{
  "source_hashes_verified": true,
  "result_hashes": {
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107300.json": "acf858f8bc1c0be012073925481b0e623f54cb8661a292f25ad07d298c9be0bb",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107301.json": "b2dd2a9e27bd30af91a048613a6b14c61cf05f4ac1ddf749887eeef3ab970c84",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107302.json": "6b8e1ee245dc85519fc02ebfb61b1458d190cdc89f78676b85fb598ffe62126b",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107303.json": "0c8abd3055c662fd4e9ca518688cdb7dce5bb28fa81b50cdf76a1696d30cbeca",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107304.json": "8799635e44921ba79abfd3a7ef90275a58f4a50097bb859ed8fa2e4a6e80ffc1",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107305.json": "57ff3c4f41c3b0d949e4158040f8b7c1409f677d015a57860d148d8428658be6",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107306.json": "1b0bad1bdebb83d71088f2b8d19e4f8a454ec2fa144abc322324d176d785015b",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107307.json": "75c816ea22192f0eb2e29a49268f5492e6c016ec9f78dbe906df3c9ce3a1efb1",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107308.json": "3dc5d6bf719441d72066f5023b0a310fa17acb3cc0f32bd64ca78613d3ed89ca",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107309.json": "fa72918b0c5866a82bf70cbe3b52f35721aab00289d31dd708419f6e17358a95",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107310.json": "f4ec6d36ac52dfa6786d312a402bf47cdc3da33effcab6410236ae254818a67b",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107311.json": "b0cfdf68362c796f9fe255708b160d5d5e17c8009269233b86196c862d7c47d8",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107312.json": "4b0a943de4fa1e1ad98e9622f635f3c1823c89dc3896310ee4138cfe8707d10d",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107313.json": "f3384d6c0a3edc0629724a1086d95aa2f4d1d3fb4f78c2eeb2e2f64afd5dd204",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107314.json": "66d42eee95ea33ce64fba64826bdecbaab90e2376878531a6d513ed03da3043f",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_truthful_107315.json": "484fece49d970be47602157e08078aab67fbc53047eb94b9bcad8ec38d82f811",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107300.json": "265b2cfd9b3d3556f253938cb8875cbb81a6580f8551606f4c3b3b091756d6ab",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107301.json": "f669d38b670144057fb5ec68fc2cdf4951c613ef622b65457fe0a2446d2419b9",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107302.json": "99d7d975578aef5084f91c1b4a055c310bea65578b9e9f24687ddfa264dbab1a",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107303.json": "943e803aa2625d1398eab64b00b25f890784dae49cf56cb9f2983a70c21609f1",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107304.json": "f3647584c685e7da2ac71ee0e7daef3ca56f632d88f40610811c2367440f6d6c",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107305.json": "2863758baf5e510e53f00b261f2ba3db6dbe26724813021791254dc48eb3a886",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107306.json": "0b8af0c1e7977c228645d60cd6e36fd666110bc1f48eafd8dc919f8c379afc6b",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107307.json": "5dccf67901ee14b76d1d44deeb1df5e044ce58b080eacf9cd84120e69438ffb7",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107308.json": "a998e165c51be8d27393a60edd9a02798fd57521a8c086cfcc498d32d4e1a4b7",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107309.json": "3eeeebadde6d3ac04bc863a8e21448cc01811ec1897b2f7cbdfa1c23d2406caf",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107310.json": "2a5198d8acd416c27598c1022a04bc935d2e5fb543a394f0b084d29544fcf0cd",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107311.json": "1552a46b8e0e98580cba40a235cb6a879ba994bdc978fd108004b946146cff04",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107312.json": "a2885e0994629b6dedc10ac36398b1a7aa57bf4dca09ecff59e8166357a0559e",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107313.json": "92c853e8ef17a7c51abea14d312d32db41acb98e8b5dff197e09dbb497bbac3f",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107314.json": "276015d2abafff30361d548bce2746a9446eba0e85c541b48d5ecca7c84cb784",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_reversed_107315.json": "4e12cc7b2c6501d69dc33675dbbd6dc9bd37eba6dbc7592b9f5644d4aaddfcef",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107300.json": "d54c77bae390c8b2c97423623fe06f372b06a8be9adfe0edc12d19afac75f6b4",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107301.json": "0821f8523e13cff5a1449da7278f7c4d1afdca94ffa5ab06347df32992de32a5",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107302.json": "bf81ac0e47ff9eade97b4c9735f6aa41cf2683208cc79e59d19d65186c94dc73",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107303.json": "a9d1420a2f439ab18e34c89bff4c0a066d0d07e935232648e4a29f7a5e8181b2",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107304.json": "38b0b2e5c04c7c8e0f494f4b76cdd5db01223b82db0f842ebd57d2550a8ef328",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107305.json": "66e2d60b2642eebc0f5368404d3ebf50fe48898fad4f1f8d5b8e808ec26ce3ab",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