{
 "schema": "five-seat-fairness-basket-v1",
 "reference": "rational_advised_llm",
 "arms": [
  "all_llm",
  "one_rational",
  "rational_advised_llm",
  "interpreter_advised_llm",
  "one_oracle",
  "all_oracle",
  "all_rational"
 ],
 "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": 0.6201430300777417,
    "ci_high": 0.6900437826532168,
    "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
   }
  },
  "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": 0.6053134954875482,
    "ci_high": 0.6745053190797836,
    "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": 0.6153988795733067,
    "ci_high": 0.6780492046556041,
    "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": 0.6243408250276867,
    "ci_high": 0.6904888855352304,
    "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
   }
  },
  "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": 0.6107054495371693,
    "ci_high": 0.6895755574098186,
    "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": 0.6116336184036487,
    "ci_high": 0.6812809657953525,
    "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
   }
  },
  "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": 0.5126514720991605,
    "ci_high": 0.6102331784787526,
    "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
   }
  }
 },
 "n_bootstrap": 10000,
 "seed": 20260809,
 "n_episodes": {
  "all_llm": 120,
  "one_rational": 120,
  "rational_advised_llm": 120,
  "interpreter_advised_llm": 120,
  "one_oracle": 120,
  "all_oracle": 120,
  "all_rational": 120
 },
 "n_deals": {
  "all_llm": 115,
  "one_rational": 92,
  "rational_advised_llm": 108,
  "interpreter_advised_llm": 115,
  "one_oracle": 110,
  "all_oracle": 120,
  "all_rational": 28
 },
 "levels": {
  "all_llm": {
   "deal_rate": {
    "estimate": 0.9583333333333334,
    "ci_low": 0.925,
    "ci_high": 0.9833333333333333,
    "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": 0.20660835047918574,
    "ci_high": 0.30600756625601455,
    "n": 115,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.07733378037747124,
    "ci_low": 0.06372168254261014,
    "ci_high": 0.08964987629498626,
    "n": 115,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.46360609046022655,
    "ci_low": 0.3565226072213674,
    "ci_high": 0.5826609489932553,
    "n": 115,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.39841757139287376,
    "ci_low": 0.3159915975593445,
    "ci_high": 0.4740919744695105,
    "n": 115,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.22312596428528939,
    "ci_low": 0.19971159081455367,
    "ci_high": 0.24672232651727338,
    "n": 115,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.5347356494115132,
    "ci_low": 0.45934698095845394,
    "ci_high": 0.6015353499949824,
    "n": 115,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.29899227726399724,
    "ci_low": 0.28754462333382413,
    "ci_high": 0.30927339521265834,
    "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": 0.8327347083333333,
    "ci_high": 0.9104252291666667,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.5124549973527001,
    "ci_low": 0.4301153246627236,
    "ci_high": 0.586181608900662,
    "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
   }
  },
  "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": 0.19683072717163422,
    "ci_high": 0.28224996743845204,
    "n": 92,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.0725120810975585,
    "ci_low": 0.06097860651045568,
    "ci_high": 0.08370679860351421,
    "n": 92,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.44434457646545117,
    "ci_low": 0.34251356481754514,
    "ci_high": 0.5676758504505426,
    "n": 92,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.41411311378312343,
    "ci_low": 0.3323445296545228,
    "ci_high": 0.49140176345459324,
    "n": 92,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.23136952807084968,
    "ci_low": 0.2087369470730114,
    "ci_high": 0.2545594254167545,
    "n": 92,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.5063123982328782,
    "ci_low": 0.43981796588074573,
    "ci_high": 0.5641182063092108,
    "n": 92,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.30102142748483496,
    "ci_low": 0.28908559020113483,
    "ci_high": 0.3133682464419921,
    "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": 0.6125244166666667,
    "ci_high": 0.7606728333333334,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.38817283864520663,
    "ci_low": 0.3200574611095578,
    "ci_high": 0.45228780607010843,
    "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": 0.22079647397565216,
    "ci_high": 0.46032524493968746,
