René's URL Explorer Experiment

{
  "@context": {
    "@language": "en",
    "@vocab": "https:\/\/schema.org\/",
    "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",
    "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\/SALT-NLP\/Sketch2Code-hf\/tree\/refs%2Fconvert%2Fparquet",
      "encodingFormat": "git+https",
      "sha256": "https:\/\/github.com\/mlcommons\/croissant\/issues\/80"
    },
    {
      "@type": "cr:FileSet",
      "@id": "parquet-files-for-config-default",
      "name": "parquet-files-for-config-default",
      "description": "The underlying Parquet files as converted by Hugging Face (see: https:\/\/huggingface.co\/docs\/dataset-viewer\/parquet).",
      "containedIn": {
        "@id": "repo"
      },
      "encodingFormat": "application\/x-parquet",
      "includes": "default\/*\/*.parquet"
    }
  ],
  "recordSet": [
    {
      "@type": "cr:RecordSet",
      "dataType": "cr:Split",
      "key": {
        "@id": "default_splits\/split_name"
      },
      "@id": "default_splits",
      "name": "default_splits",
      "description": "Splits for the default config.",
      "field": [
        {
          "@type": "cr:Field",
          "@id": "default_splits\/split_name",
          "name": "split_name",
          "description": "The name of the split.",
          "dataType": "sc:Text"
        }
      ],
      "data": [
        {
          "default_splits\/split_name": "train"
        }
      ]
    },
    {
      "@type": "cr:RecordSet",
      "@id": "default",
      "name": "default",
      "description": "SALT-NLP\/Sketch2Code-hf - 'default' subset",
      "field": [
        {
          "@type": "cr:Field",
          "@id": "default\/split",
          "name": "default\/split",
          "description": "Split to which the example belongs to.",
          "dataType": "sc:Text",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-default"
            },
            "extract": {
              "fileProperty": "fullpath"
            },
            "transform": {
              "regex": "default\/(?:partial-)?(train)\/.+parquet$"
            }
          },
          "references": {
            "field": {
              "@id": "default_splits\/split_name"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "default\/id",
          "name": "default\/id",
          "description": "Column 'id' from the Hugging Face parquet file.",
          "dataType": "sc:Text",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-default"
            },
            "extract": {
              "column": "id"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "default\/sketch",
          "name": "default\/sketch",
          "description": "Image column 'sketch' from the Hugging Face parquet file.",
          "dataType": "sc:ImageObject",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-default"
            },
            "extract": {
              "column": "sketch"
            },
            "transform": {
              "jsonPath": "bytes"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "default\/source_html",
          "name": "default\/source_html",
          "description": "Column 'source_html' from the Hugging Face parquet file.",
          "dataType": "sc:Text",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-default"
            },
            "extract": {
              "column": "source_html"
            }
          }
        },
        {
          "@type": "cr:Field",
          "@id": "default\/source_screenshot",
          "name": "default\/source_screenshot",
          "description": "Image column 'source_screenshot' from the Hugging Face parquet file.",
          "dataType": "sc:ImageObject",
          "source": {
            "fileSet": {
              "@id": "parquet-files-for-config-default"
            },
            "extract": {
              "column": "source_screenshot"
            },
            "transform": {
              "jsonPath": "bytes"
            }
          }
        }
      ]
    }
  ],
  "conformsTo": "http:\/\/mlcommons.org\/croissant\/1.0",
  "name": "Sketch2Code-hf",
  "description": "The Sketch2Code dataset consists of 731 human-drawn sketches paired with 484 real-world webpages from the Design2Code dataset, serving to benchmark Vision-Language Models (VLMs) on converting rudimentary sketches into web design prototypes.\nSee the dataset in raw files here.\nNote that all images in these webpages are replaced by a blue placeholder image (rick.jpg).\nPlease refer to our Project Page for more detailed information.\n",
  "alternateName": [
    "SALT-NLP\/Sketch2Code-hf"
  ],
  "creator": {
    "@type": "Organization",
    "name": "Social And Language Technology Lab",
    "url": "https:\/\/huggingface.co\/SALT-NLP"
  },
  "keywords": [
    "\u003c 1K",
    "parquet",
    "Image",
    "Text",
    "Datasets",
    "pandas",
    "Croissant",
    "Polars",
    "🇺🇸 Region: US"
  ],
  "url": "https:\/\/huggingface.co\/datasets\/SALT-NLP\/Sketch2Code-hf"
}