107306.json": "6e52688477288377918ecb2c0717c92948a635f4c9df379e3f227b4716ff04c3",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107307.json": "a41b1af882b1ceb8ee0587e9de6d19b076f92fbb9a46a899e2275e3388b7b7b5",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107308.json": "54fb5b48b04e54b2630a318b8899bf8c9bc8a04dfde81ccf701bbb3bd5560ea6",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107309.json": "707a2b60b1a5f40e1115ee602ec3433c27a74f0bda79840921e320854b8ae323",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107310.json": "5aea2d5d3802744715f748d9f2612fda956ffaa168e27b8d00e958ad0fa2331e",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107311.json": "caf67818bba1841945c5f4518f7d89d7ac3c6d240b73b509fc9ea9b0876d0c7f",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107312.json": "684f8a208b3b0a70b123987232c63da76f75762b515cebc2cba673103e29a33b",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107313.json": "66890ae32de584b4ec4457b25492ea594c4bfc9cdc455533ff3aadae01a81739",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107314.json": "c99c3001954f30bbf9467bf00cfe75391c9e8c16f772259424adfd3225e29def",
    "scratch\\social_cartpole_shc_teacher_finish_v2_parallel\\confirmation\\teacher_none_107315.json": "3cc4b4aa90c52974f113183819260b39235e14df9a875817f8e078d225218dd1"
  },
  "counts": {
    "teacher_truthful": {
      "near": {
        "complete": 1600,
        "upright": 1600
      },
      "lean": {
        "complete": 1600,
        "upright": 1600
      }
    },
    "teacher_reversed": {
      "near": {
        "complete": 0,
        "upright": 0
      },
      "lean": {
        "complete": 0,
        "upright": 0
      }
    },
    "teacher_none": {
      "near": {
        "complete": 800,
        "upright": 661
      },
      "lean": {
        "complete": 798,
        "upright": 601
      }
    }
  },
  "paired": {
    "teacher_reversed": {
      "near": {
        "complete": {
          "wins": 16,
          "ties": 0,
          "losses": 0
        },
        "upright": {
          "wins": 16,
          "ties": 0,
          "losses": 0
        }
      },
      "lean": {
        "complete": {
          "wins": 16,
          "ties": 0,
          "losses": 0
        },
        "upright": {
          "wins": 16,
          "ties": 0,
          "losses": 0
        }
      }
    },
    "teacher_none": {
      "near": {
        "complete": {
          "wins": 8,
          "ties": 8,
          "losses": 0
        },
        "upright": {
          "wins": 11,
          "ties": 5,
          "losses": 0
        }
      },
      "lean": {
        "complete": {
          "wins": 10,
          "ties": 6,
          "losses": 0
        },
        "upright": {
          "wins": 11,
          "ties": 5,
          "losses": 0
        }
      }
    }
  },
  "confirmation": {
    "passed": true,
    "all_teacher_runs_complete_and_upright": true,
    "summary": {
      "teacher_truthful": {
        "near": {
          "complete": 1.0,
          "upright": 1.0,
          "steps": 500.0,
          "angle_rms": 0.22941257784585134
        },
        "lean": {
          "complete": 1.0,
          "upright": 1.0,
          "steps": 500.0,
          "angle_rms": 0.7795294907740011
        }
      },
      "teacher_reversed": {
        "near": {
          "complete": 0.0,
          "upright": 0.0,
          "steps": 72.79624999999999,
          "angle_rms": 9.998328347618322
        },
        "lean": {
          "complete": 0.0,
          "upright": 0.0,
          "steps": 68.87312499999999,
          "angle_rms": 10.570244828343988
        }
      },
      "teacher_none": {
        "near": {
          "complete": 0.5,
          "upright": 0.413125,
          "steps": 269.24812499999996,
          "angle_rms": 5.181093731510394
        },
        "lean": {
          "complete": 0.49875,
          "upright": 0.375625,
          "steps": 267.49125,
          "angle_rms": 6.404625700530473
        }
      }
    },
    "rows": [
      {
        "seed": 107300,
        "arm": "teacher_truthful",
        "reward": [
          0.32561829975946927,
          -0.9455013076996523
        ],
        "preference_agreement": 0.9375,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.23600290469452712,
          "objective": 162.62390069166224,
          "teacher_objective": 499.80407304932965
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7854048693046158,
          "objective": 161.08903996163136,
          "teacher_objective": 498.18074295181236
        },
        "elapsed": 14.957649946212769
      },
      {
        "seed": 107300,
        "arm": "teacher_reversed",
        "reward": [
          -0.32561829975946927,
          0.9455013076996523
        ],
        "preference_agreement": 0.0625,
        "near": {
          "steps": 88.31,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.703598187900292,
          "objective": 12.370096461957427,
          "teacher_objective": 44.81408076772322
        },
        "lean": {
          "steps": 85.31,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.718628842905568,
          "objective": 12.831209443088879,
