README.md

---
dataset_info:
  features:
  - name: image
    dtype: image
  - name: text
    dtype: string
  - name: label
    dtype:
      class_label:
        names:
          '0': non_sct
          '1': sct
  - name: doc_id
    dtype: string
  - name: year
    dtype: int64
  - name: company
    dtype: string
  splits:
  - name: train
    num_bytes: 1124059117
    num_examples: 11998
  - name: test
    num_bytes: 279927277
    num_examples: 3000
  download_size: 1255047427
  dataset_size: 1403986394
configs:
- config_name: default
  data_files:
  - split: train
    path: data/train-*
  - split: test
    path: data/test-*
---