README.md

metadata

dataset_info:
  features:
    - name: contestId
      dtype: int64
    - name: index
      dtype: string
    - name: name
      dtype: string
    - name: type
      dtype: string
    - name: rating
      dtype: int64
    - name: tags
      sequence: string
    - name: title
      dtype: string
    - name: time-limit
      dtype: string
    - name: memory-limit
      dtype: string
    - name: problem-description
      dtype: string
    - name: input-specification
      dtype: string
    - name: output-specification
      dtype: string
    - name: demo-input
      sequence: string
    - name: demo-output
      sequence: string
    - name: note
      dtype: string
    - name: points
      dtype: float64
    - name: test_cases
      list:
        - name: input
          dtype: string
        - name: output
          dtype: string
    - name: creationTimeSeconds
      dtype: int64
    - name: relativeTimeSeconds
      dtype: int64
    - name: programmingLanguage
      dtype: string
    - name: verdict
      dtype: string
    - name: testset
      dtype: string
    - name: passedTestCount
      dtype: int64
    - name: timeConsumedMillis
      dtype: int64
    - name: memoryConsumedBytes
      dtype: int64
    - name: code
      dtype: string
    - name: instruction_seed
      dtype: string
    - name: response
      dtype: string
    - name: score
      dtype: float64
    - name: reasoning
      dtype: string
    - name: deepseek_solution
      dtype: string
    - name: __original_row_idx
      dtype: int64
    - name: source
      dtype: string
    - name: final_reasoning_trace
      dtype: string
    - name: conversations
      list:
        - name: from
          dtype: string
        - name: value
          dtype: string
  splits:
    - name: train
      num_bytes: 2002788032
      num_examples: 31600
  download_size: 838913540
  dataset_size: 2002788032
configs:
  - config_name: default
    data_files:
      - split: train
        path: data/train-*