          "teacher_objective": 42.359550048354606
        },
        "elapsed": 15.718990087509155
      },
      {
        "seed": 107300,
        "arm": "teacher_none",
        "reward": [
          -0.6734521921979543,
          -0.739230779137185
        ],
        "preference_agreement": 0.587890625,
        "near": {
          "steps": 8.82,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 7.120282819217984,
          "objective": -7.434630894825051,
          "teacher_objective": 6.797921642570437
        },
        "lean": {
          "steps": 5.53,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.120199992178884,
          "objective": -5.572367297629817,
          "teacher_objective": 3.0298650936419564
        },
        "elapsed": 22.06125283241272
      },
      {
        "seed": 107301,
        "arm": "teacher_truthful",
        "reward": [
          0.30310781717869967,
          -0.9529562692826802
        ],
        "preference_agreement": 0.92578125,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.22660934322192816,
          "objective": 151.3823070562816,
          "teacher_objective": 499.8199271691686
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7686524040997207,
          "objective": 149.91121371299548,
          "teacher_objective": 498.2762116906048
        },
        "elapsed": 14.790843963623047
      },
      {
        "seed": 107301,
        "arm": "teacher_reversed",
        "reward": [
          -0.3031078171786996,
          0.9529562692826802
        ],
        "preference_agreement": 0.07421875,
        "near": {
          "steps": 88.84,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.650911805623059,
          "objective": 14.569858414896478,
          "teacher_objective": 45.293450981240774
        },
        "lean": {
          "steps": 70.29,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.221229861449235,
          "objective": 11.665771670806977,
          "teacher_objective": 35.69111943949302
        },
        "elapsed": 15.120710372924805
      },
      {
        "seed": 107301,
        "arm": "teacher_none",
        "reward": [
          0.9466061077292276,
          -0.3223924267251358
        ],
        "preference_agreement": 1.0,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.26354350603133114,
          "objective": 473.2232147932384,
          "teacher_objective": 499.7523543831773
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.8490555316448127,
          "objective": 472.60003345221344,
          "teacher_objective": 497.81936437049194
        },
        "elapsed": 14.277136325836182
      },
      {
        "seed": 107302,
        "arm": "teacher_truthful",
        "reward": [
          0.32419628236781245,
          -0.9459898363613054
        ],
        "preference_agreement": 0.9375,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.2345604690931989,
          "objective": 161.91535875881536,
          "teacher_objective": 499.80678182992546
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7804272747931467,
          "objective": 160.40948422313255,
          "teacher_objective": 498.2149311801606
        },
        "elapsed": 14.32387924194336
      },
      {
        "seed": 107302,
        "arm": "teacher_reversed",
        "reward": [
          -0.32419628236781245,
          0.9459898363613054
        ],
        "preference_agreement": 0.0625,
        "near": {
          "steps": 88.78,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.816306863779587,
          "objective": 13.114798281923004,
          "teacher_objective": 44.490999611061845
        },
        "lean": {
          "steps": 90.1,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.96933521838072,
          "objective": 14.399785581714816,
          "teacher_objective": 44.00027572516261
        },
        "elapsed": 14.822839260101318
      },
      {
        "seed": 107302,
        "arm": "teacher_none",
        "reward": [
          0.6683372393611415,
          0.7438584102388897
        ],
        "preference_agreement": 0.412109375,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 0.95,
          "angle_rms": 3.6437490876141196,
          "objective": 365.3139977171752,
          "teacher_objective": 458.12996450950624
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 0.51,
          "angle_rms": 4.466341309072027,
          "objective": 379.4233131471764,
          "teacher_objective": 439.16222113819737
        },
        "elapsed": 14.21321415901184
      },
      {
        "seed": 107303,
        "arm": "teacher_truthful",
        "reward": [
          0.24450123614784755,
          -0.9696489805708942
        ],
        "preference_agreement": 0.875,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.2418545644213172,
          "objective": 122.05039994823805,
          "teacher_objective": 499.7935148391866
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7923389442927378,
          "objective": 120.45584414599418,
          "teacher_objective": 498.14904778544405
        },
        "elapsed": 14.320424318313599
      },
      {
        "seed": 107303,
        "arm": "teacher_reversed",
        "reward": [
