{
  "@context": {
    "@language": "en",
    "@vocab": "https://schema.org/",
    "arrayShape": "cr:arrayShape",
    "citeAs": "cr:citeAs",
    "column": "cr:column",
    "conformsTo": "dct:conformsTo",
    "cr": "http://mlcommons.org/croissant/",
    "data": {
      "@id": "cr:data",
      "@type": "@json"
    },
    "dataBiases": "cr:dataBiases",
    "dataCollection": "cr:dataCollection",
    "dataType": {
      "@id": "cr:dataType",
      "@type": "@vocab"
    },
    "dct": "http://purl.org/dc/terms/",
    "extract": "cr:extract",
    "field": "cr:field",
    "fileProperty": "cr:fileProperty",
    "fileObject": "cr:fileObject",
    "fileSet": "cr:fileSet",
    "format": "cr:format",
    "includes": "cr:includes",
    "isArray": "cr:isArray",
    "isLiveDataset": "cr:isLiveDataset",
    "jsonPath": "cr:jsonPath",
    "key": "cr:key",
    "md5": "cr:md5",
    "parentField": "cr:parentField",
    "path": "cr:path",
    "personalSensitiveInformation": "cr:personalSensitiveInformation",
    "recordSet": "cr:recordSet",
    "references": "cr:references",
    "regex": "cr:regex",
    "repeated": "cr:repeated",
    "replace": "cr:replace",
    "sc": "https://schema.org/",
    "separator": "cr:separator",
    "source": "cr:source",
    "subField": "cr:subField",
    "transform": "cr:transform"
  },
  "@type": "sc:Dataset",
  "distribution": [
    {
      "@type": "cr:FileObject",
      "@id": "repo",
      "name": "repo",
      "description": "The Hugging Face git repository.",
      "contentUrl": "https://huggingface.co/datasets/zilinlin/RFC2PSM/tree/refs%2Fconvert%2Fparquet",
      "encodingFormat": "git+https",
      "sha256": "https://github.com/mlcommons/croissant/issues/80"
    },
    {
      "@type": "cr:FileSet",
      "@id": "parquet-files-for-config-psms",
      "containedIn": {
        "@id": "repo"
      },
      "encodingFormat": "application/x-parquet",
      "includes": "psms/*/*.parquet"
    },
    {
      "@type": "cr:FileSet",
      "@id": "parquet-files-for-config-rfc_chunks",
      "containedIn": {
        "@id": "repo"
      },
      "encodingFormat": "application/x-parquet",
      "includes": "rfc_chunks/*/*.parquet"
    }
  ],
  "recordSet": [
    {
      "@type": "cr:RecordSet",
      "dataType": "cr:Split",
      "key": {
        "@id": "psms_splits/split_name"
      },
      "@id": "psms_splits",
      "name": "psms_splits",
      "description": "Splits for the psms config.",
      "field": [
        {
          "@type": "cr:Field",
          "@id": "psms_splits/split_name",
          "dataType": "sc:Text"
        }
      ],
      "data": [
        {
          "psms_splits/split_name": "default"
        }
      ]
    },
    {
      "@type": "cr:RecordSet",
      "@id": "psms",
      "description": "zilinlin/RFC2PSM - 'psms' subset",
      "field": [
        {
          "@type": "cr:Field",
          "@id": "psms/split",
          "dataType": "sc:Text",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-psms"
            },
            "extract": {
              "fileProperty": "fullpath"
            },
            "transform": {
              "regex": "psms/(?:partial-)?(default)/.+parquet$"
            }
          },
          "references": {
            "field": {
              "@id": "psms_splits/split_name"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "psms/states",
          "dataType": "sc:Text",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-psms"
            },
            "extract": {
              "column": "states"
            }
          },
          "isArray": true,
          "arrayShape": "-1"
        },
        {
          "@type": "cr:Field",
          "@id": "psms/initial_state",
          "dataType": "sc:Text",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-psms"
            },
            "extract": {
              "column": "initial_state"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "psms/final_states",
          "dataType": "sc:Text",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-psms"
            },
            "extract": {
              "column": "final_states"
            }
          },
          "isArray": true,
          "arrayShape": "-1"
        },
        {
          "@type": "cr:Field",
          "@id": "psms/transitions",
          "subField": [
            {
              "@type": "cr:Field",
              "@id": "psms/transitions/from",
              "dataType": "sc:Text",
              "source": {
                "fileSet": {
                  "@id": "parquet-files-for-config-psms"
                },
