{
 "noul_agnews": {
  "n": 2000,
  "accuracy": 63.15,
  "ece": 0.081,
  "p50_ms": 507.9,
  "p95_ms": 697.3
 },
 "noul_imdb": {
  "n": 1000,
  "with_criteria": {
   "accuracy": 90.9,
   "ece": 0.037
  },
  "instructions_only": {
   "accuracy": 48.6,
   "ece": 0.081
  },
  "p50_ms": 1687.7,
  "p95_ms": 2727.8
 },
 "noul_sst2": {
  "n": 1821,
  "with_criteria": {
   "accuracy": 84.9,
   "ece": 0.031
  },
  "instructions_only": {
   "accuracy": 51.24,
   "ece": 0.058
  },
  "p50_ms": 199.9,
  "p95_ms": 410.1
 },
 "score_sst5": {
  "n": 2210,
  "accuracy": 33.57,
  "within_one": 85.16,
  "mae_expected_position": 0.79,
  "ece": 0.08,
  "p50_ms": 367.4,
  "p95_ms": 471.4
 },
 "score_yelp": {
  "n": 1000,
  "accuracy": 45.4,
  "within_one": 89.7,
  "mae_expected_position": 0.752,
  "ece": 0.091,
  "p50_ms": 1124.2,
  "p95_ms": 2273.9
 },
 "examples_banking77_k1": {
  "n": 3080,
  "examples_per_option": 1,
  "accuracy": 82.11,
  "ece": 0.017,
  "p50_ms": 168.2,
  "p95_ms": 240.9
 },
 "examples_banking77_k3": {
  "n": 3080,
  "examples_per_option": 3,
  "accuracy": 85.13,
  "ece": 0.013,
  "p50_ms": 175.3,
  "p95_ms": 238.2
 },
 "examples_banking77_k5": {
  "n": 3080,
  "examples_per_option": 5,
  "accuracy": 85.71,
  "ece": 0.015,
  "p50_ms": 187.5,
  "p95_ms": 252.4
 }
}