          -0.24450123614784755,
          0.9696489805708942
        ],
        "preference_agreement": 0.125,
        "near": {
          "steps": 90.91,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.574135369603384,
          "objective": 20.38425886496844,
          "teacher_objective": 46.964338119263594
        },
        "lean": {
          "steps": 90.11,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.734702526081241,
          "objective": 21.427577785069484,
          "teacher_objective": 45.29008573704207
        },
        "elapsed": 14.885875940322876
      },
      {
        "seed": 107303,
        "arm": "teacher_none",
        "reward": [
          -0.4274694279498675,
          0.9040298049114383
        ],
        "preference_agreement": 0.041015625,
        "near": {
          "steps": 82.42,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.594780246096532,
          "objective": 1.1558255372904216,
          "teacher_objective": 42.16927420398139
        },
        "lean": {
          "steps": 76.22,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.640487730129607,
          "objective": 1.837776212336624,
          "teacher_objective": 38.1465915529772
        },
        "elapsed": 15.613090515136719
      },
      {
        "seed": 107304,
        "arm": "teacher_truthful",
        "reward": [
          0.37820333897713304,
          -0.9257225471957286
        ],
        "preference_agreement": 0.951171875,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.22789109466103644,
          "objective": 188.93325408615948,
          "teacher_objective": 499.81807140496113
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7720571680761509,
          "objective": 187.48841106221846,
          "teacher_objective": 498.2572981167683
        },
        "elapsed": 14.190141916275024
      },
      {
        "seed": 107304,
        "arm": "teacher_reversed",
        "reward": [
          -0.37820333897713304,
          0.9257225471957286
        ],
        "preference_agreement": 0.048828125,
        "near": {
          "steps": 88.86,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.845254698867793,
          "objective": 7.527987104278029,
          "teacher_objective": 44.42429306988811
        },
        "lean": {
          "steps": 91.09,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.968690039983397,
          "objective": 8.687942299921037,
          "teacher_objective": 44.49020119632326
        },
        "elapsed": 15.083590507507324
      },
      {
        "seed": 107304,
        "arm": "teacher_none",
        "reward": [
          0.6442951766116137,
          0.7647769121743999
        ],
        "preference_agreement": 0.412109375,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.8743822583249474,
          "objective": 324.1731353284757,
          "teacher_objective": 497.3514537502057
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 1.384685895024273,
          "objective": 326.92688339743546,
          "teacher_objective": 493.7507330365921
        },
        "elapsed": 14.811012268066406
      },
      {
        "seed": 107305,
        "arm": "teacher_truthful",
        "reward": [
          0.514948123360403,
          -0.8572213426225452
        ],
        "preference_agreement": 0.982421875,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.2217573626870525,
          "objective": 257.32637344873655,
          "teacher_objective": 499.82771283900473
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.797412179260941,
          "objective": 255.85671980375307,
          "teacher_objective": 498.11327390484655
        },
        "elapsed": 17.709362268447876
      },
      {
        "seed": 107305,
        "arm": "teacher_reversed",
        "reward": [
          -0.514948123360403,
          0.8572213426225452
        ],
        "preference_agreement": 0.017578125,
        "near": {
          "steps": 8.76,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 7.092520390408822,
          "objective": -2.7923608500910024,
          "teacher_objective": 6.755168079590313
        },
        "lean": {
          "steps": 5.53,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.120199992178884,
          "objective": -0.7044941210172945,
          "teacher_objective": 3.0298650936419564
        },
        "elapsed": 33.500345945358276
      },
      {
        "seed": 107305,
        "arm": "teacher_none",
        "reward": [
          0.09051203497733237,
          -0.9958953617344858
        ],
        "preference_agreement": 0.712890625,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.22482586907620125,
          "objective": 45.079498332436216,
          "teacher_objective": 499.82275331022464
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7863027100108364,
          "objective": 43.44086364556519,
          "teacher_objective": 498.1773648991199
        },
        "elapsed": 22.957053899765015
      },
      {
        "seed": 107306,
        "arm": "teacher_truthful",
        "reward": [
          0.48274316093545044,
          -0.8757619771205243
        ],
