group: cabbq
task:
  - cabbq_age
  - cabbq_disability_status
  - cabbq_gender
  - cabbq_lgbtqia
  - cabbq_nationality
  - cabbq_physical_appearance
  - cabbq_race_ethnicity
  - cabbq_religion
  - cabbq_ses
  - cabbq_spanish_region
tag:
  - social_bias
aggregate_metric_list:
  - metric: "acc_ambig"
    weight_by_size: true
  - metric: "acc_disambig"
    weight_by_size: true
  - metric: "bias_score_ambig"
    weight_by_size: true
  - metric: "bias_score_disambig"
    weight_by_size: true

  # `weight_by_size`:
  # `true` for micro average: retain all subtasks' per-document results and take the mean over all documents' scores to get the aggregate mean
  # `false` for macro average: take the mean of the subtasks' aggregated results