{
 "schema": "five-seat-fairness-basket-v1",
 "reference": "all_llm",
 "arms": [
  "all_llm",
  "all_rational",
  "one_rational",
  "rational_advised_llm",
  "interpreter_advised_llm",
  "all_interpreter_advised_llm",
  "one_oracle",
  "all_oracle"
 ],
 "per_party_surplus_among_deals": {
  "all_llm": {
   "n_episodes": 120,
   "n_deals": 115,
   "deal_rate": 0.9583333333333334,
   "pooling": "party-observations (5 per closed deal), clustered on instance",
   "per_party_z": {
    "mean": 0.652856953489687,
    "ci_low": 0.6194737839430522,
    "ci_high": 0.6909508446902267,
    "q1": 0.4333333333,
    "median": 0.6666666667,
    "q3": 1.0,
    "n_party_obs": 575
   },
   "episode_score": {
    "mean": 0.9105530434782609,
    "q1": 0.8383,
    "median": 0.9455,
    "q3": 1.0
   }
  },
  "all_rational": {
   "n_episodes": 120,
   "n_deals": 28,
   "deal_rate": 0.23333333333333334,
   "pooling": "party-observations (5 per closed deal), clustered on instance",
   "per_party_z": {
    "mean": 0.5541257617509286,
    "ci_low": 0.512240844589861,
    "ci_high": 0.6105279093181888,
    "q1": 0.32918806162500003,
    "median": 0.56740442655,
    "q3": 0.7625,
    "n_party_obs": 140
   },
   "episode_score": {
    "mean": 0.8093928571428572,
    "q1": 0.6987000000000001,
    "median": 0.83005,
    "q3": 0.9216
   }
  },
  "one_rational": {
   "n_episodes": 120,
   "n_deals": 92,
   "deal_rate": 0.7666666666666667,
   "pooling": "party-observations (5 per closed deal), clustered on instance",
   "per_party_z": {
    "mean": 0.6386387048911086,
    "ci_low": 0.6057347615139881,
    "ci_high": 0.6746276167716206,
    "q1": 0.430555555525,
    "median": 0.6565335753,
    "q3": 1.0,
    "n_party_obs": 460
   },
   "episode_score": {
    "mean": 0.8953380434782608,
    "q1": 0.8252,
    "median": 0.9314,
    "q3": 1.0
   }
  },
  "rational_advised_llm": {
   "n_episodes": 120,
   "n_deals": 108,
   "deal_rate": 0.9,
   "pooling": "party-observations (5 per closed deal), clustered on instance",
   "per_party_z": {
    "mean": 0.6456315339927222,
    "ci_low": 0.615720378795596,
    "ci_high": 0.6777549933879805,
    "q1": 0.4137931034,
    "median": 0.6666666667,
    "q3": 1.0,
    "n_party_obs": 540
   },
   "episode_score": {
    "mean": 0.901649074074074,
    "q1": 0.8216,
    "median": 0.9254,
    "q3": 1.0
   }
  },
  "interpreter_advised_llm": {
   "n_episodes": 120,
   "n_deals": 115,
   "deal_rate": 0.9583333333333334,
   "pooling": "party-observations (5 per closed deal), clustered on instance",
   "per_party_z": {
    "mean": 0.6561403796638609,
    "ci_low": 0.6243597664578375,
    "ci_high": 0.6906941251094975,
    "q1": 0.4428571429,
    "median": 0.6666666667,
    "q3": 1.0,
    "n_party_obs": 575
   },
   "episode_score": {
    "mean": 0.919126956521739,
    "q1": 0.8443,
    "median": 0.9608,
    "q3": 1.0
   }
  },
  "all_interpreter_advised_llm": {
   "n_episodes": 120,
   "n_deals": 118,
   "deal_rate": 0.9833333333333333,
   "pooling": "party-observations (5 per closed deal), clustered on instance",
   "per_party_z": {
    "mean": 0.6521411776630339,
    "ci_low": 0.6213298443974077,
    "ci_high": 0.6857030786284783,
    "q1": 0.4137931034,
    "median": 0.6666666667,
    "q3": 1.0,
    "n_party_obs": 590
   },
   "episode_score": {
    "mean": 0.9143161016949153,
    "q1": 0.8395,
    "median": 0.96075,
    "q3": 1.0
   }
  },
  "one_oracle": {
   "n_episodes": 120,
   "n_deals": 110,
   "deal_rate": 0.9166666666666666,
   "pooling": "party-observations (5 per closed deal), clustered on instance",
   "per_party_z": {
    "mean": 0.6487857962817273,
    "ci_low": 0.612154481239137,
    "ci_high": 0.6888368376353592,
    "q1": 0.341177734775,
    "median": 0.6868872549,
    "q3": 1.0,
    "n_party_obs": 550
   },
   "episode_score": {
    "mean": 0.9042145454545453,
    "q1": 0.829375,
    "median": 0.9614499999999999,
    "q3": 1.0
   }
  },
  "all_oracle": {
   "n_episodes": 120,
   "n_deals": 120,
   "deal_rate": 1.0,
   "pooling": "party-observations (5 per closed deal), clustered on instance",
   "per_party_z": {
    "mean": 0.6447808151705168,
    "ci_low": 0.6122447502957984,
    "ci_high": 0.6815410258026775,
    "q1": 0.3103448276,
    "median": 0.6835443038,
    "q3": 1.0,
    "n_party_obs": 600
   },
   "episode_score": {
    "mean": 0.9068575,
    "q1": 0.842525,
    "median": 0.9816,
    "q3": 1.0
   }
  }
 },
 "n_bootstrap": 10000,
 "seed": 20260824,
 "n_episodes": {
  "all_llm": 120,
  "all_rational": 120,
  "one_rational": 120,
  "rational_advised_llm": 120,
  "interpreter_advised_llm": 120,
  "all_interpreter_advised_llm": 120,
  "one_oracle": 120,
  "all_oracle": 120
 },
 "n_deals": {
  "all_llm": 115,
  "all_rational": 28,
  "one_rational": 92,
  "rational_advised_llm": 108,
  "interpreter_advised_llm": 115,
  "all_interpreter_advised_llm": 118,
  "one_oracle": 110,
  "all_oracle": 120
 },
 "levels": {
  "all_llm": {
   "deal_rate": {
    "estimate": 0.9583333333333334,
    "ci_low": 0.925,
    "ci_high": 0.9916666666666667,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 115,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": 0.25662751078488905,
    "ci_low": 0.20647131522543383,
    "ci_high": 0.30581686009649894,
    "n": 115,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.07733378037747124,
    "ci_low": 0.06367860083980352,
    "ci_high": 0.08957946963856718,
    "n": 115,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.46360609046022655,
    "ci_low": 0.3574667392058307,
    "ci_high": 0.5861901303915932,
    "n": 115,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.39841757139287376,
    "ci_low": 0.3160269019249567,
    "ci_high": 0.4744810850874367,
    "n": 115,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.22312596428528939,
    "ci_low": 0.1998923309145434,
    "ci_high": 0.24702770127223717,
    "n": 115,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.5347356494115132,
    "ci_low": 0.45798930358909373,
    "ci_high": 0.6007384931612882,
    "n": 115,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.29899227726399724,
    "ci_low": 0.28719264540776496,
    "ci_high": 0.30928173363195055,
    "n": 115,
    "n_instances": 24
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": 0.8726133333333334,
    "ci_low": 0.8327463958333333,
    "ci_high": 0.91008175,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.5124549973527001,
    "ci_low": 0.42948479476814927,
    "ci_high": 0.5854649244106662,
    "n": 120,
    "n_instances": 24
   },
   "justified_walk": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 5,
    "n_instances": 5
   },
   "missed_deal": {
    "estimate": 1.0,
    "ci_low": 1.0,
    "ci_high": 1.0,
    "n": 5,
    "n_instances": 5
   },
   "ir_margin_of_no_deal": {
    "estimate": 0.2305128205128205,
    "ci_low": 0.05384615384615384,
    "ci_high": 0.40717948717948715,
    "n": 5,
    "n_instances": 5
   }
  },
  "all_rational": {
   "deal_rate": {
    "estimate": 0.23333333333333334,
    "ci_low": 0.13333333333333333,
    "ci_high": 0.3416666666666667,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 28,
    "n_instances": 14
   },
   "worst_off": {
    "estimate": 0.14694344596801961,
    "ci_low": 0.10305227396993474,
    "ci_high": 0.19566363654955463,
    "n": 28,
    "n_instances": 14
   },
   "worst_off_share": {
    "estimate": 0.05224324367491081,
    "ci_low": 0.03735657573610186,
    "ci_high": 0.06771473683288161,
    "n": 28,
    "n_instances": 14
   },
   "dist_to_nbs": {
    "estimate": 0.5995994212802717,
    "ci_low": 0.49830048189447707,
    "ci_high": 0.680616771073002,
    "n": 28,
    "n_instances": 14
   },
   "dist_to_ks": {
    "estimate": 0.5897606666492755,
    "ci_low": 0.5196553492022289,
    "ci_high": 0.6494641899634368,
    "n": 28,
    "n_instances": 14
   },
   "normalized_gini": {
    "estimate": 0.2606935627315637,
    "ci_low": 0.23831982298443363,
    "ci_high": 0.28262414494892973,
    "n": 28,
    "n_instances": 14
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.40783781598662144,
    "ci_low": 0.3181344296802588,
    "ci_high": 0.4857940488533021,
    "n": 28,
    "n_instances": 14
   },
   "max_share": {
    "estimate": 0.31364014160553955,
    "ci_low": 0.2985489333191179,
    "ci_high": 0.32656878820412993,
    "n": 28,
    "n_instances": 14
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": 0.18885833333333338,
    "ci_low": 0.11001381250000002,
    "ci_high": 0.27658052083333334,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.09516215706354499,
    "ci_low": 0.04942272114689281,
    "ci_high": 0.1453282405997018,
    "n": 120,
    "n_instances": 24
   },
   "justified_walk": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 92,
    "n_instances": 23
   },
   "missed_deal": {
    "estimate": 1.0,
    "ci_low": 1.0,
    "ci_high": 1.0,
    "n": 92,
    "n_instances": 23
   },
   "ir_margin_of_no_deal": {
    "estimate": 0.3631886152489443,
    "ci_low": 0.2859832884004634,
    "ci_high": 0.43367476388099735,
    "n": 92,
    "n_instances": 23
   }
  },
  "one_rational": {
   "deal_rate": {
    "estimate": 0.7666666666666667,
    "ci_low": 0.6833333333333333,