    "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": 0.20588192810419068,
    "ci_high": 0.29478521898544624,
    "n": 108,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.07598800278802065,
    "ci_low": 0.06420405442084354,
    "ci_high": 0.08721121659758677,
    "n": 108,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.4781650421527495,
    "ci_low": 0.38384083862143753,
    "ci_high": 0.581430530006112,
    "n": 108,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.45763156935745003,
    "ci_low": 0.37400906809654,
    "ci_high": 0.5343891029912663,
    "n": 108,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.23159563260933352,
    "ci_low": 0.20996228671838432,
    "ci_high": 0.2532847937452672,
    "n": 108,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.525631904439619,
    "ci_low": 0.4657191892852127,
    "ci_high": 0.579545192042175,
    "n": 108,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.3023671533397975,
    "ci_low": 0.29102942776003526,
    "ci_high": 0.3130323876584692,
    "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": 0.7259901458333332,
    "ci_high": 0.8836802291666667,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.4730687139956571,
    "ci_low": 0.39187728989485976,
    "ci_high": 0.5445305354572809,
    "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": 0.4563129859973735,
    "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": 0.2246920685802303,
    "ci_high": 0.30989615487474587,
    "n": 115,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.08183640825255681,
    "ci_low": 0.06906536649344422,
    "ci_high": 0.09304294329484511,
    "n": 115,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.4116431753333182,
    "ci_low": 0.3108729437989708,
    "ci_high": 0.5347941667716734,
    "n": 115,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.36606048552080234,
    "ci_low": 0.2943508222182356,
    "ci_high": 0.4300883670743269,
    "n": 115,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.2144021422360019,
    "ci_low": 0.19599785314513896,
    "ci_high": 0.2327798444558433,
    "n": 115,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.5425545088981604,
    "ci_low": 0.47726289299154334,
    "ci_high": 0.5975320288481668,
    "n": 115,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.2960790571733364,
    "ci_low": 0.2851950555597496,
    "ci_high": 0.306583161157282,
    "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": 0.8358273125,
    "ci_high": 0.9212710416666666,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.5199480710274036,
    "ci_low": 0.44140233605366574,
    "ci_high": 0.5865307672431204,
    "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
   }
  },
  "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": 0.15220588218325654,
    "ci_high": 0.2520162262625005,
    "n": 110,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.058582652990355755,
    "ci_low": 0.04724879521114121,
    "ci_high": 0.0697843321051137,
    "n": 110,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.5502155166421395,
    "ci_low": 0.4355103425799059,
    "ci_high": 0.6743700297081331,
    "n": 110,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.5241960242972619,
    "ci_low": 0.42556402400791543,
    "ci_high": 0.6137548879342425,
    "n": 110,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.26570818208794883,
    "ci_low": 0.23680217406711732,
    "ci_high": 0.29289045515917334,
    "n": 110,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.47216530427836567,
    "ci_low": 0.39488018587278173,
    "ci_high": 0.5463052174320897,
    "n": 110,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.3143537476799115,
    "ci_low": 0.2972221977659884,
    "ci_high": 0.3314974965305435,
    "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": 0.7672437083333333,
    "ci_high": 0.8842517708333332,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.4328181955885018,
    "ci_low": 0.3494684613042903,
    "ci_high": 0.5145233653643979,
    "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": 0.09909886322950232,
    "ci_high": 0.4198478030050496,
    "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": 0.1183633018112518,
    "ci_high": 0.21966347278571574,
    "n": 120,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.0484048449564163,
    "ci_low": 0.03651114441182694,
    "ci_high": 0.06066532594641663,
    "n": 120,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.6306371226240565,
    "ci_low": 0.5202313278987801,
    "ci_high": 0.7559524553199843,
    "n": 120,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.549472048212886,