        "preference_agreement": 0.970703125,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.22816968574637922,
          "objective": 241.2118942514893,
          "teacher_objective": 499.81766025426106
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7768200575939674,
          "objective": 239.82287254208447,
          "teacher_objective": 498.23158807289985
        },
        "elapsed": 24.573230266571045
      },
      {
        "seed": 107306,
        "arm": "teacher_reversed",
        "reward": [
          -0.48274316093545044,
          0.8757619771205243
        ],
        "preference_agreement": 0.029296875,
        "near": {
          "steps": 8.82,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 7.110332816637447,
          "objective": -2.4905759255207673,
          "teacher_objective": 6.802078692499919
        },
        "lean": {
          "steps": 5.53,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.120199992178884,
          "objective": -0.4800465913128834,
          "teacher_objective": 3.0298650936419564
        },
        "elapsed": 36.2082953453064
      },
      {
        "seed": 107306,
        "arm": "teacher_none",
        "reward": [
          -0.7648747896483584,
          -0.64417897835957
        ],
        "preference_agreement": 0.587890625,
        "near": {
          "steps": 9.03,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 6.959180274307714,
          "objective": -8.174687351095862,
          "teacher_objective": 7.061807862156776
        },
        "lean": {
          "steps": 5.59,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.085287770839564,
          "objective": -5.885361548877378,
          "teacher_objective": 3.091142494835434
        },
        "elapsed": 35.89725375175476
      },
      {
        "seed": 107307,
        "arm": "teacher_truthful",
        "reward": [
          0.4597734116663904,
          -0.8880362661089062
        ],
        "preference_agreement": 0.96875,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.22605241976398832,
          "objective": 229.72779420722375,
          "teacher_objective": 499.82105277449114
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7767959354215027,
          "objective": 228.31281031055775,
          "teacher_objective": 498.22766751460074
        },
        "elapsed": 21.937686920166016
      },
      {
        "seed": 107307,
        "arm": "teacher_reversed",
        "reward": [
          -0.4597734116663904,
          0.8880362661089062
        ],
        "preference_agreement": 0.03125,
        "near": {
          "steps": 8.91,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 7.111536209949691,
          "objective": -2.297423223571832,
          "teacher_objective": 6.884004054745368
        },
        "lean": {
          "steps": 5.53,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.120199992178884,
          "objective": -0.3223364995044017,
          "teacher_objective": 3.0298650936419564
        },
        "elapsed": 36.570645570755005
      },
      {
        "seed": 107307,
        "arm": "teacher_none",
        "reward": [
          -0.27148436344100274,
          0.9624428504628384
        ],
        "preference_agreement": 0.095703125,
        "near": {
          "steps": 90.67,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.603582808666586,
          "objective": 17.853868821034784,
          "teacher_objective": 46.5433736410354
        },
        "lean": {
          "steps": 91.67,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.754060132484959,
          "objective": 19.19018160887847,
          "teacher_objective": 45.87283585220826
        },
        "elapsed": 23.819313049316406
      },
      {
        "seed": 107308,
        "arm": "teacher_truthful",
        "reward": [
          0.2988176610027106,
          -0.954310224965063
        ],
        "preference_agreement": 0.923828125,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.2376778229388493,
          "objective": 149.21972609482006,
          "teacher_objective": 499.80184178940124
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7850256496548734,
          "objective": 147.67900810013816,
          "teacher_objective": 498.1873584124276
        },
        "elapsed": 22.43944478034973
      },
      {
        "seed": 107308,
        "arm": "teacher_reversed",
        "reward": [
          -0.2988176610027106,
          0.954310224965063
        ],
        "preference_agreement": 0.076171875,
        "near": {
          "steps": 89.8,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.663738766016465,
          "objective": 15.102618470885382,
          "teacher_objective": 45.855752802539584
        },
        "lean": {
          "steps": 90.76,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.860018237289273,
          "objective": 16.527606009739692,
          "teacher_objective": 45.02194147302189
        },
        "elapsed": 24.156910181045532
      },
      {
        "seed": 107308,
        "arm": "teacher_none",
        "reward": [
          -0.8560443478448011,
          0.5169023839401102
        ],
        "preference_agreement": 0.0,
        "near": {