    "ci_high": 0.8416666666666667,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 92,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": 0.23923924245411646,
    "ci_low": 0.19537577165892536,
    "ci_high": 0.28241317369658214,
    "n": 92,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.0725120810975585,
    "ci_low": 0.06055429843355707,
    "ci_high": 0.08318397130186854,
    "n": 92,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.44434457646545117,
    "ci_low": 0.340575682611722,
    "ci_high": 0.564093922423092,
    "n": 92,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.41411311378312343,
    "ci_low": 0.3320292649253537,
    "ci_high": 0.49293942281057046,
    "n": 92,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.23136952807084968,
    "ci_low": 0.2093895750008324,
    "ci_high": 0.25518462947221127,
    "n": 92,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.5063123982328782,
    "ci_low": 0.43873919579028114,
    "ci_high": 0.5654046597865545,
    "n": 92,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.30102142748483496,
    "ci_low": 0.2892884093107425,
    "ci_high": 0.3135073518706248,
    "n": 92,
    "n_instances": 24
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": 0.6864258333333334,
    "ci_low": 0.6137483125000001,
    "ci_high": 0.7577425624999999,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.38817283864520663,
    "ci_low": 0.3186217524414456,
    "ci_high": 0.45107177038512003,
    "n": 120,
    "n_instances": 24
   },
   "justified_walk": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 28,
    "n_instances": 17
   },
   "missed_deal": {
    "estimate": 1.0,
    "ci_low": 1.0,
    "ci_high": 1.0,
    "n": 28,
    "n_instances": 17
   },
   "ir_margin_of_no_deal": {
    "estimate": 0.3432439165619196,
    "ci_low": 0.2198735396552916,
    "ci_high": 0.46222137500554367,
    "n": 28,
    "n_instances": 17
   }
  },
  "rational_advised_llm": {
   "deal_rate": {
    "estimate": 0.9,
    "ci_low": 0.8083333333333333,
    "ci_high": 0.975,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 108,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": 0.2500726745763431,
    "ci_low": 0.2063917744327433,
    "ci_high": 0.29424039361929516,
    "n": 108,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.07598800278802065,
    "ci_low": 0.06427521830441092,
    "ci_high": 0.08738348422883063,
    "n": 108,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.4781650421527495,
    "ci_low": 0.3845476856743339,
    "ci_high": 0.5811657851016319,
    "n": 108,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.45763156935745003,
    "ci_low": 0.37171130567664784,
    "ci_high": 0.5348932262751342,
    "n": 108,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.23159563260933352,
    "ci_low": 0.2094661513383742,
    "ci_high": 0.2528834727200833,
    "n": 108,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.525631904439619,
    "ci_low": 0.4651633314152496,
    "ci_high": 0.580512084087885,
    "n": 108,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.3023671533397975,
    "ci_low": 0.29082342282676965,
    "ci_high": 0.3133504201684683,
    "n": 108,
    "n_instances": 24
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": 0.8114841666666666,
    "ci_low": 0.7259124791666667,
    "ci_high": 0.883988375,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.4730687139956571,
    "ci_low": 0.39274046178821503,
    "ci_high": 0.5459164784535345,
    "n": 120,
    "n_instances": 24
   },
   "justified_walk": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 12,
    "n_instances": 6
   },
   "missed_deal": {
    "estimate": 1.0,
    "ci_low": 1.0,
    "ci_high": 1.0,
    "n": 12,
    "n_instances": 6
   },
   "ir_margin_of_no_deal": {
    "estimate": 0.2559326723031295,
    "ci_low": 0.054878048780487805,
    "ci_high": 0.45698729582577124,
    "n": 12,
    "n_instances": 6
   }
  },
  "interpreter_advised_llm": {
   "deal_rate": {
    "estimate": 0.9583333333333334,
    "ci_low": 0.9166666666666666,
    "ci_high": 0.9916666666666667,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 115,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": 0.26877510570102636,
    "ci_low": 0.22423106311553548,
    "ci_high": 0.3096526624076539,
    "n": 115,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.08183640825255681,
    "ci_low": 0.06937086908548236,
    "ci_high": 0.0930265286492039,
    "n": 115,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.4116431753333182,
    "ci_low": 0.31050754010707954,
    "ci_high": 0.535713619127711,
    "n": 115,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.36606048552080234,
    "ci_low": 0.2949308321961962,
    "ci_high": 0.42970612445089684,
    "n": 115,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.2144021422360019,
    "ci_low": 0.1957667194357814,
    "ci_high": 0.2329280591499583,
    "n": 115,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.5425545088981604,
    "ci_low": 0.4771666133101167,
    "ci_high": 0.5980581706142115,
    "n": 115,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.2960790571733364,
    "ci_low": 0.28473493854469334,
    "ci_high": 0.30659785046774896,
    "n": 115,
    "n_instances": 24
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": 0.8808299999999999,
    "ci_low": 0.8361071875,
    "ci_high": 0.9208068541666666,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.5199480710274036,
    "ci_low": 0.44112465531901895,
    "ci_high": 0.587093156850545,
    "n": 120,
    "n_instances": 24
   },
   "justified_walk": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 5,
    "n_instances": 4
   },
   "missed_deal": {
    "estimate": 1.0,
    "ci_low": 1.0,
    "ci_high": 1.0,
    "n": 5,
    "n_instances": 4
   },
   "ir_margin_of_no_deal": {
    "estimate": 0.16575,
    "ci_low": 0.0,
    "ci_high": 0.414375,
    "n": 5,
    "n_instances": 4
   }
  },
  "all_interpreter_advised_llm": {
   "deal_rate": {
    "estimate": 0.9833333333333333,
    "ci_low": 0.95,
    "ci_high": 1.0,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 118,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": 0.2389542928207875,
    "ci_low": 0.19251038462271153,
    "ci_high": 0.2857846504076221,
    "n": 118,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.07295460810314856,
    "ci_low": 0.05980162178672081,
    "ci_high": 0.08533185279677549,
    "n": 118,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.5000922124858869,
    "ci_low": 0.3917775416121231,
    "ci_high": 0.6331190170797285,
    "n": 118,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.44203505520490993,
    "ci_low": 0.353029672930886,
    "ci_high": 0.524368371583769,
    "n": 118,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.22908129743019542,
    "ci_low": 0.20714596704710359,
    "ci_high": 0.2496463378699354,
    "n": 118,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.5107087466464162,
    "ci_low": 0.4359681993795025,
    "ci_high": 0.5756351317125717,
    "n": 118,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.3002355450505539,
    "ci_low": 0.28818979349139784,
    "ci_high": 0.3111509322200598,
    "n": 118,
    "n_instances": 24
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": 0.8990775000000001,
    "ci_low": 0.8558455208333333,
    "ci_high": 0.9353071458333333,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.5021969342023093,
    "ci_low": 0.4204688220253503,
    "ci_high": 0.5735244419234691,
    "n": 120,
    "n_instances": 24
   },
   "justified_walk": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 2,
    "n_instances": 1
   },
   "missed_deal": {
    "estimate": 1.0,
    "ci_low": 1.0,
    "ci_high": 1.0,
    "n": 2,
    "n_instances": 1
   },
   "ir_margin_of_no_deal": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 2,
    "n_instances": 1
   }
  },
  "one_oracle": {
   "deal_rate": {
    "estimate": 0.9166666666666666,
    "ci_low": 0.85,
    "ci_high": 0.9666666666666667,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 110,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": 0.20052420434418816,
    "ci_low": 0.15143508907990977,
    "ci_high": 0.25195539862931166,
    "n": 110,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.058582652990355755,
    "ci_low": 0.04697928120159507,
    "ci_high": 0.06975492021512701,
    "n": 110,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.5502155166421395,
    "ci_low": 0.43575462557431854,
    "ci_high": 0.6762484397097723,
    "n": 110,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.5241960242972619,
    "ci_low": 0.4262773163488013,
    "ci_high": 0.6142913358820019,
    "n": 110,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.26570818208794883,
    "ci_low": 0.23685672397692456,
    "ci_high": 0.2936840515423784,
    "n": 110,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.47216530427836567,
    "ci_low": 0.3925629996935331,
    "ci_high": 0.5476266384113754,
    "n": 110,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.3143537476799115,
    "ci_low": 0.2969871213773641,
    "ci_high": 0.33193909907223723,
    "n": 110,
    "n_instances": 24
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": 0.8288633333333332,