    "ci_low": 0.44877145966030035,
    "ci_high": 0.6487582137658562,
    "n": 120,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.2854855910779398,
    "ci_low": 0.2557754883631389,
    "ci_high": 0.31435320789081594,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.405530944848298,
    "ci_low": 0.31578914493347343,
    "ci_high": 0.4914876556657148,
    "n": 120,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.31912538492110715,
    "ci_low": 0.3027884961625283,
    "ci_high": 0.33555231350944,
    "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": 0.8802970625,
    "ci_high": 0.9325118541666666,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.405530944848298,
    "ci_low": 0.31578914493347343,
    "ci_high": 0.4914876556657148,
    "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
   }
  },
  "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": 0.10277973891405223,
    "ci_high": 0.19436100475353346,
    "n": 28,
    "n_instances": 14
   },
   "worst_off_share": {
    "estimate": 0.05224324367491081,
    "ci_low": 0.03743994830704269,
    "ci_high": 0.06737766341088748,
    "n": 28,
    "n_instances": 14
   },
   "dist_to_nbs": {
    "estimate": 0.5995994212802717,
    "ci_low": 0.4997858176694715,
    "ci_high": 0.6796781512666987,
    "n": 28,
    "n_instances": 14
   },
   "dist_to_ks": {
    "estimate": 0.5897606666492755,
    "ci_low": 0.520696106253425,
    "ci_high": 0.6487571656266502,
    "n": 28,
    "n_instances": 14
   },
   "normalized_gini": {
    "estimate": 0.2606935627315637,
    "ci_low": 0.23841425650619627,
    "ci_high": 0.28292756312641415,
    "n": 28,
    "n_instances": 14
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.40783781598662144,
    "ci_low": 0.31631314866100474,
    "ci_high": 0.4849954848827147,
    "n": 28,
    "n_instances": 14
   },
   "max_share": {
    "estimate": 0.31364014160553955,
    "ci_low": 0.29899385144477997,
    "ci_high": 0.3265161495559122,
    "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": 0.1109945625,
    "ci_high": 0.2776496041666667,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.09516215706354499,
    "ci_low": 0.05037852437035143,
    "ci_high": 0.14536570809198895,
    "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": 0.285458998992857,
    "ci_high": 0.43594435365406176,
    "n": 92,
    "n_instances": 23
   }
  }
 },
 "paired_minus_reference": {
  "all_llm": {
   "deal_rate": {
    "estimate": 0.058333333333333334,
    "ci_low": -0.016666666666666666,
    "ci_high": 0.15,
    "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": -0.017174476433832724,
    "ci_high": 0.026634591214021192,
    "n": 105,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.0016530070612752986,
    "ci_low": -0.005106863959339499,
    "ci_high": 0.008927451068141747,
    "n": 105,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": -0.01941517414073938,
    "ci_low": -0.0713080376254483,
    "ci_high": 0.028652821140940688,
    "n": 105,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": -0.04359032273774962,
    "ci_low": -0.09295984703308392,
    "ci_high": 0.0026189139167547846,
    "n": 105,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": -0.009342265150020847,
    "ci_low": -0.025949767022194647,
    "ci_high": 0.00435867509136858,
    "n": 105,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.015993210483082845,
    "ci_low": -0.0036075498055912368,
    "ci_high": 0.03743182688271353,
    "n": 105,
    "n_instances": 24
   },
   "max_share": {
    "estimate": -0.002669012637296196,
    "ci_low": -0.010214984461826008,
    "ci_high": 0.00379371672974635,
    "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": -0.008756312499999998,
    "ci_high": 0.15151179166666662,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.0393862833570429,
    "ci_low": -0.00672862252551754,
    "ci_high": 0.10611192521742129,
    "n": 120,
    "n_instances": 24
   }
  },
  "one_rational": {
   "deal_rate": {
    "estimate": -0.13333333333333333,
    "ci_low": -0.21666666666666667,
    "ci_high": -0.05,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 88,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": -0.015567723095736924,
    "ci_low": -0.04780563794302597,
    "ci_high": 0.01514999069308827,
    "n": 88,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": -0.0052378662336368615,
    "ci_low": -0.015358452345668665,
    "ci_high": 0.004579883233143351,
    "n": 88,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": -0.03656957137963972,
    "ci_low": -0.10708059149953383,
    "ci_high": 0.028715826839108047,
    "n": 88,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": -0.04065826216687626,
