{
  "@context": {
    "@language": "en",
    "cr": "http://mlcommons.org/croissant/",
    "schema": "http://schema.org/",
    "dct": "http://purl.org/dc/terms/",
    "xsd": "http://www.w3.org/2001/XMLSchema#",
    "@vocab": "http://mlcommons.org/croissant/",
    "name": "schema:name",
    "description": "schema:description",
    "version": "schema:version",
    "datePublished": {
      "@id": "schema:datePublished",
      "@type": "xsd:dateTime"
    },
    "license": {
      "@id": "schema:license",
      "@type": "@id"
    },
    "creator": "schema:creator",
    "recordCount": {
      "@id": "cr:recordCount",
      "@type": "xsd:integer"
    },
    "fileCount": {
      "@id": "cr:fileCount",
      "@type": "xsd:integer"
    },
    "distribution": "schema:distribution",
    "contentUrl": {
      "@id": "schema:contentUrl",
      "@type": "@id"
    },
    "encodingFormat": "schema:encodingFormat",
    "sha256": "cr:sha256"
  },
  "@id": "https://github.com/PaperAnalyticalDeviceND/pad_dataset_registry/tree/main/datasets/FHI360_Subset_PADFusion_v2.0",
  "@type": [
    "cr:Dataset",
    "schema:Dataset"
  ],
  "name": "FHI360_Subset_PADFusion_v2.0",
  "description": "CNN training corpus for the PaperAnalyticalDeviceND/model_fusion PAD + NIR multimodal fusion project. 503 PAD card images from 85 unique sample IDs covering four antibiotic APIs (Amoxicillin, Ciprofloxacin, Doxycycline, Isoniazid) at five concentration buckets (0, 20, 50, 80, 100 percent) plus a Cellulose zero-API control. Frozen 60/25/15 train/test/categorize split.",
  "version": "v2.0",
  "datePublished": "2026-06-07T18:04:48Z",
  "license": "https://www.apache.org/licenses/LICENSE-2.0",
  "creator": {
    "@type": "schema:Person",
    "name": "Mike, M., Sweet, C. (Lieberman Lab, University of Notre Dame)",
    "url": "https://github.com/PaperAnalyticalDeviceND"
  },
  "publisher": {
    "@type": "schema:Organization",
    "name": "PaperAnalyticalDeviceND",
    "url": "https://github.com/PaperAnalyticalDeviceND"
  },
  "url": "https://github.com/PaperAnalyticalDeviceND/pad_dataset_registry/tree/main/datasets/FHI360_Subset_PADFusion_v2.0",
  "isAccessibleForFree": true,
  "keywords": [
    "DATASET_NAME",
    "machine learning",
    "computer vision",
    "dataset"
  ],
  "citations": [],
  "distribution": [
    {
      "@type": [
        "cr:FileObject",
        "schema:MediaObject",
        "schema:DataDownload"
      ],
      "@id": "datasets/FHI360_Subset_PADFusion_v2.0/metadata_dev.csv",
      "name": "metadata_dev.csv",
      "description": "Train dataset for FHI360_Subset_PADFusion_v2.0",
      "contentUrl": "https://github.com/PaperAnalyticalDeviceND/pad_dataset_registry/raw/main/datasets/FHI360_Subset_PADFusion_v2.0/metadata_dev.csv",
      "encodingFormat": "text/csv",
      "sha256": "1c26efdb76136295fdecd9f5eb1d583b782d5e2b89f6c667bd499bdd7a493366",
      "dateModified": "2026-06-07T18:04:48Z",
      "contentSize": "60555 bytes",
      "inLanguage": "en"
    },
    {
      "@type": [
        "cr:FileObject",
        "schema:MediaObject",
        "schema:DataDownload"
      ],
      "@id": "datasets/FHI360_Subset_PADFusion_v2.0/metadata_test.csv",
      "name": "metadata_test.csv",
      "description": "Test dataset for FHI360_Subset_PADFusion_v2.0",
      "contentUrl": "https://github.com/PaperAnalyticalDeviceND/pad_dataset_registry/raw/main/datasets/FHI360_Subset_PADFusion_v2.0/metadata_test.csv",
      "encodingFormat": "text/csv",
      "sha256": "585d18db07f96d3f7b5a5c251e46ea6cd01770c1152867a914bf2debf25a29dd",
      "dateModified": "2026-06-07T18:04:48Z",
      "contentSize": "20551 bytes",
      "inLanguage": "en"
    },
    {
      "@type": [
        "cr:FileObject",
        "schema:MediaObject",
        "schema:DataDownload"
      ],
      "@id": "datasets/FHI360_Subset_PADFusion_v2.0/metadata_val.csv",
      "name": "metadata_val.csv",
      "description": "Validation dataset for FHI360_Subset_PADFusion_v2.0",
      "contentUrl": "https://github.com/PaperAnalyticalDeviceND/pad_dataset_registry/raw/main/datasets/FHI360_Subset_PADFusion_v2.0/metadata_val.csv",
      "encodingFormat": "text/csv",
      "sha256": "c079f95b5cdd38b4c21784c2f7d49b625436dd1389bf539657bfd4a0496e9e3b",
      "dateModified": "2026-06-07T18:04:48Z",
      "contentSize": "16632 bytes",
      "inLanguage": "en"
    }
  ],
  "recordCount": 503,
  "fileCount": 3,
  "temporalCoverage": "DATE",
  "datasetSchema": {
    "@type": "cr:TableSchema",
    "columns": [
      {
        "@type": "xsd:integer",
        "name": "id",
        "description": "Column: id",
        "dataType": "integer"
      },
      {
        "@type": "xsd:integer",
        "name": "sample_id",
        "description": "Column: sample_id",
        "dataType": "integer"
      },
      {
        "@type": "xsd:string",
        "name": "sample_name",
        "description": "Column: sample_name",
        "dataType": "string"
      },
      {
        "@type": "xsd:integer",
        "name": "quantity",
        "description": "Column: quantity",
        "dataType": "integer"
      },
      {
        "@type": "xsd:string",
        "name": "camera_type_1",
        "description": "Column: camera_type_1",
        "dataType": "string"
      },
      {
        "@type": "xsd:string",
        "name": "url",
        "description": "Column: url",
        "dataType": "string"
      },
      {
        "@type": "xsd:string",
        "name": "hashlib_md5",
        "description": "Column: hashlib_md5",
        "dataType": "string"
      },
      {
        "@type": "xsd:string",
        "name": "image_name",
        "description": "Column: image_name",
        "dataType": "string"
      }
    ]
  },
  "dataSplits": [
    {
      "@type": "cr:DataSplit",
      "name": "train",
      "description": "Training data split",
      "recordCount": 312,
      "splits": [
        {
          "@type": "schema:PropertyValue",
          "propertyID": "train",
          "value": "train"
        }
      ]
    },
    {
      "@type": "cr:DataSplit",
      "name": "validation",
      "description": "Validation data split",
      "recordCount": 85,
      "splits": [
        {
          "@type": "schema:PropertyValue",
          "propertyID": "validation",
          "value": "validation"
        }
      ]
    },
    {
      "@type": "cr:DataSplit",
      "name": "test",
      "description": "Test data split",
      "recordCount": 106,
      "splits": [
        {
          "@type": "schema:PropertyValue",
          "propertyID": "test",
          "value": "test"
        }
      ]
    }
  ]
}