    "ci_low": 0.7654844374999998,
    "ci_high": 0.8848064374999999,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.4328181955885018,
    "ci_low": 0.34732690135077005,
    "ci_high": 0.5163220332651305,
    "n": 120,
    "n_instances": 24
   },
   "justified_walk": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 10,
    "n_instances": 8
   },
   "missed_deal": {
    "estimate": 1.0,
    "ci_low": 1.0,
    "ci_high": 1.0,
    "n": 10,
    "n_instances": 8
   },
   "ir_margin_of_no_deal": {
    "estimate": 0.2390978586087305,
    "ci_low": 0.09811748759654239,
    "ci_high": 0.4188838048221428,
    "n": 10,
    "n_instances": 8
   }
  },
  "all_oracle": {
   "deal_rate": {
    "estimate": 1.0,
    "ci_low": 1.0,
    "ci_high": 1.0,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": 0.1664140067203309,
    "ci_low": 0.11838579865840172,
    "ci_high": 0.22038585113159195,
    "n": 120,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.0484048449564163,
    "ci_low": 0.03655166884610843,
    "ci_high": 0.06081287308528416,
    "n": 120,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.6306371226240565,
    "ci_low": 0.5230954178507597,
    "ci_high": 0.7582274223938094,
    "n": 120,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.549472048212886,
    "ci_low": 0.44957582803493834,
    "ci_high": 0.6480803067681641,
    "n": 120,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.2854855910779398,
    "ci_low": 0.2549050713822432,
    "ci_high": 0.3142169367702321,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.405530944848298,
    "ci_low": 0.3165125911848889,
    "ci_high": 0.4952474569966038,
    "n": 120,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.31912538492110715,
    "ci_low": 0.30277347783640146,
    "ci_high": 0.3360125635254274,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": 0.9068575,
    "ci_low": 0.8796784375,
    "ci_high": 0.9326443541666667,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.405530944848298,
    "ci_low": 0.3165125911848889,
    "ci_high": 0.4952474569966038,
    "n": 120,
    "n_instances": 24
   },
   "justified_walk": {
    "estimate": null,
    "ci_low": null,
    "ci_high": null,
    "n": 0,
    "n_instances": 0
   },
   "missed_deal": {
    "estimate": null,
    "ci_low": null,
    "ci_high": null,
    "n": 0,
    "n_instances": 0
   },
   "ir_margin_of_no_deal": {
    "estimate": null,
    "ci_low": null,
    "ci_high": null,
    "n": 0,
    "n_instances": 0
   }
  }
 },
 "paired_minus_reference": {
  "all_rational": {
   "deal_rate": {
    "estimate": -0.725,
    "ci_low": -0.8333333333333334,
    "ci_high": -0.6083333333333333,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 28,
    "n_instances": 14
   },
   "worst_off": {
    "estimate": -0.09601933058200689,
    "ci_low": -0.1625251342052812,
    "ci_high": -0.02266779644889123,
    "n": 28,
    "n_instances": 14
   },
   "worst_off_share": {
    "estimate": -0.028237270199012482,
    "ci_low": -0.05049540289733727,
    "ci_high": -0.005271000706478527,
    "n": 28,
    "n_instances": 14
   },
   "dist_to_nbs": {
    "estimate": 0.07613537727454613,
    "ci_low": -0.07844977100716566,
    "ci_high": 0.25539196994306185,
    "n": 28,
    "n_instances": 14
   },
   "dist_to_ks": {
    "estimate": 0.11884514841560789,
    "ci_low": -0.022217819082625923,
    "ci_high": 0.29674709763662094,
    "n": 28,
    "n_instances": 14
   },
   "normalized_gini": {
    "estimate": 0.03064648220408337,
    "ci_low": -0.0036850882810818978,
    "ci_high": 0.06732715343466812,
    "n": 28,
    "n_instances": 14
   },
   "normalized_nash_welfare_conditional": {
    "estimate": -0.10288294566010638,
    "ci_low": -0.19499098671256196,
    "ci_high": -0.024729559512160146,
    "n": 28,
    "n_instances": 14
   },
   "max_share": {
    "estimate": 0.006212406645721159,
    "ci_low": -0.013103699061365175,
    "ci_high": 0.022124702575160252,
    "n": 28,
    "n_instances": 14
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": -0.6837549999999999,
    "ci_low": -0.7858409583333335,
    "ci_high": -0.5790527291666666,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": -0.4172928402891551,
    "ci_low": -0.5093910481214442,
    "ci_high": -0.32522197222918675,
    "n": 120,
    "n_instances": 24
   }
  },
  "one_rational": {
   "deal_rate": {
    "estimate": -0.19166666666666668,
    "ci_low": -0.275,
    "ci_high": -0.10833333333333334,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 90,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": -0.010511324890106739,
    "ci_low": -0.04324943666311552,
    "ci_high": 0.020266378424554844,
    "n": 90,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": -0.004126056934631155,
    "ci_low": -0.015093663292730649,
    "ci_high": 0.005806197335060843,
    "n": 90,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": -0.04831218602726004,
    "ci_low": -0.14157948655620703,
    "ci_high": 0.04533935771358403,
    "n": 90,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": -0.012480152104404563,
    "ci_low": -0.09625531263254553,
    "ci_high": 0.07239400792173319,
    "n": 90,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.004812690536127199,
    "ci_low": -0.01570743063984344,
    "ci_high": 0.026152615392504637,
    "n": 90,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": -0.023579400570546343,
    "ci_low": -0.06601912252009505,
    "ci_high": 0.014687927595631211,
    "n": 90,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.0004958005576147857,
    "ci_low": -0.008757269342508292,
    "ci_high": 0.010240028531280178,
    "n": 90,
    "n_instances": 24
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": -0.1861875,
    "ci_low": -0.2652688541666667,
    "ci_high": -0.10664083333333335,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": -0.12428215870749343,
    "ci_low": -0.18734137878594226,
    "ci_high": -0.06432207810195843,
    "n": 120,
    "n_instances": 24
   }
  },
  "rational_advised_llm": {
   "deal_rate": {
    "estimate": -0.058333333333333334,
    "ci_low": -0.15,
    "ci_high": 0.016666666666666666,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 105,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": -0.00464881545199529,
    "ci_low": -0.026780493568663483,
    "ci_high": 0.017983514536632675,
    "n": 105,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": -0.0016530070612752986,
    "ci_low": -0.008877932048148535,
    "ci_high": 0.00525035483478764,
    "n": 105,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.01941517414073938,
    "ci_low": -0.030862406884128574,
    "ci_high": 0.07180493866932326,
    "n": 105,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.04359032273774962,
    "ci_low": -0.0028717453580671955,
    "ci_high": 0.0941485356616561,
    "n": 105,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.009342265150020847,
    "ci_low": -0.004633874493526379,
    "ci_high": 0.02607869125990941,
    "n": 105,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": -0.015993210483082845,
    "ci_low": -0.03740446506131002,
    "ci_high": 0.0039739189319309125,
    "n": 105,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.002669012637296196,
    "ci_low": -0.003822441792869753,
    "ci_high": 0.010238181710587435,
    "n": 105,
    "n_instances": 24
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": -0.061129166666666665,
    "ci_low": -0.15087564583333335,
    "ci_high": 0.009340979166666662,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": -0.0393862833570429,
    "ci_low": -0.10542399360987251,
    "ci_high": 0.007461987178622596,
    "n": 120,
    "n_instances": 24
   }
  },
  "interpreter_advised_llm": {
   "deal_rate": {
    "estimate": 0.0,
    "ci_low": -0.041666666666666664,
    "ci_high": 0.041666666666666664,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 112,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": 0.01145654830300744,
    "ci_low": -0.01152322578428064,
    "ci_high": 0.03438263799463079,
    "n": 112,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.004250526761351897,
    "ci_low": -0.0015814729646609197,
    "ci_high": 0.010504035342132111,
    "n": 112,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": -0.054294185752131977,
    "ci_low": -0.11037123051341943,
    "ci_high": 0.0032732375733464324,
    "n": 112,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": -0.04025546359113811,
    "ci_low": -0.09653285985118164,
    "ci_high": 0.015211548834301298,
    "n": 112,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": -0.008972828207228474,
    "ci_low": -0.01971727353893173,
    "ci_high": 0.0014937725000351567,
    "n": 112,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.003968466360351362,
    "ci_low": -0.023168958063747153,
    "ci_high": 0.03290502759688034,
    "n": 112,
    "n_instances": 24
   },
   "max_share": {
    "estimate": -0.003043165801135127,
    "ci_low": -0.00868535318851284,
    "ci_high": 0.0022863899713994646,
    "n": 112,
    "n_instances": 24
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": 0.008216666666666662,
    "ci_low": -0.033494416666666665,