    "ci_low": -0.11813360419692012,
    "ci_high": 0.03182233947645342,
    "n": 88,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.002135628281294717,
    "ci_low": -0.017429012588677312,
    "ci_high": 0.020160997565510146,
    "n": 88,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": -0.019518711859381758,
    "ci_low": -0.05337113410353349,
    "ci_high": 0.012289452611185702,
    "n": 88,
    "n_instances": 24
   },
   "max_share": {
    "estimate": -0.0010866712212825246,
    "ci_low": -0.00983410906468484,
    "ci_high": 0.00788632039454762,
    "n": 88,
    "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": -0.12505833333333335,
    "ci_low": -0.19965599999999997,
    "ci_high": -0.04624804166666667,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": -0.08489587535045051,
    "ci_low": -0.13950672976746323,
    "ci_high": -0.028437559705253884,
    "n": 120,
    "n_instances": 24
   }
  },
  "interpreter_advised_llm": {
   "deal_rate": {
    "estimate": 0.058333333333333334,
    "ci_low": -0.008333333333333333,
    "ci_high": 0.14166666666666666,
    "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": 0.01784403643093942,
    "ci_low": -0.007375080806021105,
    "ci_high": 0.04271231268764003,
    "n": 106,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": 0.006654347648928932,
    "ci_low": -0.0010560601427259731,
    "ci_high": 0.014537452335377022,
    "n": 106,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": -0.06750503648087798,
    "ci_low": -0.13408960918743867,
    "ci_high": 0.0004358859785666099,
    "n": 106,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": -0.08128661532384482,
    "ci_low": -0.14991064391956094,
    "ci_high": -0.012963385636922165,
    "n": 106,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": -0.017331707920076208,
    "ci_low": -0.0353522378605193,
    "ci_high": -0.0022285380127154606,
    "n": 106,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": 0.019165268098301762,
    "ci_low": -0.0075357043541856,
    "ci_high": 0.04759203438476144,
    "n": 106,
    "n_instances": 24
   },
   "max_share": {
    "estimate": -0.004758555298940799,
    "ci_low": -0.014656925536241806,
    "ci_high": 0.003543484798926732,
    "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": 0.06934583333333334,
    "ci_low": 0.003792354166666661,
    "ci_high": 0.15527152083333332,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": 0.04687935703174647,
    "ci_low": -0.007957064540972033,
    "ci_high": 0.11581000580512628,
    "n": 120,
    "n_instances": 24
   }
  },
  "one_oracle": {
   "deal_rate": {
    "estimate": 0.016666666666666666,
    "ci_low": -0.05,
    "ci_high": 0.10833333333333334,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 101,
    "n_instances": 24
   },
   "worst_off": {
    "estimate": -0.057487246563529,
    "ci_low": -0.08745517437080118,
    "ci_high": -0.03049723168781665,
    "n": 101,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": -0.01830433492156714,
    "ci_low": -0.0276546370674995,
    "ci_high": -0.009821254627079702,
    "n": 101,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.07501949769210059,
    "ci_low": 0.0263354124363131,
    "ci_high": 0.1240209806819489,
    "n": 101,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.08584127980622677,
    "ci_low": 0.02660410140668103,
    "ci_high": 0.15192918538622546,
    "n": 101,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.037458981650735634,
    "ci_low": 0.02230584147716231,
    "ci_high": 0.05328121705153965,
    "n": 101,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": -0.057124048576351026,
    "ci_low": -0.08800842403994062,
    "ci_high": -0.029068361972505705,
    "n": 101,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.01597965954552214,
    "ci_low": 0.007040740327745583,
    "ci_high": 0.02523668463714826,
    "n": 101,
    "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": 0.01737916666666666,
    "ci_low": -0.05821425,
    "ci_high": 0.11134712499999996,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": -0.04025051840715526,
    "ci_low": -0.09541987250167384,
    "ci_high": 0.03524101489843232,
    "n": 120,
    "n_instances": 24
   }
  },
  "all_oracle": {
   "deal_rate": {
    "estimate": 0.1,
    "ci_low": 0.025,
    "ci_high": 0.19166666666666668,
    "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": -0.08323813447524094,
    "ci_low": -0.12485824134423351,
    "ci_high": -0.04388381121595352,
    "n": 108,
    "n_instances": 24
   },
   "worst_off_share": {
    "estimate": -0.026964671393345477,
    "ci_low": -0.03952181502418694,