          "steps": 8.79,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 7.119550547458172,
          "objective": -6.480568572750465,
          "teacher_objective": 6.770157806882345
        },
        "lean": {
          "steps": 5.53,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.120199992178884,
          "objective": -3.441599550313393,
          "teacher_objective": 3.0298650936419564
        },
        "elapsed": 32.449745893478394
      },
      {
        "seed": 107309,
        "arm": "teacher_truthful",
        "reward": [
          0.3826983723769821,
          -0.9238733440142153
        ],
        "preference_agreement": 0.951171875,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.2224579449443028,
          "objective": 191.1889804488162,
          "teacher_objective": 499.8265933953904
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.778640883529552,
          "objective": 189.7029810151277,
          "teacher_objective": 498.2181484247498
        },
        "elapsed": 21.472238779067993
      },
      {
        "seed": 107309,
        "arm": "teacher_reversed",
        "reward": [
          -0.3826983723769821,
          0.9238733440142153
        ],
        "preference_agreement": 0.048828125,
        "near": {
          "steps": 89.72,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.571841259031698,
          "objective": 5.938243097096579,
          "teacher_objective": 46.1275083151877
        },
        "lean": {
          "steps": 88.92,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.651618292789914,
          "objective": 6.842559905401985,
          "teacher_objective": 44.68006230510494
        },
        "elapsed": 19.57421350479126
      },
      {
        "seed": 107309,
        "arm": "teacher_none",
        "reward": [
          -0.78413377754795,
          0.6205918295533562
        ],
        "preference_agreement": 0.0,
        "near": {
          "steps": 8.78,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 7.11175417136876,
          "objective": -5.634012464153519,
          "teacher_objective": 6.764694539698333
        },
        "lean": {
          "steps": 5.53,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.120199992178884,
          "objective": -2.784696494173216,
          "teacher_objective": 3.0298650936419564
        },
        "elapsed": 33.105135917663574
      },
      {
        "seed": 107310,
        "arm": "teacher_truthful",
        "reward": [
          0.3904643522625708,
          -0.9206180476246221
        ],
        "preference_agreement": 0.951171875,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.23615478999335018,
          "objective": 195.0519435258879,
          "teacher_objective": 499.80422651297954
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7892911882050925,
          "objective": 193.53913310237277,
          "teacher_objective": 498.16097128089
        },
        "elapsed": 21.851996183395386
      },
      {
        "seed": 107310,
        "arm": "teacher_reversed",
        "reward": [
          -0.3904643522625708,
          0.9206180476246221
        ],
        "preference_agreement": 0.048828125,
        "near": {
          "steps": 88.04,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.593670468051343,
          "objective": 5.121606693580919,
          "teacher_objective": 45.136117799677514
        },
        "lean": {
          "steps": 82.16,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.603928720560619,
          "objective": 5.705613539051853,
          "teacher_objective": 41.11565504234844
        },
        "elapsed": 24.61145257949829
      },
      {
        "seed": 107310,
        "arm": "teacher_none",
        "reward": [
          -0.9921424599452511,
          -0.12511330534274026
        ],
        "preference_agreement": 0.587890625,
        "near": {
          "steps": 8.76,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 7.092520390408822,
          "objective": -8.94199909733949,
          "teacher_objective": 6.755168079590313
        },
        "lean": {
          "steps": 5.53,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.120199992178884,
          "objective": -5.799347945434455,
          "teacher_objective": 3.0298650936419564
        },
        "elapsed": 36.320971727371216
      },
      {
        "seed": 107311,
        "arm": "teacher_truthful",
        "reward": [
          0.35018395012512604,
          -0.9366809494565176
        ],
        "preference_agreement": 0.943359375,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.224973366347156,
          "objective": 174.92592019586755,
          "teacher_objective": 499.82271992742903
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7646171232189483,
          "objective": 173.4971324969196,
          "teacher_objective": 498.29734706724963
        },
        "elapsed": 22.807038068771362
      },
      {
        "seed": 107311,
        "arm": "teacher_reversed",
        "reward": [
          -0.35018395012512604,
          0.9366809494565176
        ],
        "preference_agreement": 0.056640625,
        "near": {
          "steps": 89.19,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.746857518026346,