    "ci_high": 0.05044252083333333,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.00749307367470356,
    "ci_low": -0.0320572969829185,
    "ci_high": 0.0452007103553319,
    "n": 120,
    "n_instances": 24
   }
  },
  "all_interpreter_advised_llm": {
   "deal_rate": {
    "estimate": 0.025,
    "ci_low": -0.008333333333333333,
    "ci_high": 0.058333333333333334,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 113,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": -0.015069913172529767,
    "ci_low": -0.04396225816276393,
    "ci_high": 0.01327006098185081,
    "n": 113,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": -0.0036074481016949538,
    "ci_low": -0.011556139839909146,
    "ci_high": 0.004544705082927359,
    "n": 113,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.025681359877088975,
    "ci_low": -0.0465454594395808,
    "ci_high": 0.09944288138116603,
    "n": 113,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.04349796520997925,
    "ci_low": -0.022527438874139362,
    "ci_high": 0.11217998221613337,
    "n": 113,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.005159624294063291,
    "ci_low": -0.006919831250235241,
    "ci_high": 0.016798805255917714,
    "n": 113,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": -0.024106112410242103,
    "ci_low": -0.06936247258779317,
    "ci_high": 0.01062752704219042,
    "n": 113,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.0011415280548554452,
    "ci_low": -0.004477739151643487,
    "ci_high": 0.006766520606249174,
    "n": 113,
    "n_instances": 24
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": 0.026464166666666667,
    "ci_low": -0.010255104166666666,
    "ci_high": 0.06551799999999999,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": -0.010258063150390793,
    "ci_low": -0.05617274262139232,
    "ci_high": 0.026959512438319122,
    "n": 120,
    "n_instances": 24
   }
  },
  "one_oracle": {
   "deal_rate": {
    "estimate": -0.041666666666666664,
    "ci_low": -0.1,
    "ci_high": 0.016666666666666666,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 106,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": -0.060353359738015915,
    "ci_low": -0.09215353402719913,
    "ci_high": -0.03238434830402131,
    "n": 106,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": -0.019779060194180596,
    "ci_low": -0.030414559564296256,
    "ci_high": -0.010802815357185311,
    "n": 106,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.07863394787826475,
    "ci_low": 0.015174773992301828,
    "ci_high": 0.14764824317192515,
    "n": 106,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.11593008594127932,
    "ci_low": 0.05940375849472473,
    "ci_high": 0.18239621826459934,
    "n": 106,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.04315785119943256,
    "ci_low": 0.024772103793313228,
    "ci_high": 0.06527576158508315,
    "n": 106,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": -0.06904703502676467,
    "ci_low": -0.10975533567068414,
    "ci_high": -0.034566079023316015,
    "n": 106,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.01533983365562051,
    "ci_low": 0.005146794544161374,
    "ci_high": 0.027568261259012437,
    "n": 106,
    "n_instances": 24
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": -0.04375,
    "ci_low": -0.1034201875,
    "ci_high": 0.012116791666666635,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": -0.0796368017641982,
    "ci_low": -0.1263193102084146,
    "ci_high": -0.03404483419317548,
    "n": 120,
    "n_instances": 24
   }
  },
  "all_oracle": {
   "deal_rate": {
    "estimate": 0.041666666666666664,
    "ci_low": 0.008333333333333333,
    "ci_high": 0.075,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 115,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": -0.08624554900577996,
    "ci_low": -0.1301815802024233,
    "ci_high": -0.043153851328799724,
    "n": 115,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": -0.027861756178209657,
    "ci_low": -0.04214552609646493,
    "ci_high": -0.014664396773068095,
    "n": 115,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.15760131955439596,
    "ci_low": 0.07156723772987213,
    "ci_high": 0.24807706074064864,
    "n": 115,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.15904260849844643,
    "ci_low": 0.0666264005531866,
    "ci_high": 0.24984375857536714,
    "n": 115,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.06112756545726602,
    "ci_low": 0.03292893419209807,
    "ci_high": 0.09068718364690873,
    "n": 115,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": -0.12385867449133948,
    "ci_low": -0.1888136386841239,
    "ci_high": -0.06082696793462639,
    "n": 115,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.020426943872637302,
    "ci_low": 0.007034126712418384,
    "ci_high": 0.03498274699389827,
    "n": 115,
    "n_instances": 24
   },
   "below_threshold_episode": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 120,
    "n_instances": 24
   },
   "normalized_primary": {
    "estimate": 0.034244166666666666,
    "ci_low": 0.0009074166666666613,
    "ci_high": 0.07406479166666663,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": -0.10692405250440208,
    "ci_low": -0.17052145745564792,
    "ci_high": -0.047449044992881786,
    "n": 120,
    "n_instances": 24
   }
  }
 },
 "all_instances_feasible": true,
 "instance_geometry": [
  {
   "instance_id": "scorable_negotiation-L4-faf2ca7d47",
   "difficulty_scalar": 0.694187,
   "difficulty_tags": "hard;no-clear-win-win;pivotal-seat;small-frontier",
   "n_deals": 256,
   "n_ir_deals": 5,
   "feasible_all_ir": true,
   "ir_margin": 0.0
  },
  {
   "instance_id": "scorable_negotiation-L4-712ba36a4f",
   "difficulty_scalar": 0.706191,
   "difficulty_tags": "hard;no-clear-win-win;pivotal-seat",
   "n_deals": 256,
   "n_ir_deals": 4,
   "feasible_all_ir": true,
   "ir_margin": 0.0
  },
  {
   "instance_id": "scorable_negotiation-L3-9a673abad3",
   "difficulty_scalar": 0.699699,
   "difficulty_tags": "hard;high-conflict;pivotal-seat",
   "n_deals": 256,
   "n_ir_deals": 9,
   "feasible_all_ir": true,
   "ir_margin": 0.08620689655172414
  },
  {
   "instance_id": "scorable_negotiation-L3-9a1b1c0960",
   "difficulty_scalar": 0.689368,
   "difficulty_tags": "hard;pivotal-seat",
   "n_deals": 256,
   "n_ir_deals": 8,
   "feasible_all_ir": true,
   "ir_margin": 0.18421052631578946
  },
  {
   "instance_id": "scorable_negotiation-L2-103cef6017",
   "difficulty_scalar": 0.638165,
   "difficulty_tags": "medium;small-frontier",
   "n_deals": 256,
   "n_ir_deals": 15,
   "feasible_all_ir": true,
   "ir_margin": 0.2692307692307692
  },
  {
   "instance_id": "scorable_negotiation-L2-1fc37540c8",
   "difficulty_scalar": 0.676476,
   "difficulty_tags": "high-conflict;large-frontier;medium;no-clear-win-win",
   "n_deals": 256,
   "n_ir_deals": 17,
   "feasible_all_ir": true,
   "ir_margin": 0.3103448275862069
  },
  {
   "instance_id": "scorable_negotiation-L0-32200851b2",
   "difficulty_scalar": 0.562257,
   "difficulty_tags": "easy;high-conflict",
   "n_deals": 256,
   "n_ir_deals": 47,
   "feasible_all_ir": true,
   "ir_margin": 0.32926829268292684
  },
  {
   "instance_id": "scorable_negotiation-L1-996daa4124",
   "difficulty_scalar": 0.61343,
   "difficulty_tags": "easy;large-frontier",
   "n_deals": 256,
   "n_ir_deals": 22,
   "feasible_all_ir": true,
   "ir_margin": 0.3333333333333333
  },
  {
   "instance_id": "scorable_negotiation-L4-d49e5fe070",
   "difficulty_scalar": 0.672467,
   "difficulty_tags": "medium;small-frontier",
   "n_deals": 256,
   "n_ir_deals": 5,
   "feasible_all_ir": true,
   "ir_margin": 0.36
  },
  {
   "instance_id": "scorable_negotiation-L0-611ee402f7",
   "difficulty_scalar": 0.55854,
   "difficulty_tags": "easy",
   "n_deals": 256,
   "n_ir_deals": 43,
   "feasible_all_ir": true,
   "ir_margin": 0.417910447761194
  },
  {
   "instance_id": "scorable_negotiation-L2-df1e479b72",
   "difficulty_scalar": 0.63001,
   "difficulty_tags": "medium;small-frontier",
   "n_deals": 256,
   "n_ir_deals": 21,
   "feasible_all_ir": true,
   "ir_margin": 0.43103448275862066
  },
  {
   "instance_id": "scorable_negotiation-L3-a8641f6c33",
   "difficulty_scalar": 0.651538,
   "difficulty_tags": "medium;small-frontier",
   "n_deals": 256,
   "n_ir_deals": 8,
   "feasible_all_ir": true,
   "ir_margin": 0.43333333333333335
  },
  {
   "instance_id": "scorable_negotiation-L1-19dae4b672",
   "difficulty_scalar": 0.62258,
   "difficulty_tags": "high-conflict;medium",
   "n_deals": 256,
   "n_ir_deals": 27,
   "feasible_all_ir": true,
   "ir_margin": 0.4387755102040816
  },
  {
   "instance_id": "scorable_negotiation-L0-65113008ad",
   "difficulty_scalar": 0.624796,
   "difficulty_tags": "medium",
   "n_deals": 256,
   "n_ir_deals": 29,
   "feasible_all_ir": true,
   "ir_margin": 0.43902439024390244
  },
  {
   "instance_id": "scorable_negotiation-L0-34733a57e6",
   "difficulty_scalar": 0.561029,
   "difficulty_tags": "easy;large-frontier",
   "n_deals": 256,
   "n_ir_deals": 45,
   "feasible_all_ir": true,
   "ir_margin": 0.4523809523809524
  },
  {
   "instance_id": "scorable_negotiation-L2-adac68f4ac",
   "difficulty_scalar": 0.642993,
   "difficulty_tags": "large-frontier;medium",