                "extract": {
                  "column": "transitions"
                },
                "transform": {
                  "jsonPath": "from"
                }
              }
            },
            {
              "@type": "cr:Field",
              "@id": "psms/transitions/to",
              "dataType": "sc:Text",
              "source": {
                "fileSet": {
                  "@id": "parquet-files-for-config-psms"
                },
                "extract": {
                  "column": "transitions"
                },
                "transform": {
                  "jsonPath": "to"
                }
              }
            },
            {
              "@type": "cr:Field",
              "@id": "psms/transitions/event",
              "dataType": "sc:Text",
              "source": {
                "fileSet": {
                  "@id": "parquet-files-for-config-psms"
                },
                "extract": {
                  "column": "transitions"
                },
                "transform": {
                  "jsonPath": "event"
                }
              }
            },
            {
              "@type": "cr:Field",
              "@id": "psms/transitions/action",
              "dataType": "sc:Text",
              "source": {
                "fileSet": {
                  "@id": "parquet-files-for-config-psms"
                },
                "extract": {
                  "column": "transitions"
                },
                "transform": {
                  "jsonPath": "action"
                }
              }
            }
          ],
          "isArray": true,
          "arrayShape": "-1"
        }
      ]
    },
    {
      "@type": "cr:RecordSet",
      "dataType": "cr:Split",
      "key": {
        "@id": "rfc_chunks_splits/split_name"
      },
      "@id": "rfc_chunks_splits",
      "name": "rfc_chunks_splits",
      "description": "Splits for the rfc_chunks config.",
      "field": [
        {
          "@type": "cr:Field",
          "@id": "rfc_chunks_splits/split_name",
          "dataType": "sc:Text"
        }
      ],
      "data": [
        {
          "rfc_chunks_splits/split_name": "default"
        }
      ]
    },
    {
      "@type": "cr:RecordSet",
      "@id": "rfc_chunks",
      "description": "zilinlin/RFC2PSM - 'rfc_chunks' subset",
      "field": [
        {
          "@type": "cr:Field",
          "@id": "rfc_chunks/split",
          "dataType": "sc:Text",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-rfc_chunks"
            },
            "extract": {
              "fileProperty": "fullpath"
            },
            "transform": {
              "regex": "rfc_chunks/(?:partial-)?(default)/.+parquet$"
            }
          },
          "references": {
            "field": {
              "@id": "rfc_chunks_splits/split_name"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "rfc_chunks/section_number",
          "dataType": "sc:Text",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-rfc_chunks"
            },
            "extract": {
              "column": "section_number"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "rfc_chunks/section_name",
          "dataType": "sc:Text",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-rfc_chunks"
            },
            "extract": {
              "column": "section_name"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "rfc_chunks/tag",
          "dataType": "sc:Text",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-rfc_chunks"
            },
            "extract": {
              "column": "tag"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "rfc_chunks/content",
          "dataType": "sc:Text",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-rfc_chunks"
            },
            "extract": {
              "column": "content"
            }
          }
        }
      ]
    }
  ],
  "conformsTo": "http://mlcommons.org/croissant/1.1",
  "name": "RFC2PSM",
  "description": "zilinlin/RFC2PSM dataset hosted on Hugging Face and contributed by the HF Datasets community",
  "alternateName": [
    "zilinlin/RFC2PSM"
  ],
  "creator": {
    "@type": "Person",
    "name": "Anonymous Random",
    "url": "https://huggingface.co/zilinlin"
  },
  "keywords": [
    "mit",
    "< 1K",
    "json",
    "Text",
    "Datasets",
    "Dask",
    "Croissant",
    "\ud83c\uddfa\ud83c\uddf8 Region: US"
  ],
  "license": "https://choosealicense.com/licenses/mit/",
  "url": "https://huggingface.co/datasets/zilinlin/RFC2PSM"
}