{
 "schema": 1,
 "model": {
  "id": "north_nevada",
  "name": "North Nevada",
  "sha256": "cf6376aa9a090f0da26c280ef69eabf9bbdd51d1faac9ed392919c3db69be916+792fca7c24faadc1183327eec7e04d06dd6ec0e53ac7bb43cb2b9823c6cfb32f",
  "source": {
   "kind": "openpilot-master",
   "ref": "4d085424f80009ee5ea4ae8f4519ed871905b382",
   "url": "https://github.com/commaai/openpilot/pull/36276",
   "date": "2025-10-09"
  },
  "first_public": "2025-10-09",
  "on_master": "2025-10-09",
  "params_m": null,
  "gmac": null,
  "family": "vision-policy",
  "notes": "Named in the openpilot 0.10.1 release notes; the 0.10.1 tag carries The Cool People's model, merged eleven days later. Plan only, commands from modeld's get_action_from_model. Vision 2cc530ac/500, policy 0e620593/400."
 },
 "scored": {
  "date": "2026-10-28T04:04:39Z",
  "suite": "geval-1",
  "code": "d8eb40eeba87"
 },
 "baselines": [
  "lebowski_877m",
  "steam_powered"
 ],
 "sections": {
  "public_open_loop": {
   "status": "ok",
   "unit_of_evidence": "segment",
   "n": 39,
   "clusters": 23,
   "condition": "Measured. comma's public two-camera segments (openpilot CI data), native intrinsics and the device's own calibration, both cameras; every model on the same decoded frames. Truth is what the recording car did next: carState speed and acceleration, yaw rate from the device's cameraOdometry. Segments where the car never moves have no data. 39 of the 45 listed segments have a score, from 23 drives and 20 cars.",
   "baselines": [
    "lebowski_877m",
    "steam_powered"
   ],
   "metrics": [
    {
     "key": "lat_mae",
     "label": "Lateral error",
     "unit": "m/s²",
     "better": "lower",
     "value": 0.1203,
     "median": 0.09145,
     "ci": [
      0.09374,
      0.1486
     ],
     "n": 39,
     "clusters": 23,
     "paired": {
      "lebowski_877m": {
       "delta": 0.01158,
       "median": 0.009216,
       "ci": [
        0.004413,
        0.01928
       ],
       "n": 39,
       "wins": 10,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 6
      },
      "steam_powered": {
       "delta": 0.007014,
       "median": 0.006962,
       "ci": [
        0.002892,
        0.01049
       ],
       "n": 39,
       "wins": 8,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 5
      }
     }
    },
    {
     "key": "lat_mae_bl",
     "label": "Lateral error at the model's own best lead",
     "unit": "m/s²",
     "better": "lower",
     "value": 0.1131,
     "median": 0.09145,
     "ci": [
      0.08869,
      0.1393
     ],
     "n": 39,
     "clusters": 23,
     "paired": {
      "lebowski_877m": {
       "delta": 0.01173,
       "median": 0.008033,
       "ci": [
        0.006725,
        0.01795
       ],
       "n": 39,
       "wins": 7,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 3
      },
      "steam_powered": {
       "delta": 0.007562,
       "median": 0.007463,
       "ci": [
        0.00369,
        0.01129
       ],
       "n": 39,
       "wins": 9,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 5
      }
     }
    },
    {
     "key": "lat_corr",
     "label": "Lateral correlation with the car's later motion",
     "unit": "",
     "better": "higher",
     "value": 0.8341,
     "median": 0.9388,
     "ci": [
      0.765,
      0.9014
     ],
     "n": 39,
     "clusters": 23,
     "paired": {
      "lebowski_877m": {
       "delta": -0.02351,
       "median": -0.01146,
       "ci": [
        -0.0614,
        -2.515e-05
       ],
       "n": 39,
       "wins": 11,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 8
      },
      "steam_powered": {
       "delta": -0.009042,
       "median": -0.00384,
       "ci": [
        -0.01897,
        0.001442
       ],
       "n": 39,
       "wins": 10,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 6
      }
     }
    },
    {
     "key": "lat_gain",
     "label": "Lateral gain (1 = same size as the car's motion)",
     "unit": "",
     "better": "near1",
     "value": 0.8299,
     "median": 0.8977,
     "ci": [
      0.7547,
      0.9095
     ],
     "n": 39,
     "clusters": 23,
     "paired": {
      "lebowski_877m": {
       "delta": -0.002842,
       "median": -0.005322,
       "ci": [
        -0.02829,
        0.0192
       ],
       "n": 39,
       "wins": 22,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 11
      },
      "steam_powered": {
       "delta": -0.008605,
       "median": 0.005286,
       "ci": [
        -0.0484,
        0.01856
       ],
       "n": 39,
       "wins": 14,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 11
      }
     }
    },
    {
     "key": "lat_rate_rms",
     "label": "Lateral action rate, RMS (smoothness)",
     "unit": "m/s³",
     "better": "lower",
     "value": 0.4222,
     "median": 0.3935,
     "ci": [
      0.338,
      0.5171
     ],
     "n": 39,
     "clusters": 23,
     "paired": {
      "lebowski_877m": {
       "delta": -0.2417,
       "median": -0.2085,
       "ci": [
        -0.2879,
        -0.1938
       ],
       "n": 39,
       "wins": 39,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 23
      },
      "steam_powered": {
       "delta": 0.004018,
       "median": 0.005746,
       "ci": [
        -0.005281,
        0.01415
       ],
       "n": 39,
       "wins": 18,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 10
      }
     }
    },
    {
     "key": "lat_best_lag",
     "label": "Lead of the lateral request over the car's motion",
     "unit": "s",
     "better": "lower",
     "value": 0.5681,
     "median": 0.525,
     "ci": [
      0.4536,
      0.6833
     ],
     "n": 36,
     "clusters": 22,
     "paired": {
      "lebowski_877m": {
       "delta": 0.1779,
       "median": 0.1,
       "ci": [
        0.08391,
        0.2862
       ],
       "n": 34,
       "wins": 5,
       "ties": 6,
       "clusters": 21,
       "cluster_wins": 2
      },
      "steam_powered": {
       "delta": 0.04714,
       "median": 0.05,
       "ci": [
        0.002855,
        0.1014
       ],
       "n": 35,
       "wins": 6,
       "ties": 8,
       "clusters": 22,
       "cluster_wins": 4
      }
     }
    },
    {
     "key": "lon_mae",
     "label": "Longitudinal error",
     "unit": "m/s²",
     "better": "lower",
     "value": 0.3289,
     "median": 0.2934,
     "ci": [
      0.2835,
      0.3806
     ],
     "n": 39,
     "clusters": 23,
     "paired": {
      "lebowski_877m": {
       "delta": 0.0208,
       "median": 0.0143,
       "ci": [