   "n_deals": 256,
   "n_ir_deals": 17,
   "feasible_all_ir": true,
   "ir_margin": 0.4666666666666667
  },
  {
   "instance_id": "scorable_negotiation-L2-0aa50f7b83",
   "difficulty_scalar": 0.679768,
   "difficulty_tags": "hard;high-conflict;large-frontier;no-clear-win-win",
   "n_deals": 256,
   "n_ir_deals": 14,
   "feasible_all_ir": true,
   "ir_margin": 0.46875
  },
  {
   "instance_id": "scorable_negotiation-L0-a483b0d80d",
   "difficulty_scalar": 0.546303,
   "difficulty_tags": "easy",
   "n_deals": 256,
   "n_ir_deals": 40,
   "feasible_all_ir": true,
   "ir_margin": 0.4727272727272727
  },
  {
   "instance_id": "scorable_negotiation-L1-a9097927ce",
   "difficulty_scalar": 0.551691,
   "difficulty_tags": "easy",
   "n_deals": 256,
   "n_ir_deals": 37,
   "feasible_all_ir": true,
   "ir_margin": 0.4827586206896552
  },
  {
   "instance_id": "scorable_negotiation-L4-8a29217702",
   "difficulty_scalar": 0.68927,
   "difficulty_tags": "hard;high-conflict;no-clear-win-win;small-frontier",
   "n_deals": 256,
   "n_ir_deals": 4,
   "feasible_all_ir": true,
   "ir_margin": 0.49122807017543857
  },
  {
   "instance_id": "scorable_negotiation-L3-46e1252af7",
   "difficulty_scalar": 0.684076,
   "difficulty_tags": "hard;pivotal-seat",
   "n_deals": 256,
   "n_ir_deals": 8,
   "feasible_all_ir": true,
   "ir_margin": 0.49230769230769234
  },
  {
   "instance_id": "scorable_negotiation-L1-aabb4d986b",
   "difficulty_scalar": 0.614162,
   "difficulty_tags": "easy",
   "n_deals": 256,
   "n_ir_deals": 22,
   "feasible_all_ir": true,
   "ir_margin": 0.4959349593495935
  },
  {
   "instance_id": "scorable_negotiation-L1-282034699c",
   "difficulty_scalar": 0.600081,
   "difficulty_tags": "easy;large-frontier",
   "n_deals": 256,
   "n_ir_deals": 27,
   "feasible_all_ir": true,
   "ir_margin": 0.55
  },
  {
   "instance_id": "scorable_negotiation-L3-d9a0ef3c04",
   "difficulty_scalar": 0.7161,
   "difficulty_tags": "hard;no-clear-win-win;pivotal-seat",
   "n_deals": 256,
   "n_ir_deals": 5,
   "feasible_all_ir": true,
   "ir_margin": 0.651685393258427
  }
 ],
 "bank_margin_by_tag": {
  "easy": {
   "n_instances": 8,
   "mean_ir_margin": 0.44178923486561605,
   "min_ir_margin": 0.32926829268292684
  },
  "hard": {
   "n_instances": 8,
   "mean_ir_margin": 0.29679857232613394,
   "min_ir_margin": 0.0
  },
  "high-conflict": {
   "n_instances": 6,
   "mean_ir_margin": 0.35409559953339637,
   "min_ir_margin": 0.08620689655172414
  },
  "large-frontier": {
   "n_instances": 6,
   "mean_ir_margin": 0.4302459633278599,
   "min_ir_margin": 0.3103448275862069
  },
  "medium": {
   "n_instances": 8,
   "mean_ir_margin": 0.3935512475029476,
   "min_ir_margin": 0.2692307692307692
  },
  "no-clear-win-win": {
   "n_instances": 6,
   "mean_ir_margin": 0.32033471517001205,
   "min_ir_margin": 0.0
  },
  "pivotal-seat": {
   "n_instances": 6,
   "mean_ir_margin": 0.2357350847389388,
   "min_ir_margin": 0.0
  },
  "small-frontier": {
   "n_instances": 6,
   "mean_ir_margin": 0.330804442583027,
   "min_ir_margin": 0.0
  }
 },
 "walk_by_tag": {
  "all_llm": {
   "easy": {
    "n_no_deal": 2,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.44166666666666665
   },
   "hard": {
    "n_no_deal": 2,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.0
   },
   "high-conflict": {
    "n_no_deal": 0,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   },
   "large-frontier": {
    "n_no_deal": 2,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.44166666666666665
   },
   "medium": {
    "n_no_deal": 1,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.2692307692307692
   },
   "no-clear-win-win": {
    "n_no_deal": 2,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.0
   },
   "pivotal-seat": {
    "n_no_deal": 2,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.0
   },
   "small-frontier": {
    "n_no_deal": 2,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.1346153846153846
   }
  },
  "all_rational": {
   "easy": {
    "n_no_deal": 20,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.42783676535022835
   },
   "hard": {
    "n_no_deal": 39,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.30440879212936817
   },
   "high-conflict": {
    "n_no_deal": 26,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.3544311947248365
   },
   "large-frontier": {
    "n_no_deal": 22,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.42616388640095537
   },
   "medium": {
    "n_no_deal": 33,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.39347498190463465
   },
   "no-clear-win-win": {
    "n_no_deal": 28,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.3321320224112198
   },
   "pivotal-seat": {
    "n_no_deal": 29,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.2438638807644195
   },
   "small-frontier": {
    "n_no_deal": 26,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.32134240416384774
   }
  },
  "one_rational": {
   "easy": {
    "n_no_deal": 6,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.411338766538169
   },
   "hard": {
    "n_no_deal": 16,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.27746280363555487
   },
   "high-conflict": {
    "n_no_deal": 6,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.3254813710228754
   },
   "large-frontier": {
    "n_no_deal": 7,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.4438350340136055
   },
   "medium": {
    "n_no_deal": 6,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.4505653677226427
   },
   "no-clear-win-win": {
    "n_no_deal": 11,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.30966021092055984
   },
   "pivotal-seat": {
    "n_no_deal": 13,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.22986143983215387
   },
   "small-frontier": {
    "n_no_deal": 6,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.3078039927404718
   }
  },
  "rational_advised_llm": {
   "easy": {
    "n_no_deal": 1,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.32926829268292684
   },
   "hard": {
    "n_no_deal": 9,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.21832358674463936
   },
   "high-conflict": {
    "n_no_deal": 6,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.4340875668284814
   },
   "large-frontier": {
    "n_no_deal": 2,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.3885057471264368
   },
   "medium": {
    "n_no_deal": 2,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.3885057471264368
   },
   "no-clear-win-win": {
    "n_no_deal": 10,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.2275257108287961
   },
   "pivotal-seat": {
    "n_no_deal": 5,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.0
   },
   "small-frontier": {
    "n_no_deal": 6,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.32748538011695905
   }
  },
  "interpreter_advised_llm": {
   "easy": {
    "n_no_deal": 0,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   },
   "hard": {
    "n_no_deal": 4,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.1171875
   },
   "high-conflict": {
    "n_no_deal": 1,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.46875
   },
   "large-frontier": {
    "n_no_deal": 1,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.46875
   },
   "medium": {
    "n_no_deal": 1,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.36
   },
   "no-clear-win-win": {
    "n_no_deal": 4,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.1171875
   },
   "pivotal-seat": {
    "n_no_deal": 3,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.0
   },
   "small-frontier": {
    "n_no_deal": 2,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.18
   }
  },
  "all_interpreter_advised_llm": {
   "easy": {
    "n_no_deal": 0,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   },
   "hard": {
    "n_no_deal": 2,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.0
   },
   "high-conflict": {
    "n_no_deal": 0,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   },
   "large-frontier": {
    "n_no_deal": 0,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   },
   "medium": {
    "n_no_deal": 0,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   },
   "no-clear-win-win": {
    "n_no_deal": 2,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.0
   },
   "pivotal-seat": {
    "n_no_deal": 2,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.0
   },
   "small-frontier": {
    "n_no_deal": 0,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   }
  },
  "one_oracle": {
   "easy": {
    "n_no_deal": 2,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.4351457000710732
   },
   "hard": {
    "n_no_deal": 5,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.03684210526315789
   },
   "high-conflict": {
    "n_no_deal": 1,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.4387755102040816
   },
   "large-frontier": {
    "n_no_deal": 2,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.45952380952380956
   },
   "medium": {
    "n_no_deal": 3,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": 0.4454922198764564
   },
   "no-clear-win-win": {
    "n_no_deal": 4,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.0
   },
   "pivotal-seat": {
