url": "https://archive.ics.uci.edu/static/public/53/iris.zip",
          "changes": "None; upstream bytes preserved."
        },
        {
          "path": "iris/iris.data",
          "role": "runtime_source",
          "bytes": 4551,
          "sha256": "6f608b71a7317216319b4d27b4d9bc84e6abd734eda7872b71a458569e2656c0",
          "source_url": "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data",
          "changes": "None; upstream bytes preserved.",
          "extracted_from": "iris/iris.zip"
        },
        {
          "path": "iris/bezdekIris.data",
          "role": "upstream_alternate_not_loaded",
          "bytes": 4551,
          "sha256": "0fed2a99db77ec533a62dc66894d3ec6df3b58b6a8f3cf4a6b47e4086b7f97dc",
          "source_url": "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/bezdekIris.data",
          "changes": "None; upstream bytes preserved.",
          "extracted_from": "iris/iris.zip"
        },
        {
          "path": "iris/iris.names",
          "role": "upstream_metadata",
          "bytes": 2998,
          "sha256": "71a09fb3ee237614cdb9c09d06e8ae1f610ce2a274c0d77272fea8a233e5eea3",
          "source_url": "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.names",
          "changes": "None; upstream bytes preserved.",
          "extracted_from": "iris/iris.zip"
        },
        {
          "path": "iris/Index",
          "role": "upstream_index",
          "bytes": 105,
          "sha256": "fc3a4464fd2138ca649be5e0311270f5cf1f045c8e3ff1cd458f663dfe4f6790",
          "source_url": "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/Index",
          "changes": "None; upstream bytes preserved.",
          "extracted_from": "iris/iris.zip"
        }
      ]
    },
    {
      "id": "wine",
      "name": "Wine",
      "uci_repository_id": 109,
      "version": "uci-wine.data-sha256-6be6b1203f3d",
      "homepage": "https://archive.ics.uci.edu/dataset/109/wine",
      "doi": "10.24432/C5PC7J",
      "citation": "Aeberhard, S. & Forina, M. (1992). Wine [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C5PC7J.",
      "creators": [
        "Stefan Aeberhard",
        "M. Forina"
      ],
      "attribution_additional": [
        "Forina, M. et al., PARVUS, Institute of Pharmaceutical and Food Analysis and Technologies, Genoa, Italy (source recorded in wine.names).",
        "Riccardo Leardi (attribute information credited in wine.names)."
      ],
      "license": {
        "spdx": "CC-BY-4.0",
        "name": "Creative Commons Attribution 4.0 International",
        "url": "https://creativecommons.org/licenses/by/4.0/",
        "legal_code_url": "https://creativecommons.org/licenses/by/4.0/legalcode.en",
        "bundled_text": "licenses/CC-BY-4.0.txt",
        "verified_on": "2026-10-10",
        "evidence_url": "https://archive.ics.uci.edu/dataset/109/wine"
      },
      "task": "classification",
      "rows": 178,
      "feature_count": 13,
      "class_count": 3,
      "source_data": "wine/wine.data",
      "source_sha256": "6be6b1203f3d51df0b553a70e57b8a723cd405683958204f96d23d7cd6aea659",
      "source_format": {
        "encoding": "ASCII (UTF-8 compatible)",
        "delimiter": ",",
        "header": false,
        "column_index_base": 0,
        "label_column": 0,
        "blank_lines": "No blank observation records.",
        "row_order": "Unchanged UCI source order; grouped by class.",
        "numeric_notes": "Some decimal fields omit a leading zero, e.g. .28; these are data fields, not Aner source literals."
      },
      "features": [
        {
          "index": 0,
          "name": "alcohol",
          "source_name": "Alcohol",
          "source_column": 1,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": null,
          "unit_status": "not_supplied_by_upstream",
          "aner_unit_text": "unknown",
          "missing_values": 0
        },
        {
          "index": 1,
          "name": "malic_acid",
          "source_name": "Malic acid",
          "source_column": 2,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": null,
          "unit_status": "not_supplied_by_upstream",
          "aner_unit_text": "unknown",
          "missing_values": 0
        },
        {
          "index": 2,
          "name": "ash",
          "source_name": "Ash",
          "source_column": 3,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": null,
          "unit_status": "not_supplied_by_upstream",
          "aner_unit_text": "unknown",
          "missing_values": 0
        },
        {
          "index": 3,
          "name": "alcalinity_of_ash",
          "source_name": "Alcalinity of ash",
          "source_column": 4,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": null,
          "unit_status": "not_supplied_by_upstream",
          "aner_unit_text": "unknown",
          "missing_values": 0
        },
        {
          "index": 4,
          "name": "magnesium",
          "source_name": "Magnesium",
          "source_column": 5,
          "source_type": "Integer (current UCI variable metadata)",
          "aner_type": "Float64",
          "unit": null,
          "unit_status": "not_supplied_by_upstream",
          "aner_unit_text": "unknown",
          "missing_values": 0
        },
        {
          "index": 5,
          "name": "total_phenols",
          "source_name": "Total phenols",
          "source_column": 6,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": null,
          "unit_status": "not_supplied_by_upstream",
          "aner_unit_text": "unknown",
          "missing_values": 0
        },
        {
          "index": 6,
          "name": "flavanoids",
          "source_name": "Flavanoids",
          "source_column": 7,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": null,
          "unit_status": "not_supplied_by_upstream",