        0.005901,
        0.0356
       ],
       "n": 39,
       "wins": 13,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 7
      },
      "steam_powered": {
       "delta": -0.01162,
       "median": -0.003616,
       "ci": [
        -0.03195,
        0.003737
       ],
       "n": 39,
       "wins": 22,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 15
      }
     }
    },
    {
     "key": "lon_corr",
     "label": "Longitudinal correlation",
     "unit": "",
     "better": "higher",
     "value": 0.6852,
     "median": 0.7691,
     "ci": [
      0.5819,
      0.7729
     ],
     "n": 39,
     "clusters": 23,
     "paired": {
      "lebowski_877m": {
       "delta": -0.03251,
       "median": -0.0186,
       "ci": [
        -0.0592,
        -0.009801
       ],
       "n": 39,
       "wins": 12,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 4
      },
      "steam_powered": {
       "delta": -0.008545,
       "median": 0.00366,
       "ci": [
        -0.03763,
        0.01618
       ],
       "n": 39,
       "wins": 23,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 14
      }
     }
    },
    {
     "key": "lon_brake_mae",
     "label": "Longitudinal error while braking",
     "unit": "m/s²",
     "better": "lower",
     "value": 0.4372,
     "median": 0.4181,
     "ci": [
      0.3579,
      0.5281
     ],
     "n": 30,
     "clusters": 21,
     "paired": {
      "lebowski_877m": {
       "delta": 0.002929,
       "median": -0.0006255,
       "ci": [
        -0.03346,
        0.04246
       ],
       "n": 30,
       "wins": 15,
       "ties": 0,
       "clusters": 21,
       "cluster_wins": 11
      },
      "steam_powered": {
       "delta": -0.02761,
       "median": -0.01653,
       "ci": [
        -0.04974,
        -0.008929
       ],
       "n": 30,
       "wins": 21,
       "ties": 0,
       "clusters": 21,
       "cluster_wins": 15
      }
     }
    },
    {
     "key": "lon_rate_rms",
     "label": "Longitudinal action rate, RMS (smoothness)",
     "unit": "m/s³",
     "better": "lower",
     "value": 0.3883,
     "median": 0.3494,
     "ci": [
      0.3535,
      0.4283
     ],
     "n": 39,
     "clusters": 23,
     "paired": {
      "lebowski_877m": {
       "delta": -0.9448,
       "median": -0.96,
       "ci": [
        -1.097,
        -0.8066
       ],
       "n": 39,
       "wins": 39,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 23
      },
      "steam_powered": {
       "delta": 0.001639,
       "median": 0.009026,
       "ci": [
        -0.007776,
        0.009948
       ],
       "n": 39,
       "wins": 18,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 10
      }
     }
    },
    {
     "key": "v3_mae",
     "label": "Plan speed error at 3 s",
     "unit": "m/s",
     "better": "lower",
     "value": 0.9274,
     "median": 0.8921,
     "ci": [
      0.7998,
      1.072
     ],
     "n": 39,
     "clusters": 23,
     "paired": {
      "lebowski_877m": {
       "delta": 0.2116,
       "median": 0.1665,
       "ci": [
        0.1391,
        0.2865
       ],
       "n": 39,
       "wins": 5,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 1
      },
      "steam_powered": {
       "delta": -0.1481,
       "median": -0.07579,
       "ci": [
        -0.26,
        -0.05637
       ],
       "n": 39,
       "wins": 28,
       "ties": 0,
       "clusters": 23,
       "cluster_wins": 17
      }
     }
    }
   ],
   "per_unit_file": "per_unit/north_nevada/public_open_loop.csv"
  },
  "public_closed_loop": {
   "status": "not_run",
   "unit_of_evidence": "segment",
   "n": 0,
   "condition": "Measured. comma's worldmodel-4B generates each next frame at 5 Hz from 9 history frames, 5 recorded anchor frames and the car's pose; the model drives comma's ideal car (the requested curvature and acceleration happen at once) for 7.2 s from the recorded start. Distance is to the recording car's own path. One window per segment, nearest the middle, where the car holds at least 5 m/s for the window and the 4.8 s before it; segments with no such stretch are left out. Seeds 0 and 1, averaged per segment.",
   "baselines": [],
   "metrics": [],
   "per_unit_file": null
  },
  "truck_open_loop": {
   "status": "ok",
   "unit_of_evidence": "window",
   "n": 119,
   "clusters": 12,
   "condition": "Measured. The G55's recorded drives replayed through the model with both of the truck's cameras (each setup's own wide-camera calibration), road-plane warp to 1.45 m. Where the narrow lens does not cover comma's narrow view (the 8 mm lens in the V13 case), those pixels come from the wide camera, brightness matched. Truth is the truck's CAN speed and yaw rate. 30 s windows after a 5 s warm-up; window = unit, drive = cluster; results are also given per camera setup. Corpus windows of 30 s from the truck's recorded drives, scored per camera setup.",
   "baselines": [
    "lebowski_877m",
    "steam_powered"
   ],
   "metrics": [
    {
     "key": "lat_mae",
     "label": "Lateral error",
     "unit": "m/s²",
     "better": "lower",
     "value": 0.1654,
     "median": 0.1638,
     "ci": [
      0.1401,
      0.1718
     ],
     "n": 119,
     "clusters": 12,
     "paired": {
      "lebowski_877m": {
       "delta": -0.007398,
       "median": -0.0067,
       "ci": [
        -0.01613,
        0.009542
       ],
       "n": 119,
       "wins": 71,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 5
      },
      "steam_powered": {
       "delta": 0.00491,
       "median": 0.004707,
       "ci": [
        -0.002111,
        0.008668
       ],
       "n": 119,
       "wins": 45,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 7
      }
     }
    },
    {
     "key": "lat_mae_bl",
     "label": "Lateral error at the model's own best lead",
     "unit": "m/s²",
     "better": "lower",
     "value": 0.1614,
     "median": 0.1605,
     "ci": [
      0.1377,
      0.1684
     ],
     "n": 119,
     "clusters": 12,
     "paired": {
      "lebowski_877m": {
       "delta": -0.003059,
       "median": -0.00314,
       "ci": [
        -0.01217,
        0.01387
       ],
       "n": 119,
       "wins": 63,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 4
      },
      "steam_powered": {
       "delta": 0.0051,
       "median": 0.004887,
       "ci": [
        -0.001676,
        0.008816
       ],
       "n": 119,
       "wins": 44,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 6
      }
     }
    },
    {