    "n_no_deal": 5,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.03684210526315789
   },
   "small-frontier": {
    "n_no_deal": 2,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": 0.21551724137931033
   }
  },
  "all_oracle": {
   "easy": {
    "n_no_deal": 0,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   },
   "hard": {
    "n_no_deal": 0,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   },
   "high-conflict": {
    "n_no_deal": 0,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   },
   "large-frontier": {
    "n_no_deal": 0,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   },
   "medium": {
    "n_no_deal": 0,
    "n_episodes": 40,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   },
   "no-clear-win-win": {
    "n_no_deal": 0,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   },
   "pivotal-seat": {
    "n_no_deal": 0,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   },
   "small-frontier": {
    "n_no_deal": 0,
    "n_episodes": 30,
    "justified_walks": 0,
    "mean_ir_margin": NaN
   }
  }
 },
 "margin_vs_no_deal_rate": {
  "all_llm": {
   "pearson_r": -0.46490335738860106,
   "ci_low": -0.82299238891448,
   "ci_high": 0.09731743657294463,
   "n_instances": 24
  },
  "all_rational": {
   "pearson_r": -0.25578659513352464,
   "ci_low": -0.5488517932185872,
   "ci_high": 0.07936141138569625,
   "n_instances": 24
  },
  "one_rational": {
   "pearson_r": -0.2492323190001127,
   "ci_low": -0.7048046037248373,
   "ci_high": 0.31612611984622263,
   "n_instances": 24
  },
  "rational_advised_llm": {
   "pearson_r": -0.3600032700086261,
   "ci_low": -0.847151898195828,
   "ci_high": 0.17193408107008834,
   "n_instances": 24
  },
  "interpreter_advised_llm": {
   "pearson_r": -0.5460208528683343,
   "ci_low": -0.8207018530450831,
   "ci_high": 0.10410825624960722,
   "n_instances": 24
  },
  "all_interpreter_advised_llm": {
   "pearson_r": -0.4855626328238723,
   "ci_low": -0.8286912485576855,
   "ci_high": -0.367551326539692,
   "n_instances": 24
  },
  "one_oracle": {
   "pearson_r": -0.5063334214207315,
   "ci_low": -0.781302751045812,
   "ci_high": 0.1034354713186448,
   "n_instances": 24
  },
  "all_oracle": {
   "pearson_r": NaN,
   "ci_low": null,
   "ci_high": null,
   "n_instances": 24
  }
 },
 "paired_strata": {
  "all_rational": {
   "easy": {
    "deal_rate": {
     "estimate": -0.45,
     "ci_low": -0.6,
     "ci_high": -0.275,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.4468375,
     "ci_low": -0.570055,
     "ci_high": -0.326615,
     "n": 40,
     "n_instances": 8
    }
   },
   "hard": {
    "deal_rate": {
     "estimate": -0.925,
     "ci_low": -1.0,
     "ci_high": -0.825,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.8691524999999999,
     "ci_low": -0.957225,
     "ci_high": -0.7714875,
     "n": 40,
     "n_instances": 8
    }
   },
   "high-conflict": {
    "deal_rate": {
     "estimate": -0.8666666666666667,
     "ci_low": -0.9666666666666667,
     "ci_high": -0.7333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.81754,
     "ci_low": -0.9270999999999998,
     "ci_high": -0.69025,
     "n": 30,
     "n_instances": 6
    }
   },
   "large-frontier": {
    "deal_rate": {
     "estimate": -0.6666666666666666,
     "ci_low": -0.9,
     "ci_high": -0.43333333333333335,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.6466466666666668,
     "ci_low": -0.8229299999999999,
     "ci_high": -0.45597000000000004,
     "n": 30,
     "n_instances": 6
    }
   },
   "medium": {
    "deal_rate": {
     "estimate": -0.8,
     "ci_low": -0.925,
     "ci_high": -0.65,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.735275,
     "ci_low": -0.8892325,
     "ci_high": -0.5439425,
     "n": 40,
     "n_instances": 8
    }
   },
   "no-clear-win-win": {
    "deal_rate": {
     "estimate": -0.8666666666666667,
     "ci_low": -0.9666666666666667,
     "ci_high": -0.7333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.8241600000000001,
     "ci_low": -0.94159,
     "ci_high": -0.70762,
     "n": 30,
     "n_instances": 6
    }
   },
   "pivotal-seat": {
    "deal_rate": {
     "estimate": -0.9,
     "ci_low": -1.0,
     "ci_high": -0.7666666666666667,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.8493233333333333,
     "ci_low": -0.9590599999999998,
     "ci_high": -0.73526,
     "n": 30,
     "n_instances": 6
    }
   },
   "small-frontier": {
    "deal_rate": {
     "estimate": -0.8,
     "ci_low": -0.9666666666666667,
     "ci_high": -0.6,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.7377333333333334,
     "ci_low": -0.9399466666666666,
     "ci_high": -0.47503333333333336,
     "n": 30,
     "n_instances": 6
    }
   }
  },
  "one_rational": {
   "easy": {
    "deal_rate": {
     "estimate": -0.1,
     "ci_low": -0.225,
     "ci_high": 0.025,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.09625499999999998,
     "ci_low": -0.19690337500000005,
     "ci_high": 0.02540006249999998,
     "n": 40,
     "n_instances": 8
    }
   },
   "hard": {
    "deal_rate": {
     "estimate": -0.35,
     "ci_low": -0.45,
     "ci_high": -0.25,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.3424175,
     "ci_low": -0.43495249999999996,
     "ci_high": -0.2594023125,
     "n": 40,
     "n_instances": 8
    }
   },
   "high-conflict": {
    "deal_rate": {
     "estimate": -0.2,
     "ci_low": -0.3333333333333333,
     "ci_high": -0.06666666666666667,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.21954333333333334,
     "ci_low": -0.32718,
     "ci_high": -0.11168,
     "n": 30,
     "n_instances": 6
    }
   },
   "large-frontier": {
    "deal_rate": {
     "estimate": -0.16666666666666666,
     "ci_low": -0.4,
     "ci_high": 0.03333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.14880666666666667,
     "ci_low": -0.3586500000000001,
     "ci_high": 0.06609333333333332,
     "n": 30,
     "n_instances": 6
    }
   },
   "medium": {
    "deal_rate": {
     "estimate": -0.125,
     "ci_low": -0.3,
     "ci_high": 0.025,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.11989000000000001,
     "ci_low": -0.27598749999999994,
     "ci_high": 0.008635000000000004,
     "n": 40,
     "n_instances": 8
    }
   },
   "no-clear-win-win": {
    "deal_rate": {
     "estimate": -0.3,
     "ci_low": -0.4666666666666667,
     "ci_high": -0.16583333333334546,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.30536333333333343,
     "ci_low": -0.4652233333333333,
     "ci_high": -0.16580825000000488,
     "n": 30,
     "n_instances": 6
    }
   },
   "pivotal-seat": {
    "deal_rate": {
     "estimate": -0.36666666666666664,
     "ci_low": -0.4666666666666667,
     "ci_high": -0.26666666666666666,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.35567333333333345,
     "ci_low": -0.4656166666666666,
     "ci_high": -0.25987000000000005,
     "n": 30,
     "n_instances": 6
    }
   },
   "small-frontier": {
    "deal_rate": {
     "estimate": -0.13333333333333333,
     "ci_low": -0.26666666666666666,
     "ci_high": 0.03333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.13011999999999999,
     "ci_low": -0.2674166666666667,
     "ci_high": 0.022016666666666677,
     "n": 30,
     "n_instances": 6
    }
   }
  },
  "rational_advised_llm": {
   "easy": {
    "deal_rate": {
     "estimate": 0.025,
     "ci_low": -0.05,
     "ci_high": 0.1,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.016370000000000003,
     "ci_low": -0.058704999999999986,
     "ci_high": 0.09389,
     "n": 40,
     "n_instances": 8
    }
   },
   "hard": {
    "deal_rate": {
     "estimate": -0.175,
     "ci_low": -0.375,
     "ci_high": -0.025,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.17596499999999998,
     "ci_low": -0.37988750000000004,
     "ci_high": -0.016898125000000253,
     "n": 40,
     "n_instances": 8
    }
   },
   "high-conflict": {
    "deal_rate": {
     "estimate": -0.2,
     "ci_low": -0.4666666666666667,
     "ci_high": -0.03333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.19425,
     "ci_low": -0.45758,
     "ci_high": -0.031279999999999995,
     "n": 30,
     "n_instances": 6
    }
   },
   "large-frontier": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": -0.13333333333333333,
     "ci_high": 0.13333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.004086666666666665,
     "ci_low": -0.11746999999999999,
     "ci_high": 0.10984000000000001,
     "n": 30,
     "n_instances": 6
    }
   },
   "medium": {
    "deal_rate": {
     "estimate": -0.025,
     "ci_low": -0.1,
     "ci_high": 0.05,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.023792499999999994,
     "ci_low": -0.098518125,
     "ci_high": 0.05180174999999997,
     "n": 40,
     "n_instances": 8
    }
   },
   "no-clear-win-win": {
    "deal_rate": {
     "estimate": -0.26666666666666666,
     "ci_low": -0.5,
     "ci_high": -0.06666666666666667,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.27221000000000006,
     "ci_low": -0.4963033333333333,
     "ci_high": -0.08784666666666667,
     "n": 30,
     "n_instances": 6
    }
   },
   "pivotal-seat": {
    "deal_rate": {
     "estimate": -0.1,
     "ci_low": -0.23333333333333334,
     "ci_high": 0.0,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.10128666666666668,