    "ci_high": -0.015137828286597045,
    "n": 108,
    "n_instances": 24
   },
   "dist_to_nbs": {
    "estimate": 0.15320993826092633,
    "ci_low": 0.07280714047515024,
    "ci_high": 0.235117693002916,
    "n": 108,
    "n_instances": 24
   },
   "dist_to_ks": {
    "estimate": 0.12259299363363763,
    "ci_low": 0.030764053553751135,
    "ci_high": 0.21520917185294325,
    "n": 108,
    "n_instances": 24
   },
   "normalized_gini": {
    "estimate": 0.05378815874169244,
    "ci_low": 0.029634386389922926,
    "ci_high": 0.08011304493144648,
    "n": 108,
    "n_instances": 24
   },
   "normalized_nash_welfare_conditional": {
    "estimate": -0.11220963032454075,
    "ci_low": -0.17138519345139636,
    "ci_high": -0.05871878067055312,
    "n": 108,
    "n_instances": 24
   },
   "max_share": {
    "estimate": 0.01799575895469403,
    "ci_low": 0.006256043831593418,
    "ci_high": 0.031399436107660855,
    "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": 0.09537333333333334,
    "ci_low": 0.01912497916666667,
    "ci_high": 0.19166831249999994,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": -0.06753776914735915,
    "ci_low": -0.13467570514848728,
    "ci_high": 0.004501884972558235,
    "n": 120,
    "n_instances": 24
   }
  },
  "all_rational": {
   "deal_rate": {
    "estimate": -0.6666666666666666,
    "ci_low": -0.775,
    "ci_high": -0.55,
    "n": 120,
    "n_instances": 24
   },
   "below_threshold_accept": {
    "estimate": 0.0,
    "ci_low": 0.0,
    "ci_high": 0.0,
    "n": 27,
    "n_instances": 14
   },
   "worst_off": {
    "estimate": -0.12418673405963024,
    "ci_low": -0.2109844326321454,
    "ci_high": -0.053002389515325855,
    "n": 27,
    "n_instances": 14
   },
   "worst_off_share": {
    "estimate": -0.036102351133913246,
    "ci_low": -0.06430076418185073,
    "ci_high": -0.012022386494047115,
    "n": 27,
    "n_instances": 14
   },
   "dist_to_nbs": {
    "estimate": 0.045866712073663954,
    "ci_low": -0.12243335744680967,
    "ci_high": 0.19172101613851183,
    "n": 27,
    "n_instances": 14
   },
   "dist_to_ks": {
    "estimate": 0.097548437846802,
    "ci_low": -0.10440075414153346,
    "ci_high": 0.2893698483419716,
    "n": 27,
    "n_instances": 14
   },
   "normalized_gini": {
    "estimate": 0.032977244039466294,
    "ci_low": -0.006899458693643506,
    "ci_high": 0.08225954271928151,
    "n": 27,
    "n_instances": 14
   },
   "normalized_nash_welfare_conditional": {
    "estimate": -0.10598017495294662,
    "ci_low": -0.17399415519330344,
    "ci_high": -0.044016417154530516,
    "n": 27,
    "n_instances": 14
   },
   "max_share": {
    "estimate": 0.00229732325366299,
    "ci_low": -0.027895422947579514,
    "ci_high": 0.03182561844784422,
    "n": 27,
    "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": -0.6226258333333333,
    "ci_low": -0.7326825416666667,
    "ci_high": -0.5109391458333333,
    "n": 120,
    "n_instances": 24
   },
   "normalized_nash_welfare": {
    "estimate": -0.37790655693211217,
    "ci_low": -0.45816890260293264,
    "ci_high": -0.29818912511481294,
    "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
   }
  },
  "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
   }
  },
  "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
   }
  },
  "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
   }
  }
 },
 "margin_vs_no_deal_rate": {
  "all_llm": {
   "pearson_r": -0.46490335738860106,
   "ci_low": -0.8231415110480709,
   "ci_high": 0.08922968287703967,
   "n_instances": 24
  },
  "one_rational": {
   "pearson_r": -0.2492323190001127,
   "ci_low": -0.6984654747678015,
   "ci_high": 0.3083499966431045,
   "n_instances": 24
  },
  "rational_advised_llm": {
   "pearson_r": -0.3600032700086261,
   "ci_low": -0.8481456363867811,
   "ci_high": 0.1835409039145551,
   "n_instances": 24
  },
  "interpreter_advised_llm": {
   "pearson_r": -0.5460208528683343,
   "ci_low": -0.8154702739866616,
   "ci_high": 0.10560649031965162,
   "n_instances": 24
  },
  "one_oracle": {
   "pearson_r": -0.5063334214207315,
   "ci_low": -0.7823223392128961,
   "ci_high": 0.09759928568247297,
   "n_instances": 24
  },
  "all_oracle": {
   "pearson_r": NaN,
   "ci_low": null,
   "ci_high": null,
   "n_instances": 24
  },
  "all_rational": {
   "pearson_r": -0.25578659513352464,
   "ci_low": -0.544670415394607,
   "ci_high": 0.08202613376003876,
   "n_instances": 24
  }
 },
 "paired_strata": {
  "all_llm": {
   "easy": {
    "deal_rate": {
     "estimate": -0.025,
     "ci_low": -0.1,
     "ci_high": 0.05,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.016370000000000003,
     "ci_low": -0.09564237500000002,