     "key": "lat_corr",
     "label": "Lateral correlation with the car's later motion",
     "unit": "",
     "better": "higher",
     "value": 0.8356,
     "median": 0.9127,
     "ci": [
      0.804,
      0.8549
     ],
     "n": 119,
     "clusters": 12,
     "paired": {
      "lebowski_877m": {
       "delta": 0.06878,
       "median": 0.02964,
       "ci": [
        0.02918,
        0.08366
       ],
       "n": 119,
       "wins": 99,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 10
      },
      "steam_powered": {
       "delta": -0.001499,
       "median": -0.003111,
       "ci": [
        -0.006679,
        0.006022
       ],
       "n": 119,
       "wins": 38,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 5
      }
     }
    },
    {
     "key": "lat_gain",
     "label": "Lateral gain (1 = same size as the car's motion)",
     "unit": "",
     "better": "near1",
     "value": 0.8928,
     "median": 0.8994,
     "ci": [
      0.8609,
      0.9646
     ],
     "n": 119,
     "clusters": 12,
     "paired": {
      "lebowski_877m": {
       "delta": -0.05205,
       "median": -0.03962,
       "ci": [
        -0.07234,
        0.009243
       ],
       "n": 119,
       "wins": 79,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 7
      },
      "steam_powered": {
       "delta": 0.003067,
       "median": 0.006124,
       "ci": [
        -0.004063,
        0.01787
       ],
       "n": 119,
       "wins": 55,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 5
      }
     }
    },
    {
     "key": "lat_rate_rms",
     "label": "Lateral action rate, RMS (smoothness)",
     "unit": "m/s³",
     "better": "lower",
     "value": 0.7275,
     "median": 0.6356,
     "ci": [
      0.4112,
      0.8057
     ],
     "n": 119,
     "clusters": 12,
     "paired": {
      "lebowski_877m": {
       "delta": -1.563,
       "median": -1.391,
       "ci": [
        -1.818,
        -0.7905
       ],
       "n": 119,
       "wins": 119,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 12
      },
      "steam_powered": {
       "delta": 0.07502,
       "median": 0.06574,
       "ci": [
        0.02472,
        0.09305
       ],
       "n": 119,
       "wins": 20,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 3
      }
     }
    },
    {
     "key": "lat_best_lag",
     "label": "Lead of the lateral request over the car's motion",
     "unit": "s",
     "better": "lower",
     "value": 0.6919,
     "median": 0.65,
     "ci": [
      0.6475,
      0.7174
     ],
     "n": 118,
     "clusters": 12,
     "paired": {
      "lebowski_877m": {
       "delta": 0.07458,
       "median": 0.1,
       "ci": [
        -0.008523,
        0.1658
       ],
       "n": 118,
       "wins": 24,
       "ties": 14,
       "clusters": 12,
       "cluster_wins": 2
      },
      "steam_powered": {
       "delta": -0.0008475,
       "median": 0.0,
       "ci": [
        -0.01957,
        0.02817
       ],
       "n": 118,
       "wins": 36,
       "ties": 47,
       "clusters": 12,
       "cluster_wins": 7
      }
     }
    },
    {
     "key": "lon_mae",
     "label": "Longitudinal error",
     "unit": "m/s²",
     "better": "lower",
     "value": 0.3242,
     "median": 0.316,
     "ci": [
      0.2734,
      0.3553
     ],
     "n": 119,
     "clusters": 12,
     "paired": {
      "lebowski_877m": {
       "delta": -0.04444,
       "median": -0.03363,
       "ci": [
        -0.07021,
        0.007371
       ],
       "n": 119,
       "wins": 83,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 6
      },
      "steam_powered": {
       "delta": -0.02144,
       "median": -0.01517,
       "ci": [
        -0.04186,
        -0.008884
       ],
       "n": 119,
       "wins": 79,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 9
      }
     }
    },
    {
     "key": "lon_corr",
     "label": "Longitudinal correlation",
     "unit": "",
     "better": "higher",
     "value": 0.3612,
     "median": 0.3618,
     "ci": [
      0.2968,
      0.556
     ],
     "n": 119,
     "clusters": 12,
     "paired": {
      "lebowski_877m": {
       "delta": 0.03432,
       "median": 0.01448,
       "ci": [
        -0.06438,
        0.05997
       ],
       "n": 119,
       "wins": 67,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 6
      },
      "steam_powered": {
       "delta": 0.02591,
       "median": 0.005819,
       "ci": [
        -0.004535,
        0.08094
       ],
       "n": 119,
       "wins": 61,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 8
      }
     }
    },
    {
     "key": "lon_brake_mae",
     "label": "Longitudinal error while braking",
     "unit": "m/s²",
     "better": "lower",
     "value": 0.7097,
     "median": 0.7064,
     "ci": [
      0.5884,
      0.7514
     ],
     "n": 81,
     "clusters": 12,
     "paired": {
      "lebowski_877m": {
       "delta": 0.2109,
       "median": 0.2162,
       "ci": [
        0.03417,
        0.2725
       ],
       "n": 81,
       "wins": 11,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 3
      },
      "steam_powered": {
       "delta": -0.02271,
       "median": -0.01914,
       "ci": [
        -0.06652,
        0.08026
       ],
       "n": 81,
       "wins": 45,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 5
      }
     }
    },
    {
     "key": "lon_rate_rms",
     "label": "Longitudinal action rate, RMS (smoothness)",
     "unit": "m/s³",
     "better": "lower",
     "value": 0.6308,
     "median": 0.6108,
     "ci": [
      0.465,
      0.6885
     ],
     "n": 119,
     "clusters": 12,
     "paired": {
      "lebowski_877m": {
       "delta": -4.979,
       "median": -4.3,
       "ci": [
        -6.029,
        -2.761
       ],
       "n": 119,
       "wins": 119,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 12
      },
      "steam_powered": {
       "delta": 0.0605,
       "median": 0.07269,
       "ci": [
        -0.005042,
        0.08147
       ],
       "n": 119,
       "wins": 33,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 5
      }
     }
    },
    {
     "key": "v3_mae",
     "label": "Plan speed error at 3 s",
     "unit": "m/s",
     "better": "lower",
     "value": 2.432,
     "median": 2.321,
     "ci": [
      1.28,
      3.131
     ],
     "n": 119,
     "clusters": 12,
     "paired": {
      "lebowski_877m": {
       "delta": 0.435,
       "median": 0.2404,
       "ci": [
        0.02435,
        1.134
       ],
       "n": 119,