     "ci_low": -0.22857333333333332,
     "ci_high": 0.001906666666666664,
     "n": 30,
     "n_instances": 6
    }
   },
   "small-frontier": {
    "deal_rate": {
     "estimate": -0.13333333333333333,
     "ci_low": -0.4,
     "ci_high": 0.06666666666666667,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.1428133333333333,
     "ci_low": -0.42138000000000003,
     "ci_high": 0.058336666666666676,
     "n": 30,
     "n_instances": 6
    }
   }
  },
  "interpreter_advised_llm": {
   "easy": {
    "deal_rate": {
     "estimate": 0.05,
     "ci_low": 0.0,
     "ci_high": 0.125,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.06315000000000001,
     "ci_low": 0.00909362500000001,
     "ci_high": 0.13073206249999986,
     "n": 40,
     "n_instances": 8
    }
   },
   "hard": {
    "deal_rate": {
     "estimate": -0.05,
     "ci_low": -0.125,
     "ci_high": 0.0,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.0423225,
     "ci_low": -0.11065981250000001,
     "ci_high": 0.018774999999999997,
     "n": 40,
     "n_instances": 8
    }
   },
   "high-conflict": {
    "deal_rate": {
     "estimate": -0.03333333333333333,
     "ci_low": -0.1,
     "ci_high": 0.0,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.022353333333333343,
     "ci_low": -0.08844333333333333,
     "ci_high": 0.02214999999999999,
     "n": 30,
     "n_instances": 6
    }
   },
   "large-frontier": {
    "deal_rate": {
     "estimate": 0.03333333333333333,
     "ci_low": -0.06666666666666667,
     "ci_high": 0.13333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.04089666666666668,
     "ci_low": -0.0619230833333333,
     "ci_high": 0.1519333333333333,
     "n": 30,
     "n_instances": 6
    }
   },
   "medium": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": -0.075,
     "ci_high": 0.075,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.003822500000000001,
     "ci_low": -0.06857250000000001,
     "ci_high": 0.0748928125,
     "n": 40,
     "n_instances": 8
    }
   },
   "no-clear-win-win": {
    "deal_rate": {
     "estimate": -0.06666666666666667,
     "ci_low": -0.13333333333333333,
     "ci_high": 0.0,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.05902666666666668,
     "ci_low": -0.13701333333333332,
     "ci_high": 0.015290000000000003,
     "n": 30,
     "n_instances": 6
    }
   },
   "pivotal-seat": {
    "deal_rate": {
     "estimate": -0.03333333333333333,
     "ci_low": -0.1,
     "ci_high": 0.0,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.026766666666666668,
     "ci_low": -0.10633666666666668,
     "ci_high": 0.03854333333333334,
     "n": 30,
     "n_instances": 6
    }
   },
   "small-frontier": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": -0.1,
     "ci_high": 0.1,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.01621666666666667,
     "ci_low": -0.08424999999999999,
     "ci_high": 0.10709999999999999,
     "n": 30,
     "n_instances": 6
    }
   }
  },
  "all_interpreter_advised_llm": {
   "easy": {
    "deal_rate": {
     "estimate": 0.05,
     "ci_low": 0.0,
     "ci_high": 0.125,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.05291249999999999,
     "ci_low": 0.008327312499999993,
     "ci_high": 0.11253499999999998,
     "n": 40,
     "n_instances": 8
    }
   },
   "hard": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": -0.075,
     "ci_high": 0.075,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.012180000000000002,
     "ci_low": -0.0688151875,
     "ci_high": 0.10087412499999998,
     "n": 40,
     "n_instances": 8
    }
   },
   "high-conflict": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": 0.0,
     "ci_high": 0.0,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.007706666666666662,
     "ci_low": -0.014816666666666664,
     "ci_high": 0.031249999999999986,
     "n": 30,
     "n_instances": 6
    }
   },
   "large-frontier": {
    "deal_rate": {
     "estimate": 0.06666666666666667,
     "ci_low": 0.0,
     "ci_high": 0.13333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.04802666666666666,
     "ci_low": -0.011209999999999998,
     "ci_high": 0.12843749999999937,
     "n": 30,
     "n_instances": 6
    }
   },
   "medium": {
    "deal_rate": {
     "estimate": 0.025,
     "ci_low": 0.0,
     "ci_high": 0.075,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.014300000000000007,
     "ci_low": -0.024592499999999993,
     "ci_high": 0.06978500000000001,
     "n": 40,
     "n_instances": 8
    }
   },
   "no-clear-win-win": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": -0.1,
     "ci_high": 0.1,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.003880000000000013,
     "ci_low": -0.10353666666666665,
     "ci_high": 0.12782000000000002,
     "n": 30,
     "n_instances": 6
    }
   },
   "pivotal-seat": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": -0.1,
     "ci_high": 0.1,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.020793333333333337,
     "ci_low": -0.08851241666666664,
     "ci_high": 0.1408866666666667,
     "n": 30,
     "n_instances": 6
    }
   },
   "small-frontier": {
    "deal_rate": {
     "estimate": 0.06666666666666667,
     "ci_low": 0.0,
     "ci_high": 0.13333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.06394000000000001,
     "ci_low": -0.025059999999999992,
     "ci_high": 0.16707666666666665,
     "n": 30,
     "n_instances": 6
    }
   }
  },
  "one_oracle": {
   "easy": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": -0.1,
     "ci_high": 0.1,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.0034524999999999916,
     "ci_low": -0.097901375,
     "ci_high": 0.09522624999999986,
     "n": 40,
     "n_instances": 8
    }
   },
   "hard": {
    "deal_rate": {
     "estimate": -0.075,
     "ci_low": -0.175,
     "ci_high": 0.0,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.08085500000000001,
     "ci_low": -0.19456,
     "ci_high": 0.004419999999999999,
     "n": 40,
     "n_instances": 8
    }
   },
   "high-conflict": {
    "deal_rate": {
     "estimate": -0.03333333333333333,
     "ci_low": -0.1,
     "ci_high": 0.0,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.035946666666666675,
     "ci_low": -0.12365333333333334,
     "ci_high": 0.018163583333333268,
     "n": 30,
     "n_instances": 6
    }
   },
   "large-frontier": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": -0.13333333333333333,
     "ci_high": 0.13333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.006763333333333343,
     "ci_low": -0.11209333333333334,
     "ci_high": 0.11117333333333332,
     "n": 30,
     "n_instances": 6
    }
   },
   "medium": {
    "deal_rate": {
     "estimate": -0.05,
     "ci_low": -0.15,
     "ci_high": 0.05,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.04694250000000001,
     "ci_low": -0.1374555,
     "ci_high": 0.04477187499999989,
     "n": 40,
     "n_instances": 8
    }
   },
   "no-clear-win-win": {
    "deal_rate": {
     "estimate": -0.06666666666666667,
     "ci_low": -0.2,
     "ci_high": 0.0,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.06049666666666666,
     "ci_low": -0.1988633333333333,
     "ci_high": 0.014676833333333235,
     "n": 30,
     "n_instances": 6
    }
   },
   "pivotal-seat": {
    "deal_rate": {
     "estimate": -0.1,
     "ci_low": -0.23333333333333334,
     "ci_high": 0.0,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.10819666666666668,
     "ci_low": -0.24617333333333333,
     "ci_high": 0.005270000000000005,
     "n": 30,
     "n_instances": 6
    }
   },
   "small-frontier": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": -0.1,
     "ci_high": 0.1,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.012919999999999994,
     "ci_low": -0.0813,
     "ci_high": 0.09570333333333333,
     "n": 30,
     "n_instances": 6
    }
   }
  },
  "all_oracle": {
   "easy": {
    "deal_rate": {
     "estimate": 0.05,
     "ci_low": 0.0,
     "ci_high": 0.125,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.016247500000000015,
     "ci_low": -0.028485,
     "ci_high": 0.06430325,
     "n": 40,
     "n_instances": 8
    }
   },
   "hard": {
    "deal_rate": {
     "estimate": 0.05,
     "ci_low": 0.0,
     "ci_high": 0.1,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.0649325,
     "ci_low": -0.006227500000000006,
     "ci_high": 0.15460500000000002,
     "n": 40,
     "n_instances": 8
    }
   },
   "high-conflict": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": 0.0,
     "ci_high": 0.0,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.02970666666666667,
     "ci_low": -0.06457666666666667,
     "ci_high": 0.013349999999999996,
     "n": 30,
     "n_instances": 6
    }
   },
   "large-frontier": {
    "deal_rate": {
     "estimate": 0.06666666666666667,
     "ci_low": 0.0,
     "ci_high": 0.13333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.04246666666666666,
     "ci_low": -0.01455333333333334,
     "ci_high": 0.09363666666666665,
     "n": 30,
     "n_instances": 6
    }
   },
   "medium": {
    "deal_rate": {
     "estimate": 0.025,
     "ci_low": 0.0,
     "ci_high": 0.075,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.021552500000000002,
     "ci_low": -0.024745625,
