{
  "builder_name": "parquet",
  "citation": "",
  "config_name": "default",
  "dataset_name": "astro_paper_corpus",
  "dataset_size": 4128813829,
  "description": "",
  "download_checksums": {
    "hf://datasets/JSALT2024-Astro-LLMs/astro_paper_corpus@b957a28700badb3b5f5c7af06ea77a2560ab6e46/data/train-00000-of-00009.parquet": {
      "num_bytes": 240072323,
      "checksum": null
    },
    "hf://datasets/JSALT2024-Astro-LLMs/astro_paper_corpus@b957a28700badb3b5f5c7af06ea77a2560ab6e46/data/train-00001-of-00009.parquet": {
      "num_bytes": 235851056,
      "checksum": null
    },
    "hf://datasets/JSALT2024-Astro-LLMs/astro_paper_corpus@b957a28700badb3b5f5c7af06ea77a2560ab6e46/data/train-00002-of-00009.parquet": {
      "num_bytes": 236413937,
      "checksum": null
    },
    "hf://datasets/JSALT2024-Astro-LLMs/astro_paper_corpus@b957a28700badb3b5f5c7af06ea77a2560ab6e46/data/train-00003-of-00009.parquet": {
      "num_bytes": 237728419,
      "checksum": null
    },
    "hf://datasets/JSALT2024-Astro-LLMs/astro_paper_corpus@b957a28700badb3b5f5c7af06ea77a2560ab6e46/data/train-00004-of-00009.parquet": {
      "num_bytes": 236710419,
      "checksum": null
    },
    "hf://datasets/JSALT2024-Astro-LLMs/astro_paper_corpus@b957a28700badb3b5f5c7af06ea77a2560ab6e46/data/train-00005-of-00009.parquet": {
      "num_bytes": 239567004,
      "checksum": null
    },
    "hf://datasets/JSALT2024-Astro-LLMs/astro_paper_corpus@b957a28700badb3b5f5c7af06ea77a2560ab6e46/data/train-00006-of-00009.parquet": {
      "num_bytes": 234863979,
      "checksum": null
    },
    "hf://datasets/JSALT2024-Astro-LLMs/astro_paper_corpus@b957a28700badb3b5f5c7af06ea77a2560ab6e46/data/train-00007-of-00009.parquet": {
      "num_bytes": 232662046,
      "checksum": null
    },
    "hf://datasets/JSALT2024-Astro-LLMs/astro_paper_corpus@b957a28700badb3b5f5c7af06ea77a2560ab6e46/data/train-00008-of-00009.parquet": {
      "num_bytes": 237444927,
      "checksum": null
    }
  },
  "download_size": 2131314110,
  "features": {
    "id": {
      "dtype": "string",
      "_type": "Value"
    },
    "author": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "bibcode": {
      "dtype": "string",
      "_type": "Value"
    },
    "title": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "citation_count": {
      "dtype": "int64",
      "_type": "Value"
    },
    "aff": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "citation": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "database": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "read_count": {
      "dtype": "int64",
      "_type": "Value"
    },
    "keyword": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "reference": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "doi": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "subfolder": {
      "dtype": "string",
      "_type": "Value"
    },
    "filename": {
      "dtype": "string",
      "_type": "Value"
    },
    "introduction": {
      "dtype": "string",
      "_type": "Value"
    },
    "conclusions": {
      "dtype": "string",
      "_type": "Value"
    },
    "year": {
      "dtype": "int64",
      "_type": "Value"
    },
    "month": {
      "dtype": "int64",
      "_type": "Value"
    },
    "arxiv_id": {
      "dtype": "string",
      "_type": "Value"
    },
    "abstract": {
      "dtype": "string",
      "_type": "Value"
    },
    "failed_ids": {
      "dtype": "bool",
      "_type": "Value"
    },
    "keyword_search": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "umap_x": {
      "dtype": "float32",
      "_type": "Value"
    },
    "umap_y": {
      "dtype": "float32",
      "_type": "Value"
    },
    "clust_id": {
      "dtype": "int64",
      "_type": "Value"
    }
  },
  "homepage": "",
  "license": "",
  "size_in_bytes": 6260127939,
  "splits": {
    "train": {
      "name": "train",
      "num_bytes": 4128813829,
      "num_examples": 271544,
      "shard_lengths": [
        33172,
        33172,
        33172,
        33172,
        33172,
        33171,
        34171,
        34171,
        4171
      ],
      "dataset_name": "astro_paper_corpus"
    }
  },
  "version": {
    "version_str": "0.0.0",
    "major": 0,
    "minor": 0,
    "patch": 0
  }
}