       "wins": 37,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 4
      },
      "steam_powered": {
       "delta": -0.2872,
       "median": -0.3046,
       "ci": [
        -0.3188,
        -0.2178
       ],
       "n": 119,
       "wins": 97,
       "ties": 0,
       "clusters": 12,
       "cluster_wins": 12
      }
     }
    }
   ],
   "per_unit_file": null,
   "by_group": {
    "stock-aimedup": {
     "n": 4,
     "clusters": 2,
     "metrics": [
      {
       "key": "lat_mae",
       "value": 0.09263,
       "median": 0.09292,
       "ci": null,
       "n": 4,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": -0.0485,
         "median": -0.05126,
         "ci": null,
         "n": 4,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": -0.01525,
         "median": -0.01769,
         "ci": null,
         "n": 4,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "lat_mae_bl",
       "value": 0.09177,
       "median": 0.09121,
       "ci": null,
       "n": 4,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": -0.0478,
         "median": -0.05228,
         "ci": null,
         "n": 4,
         "wins": 3,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": -0.01237,
         "median": -0.01356,
         "ci": null,
         "n": 4,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "lat_corr",
       "value": 0.8873,
       "median": 0.9467,
       "ci": null,
       "n": 4,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": 0.09215,
         "median": 0.1075,
         "ci": null,
         "n": 4,
         "wins": 3,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": 0.05045,
         "median": 0.01865,
         "ci": null,
         "n": 4,
         "wins": 2,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "lat_gain",
       "value": 0.8302,
       "median": 0.9138,
       "ci": null,
       "n": 4,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": -0.1107,
         "median": -0.1506,
         "ci": null,
         "n": 4,
         "wins": 3,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": 0.05396,
         "median": 0.06744,
         "ci": null,
         "n": 4,
         "wins": 0,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "lat_rate_rms",
       "value": 0.3179,
       "median": 0.3151,
       "ci": null,
       "n": 4,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": -0.835,
         "median": -0.8823,
         "ci": null,
         "n": 4,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": -0.05075,
         "median": -0.04915,
         "ci": null,
         "n": 4,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "lat_best_lag",
       "value": 0.6625,
       "median": 0.675,
       "ci": null,
       "n": 4,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": 0.15,
         "median": 0.125,
         "ci": null,
         "n": 4,
         "wins": 0,
         "ties": 1,
         "clusters": 2,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": -0.0875,
         "median": -0.075,
         "ci": null,
         "n": 4,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "lon_mae",
       "value": 0.4526,
       "median": 0.4403,
       "ci": null,
       "n": 4,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": -0.325,
         "median": -0.2983,
         "ci": null,
         "n": 4,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": -0.1651,
         "median": -0.174,
         "ci": null,
         "n": 4,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "lon_corr",
       "value": 0.3524,
       "median": 0.277,
       "ci": null,
       "n": 4,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": -0.183,
         "median": -0.1587,
         "ci": null,
         "n": 4,
         "wins": 1,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": 0.04498,
         "median": 0.04581,
         "ci": null,
         "n": 4,
         "wins": 2,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lon_brake_mae",
       "value": 1.011,
       "median": 1.011,
       "ci": null,
       "n": 2,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": 0.8231,
         "median": 0.8231,
         "ci": null,
         "n": 2,
         "wins": 0,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": -0.06722,
         "median": -0.06722,
         "ci": null,
         "n": 2,
         "wins": 1,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lon_rate_rms",
       "value": 0.4862,
       "median": 0.4202,
       "ci": null,
       "n": 4,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": -2.808,
         "median": -2.942,
         "ci": null,
         "n": 4,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": -0.05678,
         "median": -0.04678,
         "ci": null,
         "n": 4,
         "wins": 3,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "v3_mae",
       "value": 1.656,
       "median": 1.642,
       "ci": null,
       "n": 4,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": -0.7329,
         "median": -0.5095,
         "ci": null,
         "n": 4,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": -0.3425,
         "median": -0.3688,
         "ci": null,
         "n": 4,
         "wins": 3,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        }
       }
      }
     ]
    },
    "stock-dual": {
     "n": 13,
     "clusters": 4,
     "metrics": [
      {
       "key": "lat_mae",
       "value": 0.1442,
       "median": 0.1327,
       "ci": null,
       "n": 13,
       "clusters": 4,
       "paired": {
        "lebowski_877m": {
         "delta": -0.00104,
         "median": -0.0067,
         "ci": null,
         "n": 13,
         "wins": 8,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": 0.01077,
         "median": 0.01007,
         "ci": null,
         "n": 13,
         "wins": 5,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "lat_mae_bl",
       "value": 0.1411,
       "median": 0.1284,
       "ci": null,
       "n": 13,
       "clusters": 4,
       "paired": {
        "lebowski_877m": {
         "delta": 0.001882,
         "median": 0.001459,
         "ci": null,
         "n": 13,
         "wins": 6,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": 0.01103,
         "median": 0.01106,
         "ci": null,
         "n": 13,
         "wins": 5,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "lat_corr",
       "value": 0.8431,
       "median": 0.8954,
       "ci": null,
       "n": 13,
       "clusters": 4,