     "ci_high": 0.057419999999999985,
     "n": 40,
     "n_instances": 8
    }
   },
   "hard": {
    "deal_rate": {
     "estimate": 0.175,
     "ci_low": 0.025,
     "ci_high": 0.375,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.17596499999999998,
     "ci_low": 0.017077500000000006,
     "ci_high": 0.3869284374999995,
     "n": 40,
     "n_instances": 8
    }
   },
   "high-conflict": {
    "deal_rate": {
     "estimate": 0.2,
     "ci_low": 0.03333333333333333,
     "ci_high": 0.4666666666666667,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.19425,
     "ci_low": 0.031279999999999995,
     "ci_high": 0.45588666666666666,
     "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": -0.10984,
     "ci_high": 0.11720333333333333,
     "n": 30,
     "n_instances": 6
    }
   },
   "medium": {
    "deal_rate": {
     "estimate": 0.025,
     "ci_low": -0.05,
     "ci_high": 0.1,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.023792499999999994,
     "ci_low": -0.051324999999999996,
     "ci_high": 0.09841724999999993,
     "n": 40,
     "n_instances": 8
    }
   },
   "no-clear-win-win": {
    "deal_rate": {
     "estimate": 0.26666666666666666,
     "ci_low": 0.06666666666666667,
     "ci_high": 0.5,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.27221000000000006,
     "ci_low": 0.08727333333333336,
     "ci_high": 0.4963033333333333,
     "n": 30,
     "n_instances": 6
    }
   },
   "pivotal-seat": {
    "deal_rate": {
     "estimate": 0.1,
     "ci_low": 0.0,
     "ci_high": 0.23333333333333334,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.10128666666666668,
     "ci_low": -0.001906666666666664,
     "ci_high": 0.22857333333333335,
     "n": 30,
     "n_instances": 6
    }
   },
   "small-frontier": {
    "deal_rate": {
     "estimate": 0.13333333333333333,
     "ci_low": -0.06666666666666667,
     "ci_high": 0.43333333333333335,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.1428133333333333,
     "ci_low": -0.058336666666666676,
     "ci_high": 0.42613333333333336,
     "n": 30,
     "n_instances": 6
    }
   }
  },
  "one_rational": {
   "easy": {
    "deal_rate": {
     "estimate": -0.125,
     "ci_low": -0.225,
     "ci_high": -0.025,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.112625,
     "ci_low": -0.18891931250000002,
     "ci_high": -0.040122500000000005,
     "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": -0.1664525,
     "ci_low": -0.3382075,
     "ci_high": 0.029722499999999985,
     "n": 40,
     "n_instances": 8
    }
   },
   "high-conflict": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": -0.2,
     "ci_high": 0.2,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.02529333333333333,
     "ci_low": -0.21867666666666666,
     "ci_high": 0.18186,
     "n": 30,
     "n_instances": 6
    }
   },
   "large-frontier": {
    "deal_rate": {
     "estimate": -0.16666666666666666,
     "ci_low": -0.3333333333333333,
     "ci_high": 0.0,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.14472,
     "ci_low": -0.29835666666666666,
     "ci_high": 0.01552666666666667,
     "n": 30,
     "n_instances": 6
    }
   },
   "medium": {
    "deal_rate": {
     "estimate": -0.1,
     "ci_low": -0.225,
     "ci_high": 0.025,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.09609749999999999,
     "ci_low": -0.21004499999999998,
     "ci_high": 0.010777499999999999,
     "n": 40,
     "n_instances": 8
    }
   },
   "no-clear-win-win": {
    "deal_rate": {
     "estimate": -0.03333333333333333,
     "ci_low": -0.3,
     "ci_high": 0.2,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.03315333333333333,
     "ci_low": -0.2665833333333333,
     "ci_high": 0.18815666666666664,
     "n": 30,
     "n_instances": 6
    }
   },
   "pivotal-seat": {
    "deal_rate": {
     "estimate": -0.26666666666666666,
     "ci_low": -0.43333333333333335,
     "ci_high": -0.1,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.2543866666666667,
     "ci_low": -0.39465,
     "ci_high": -0.11101666666666667,
     "n": 30,
     "n_instances": 6
    }
   },
   "small-frontier": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": -0.13333333333333333,
     "ci_high": 0.16666666666666666,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.012693333333333341,
     "ci_low": -0.10822,
     "ci_high": 0.18012000000000003,
     "n": 30,
     "n_instances": 6
    }
   }
  },
  "interpreter_advised_llm": {
   "easy": {
    "deal_rate": {
     "estimate": 0.025,
     "ci_low": 0.0,
     "ci_high": 0.075,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.04677999999999999,
     "ci_low": 0.01028999999999998,
     "ci_high": 0.09403699999999997,
