data/dataset_info.json

{
  "builder_name": "parquet",
  "citation": "",
  "config_name": "default",
  "dataset_name": "pathfinder_arxiv_data_galaxy",
  "dataset_size": 505886100,
  "description": "",
  "download_checksums": {
    "hf://datasets/kiyer/pathfinder_arxiv_data_galaxy@29754b03f3cd82e4051ece1cf96605f8756bc197/data/train-00000-of-00001.parquet": {
      "num_bytes": 379674094,
      "checksum": null
    }
  },
  "download_size": 379674094,
  "features": {
    "ads_id": {
      "dtype": "string",
      "_type": "Value"
    },
    "arxiv_id": {
      "dtype": "string",
      "_type": "Value"
    },
    "title": {
      "dtype": "string",
      "_type": "Value"
    },
    "abstract": {
      "dtype": "string",
      "_type": "Value"
    },
    "embed": {
      "feature": {
        "dtype": "float32",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "umap_x": {
      "dtype": "float32",
      "_type": "Value"
    },
    "umap_y": {
      "dtype": "float32",
      "_type": "Value"
    },
    "date": {
      "dtype": "date32",
      "_type": "Value"
    },
    "cites": {
      "dtype": "int64",
      "_type": "Value"
    },
    "bibcode": {
      "dtype": "string",
      "_type": "Value"
    },
    "keywords": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "ads_keywords": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "read_count": {
      "dtype": "int64",
      "_type": "Value"
    },
    "doi": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "authors": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "aff": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "cite_bibcodes": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "ref_bibcodes": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    }
  },
  "homepage": "",
  "license": "",
  "size_in_bytes": 885560194,
  "splits": {
    "train": {
      "name": "train",
      "num_bytes": 505886100,
      "num_examples": 41195,
      "shard_lengths": [
        41000,
        195
      ],
      "dataset_name": "pathfinder_arxiv_data_galaxy"
    }
  },
  "version": {
    "version_str": "0.0.0",
    "major": 0,
    "minor": 0,
    "patch": 0
  }
}