       "paired": {
        "lebowski_877m": {
         "delta": 0.0298,
         "median": -0.001633,
         "ci": null,
         "n": 13,
         "wins": 6,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 3
        },
        "steam_powered": {
         "delta": -0.01123,
         "median": -0.01119,
         "ci": null,
         "n": 13,
         "wins": 3,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lat_gain",
       "value": 0.9681,
       "median": 0.9132,
       "ci": null,
       "n": 13,
       "clusters": 4,
       "paired": {
        "lebowski_877m": {
         "delta": 0.01871,
         "median": -0.003726,
         "ci": null,
         "n": 13,
         "wins": 7,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": -0.005768,
         "median": -0.01772,
         "ci": null,
         "n": 13,
         "wins": 9,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 3
        }
       }
      },
      {
       "key": "lat_rate_rms",
       "value": 0.3724,
       "median": 0.3155,
       "ci": null,
       "n": 13,
       "clusters": 4,
       "paired": {
        "lebowski_877m": {
         "delta": -0.8035,
         "median": -0.7898,
         "ci": null,
         "n": 13,
         "wins": 13,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 4
        },
        "steam_powered": {
         "delta": 0.0438,
         "median": 0.03429,
         "ci": null,
         "n": 13,
         "wins": 1,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "lat_best_lag",
       "value": 0.6885,
       "median": 0.65,
       "ci": null,
       "n": 13,
       "clusters": 4,
       "paired": {
        "lebowski_877m": {
         "delta": 0.1769,
         "median": 0.15,
         "ci": null,
         "n": 13,
         "wins": 0,
         "ties": 2,
         "clusters": 4,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": 0.01538,
         "median": 0.0,
         "ci": null,
         "n": 13,
         "wins": 4,
         "ties": 5,
         "clusters": 4,
         "cluster_wins": 3
        }
       }
      },
      {
       "key": "lon_mae",
       "value": 0.2635,
       "median": 0.2454,
       "ci": null,
       "n": 13,
       "clusters": 4,
       "paired": {
        "lebowski_877m": {
         "delta": 0.03528,
         "median": 0.01762,
         "ci": null,
         "n": 13,
         "wins": 2,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": -0.02413,
         "median": -0.02145,
         "ci": null,
         "n": 13,
         "wins": 10,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 3
        }
       }
      },
      {
       "key": "lon_corr",
       "value": 0.5922,
       "median": 0.6972,
       "ci": null,
       "n": 13,
       "clusters": 4,
       "paired": {
        "lebowski_877m": {
         "delta": -0.04198,
         "median": -0.01594,
         "ci": null,
         "n": 13,
         "wins": 5,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": 0.0875,
         "median": 0.07332,
         "ci": null,
         "n": 13,
         "wins": 9,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 4
        }
       }
      },
      {
       "key": "lon_brake_mae",
       "value": 0.634,
       "median": 0.6649,
       "ci": null,
       "n": 6,
       "clusters": 4,
       "paired": {
        "lebowski_877m": {
         "delta": -0.01329,
         "median": -0.01279,
         "ci": null,
         "n": 6,
         "wins": 3,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": -0.05745,
         "median": -0.04832,
         "ci": null,
         "n": 6,
         "wins": 4,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "lon_rate_rms",
       "value": 0.3787,
       "median": 0.3589,
       "ci": null,
       "n": 13,
       "clusters": 4,
       "paired": {
        "lebowski_877m": {
         "delta": -1.835,
         "median": -1.804,
         "ci": null,
         "n": 13,
         "wins": 13,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 4
        },
        "steam_powered": {
         "delta": -0.02053,
         "median": -0.01888,
         "ci": null,
         "n": 13,
         "wins": 9,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "v3_mae",
       "value": 0.9581,
       "median": 0.8496,
       "ci": null,
       "n": 13,
       "clusters": 4,
       "paired": {
        "lebowski_877m": {
         "delta": 0.1169,
         "median": 0.1144,
         "ci": null,
         "n": 13,
         "wins": 4,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": -0.1408,
         "median": -0.08562,
         "ci": null,
         "n": 13,
         "wins": 10,
         "ties": 0,
         "clusters": 4,
         "cluster_wins": 4
        }
       }
      }
     ]
    },
    "stock-newcase": {
     "n": 2,
     "clusters": 1,
     "metrics": [
      {
       "key": "lat_mae",
       "value": 0.166,
       "median": 0.166,
       "ci": null,
       "n": 2,
       "clusters": 1,
       "paired": {
        "lebowski_877m": {
         "delta": 0.03169,
         "median": 0.03169,
         "ci": null,
         "n": 2,
         "wins": 0,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": -0.0003498,
         "median": -0.0003498,
         "ci": null,
         "n": 2,
         "wins": 1,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lat_mae_bl",
       "value": 0.1648,
       "median": 0.1648,
       "ci": null,
       "n": 2,
       "clusters": 1,
       "paired": {
        "lebowski_877m": {
         "delta": 0.02962,
         "median": 0.02962,
         "ci": null,
         "n": 2,
         "wins": 0,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": 0.003053,
         "median": 0.003053,
         "ci": null,
         "n": 2,
         "wins": 1,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "lat_corr",
       "value": 0.8485,
       "median": 0.8485,
       "ci": null,
       "n": 2,
       "clusters": 1,
       "paired": {
        "lebowski_877m": {
         "delta": 0.000924,
         "median": 0.000924,
         "ci": null,
         "n": 2,
         "wins": 1,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": 0.002293,
         "median": 0.002293,
         "ci": null,
         "n": 2,
         "wins": 1,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lat_gain",
       "value": 0.7929,
       "median": 0.7929,
       "ci": null,
       "n": 2,
       "clusters": 1,
       "paired": {
        "lebowski_877m": {
         "delta": -0.002956,
         "median": -0.002956,