     "n": 40,
     "n_instances": 8
    }
   },
   "hard": {
    "deal_rate": {
     "estimate": 0.125,
     "ci_low": -0.025,
     "ci_high": 0.35,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.13364250000000003,
     "ci_low": -0.030772624999999998,
     "ci_high": 0.348755,
     "n": 40,
     "n_instances": 8
    }
   },
   "high-conflict": {
    "deal_rate": {
     "estimate": 0.16666666666666666,
     "ci_low": -0.03333333333333333,
     "ci_high": 0.43333333333333335,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.17189666666666667,
     "ci_low": -0.029970000000000004,
     "ci_high": 0.44557,
     "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": 0.04498333333333333,
     "ci_low": -0.05540666666666669,
     "ci_high": 0.13931000000000002,
     "n": 30,
     "n_instances": 6
    }
   },
   "medium": {
    "deal_rate": {
     "estimate": 0.025,
     "ci_low": -0.05,
     "ci_high": 0.1,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.027615,
     "ci_low": -0.0608425,
     "ci_high": 0.1123375,
     "n": 40,
     "n_instances": 8
    }
   },
   "no-clear-win-win": {
    "deal_rate": {
     "estimate": 0.2,
     "ci_low": -0.03333333333333333,
     "ci_high": 0.4666666666666667,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.2131833333333333,
     "ci_low": -2.999999999997819e-05,
     "ci_high": 0.47618,
     "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": 0.07452,
     "ci_low": -0.011706666666666659,
     "ci_high": 0.16438666666666665,
     "n": 30,
     "n_instances": 6
    }
   },
   "small-frontier": {
    "deal_rate": {
     "estimate": 0.13333333333333333,
     "ci_low": -0.06666666666666667,
     "ci_high": 0.43333333333333335,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.15902999999999998,
     "ci_low": -0.05447333333333333,
     "ci_high": 0.4407433333333334,
     "n": 30,
     "n_instances": 6
    }
   }
  },
  "one_oracle": {
   "easy": {
    "deal_rate": {
     "estimate": -0.025,
     "ci_low": -0.1,
     "ci_high": 0.05,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.019822500000000014,
     "ci_low": -0.11075750000000002,
     "ci_high": 0.07192,
     "n": 40,
     "n_instances": 8
    }
   },
   "hard": {
    "deal_rate": {
     "estimate": 0.1,
     "ci_low": -0.05,
     "ci_high": 0.325,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.09511,
     "ci_low": -0.07367,
     "ci_high": 0.324555,
     "n": 40,
     "n_instances": 8
    }
   },
   "high-conflict": {
    "deal_rate": {
     "estimate": 0.16666666666666666,
     "ci_low": -0.03333333333333333,
     "ci_high": 0.43333333333333335,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.15830333333333332,
     "ci_low": -0.05587666666666668,
     "ci_high": 0.4315533333333333,
     "n": 30,
     "n_instances": 6
    }
   },
   "large-frontier": {
    "deal_rate": {
     "estimate": 0.0,
     "ci_low": -0.1,
     "ci_high": 0.1,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.0026766666666666866,
     "ci_low": -0.08774000000000001,
     "ci_high": 0.08591999999999998,
     "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": -0.02315000000000001,
     "ci_low": -0.114015,
     "ci_high": 0.06799,
     "n": 40,
     "n_instances": 8
    }
   },
   "no-clear-win-win": {
    "deal_rate": {
     "estimate": 0.2,
     "ci_low": 0.03333333333333333,
     "ci_high": 0.4666666666666667,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.21171333333333334,
     "ci_low": 0.04504666666666668,
     "ci_high": 0.4619366666666666,
     "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": -0.0069099999999999865,
     "ci_low": -0.12477333333333333,
     "ci_high": 0.10233666666666667,
     "n": 30,
     "n_instances": 6
    }
   },
   "small-frontier": {
    "deal_rate": {
     "estimate": 0.13333333333333333,
     "ci_low": -0.06666666666666667,
     "ci_high": 0.43333333333333335,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.15573333333333333,
     "ci_low": -0.05270666666666667,
     "ci_high": 0.4337,
     "n": 30,
     "n_instances": 6
    }
   }
  },
  "all_oracle": {
   "easy": {
    "deal_rate": {
     "estimate": 0.025,
     "ci_low": 0.0,
     "ci_high": 0.075,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.00012250000000000038,
     "ci_low": -0.057458312500000004,
     "ci_high": 0.055566,
     "n": 40,
     "n_instances": 8
    }
   },
   "hard": {
    "deal_rate": {
     "estimate": 0.225,
     "ci_low": 0.05,
     "ci_high": 0.45,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.2408975,
     "ci_low": 0.04566999999999999,
     "ci_high": 0.46324000000000004,
     "n": 40,
     "n_instances": 8
    }
   },
   "high-conflict": {