     "ci_high": 0.06991956249999998,
     "n": 40,
     "n_instances": 8
    }
   },
   "no-clear-win-win": {
    "deal_rate": {
     "estimate": 0.06666666666666667,
     "ci_low": 0.0,
     "ci_high": 0.13333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.08198333333333334,
     "ci_low": -0.016203333333333337,
     "ci_high": 0.19658666666666672,
     "n": 30,
     "n_instances": 6
    }
   },
   "pivotal-seat": {
    "deal_rate": {
     "estimate": 0.06666666666666667,
     "ci_low": 0.0,
     "ci_high": 0.13333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.07603666666666667,
     "ci_low": -0.016820000000000012,
     "ci_high": 0.19633666666666666,
     "n": 30,
     "n_instances": 6
    }
   },
   "small-frontier": {
    "deal_rate": {
     "estimate": 0.06666666666666667,
     "ci_low": 0.0,
     "ci_high": 0.13333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.08898000000000002,
     "ci_low": 0.005826666666666673,
     "ci_high": 0.19663666666666663,
     "n": 30,
     "n_instances": 6
    }
   }
  }
 },
 "no_deal_scatter": {
  "all_llm": [
   [
    0.0,
    0.2
   ],
   [
    0.0,
    0.2
   ],
   [
    0.08620689655172414,
    0.0
   ],
   [
    0.18421052631578946,
    0.0
   ],
   [
    0.2692307692307692,
    0.2
   ],
   [
    0.3103448275862069,
    0.0
   ],
   [
    0.32926829268292684,
    0.0
   ],
   [
    0.3333333333333333,
    0.2
   ],
   [
    0.36,
    0.0
   ],
   [
    0.417910447761194,
    0.0
   ],
   [
    0.43103448275862066,
    0.0
   ],
   [
    0.43333333333333335,
    0.0
   ],
   [
    0.4387755102040816,
    0.0
   ],
   [
    0.43902439024390244,
    0.0
   ],
   [
    0.4523809523809524,
    0.0
   ],
   [
    0.4666666666666667,
    0.0
   ],
   [
    0.46875,
    0.0
   ],
   [
    0.4727272727272727,
    0.0
   ],
   [
    0.4827586206896552,
    0.0
   ],
   [
    0.49122807017543857,
    0.0
   ],
   [
    0.49230769230769234,
    0.0
   ],
   [
    0.4959349593495935,
    0.0
   ],
   [
    0.55,
    0.2
   ],
   [
    0.651685393258427,
    0.0
   ]
  ],
  "all_rational": [
   [
    0.0,
    0.8
   ],
   [
    0.0,
    1.0
   ],
   [
    0.08620689655172414,
    1.0
   ],
   [
    0.18421052631578946,
    1.0
   ],
   [
    0.2692307692307692,
    0.8
   ],
   [
    0.3103448275862069,
    0.8
   ],
   [
    0.32926829268292684,
    0.6
   ],
   [
    0.3333333333333333,
    0.6
   ],
   [
    0.36,
    1.0
   ],
   [
    0.417910447761194,
    0.8
   ],
   [
    0.43103448275862066,
    1.0
   ],
   [
    0.43333333333333335,
    0.4
   ],
   [
    0.4387755102040816,
    0.8
   ],
   [
    0.43902439024390244,
    0.8
   ],
   [
    0.4523809523809524,
    0.6
   ],
   [
    0.4666666666666667,
    1.0
   ],
   [
    0.46875,
    1.0
   ],
   [
    0.4727272727272727,
    0.0
   ],
   [
    0.4827586206896552,
    0.6
   ],
   [
    0.49122807017543857,
    1.0
   ],
   [
    0.49230769230769234,
    1.0
   ],
   [
    0.4959349593495935,
    0.4
   ],
   [
    0.55,
    0.4
   ],
   [
    0.651685393258427,
    1.0
   ]
  ],
  "one_rational": [
   [
    0.0,
    0.4
   ],
   [
    0.0,
    0.6
   ],
   [
    0.08620689655172414,
    0.4
   ],
   [
    0.18421052631578946,
    0.4
   ],
   [
    0.2692307692307692,
    0.0
   ],
   [
    0.3103448275862069,
    0.0
   ],
   [
    0.32926829268292684,
    0.2
   ],
   [
    0.3333333333333333,
    0.2
   ],
   [
    0.36,
    0.0
   ],
   [
    0.417910447761194,
    0.2
   ],
   [
    0.43103448275862066,
    0.2
   ],
   [
    0.43333333333333335,
    0.2
   ],
   [
    0.4387755102040816,
    0.0
   ],
   [
    0.43902439024390244,
    0.2
   ],
   [
    0.4523809523809524,
    0.4
   ],
   [
    0.4666666666666667,
    0.6
   ],
   [
    0.46875,
    0.2
   ],
   [
    0.4727272727272727,
    0.0
   ],
   [
    0.4827586206896552,
    0.2
   ],
   [
    0.49122807017543857,
    0.4
   ],
   [
    0.49230769230769234,
    0.2
   ],
   [
    0.4959349593495935,
    0.0
   ],
   [
    0.55,
    0.0
   ],
   [
    0.651685393258427,
    0.6
   ]
  ],
  "rational_advised_llm": [
   [
    0.0,
    0.4
   ],
   [
    0.0,
    0.6
   ],
   [
    0.08620689655172414,
    0.0
   ],
   [
    0.18421052631578946,
    0.0
   ],
   [
    0.2692307692307692,
    0.0
   ],
   [
    0.3103448275862069,
    0.2
   ],
   [
    0.32926829268292684,
    0.2
   ],
   [
    0.3333333333333333,
    0.0
   ],
   [
    0.36,
    0.0
   ],
   [
    0.417910447761194,
    0.0
   ],
   [
    0.43103448275862066,
    0.0
   ],
   [
    0.43333333333333335,
    0.0
   ],
   [
    0.4387755102040816,
    0.0
   ],
   [
    0.43902439024390244,
    0.0
   ],
   [
    0.4523809523809524,
    0.0
   ],
   [
    0.4666666666666667,
    0.2
   ],
   [
    0.46875,
    0.0
   ],
   [
    0.4727272727272727,
    0.0
   ],
   [
    0.4827586206896552,
    0.0
   ],
   [
    0.49122807017543857,
    0.8
   ],
   [
    0.49230769230769234,
    0.0
   ],
   [
    0.4959349593495935,
    0.0
   ],
   [
    0.55,
    0.0
   ],
   [
    0.651685393258427,
    0.0
   ]
  ],
  "interpreter_advised_llm": [
   [
    0.0,
    0.2
   ],
   [
    0.0,
    0.4
   ],
   [
    0.08620689655172414,
    0.0
   ],
   [
    0.18421052631578946,
    0.0
   ],
   [
    0.2692307692307692,
    0.0
   ],
   [
    0.3103448275862069,
    0.0
   ],
   [
    0.32926829268292684,
    0.0
   ],
   [
    0.3333333333333333,
    0.0
   ],
   [
    0.36,
    0.2
   ],
   [
    0.417910447761194,
    0.0
   ],
   [
    0.43103448275862066,
    0.0
   ],
   [
    0.43333333333333335,
    0.0
   ],
   [
    0.4387755102040816,
    0.0
   ],
   [
    0.43902439024390244,
    0.0
   ],
   [
    0.4523809523809524,
    0.0
   ],
   [
    0.4666666666666667,
    0.0
   ],
   [
    0.46875,
    0.2
   ],
   [
    0.4727272727272727,
    0.0
   ],
   [
    0.4827586206896552,
    0.0
   ],
   [
    0.49122807017543857,
    0.0
   ],
   [
    0.49230769230769234,
    0.0
   ],
   [
    0.4959349593495935,
    0.0
   ],
   [
    0.55,
    0.0
   ],
   [
    0.651685393258427,
    0.0
   ]
  ],
  "all_interpreter_advised_llm": [
   [
    0.0,
    0.0
   ],
   [
    0.0,
    0.4
   ],
   [
    0.08620689655172414,
    0.0
   ],
   [
    0.18421052631578946,
    0.0
   ],
   [
    0.2692307692307692,
    0.0
   ],
   [
    0.3103448275862069,
    0.0
   ],
   [
    0.32926829268292684,
    0.0
   ],
   [
    0.3333333333333333,
    0.0
   ],
   [
    0.36,
    0.0
   ],
   [
    0.417910447761194,
    0.0
   ],
   [
    0.43103448275862066,
    0.0
   ],
   [
    0.43333333333333335,
    0.0
   ],
   [
    0.4387755102040816,
    0.0
   ],
   [
    0.43902439024390244,
    0.0
   ],
   [
    0.4523809523809524,
    0.0
   ],
   [
    0.4666666666666667,
    0.0
   ],
   [
    0.46875,
    0.0
   ],
   [
    0.4727272727272727,
    0.0
   ],
   [
    0.4827586206896552,
    0.0
   ],
   [
    0.49122807017543857,
    0.0
   ],
   [
    0.49230769230769234,
    0.0
   ],
   [
    0.4959349593495935,
    0.0
   ],
   [
    0.55,
    0.0
   ],
   [
    0.651685393258427,
    0.0
   ]
  ],
  "one_oracle": [
   [
    0.0,
    0.2
   ],
   [
    0.0,
    0.6
   ],
   [
    0.08620689655172414,
    0.0
   ],
   [
    0.18421052631578946,
    0.2
   ],
   [
    0.2692307692307692,
    0.0
   ],
   [
    0.3103448275862069,
    0.0
   ],
   [
    0.32926829268292684,
    0.0
   ],
   [
    0.3333333333333333,
    0.0
   ],
   [
    0.36,
    0.0
   ],
   [
    0.417910447761194,
    0.2
   ],
   [
    0.43103448275862066,
    0.2
   ],
   [
    0.43333333333333335,
    0.0
   ],
   [
    0.4387755102040816,
    0.2
   ],
   [
    0.43902439024390244,
    0.0
   ],
   [
    0.4523809523809524,
    0.2
   ],
   [
    0.4666666666666667,
    0.2
   ],
   [
    0.46875,
    0.0
   ],
   [
    0.4727272727272727,
    0.0
   ],
   [
    0.4827586206896552,
    0.0
   ],
   [
    0.49122807017543857,
    0.0
   ],
   [
    0.49230769230769234,
    0.0
   ],
   [
    0.4959349593495935,
    0.0
   ],
   [
    0.55,
    0.0
   ],
   [
    0.651685393258427,
    0.0
   ]
  ],
  "all_oracle": [
   [
    0.0,
    0.0
   ],
   [
    0.0,
    0.0
   ],
   [
    0.08620689655172414,
    0.0
   ],
   [
    0.18421052631578946,
    0.0
   ],
   [
    0.2692307692307692,
    0.0
   ],
   [
    0.3103448275862069,
    0.0
   ],
   [
    0.32926829268292684,
    0.0
   ],
   [
    0.3333333333333333,
    0.0
   ],
   [
    0.36,
    0.0
   ],
   [
    0.417910447761194,
    0.0
   ],
   [
    0.43103448275862066,
    0.0
   ],
   [
    0.43333333333333335,
    0.0
   ],
   [
    0.4387755102040816,
    0.0
   ],
   [
    0.43902439024390244,
    0.0
   ],
   [
    0.4523809523809524,
    0.0
   ],
   [
    0.4666666666666667,
    0.0
   ],
   [
    0.46875,
    0.0
   ],
   [
    0.4727272727272727,
    0.0
   ],
   [
    0.4827586206896552,
    0.0
   ],
   [
    0.49122807017543857,
    0.0
   ],
   [
    0.49230769230769234,
    0.0
   ],
   [
    0.4959349593495935,
    0.0
   ],
   [
    0.55,
    0.0
   ],
   [
    0.651685393258427,
    0.0
   ]
  ]
 },
 "plots": [
  ".claude/products/five-seat-advised-advocate-wave3/fairness_basket_vs_all_llm/fairness_basket.png",
  ".claude/products/five-seat-advised-advocate-wave3/fairness_basket_vs_all_llm/fairness_basket.pdf"
 ]
}