         "ci": null,
         "n": 2,
         "wins": 1,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": 0.01255,
         "median": 0.01255,
         "ci": null,
         "n": 2,
         "wins": 1,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "lat_rate_rms",
       "value": 0.4666,
       "median": 0.4666,
       "ci": null,
       "n": 2,
       "clusters": 1,
       "paired": {
        "lebowski_877m": {
         "delta": -0.809,
         "median": -0.809,
         "ci": null,
         "n": 2,
         "wins": 2,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": -0.06025,
         "median": -0.06025,
         "ci": null,
         "n": 2,
         "wins": 1,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lat_best_lag",
       "value": 0.65,
       "median": 0.65,
       "ci": null,
       "n": 2,
       "clusters": 1,
       "paired": {
        "lebowski_877m": {
         "delta": 0.15,
         "median": 0.15,
         "ci": null,
         "n": 2,
         "wins": 0,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": 0.125,
         "median": 0.125,
         "ci": null,
         "n": 2,
         "wins": 0,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "lon_mae",
       "value": 0.4019,
       "median": 0.4019,
       "ci": null,
       "n": 2,
       "clusters": 1,
       "paired": {
        "lebowski_877m": {
         "delta": 0.03934,
         "median": 0.03934,
         "ci": null,
         "n": 2,
         "wins": 1,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": -0.05053,
         "median": -0.05053,
         "ci": null,
         "n": 2,
         "wins": 2,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lon_corr",
       "value": 0.4113,
       "median": 0.4113,
       "ci": null,
       "n": 2,
       "clusters": 1,
       "paired": {
        "lebowski_877m": {
         "delta": -0.0753,
         "median": -0.0753,
         "ci": null,
         "n": 2,
         "wins": 0,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": -0.08362,
         "median": -0.08362,
         "ci": null,
         "n": 2,
         "wins": 0,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "lon_brake_mae",
       "value": 0.3159,
       "median": 0.3159,
       "ci": null,
       "n": 2,
       "clusters": 1,
       "paired": {
        "lebowski_877m": {
         "delta": -0.1874,
         "median": -0.1874,
         "ci": null,
         "n": 2,
         "wins": 2,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": 0.09306,
         "median": 0.09306,
         "ci": null,
         "n": 2,
         "wins": 0,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "lon_rate_rms",
       "value": 0.5652,
       "median": 0.5652,
       "ci": null,
       "n": 2,
       "clusters": 1,
       "paired": {
        "lebowski_877m": {
         "delta": -2.791,
         "median": -2.791,
         "ci": null,
         "n": 2,
         "wins": 2,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": -0.01335,
         "median": -0.01335,
         "ci": null,
         "n": 2,
         "wins": 1,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "v3_mae",
       "value": 2.023,
       "median": 2.023,
       "ci": null,
       "n": 2,
       "clusters": 1,
       "paired": {
        "lebowski_877m": {
         "delta": -0.07079,
         "median": -0.07079,
         "ci": null,
         "n": 2,
         "wins": 1,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": -0.487,
         "median": -0.487,
         "ci": null,
         "n": 2,
         "wins": 2,
         "ties": 0,
         "clusters": 1,
         "cluster_wins": 1
        }
       }
      }
     ]
    },
    "v13-8mm": {
     "n": 92,
     "clusters": 3,
     "metrics": [
      {
       "key": "lat_mae",
       "value": 0.172,
       "median": 0.1674,
       "ci": null,
       "n": 92,
       "clusters": 3,
       "paired": {
        "lebowski_877m": {
         "delta": -0.009549,
         "median": -0.01096,
         "ci": null,
         "n": 92,
         "wins": 57,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": 0.00471,
         "median": 0.004905,
         "ci": null,
         "n": 92,
         "wins": 34,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "lat_mae_bl",
       "value": 0.1677,
       "median": 0.1627,
       "ci": null,
       "n": 92,
       "clusters": 3,
       "paired": {
        "lebowski_877m": {
         "delta": -0.004491,
         "median": -0.004825,
         "ci": null,
         "n": 92,
         "wins": 52,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": 0.004755,
         "median": 0.005027,
         "ci": null,
         "n": 92,
         "wins": 33,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "lat_corr",
       "value": 0.8306,
       "median": 0.9138,
       "ci": null,
       "n": 92,
       "clusters": 3,
       "paired": {
        "lebowski_877m": {
         "delta": 0.08214,
         "median": 0.03666,
         "ci": null,
         "n": 92,
         "wins": 85,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 3
        },
        "steam_powered": {
         "delta": -0.002235,
         "median": -0.003017,
         "ci": null,
         "n": 92,
         "wins": 28,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "lat_gain",
       "value": 0.8821,
       "median": 0.8786,
       "ci": null,
       "n": 92,
       "clusters": 3,
       "paired": {
        "lebowski_877m": {
         "delta": -0.06829,
         "median": -0.06483,
         "ci": null,
         "n": 92,
         "wins": 67,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 3
        },
        "steam_powered": {
         "delta": 0.002138,
         "median": 0.006494,
         "ci": null,
         "n": 92,
         "wins": 41,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lat_rate_rms",
       "value": 0.8234,
       "median": 0.7411,
       "ci": null,
       "n": 92,
       "clusters": 3,
       "paired": {
        "lebowski_877m": {
         "delta": -1.794,
         "median": -1.636,
         "ci": null,
         "n": 92,
         "wins": 92,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 3
        },
        "steam_powered": {
         "delta": 0.0914,
         "median": 0.08625,
         "ci": null,
         "n": 92,
         "wins": 13,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "lat_best_lag",
       "value": 0.6984,
       "median": 0.65,
       "ci": null,
       "n": 91,
       "clusters": 3,