          "objective": 10.112048990383094,
          "teacher_objective": 45.05015117951068
        },
        "lean": {
          "steps": 89.18,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.859142624811977,
          "objective": 11.102017889802491,
          "teacher_objective": 43.98699955889694
        },
        "elapsed": 23.720547676086426
      },
      {
        "seed": 107311,
        "arm": "teacher_none",
        "reward": [
          0.8899935836748342,
          -0.455973048564963
        ],
        "preference_agreement": 1.0,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.2272683802103744,
          "objective": 444.9142784671642,
          "teacher_objective": 499.81903893111087
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7720455794390978,
          "objective": 444.2030483096152,
          "teacher_objective": 498.2592314824309
        },
        "elapsed": 22.34572744369507
      },
      {
        "seed": 107312,
        "arm": "teacher_truthful",
        "reward": [
          0.4389970716706605,
          -0.8984884924497281
        ],
        "preference_agreement": 0.9609375,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.22994210185067165,
          "objective": 219.33203426465738,
          "teacher_objective": 499.81468703041605
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7741286874506389,
          "objective": 217.92398441327958,
          "teacher_objective": 498.247555271679
        },
        "elapsed": 22.156792640686035
      },
      {
        "seed": 107312,
        "arm": "teacher_reversed",
        "reward": [
          -0.4389970716706605,
          0.8984884924497281
        ],
        "preference_agreement": 0.0390625,
        "near": {
          "steps": 87.4,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.875551239198465,
          "objective": 1.2281118830237594,
          "teacher_objective": 43.32992422298055
        },
        "lean": {
          "steps": 67.44,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.172371921040815,
          "objective": 1.2613742984094805,
          "teacher_objective": 33.08526193572156
        },
        "elapsed": 23.669082641601562
      },
      {
        "seed": 107312,
        "arm": "teacher_none",
        "reward": [
          0.8899315657262565,
          -0.4560940783698178
        ],
        "preference_agreement": 1.0,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.22667198402961838,
          "objective": 444.8836559430299,
          "teacher_objective": 499.81993425481
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.8034790227531928,
          "objective": 444.0896666155626,
          "teacher_objective": 498.0790887470034
        },
        "elapsed": 21.721293687820435
      },
      {
        "seed": 107313,
        "arm": "teacher_truthful",
        "reward": [
          0.42334739539308275,
          -0.9059674292235305
        ],
        "preference_agreement": 0.95703125,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.2295856487015449,
          "objective": 211.50611183348178,
          "teacher_objective": 499.8150199911677
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7767446038516694,
          "objective": 210.07334524007715,
          "teacher_objective": 498.2335430559178
        },
        "elapsed": 21.7455632686615
      },
      {
        "seed": 107313,
        "arm": "teacher_reversed",
        "reward": [
          -0.42334739539308275,
          0.9059674292235305
        ],
        "preference_agreement": 0.04296875,
        "near": {
          "steps": 87.89,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.753341403751175,
          "objective": 2.30000998575456,
          "teacher_objective": 44.28135437715086
        },
        "lean": {
          "steps": 85.38,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.802129513261091,
          "objective": 3.2083449869978278,
          "teacher_objective": 41.94163308278334
        },
        "elapsed": 25.644986629486084
      },
      {
        "seed": 107313,
        "arm": "teacher_none",
        "reward": [
          0.3062246029666601,
          0.9519592914289515
        ],
        "preference_agreement": 0.392578125,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 0.66,
          "angle_rms": 4.521442793992087,
          "objective": 211.95095413035804,
          "teacher_objective": 438.19204962146296
        },
        "lean": {
          "steps": 495.18,
          "complete": 0.99,
          "upright": 0.49,
          "angle_rms": 4.702975654069488,
          "objective": 213.93607334033655,
          "teacher_objective": 429.7362620122233
        },
        "elapsed": 21.318966150283813
      },
      {
        "seed": 107314,
        "arm": "teacher_truthful",
        "reward": [
          0.3662741930680207,
          -0.9305069669230696
        ],
        "preference_agreement": 0.94921875,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.22074429441578533,
          "objective": 182.97832807174032,
          "teacher_objective": 499.8293742358586
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7765921121072494,
