Blame for training/data/overlap-summary.json

{
 "training_questions": 10000,
 "organiser_questions": {
  "dev=data/dev-set": 1851,
  "test=data/test-set": 2238,
  "test-old=../Dataset/Test": 2146
 },
 "excluded": 1106,
 "excluded_by_rule": {
  "same question": 0,
  "question jaccard >= 0.5": 17,
  "question containment >= 0.8": 48,
  "3+ same choices and containment >= 0.3": 11,
  "all 4 choices the same": 43,
  "meaning cosine >= 0.70": 1033
 },
 "nearest_cosine_percentiles": {
  "50": 0.598,
  "90": 0.702,
  "99": 0.805,
  "99.9": 0.899
 },
 "reported_below_threshold": 1598
}