       "paired": {
        "lebowski_877m": {
         "delta": 0.04396,
         "median": 0.1,
         "ci": null,
         "n": 91,
         "wins": 24,
         "ties": 10,
         "clusters": 3,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": 0.0005495,
         "median": 0.0,
         "ci": null,
         "n": 91,
         "wins": 24,
         "ties": 41,
         "clusters": 3,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lon_mae",
       "value": 0.3227,
       "median": 0.3148,
       "ci": null,
       "n": 92,
       "clusters": 3,
       "paired": {
        "lebowski_877m": {
         "delta": -0.05329,
         "median": -0.04922,
         "ci": null,
         "n": 92,
         "wins": 75,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 3
        },
        "steam_powered": {
         "delta": -0.01568,
         "median": -0.01285,
         "ci": null,
         "n": 92,
         "wins": 61,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "lon_corr",
       "value": 0.2973,
       "median": 0.2971,
       "ci": null,
       "n": 92,
       "clusters": 3,
       "paired": {
        "lebowski_877m": {
         "delta": 0.06363,
         "median": 0.06929,
         "ci": null,
         "n": 92,
         "wins": 61,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 3
        },
        "steam_powered": {
         "delta": 0.02235,
         "median": 0.00887,
         "ci": null,
         "n": 92,
         "wins": 48,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 2
        }
       }
      },
      {
       "key": "lon_brake_mae",
       "value": 0.7253,
       "median": 0.7178,
       "ci": null,
       "n": 65,
       "clusters": 3,
       "paired": {
        "lebowski_877m": {
         "delta": 0.2362,
         "median": 0.2382,
         "ci": null,
         "n": 65,
         "wins": 5,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": -0.01916,
         "median": -0.021,
         "ci": null,
         "n": 65,
         "wins": 36,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lon_rate_rms",
       "value": 0.6808,
       "median": 0.634,
       "ci": null,
       "n": 92,
       "clusters": 3,
       "paired": {
        "lebowski_877m": {
         "delta": -5.652,
         "median": -5.323,
         "ci": null,
         "n": 92,
         "wins": 92,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 3
        },
        "steam_powered": {
         "delta": 0.08123,
         "median": 0.09643,
         "ci": null,
         "n": 92,
         "wins": 17,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "v3_mae",
       "value": 2.794,
       "median": 2.696,
       "ci": null,
       "n": 92,
       "clusters": 3,
       "paired": {
        "lebowski_877m": {
         "delta": 0.56,
         "median": 0.4013,
         "ci": null,
         "n": 92,
         "wins": 27,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": -0.3083,
         "median": -0.338,
         "ci": null,
         "n": 92,
         "wins": 75,
         "ties": 0,
         "clusters": 3,
         "cluster_wins": 3
        }
       }
      }
     ]
    },
    "v14-8mm": {
     "n": 8,
     "clusters": 2,
     "metrics": [
      {
       "key": "lat_mae",
       "value": 0.1592,
       "median": 0.1665,
       "ci": null,
       "n": 8,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": 0.01779,
         "median": 0.01323,
         "ci": null,
         "n": 8,
         "wins": 2,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": 0.009091,
         "median": 0.008183,
         "ci": null,
         "n": 8,
         "wins": 1,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "lat_mae_bl",
       "value": 0.1567,
       "median": 0.1631,
       "ci": null,
       "n": 8,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": 0.01958,
         "median": 0.0126,
         "ci": null,
         "n": 8,
         "wins": 2,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": 0.008677,
         "median": 0.007107,
         "ci": null,
         "n": 8,
         "wins": 1,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "lat_corr",
       "value": 0.8518,
       "median": 0.9115,
       "ci": null,
       "n": 8,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": -0.01621,
         "median": 0.0003597,
         "ci": null,
         "n": 8,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 1
        },
        "steam_powered": {
         "delta": -0.004154,
         "median": -0.001367,
         "ci": null,
         "n": 8,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lat_gain",
       "value": 0.9498,
       "median": 0.9197,
       "ci": null,
       "n": 8,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": 0.03681,
         "median": 0.03501,
         "ci": null,
         "n": 8,
         "wins": 1,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": 0.0002963,
         "median": -0.003786,
         "ci": null,
         "n": 8,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lat_rate_rms",
       "value": 0.4707,
       "median": 0.4146,
       "ci": null,
       "n": 8,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": -0.6848,
         "median": -0.5898,
         "ci": null,
         "n": 8,
         "wins": 8,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": 0.03414,
         "median": 0.0367,
         "ci": null,
         "n": 8,
         "wins": 1,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "lat_best_lag",
       "value": 0.65,
       "median": 0.6,
       "ci": null,
       "n": 8,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": 0.2,
         "median": 0.2,
         "ci": null,
         "n": 8,
         "wins": 0,
         "ties": 1,
         "clusters": 2,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": -0.03125,
         "median": -0.025,
         "ci": null,
         "n": 8,
         "wins": 4,
         "ties": 1,
         "clusters": 2,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lon_mae",
       "value": 0.3564,
       "median": 0.3052,
       "ci": null,
       "n": 8,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": 0.04706,
         "median": 0.02757,
         "ci": null,
         "n": 8,
         "wins": 1,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": -0.004223,
         "median": 0.01731,
         "ci": null,
         "n": 8,
         "wins": 2,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lon_corr",
       "value": 0.7121,