          "objective": 181.489662730751,
          "teacher_objective": 498.22953093117934
        },
        "elapsed": 21.25151824951172
      },
      {
        "seed": 107314,
        "arm": "teacher_reversed",
        "reward": [
          -0.3662741930680207,
          0.9305069669230696
        ],
        "preference_agreement": 0.05078125,
        "near": {
          "steps": 69.93,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.389551977009829,
          "objective": 5.1530654924171015,
          "teacher_objective": 36.86563733821303
        },
        "lean": {
          "steps": 62.06,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.570956188681158,
          "objective": 4.837852788722426,
          "teacher_objective": 32.43224847258659
        },
        "elapsed": 22.9795503616333
      },
      {
        "seed": 107314,
        "arm": "teacher_none",
        "reward": [
          -0.10065595338729745,
          0.9949212928908971
        ],
        "preference_agreement": 0.27734375,
        "near": {
          "steps": 90.7,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.488172787159911,
          "objective": 34.21604699056088,
          "teacher_objective": 47.13319499491101
        },
        "lean": {
          "steps": 92.57,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.65765345032652,
          "objective": 36.1877075757873,
          "teacher_objective": 46.83228234735394
        },
        "elapsed": 23.07378649711609
      },
      {
        "seed": 107315,
        "arm": "teacher_truthful",
        "reward": [
          0.3369996485968888,
          -0.9415047726090258
        ],
        "preference_agreement": 0.939453125,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.2261674320525333,
          "objective": 168.33116959812824,
          "teacher_objective": 499.8208668662945
        },
        "lean": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 1.0,
          "angle_rms": 0.7775227715232116,
          "objective": 166.8288531674933,
          "teacher_objective": 498.2252122564173
        },
        "elapsed": 21.733982801437378
      },
      {
        "seed": 107315,
        "arm": "teacher_reversed",
        "reward": [
          -0.3369996485968888,
          0.9415047726090258
        ],
        "preference_agreement": 0.060546875,
        "near": {
          "steps": 90.58,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.474104588037772,
          "objective": 10.429717154042551,
          "teacher_objective": 47.080331686628654
        },
        "lean": {
          "steps": 92.58,
          "complete": 0.0,
          "upright": 0.0,
          "angle_rms": 10.630565289732155,
          "objective": 11.789670121350403,
          "teacher_objective": 46.92001097060584
        },
        "elapsed": 22.42247200012207
      },
      {
        "seed": 107315,
        "arm": "teacher_none",
        "reward": [
          0.47406521113333,
          0.880489736222468
        ],
        "preference_agreement": 0.404296875,
        "near": {
          "steps": 500.0,
          "complete": 1.0,
          "upright": 0.0,
          "angle_rms": 5.825791780203149,
          "objective": 319.77498233590654,
          "teacher_objective": 406.0268696325433
        },
        "lean": {
          "steps": 496.51,
          "complete": 0.99,
          "upright": 0.01,
          "angle_rms": 6.09083645397765,
          "objective": 323.61723748820395,
          "teacher_objective": 396.2940453121427
        },
        "elapsed": 20.427303075790405
      }
    ]
  },
  "episodes_recomputed": 9600,
  "preference_agreement": {
    "teacher_truthful": 0.9453125,
    "teacher_reversed": 0.0546875,
    "teacher_none": 0.469482421875
  },
  "replay_check": {
    "records": 192,
    "transitions": 53900,
    "max_physics_error": 0.0
  },
  "interpretation": "All sixteen independently initialized learners with truthful teacher information met the fixed absolute requirement on all 100 near and 100 lean tests each. These are finite tests, not a guarantee for arbitrary states or indefinite lifetimes. Earlier failed development procedures and their outcomes are preserved separately; all confirmation seeds were new to this version.",
  "development_history": {
    "original_teacher": "social_cartpole_shc_opening_v3: near 766/800, lean 494/800; earlier separate strict-completion superiority criterion missed.",
    "mixed_start_development": "social_cartpole_shc_teacher_finish_v1: near 800/800; lean 794/800. Longer diagnostic tests exposed delayed rail exits in seven of eight policies.",
    "final_development": "Unchanged teacher data and fitted rewards; 2,000-step training episodes and proportionate budget. All eight development policies passed all near and lean 500-step tests.",
    "separation": "The previously examined seeds 72000-72007 were used only for development in this study. Fresh confirmation seeds 107300-107315 were reserved before testing and never used to revise the procedure.",
    "execution": "Three independent workers; algorithm and settings byte-identical to the sealed sequential finish_v2. See execution_addendum.json."
  }
}