    "deal_rate": {
     "estimate": 0.2,
     "ci_low": 0.03333333333333333,
     "ci_high": 0.4666666666666667,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.16454333333333335,
     "ci_low": 0.0029999999999999953,
     "ci_high": 0.4267933333333333,
     "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": 0.04655333333333333,
     "ci_low": -0.033963333333333345,
     "ci_high": 0.12416333333333333,
     "n": 30,
     "n_instances": 6
    }
   },
   "medium": {
    "deal_rate": {
     "estimate": 0.05,
     "ci_low": 0.0,
     "ci_high": 0.125,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": 0.045345,
     "ci_low": -0.003369999999999998,
     "ci_high": 0.10146012499999997,
     "n": 40,
     "n_instances": 8
    }
   },
   "no-clear-win-win": {
    "deal_rate": {
     "estimate": 0.3333333333333333,
     "ci_low": 0.1,
     "ci_high": 0.5666666666666667,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.3541933333333334,
     "ci_low": 0.15177666666666667,
     "ci_high": 0.5889866666666667,
     "n": 30,
     "n_instances": 6
    }
   },
   "pivotal-seat": {
    "deal_rate": {
     "estimate": 0.16666666666666666,
     "ci_low": 0.0,
     "ci_high": 0.36666666666666664,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.17732333333333333,
     "ci_low": -0.016416666666666677,
     "ci_high": 0.3805466666666666,
     "n": 30,
     "n_instances": 6
    }
   },
   "small-frontier": {
    "deal_rate": {
     "estimate": 0.2,
     "ci_low": 0.0,
     "ci_high": 0.4666666666666667,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": 0.23179333333333327,
     "ci_low": 0.008530000000000005,
     "ci_high": 0.5023866666666666,
     "n": 30,
     "n_instances": 6
    }
   }
  },
  "all_rational": {
   "easy": {
    "deal_rate": {
     "estimate": -0.475,
     "ci_low": -0.625,
     "ci_high": -0.3,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.46320750000000005,
     "ci_low": -0.5921424999999999,
     "ci_high": -0.33801275,
     "n": 40,
     "n_instances": 8
    }
   },
   "hard": {
    "deal_rate": {
     "estimate": -0.75,
     "ci_low": -0.95,
     "ci_high": -0.5,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.6931875,
     "ci_low": -0.8886809375,
     "ci_high": -0.467795,
     "n": 40,
     "n_instances": 8
    }
   },
   "high-conflict": {
    "deal_rate": {
     "estimate": -0.6666666666666666,
     "ci_low": -0.9,
     "ci_high": -0.43333333333333335,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.62329,
     "ci_low": -0.8257666666666666,
     "ci_high": -0.40907333333333334,
     "n": 30,
     "n_instances": 6
    }
   },
   "large-frontier": {
    "deal_rate": {
     "estimate": -0.6666666666666666,
     "ci_low": -0.8333333333333334,
     "ci_high": -0.5333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.64256,
     "ci_low": -0.7481300000000001,
     "ci_high": -0.5390566666666666,
     "n": 30,
     "n_instances": 6
    }
   },
   "medium": {
    "deal_rate": {
     "estimate": -0.775,
     "ci_low": -0.9,
     "ci_high": -0.65,
     "n": 40,
     "n_instances": 8
    },
    "normalized_primary": {
     "estimate": -0.7114825,
     "ci_low": -0.8651274999999998,
     "ci_high": -0.5212675,
     "n": 40,
     "n_instances": 8
    }
   },
   "no-clear-win-win": {
    "deal_rate": {
     "estimate": -0.6,
     "ci_low": -0.8666666666666667,
     "ci_high": -0.3333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.5519499999999999,
     "ci_low": -0.7754600000000001,
     "ci_high": -0.32844,
     "n": 30,
     "n_instances": 6
    }
   },
   "pivotal-seat": {
    "deal_rate": {
     "estimate": -0.8,
     "ci_low": -1.0,
     "ci_high": -0.5333333333333333,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.7480366666666669,
     "ci_low": -0.9468366666666667,
     "ci_high": -0.5070133333333334,
     "n": 30,
     "n_instances": 6
    }
   },
   "small-frontier": {
    "deal_rate": {
     "estimate": -0.6666666666666666,
     "ci_low": -0.9,
     "ci_high": -0.43333333333333335,
     "n": 30,
     "n_instances": 6
    },
    "normalized_primary": {
     "estimate": -0.5949200000000001,
     "ci_low": -0.8668533333333333,
     "ci_high": -0.312,
     "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
   ]
  ],
  "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
   ]
  ],
  "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
   ]
  ],
  "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
   ]
  ]
 },
 "plots": [
  ".claude/products/five-seat-advised-advocate-wave2/fairness_basket_vs_a2/fairness_basket.png",
  ".claude/products/five-seat-advised-advocate-wave2/fairness_basket_vs_a2/fairness_basket.pdf"
 ]
}