       "median": 0.7287,
       "ci": null,
       "n": 8,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": -0.04264,
         "median": -0.02423,
         "ci": null,
         "n": 8,
         "wins": 0,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": -0.01532,
         "median": -0.0117,
         "ci": null,
         "n": 8,
         "wins": 2,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lon_brake_mae",
       "value": 0.647,
       "median": 0.7211,
       "ci": null,
       "n": 6,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": 0.0894,
         "median": 0.1025,
         "ci": null,
         "n": 6,
         "wins": 1,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": -0.05021,
         "median": -0.02026,
         "ci": null,
         "n": 6,
         "wins": 4,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 1
        }
       }
      },
      {
       "key": "lon_rate_rms",
       "value": 0.5545,
       "median": 0.4978,
       "ci": null,
       "n": 8,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": -3.979,
         "median": -3.702,
         "ci": null,
         "n": 8,
         "wins": 8,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        },
        "steam_powered": {
         "delta": 0.03097,
         "median": 0.03181,
         "ci": null,
         "n": 8,
         "wins": 3,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 0
        }
       }
      },
      {
       "key": "v3_mae",
       "value": 1.156,
       "median": 1.077,
       "ci": null,
       "n": 8,
       "clusters": 2,
       "paired": {
        "lebowski_877m": {
         "delta": 0.2239,
         "median": 0.206,
         "ci": null,
         "n": 8,
         "wins": 1,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 0
        },
        "steam_powered": {
         "delta": -0.205,
         "median": -0.1178,
         "ci": null,
         "n": 8,
         "wins": 7,
         "ties": 0,
         "clusters": 2,
         "cluster_wins": 2
        }
       }
      }
     ]
    }
   }
  },
  "truck_closed_loop": {
   "status": "not_run",
   "unit_of_evidence": "window",
   "n": 0,
   "condition": "Measured. worldmodel-4B as in the public closed loop, but the model drives a simulation of the G55's measured steering and powertrain response instead of the ideal car. The simulation starts from the truck's state (speed, yaw rate, steering, gear) in its CAN recording of the 2 s before the window; one window, whose 2 s before are not all valid CAN, starts steady at its recorded speed. Lane-following windows from the G55's drives, day and night; distance is to the driver's recorded path; seeds 0 and 1, averaged per window.",
   "baselines": [],
   "metrics": [],
   "per_unit_file": null
  },
  "truck_recovery": {
   "status": "not_run",
   "unit_of_evidence": "window",
   "n": 0,
   "condition": "Measured. The truck closed loop with a disturbance while the model drives; only the tests listed ran.",
   "baselines": [],
   "metrics": [],
   "per_unit_file": null
  }
 },
 "stills": [],
 "limits": [
  "Open-loop scores compare a model's action with what the recording driver or car did; a model that drives differently but well is scored as wrong. comma's RL residual makes the lateral action smoother, and earlier than its base's by 0.10 to 0.26 s (measured on the G55 and on 16 of comma's cars); both score as error here. Measured on the 2026-10-27 deep dive: open-loop accuracy did not predict closed-loop driving.",
  "Closed-loop numbers come from a generative world model, not a car. In a separate test on the G55's windows, worldmodel-4B followed an added yaw command through 2 s but showed 0 to 20% of an added lateral offset 3 to 4 s later; past about 4 s the recorded anchor frames also pull every model back toward the recorded path. The front page reports 2 s.",
  "Intervals are 95% percentile bootstraps that resample whole drives (the drive a public segment was cut from, the recorded drive a truck window comes from), so segments of one drive count once. Below 10 drives there is no interval: the braking-lead test comes from one drive and reports means and win counts only.",
  "Paired deltas are model minus baseline on the units both have (for lateral gain, the change in its distance from 1); wins count units where the model is better in the metric's direction.",
  "The lead of the lateral request is the shift, searched from 0 to 1.5 s, at which the request best correlates with the car's later lateral motion; a larger value means the request comes earlier. A value at either edge is censored and left out. Plan speed error at 3 s reads the plan head, which does not separate models built on one frozen base: it is identical on every segment for the four f22e06e5 models, and for Cinque v2 and v3.",
  "Truck open loop comes from few drives, and the camera setup changed between them (lens, housing, aim); the pooled number mixes setups, so read the per-setup numbers too. The 8 mm setups' wide camera recorded about 7-10 fps, so its frame can be up to ~60 ms from the narrow one. On the V14 setup up to 7 of a window's 700 steps are ~100 ms (one camera frame dropped). The camera's aim is the truck's live calibration learned on each drive; drives whose recorded calibration was carried over from another drive are left out.",
  "A historical model, run outside comma's software with its own release's inputs, camera warp and command (engines/legacy.py). Checked against comma's CI model replay of this model (made on a comma device, 60 frames of one route): the plan's lateral position is 0.027 m RMS from comma's output; every other model here is 0.67 m or more from it on the same check.",
  "Trained for the comma devices and cameras of its time, not for the G55's camera or for every camera among comma's public segments: of those 45 segments 26 record the OX03C10 sensor, 6 the AR0231, 4 the OS04C10 and 9 none; 30 were recorded 2021 to 2024 and 15 come from devices whose route names carry no date.",
  "Not run in closed loop: the G55 closed-loop and recovery tests need this release's controller inside the world-model loop, which is not built yet.",
  "The commands are 0.10's modeld (get_action_from_model on the plan, lateral delay = steer actuator delay + 0.2 s, smoothed over 0.1 s lateral and 0.3 s longitudinal); the newest models are scored on their own unsmoothed action head, so lateral action rates are not comparable across these eras."
 ]
}