          "aner_unit_text": "unknown",
          "missing_values": 0
        },
        {
          "index": 7,
          "name": "nonflavanoid_phenols",
          "source_name": "Nonflavanoid phenols",
          "source_column": 8,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": null,
          "unit_status": "not_supplied_by_upstream",
          "aner_unit_text": "unknown",
          "missing_values": 0
        },
        {
          "index": 8,
          "name": "proanthocyanins",
          "source_name": "Proanthocyanins",
          "source_column": 9,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": null,
          "unit_status": "not_supplied_by_upstream",
          "aner_unit_text": "unknown",
          "missing_values": 0
        },
        {
          "index": 9,
          "name": "color_intensity",
          "source_name": "Color intensity",
          "source_column": 10,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": null,
          "unit_status": "not_supplied_by_upstream",
          "aner_unit_text": "unknown",
          "missing_values": 0
        },
        {
          "index": 10,
          "name": "hue",
          "source_name": "Hue",
          "source_column": 11,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": null,
          "unit_status": "not_supplied_by_upstream",
          "aner_unit_text": "unknown",
          "missing_values": 0
        },
        {
          "index": 11,
          "name": "od280_od315_of_diluted_wines",
          "source_name": "OD280/OD315 of diluted wines",
          "source_column": 12,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": null,
          "unit_status": "not_supplied_by_upstream",
          "aner_unit_text": "unknown",
          "missing_values": 0
        },
        {
          "index": 12,
          "name": "proline",
          "source_name": "Proline",
          "source_column": 13,
          "source_type": "Continuous",
          "aner_type": "Float64",
          "unit": null,
          "unit_status": "not_supplied_by_upstream",
          "aner_unit_text": "unknown",
          "missing_values": 0
        }
      ],
      "labels": [
        {
          "index": 0,
          "source_value": "1",
          "name": "class_1",
          "count": 59,
          "cultivar_name": null
        },
        {
          "index": 1,
          "source_value": "2",
          "name": "class_2",
          "count": 71,
          "cultivar_name": null
        },
        {
          "index": 2,
          "source_value": "3",
          "name": "class_3",
          "count": 48,
          "cultivar_name": null
        }
      ],
      "missing_values": 0,
      "nonfinite_feature_values": 0,
      "distinct_complete_records": 178,
      "duplicate_complete_record_groups_1_based": [],
      "variant_policy": "Use original UCI wine.data unchanged. This is the three-cultivar Wine recognition dataset, not Wine Quality.",
      "runtime_representation_changes": [
        "Decimal features parsed as Float64, including integer-valued measurements.",
        "Source class codes 1/2/3 encoded as zero-based 0/1/2.",
        "Original row IDs are zero-based positions among source records.",
        "No observations corrected, removed, imputed, rescaled, or reordered by the raw loader."
      ],
      "limitations": [
        "Small historical dataset from one Italian region and three cultivars.",
        "Official supplied metadata does not identify measurement units or cultivar names.",
        "This task identifies cultivar class; it does not predict a wine quality score.",
        "No official train/test split is supplied; differently scaled measurements require deliberate preprocessing."
      ],
      "files": [
        {
          "path": "wine/wine.zip",
          "role": "official_archive",
          "bytes": 6038,
          "sha256": "2bae62c4481220623579d4c4fb36b55652b6b75e06e49fa1981b8198362dfdab",
          "source_url": "https://archive.ics.uci.edu/static/public/109/wine.zip",
          "changes": "None; upstream bytes preserved."
        },
        {
          "path": "wine/wine.data",
          "role": "runtime_source",
          "bytes": 10782,
          "sha256": "6be6b1203f3d51df0b553a70e57b8a723cd405683958204f96d23d7cd6aea659",
          "source_url": "https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data",
          "changes": "None; upstream bytes preserved.",
          "extracted_from": "wine/wine.zip"
        },
        {
          "path": "wine/wine.names",
          "role": "upstream_metadata",
          "bytes": 3036,
          "sha256": "f1b84f2ef845e0bdebf13e14fa7a213e56de4f1baa40c5974dbd1ee51c5ae710",
          "source_url": "https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.names",
          "changes": "None; upstream bytes preserved.",
          "extracted_from": "wine/wine.zip"
        },
        {
          "path": "wine/Index",
          "role": "upstream_index",
          "bytes": 105,
          "sha256": "c24d1f17df97bdde234913bb0a3334227215eefd0ad3d6a9988151d49971cba7",
          "source_url": "https://archive.ics.uci.edu/ml/machine-learning-databases/wine/Index",
          "changes": "None; upstream bytes preserved.",
          "extracted_from": "wine/wine.zip"
        }
      ]
    }
  ],
  "shared_assets": [
    {
      "path": "licenses/CC-BY-4.0.txt",
      "role": "official_unmodified_license_text",
      "bytes": 18657,
      "sha256": "9ba9550ad48438d0836ddab3da480b3b69ffa0aac7b7878b5a0039e7ab429411",
      "source_url": "https://creativecommons.org/licenses/by/4.0/legalcode.txt",
      "changes": "None; upstream bytes preserved.",
      "text_copyright_status": "CC0 according to Creative Commons legal-tool text policy.",
      "text_copyright_policy": "https://creativecommons.org/policies/#license"
    }
  ]
}