croissant_metadata.json

{
  "@type": "sc:Dataset",
  "name": "CiteME",
  "description": "This dataset contains excerpts from academic papers, along with titles of papers cited in these excerpts.",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "url": "N/A",
  "distribution": [
    {
      "@type": "cr:FileObject",
      "@id": "DATASET.csv",
      "name": "DATASET.csv",
      "contentUrl": "DATASET.csv",
      "encodingFormat": "text/csv",
      "sha256": "30a1f945f1ed0ad6192934fd914a70053397428f347e931901496a00194f1959"
    }
  ],
  "recordSet": [
    {
      "@type": "cr:RecordSet",
      "name": "Citations",
      "description": "Records of citations with their schema.",
      "field": [
        {
          "@type": "cr:Field",
          "name": "excerpt",
          "description": "Text excerpt from the source paper.",
          "dataType": "sc:Text",
          "references": {
            "fileObject": { "@id": "DATASET.csv" },
            "extract": {
              "column": "excerpt"
            }
          }
        },
        {
          "@type": "cr:Field",
          "name": "source_paper_title",
          "description": "Title of the paper the excerpt came from.",
          "dataType": "sc:Text",
          "references": {
            "fileObject": { "@id": "DATASET.csv" },
            "extract": {
              "column": "source_paper_title"
            }
          }
        },
        {
          "@type": "cr:Field",
          "name": "source_paper_url",
          "description": "URL of the paper the excerpt came from.",
          "dataType": "sc:URL",
          "references": {
            "fileObject": { "@id": "DATASET.csv" },
            "extract": {
              "column": "source_paper_url"
            }
          }
        },
        {
          "@type": "cr:Field",
          "name": "target_paper_title",
          "description": "Title of the paper the excerpt cites.",
          "dataType": "sc:Text",
          "references": {
            "fileObject": { "@id": "DATASET.csv" },
            "extract": {
              "column": "target_paper_title"
            }
          }
        },
        {
          "@type": "cr:Field",
          "name": "target_paper_url",
          "description": "URL of the paper the excerpt cites.",
          "dataType": "sc:URL",
          "references": {
            "fileObject": { "@id": "DATASET.csv" },
            "extract": {
              "column": "target_paper_url"
            }
          }
        },
        {
          "@type": "cr:Field",
          "name": "year",
          "description": "Publish year of the source paper.",
          "dataType": "sc:Integer",
          "references": {
            "fileObject": { "@id": "DATASET.csv" },
            "extract": {
              "column": "year"
            }
          }
        },
        {
          "@type": "cr:Field",
          "name": "split",
          "description": "Dataset split (train or test).",
          "dataType": "sc:Text",
          "references": {
            "fileObject": { "@id": "DATASET.csv" },
            "extract": {
              "column": "split"
            }
          }
        }
      ]
    }
  ]
}