slipstream / data /bench.json
ashaibani's picture
Upload folder using huggingface_hub
2d4823c verified
Raw
History Blame Contribute Delete
84.4 kB
{
"n_test": 117,
"n_eval": 107,
"strata": [
"short",
"medium",
"long",
"very_long"
],
"stages": [
"0.25",
"0.40",
"0.60",
"0.75"
],
"primary": "0.40",
"methods": {
"naive_onplan": {
"family": "naive",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.44,
"eac_mpe_med": -1.91,
"finish_err_med": 1.0,
"finish_ape_med": 7.69,
"finish_mpe_med": -7.69
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.44,
"eac_mpe_med": -1.91,
"finish_err_med": 1.0,
"finish_ape_med": 7.69,
"finish_mpe_med": -7.69
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.44,
"eac_mpe_med": -1.91,
"finish_err_med": 1.0,
"finish_ape_med": 7.69,
"finish_mpe_med": -7.69
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.44,
"eac_mpe_med": -1.91,
"finish_err_med": 1.0,
"finish_ape_med": 7.69,
"finish_mpe_med": -7.69
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 4.21,
"eac_mpe_med": -2.48,
"finish_err_med": 0.0,
"finish_ape_med": 0.0,
"finish_mpe_med": 0.0
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 5.21,
"eac_mpe_med": -0.67,
"finish_err_med": 1.0,
"finish_ape_med": 11.11,
"finish_mpe_med": -11.11
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 3.13,
"eac_mpe_med": -2.71,
"finish_err_med": 1.0,
"finish_ape_med": 7.69,
"finish_mpe_med": -7.69
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 5.86,
"eac_mpe_med": -5.86,
"finish_err_med": 6.0,
"finish_ape_med": 14.87,
"finish_mpe_med": -14.87
}
}
},
"last_value": {
"family": "naive",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.22,
"eac_mpe_med": -0.1,
"finish_err_med": 3.61,
"finish_ape_med": 36.88,
"finish_mpe_med": 10.43
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.22,
"eac_mpe_med": -0.58,
"finish_err_med": 2.16,
"finish_ape_med": 26.31,
"finish_mpe_med": 8.05
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.22,
"eac_mpe_med": -0.41,
"finish_err_med": 2.05,
"finish_ape_med": 23.83,
"finish_mpe_med": 8.05
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.39,
"eac_mpe_med": -0.13,
"finish_err_med": 1.19,
"finish_ape_med": 15.01,
"finish_mpe_med": -2.43
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 3.22,
"eac_mpe_med": 0.06,
"finish_err_med": 0.63,
"finish_ape_med": 14.57,
"finish_mpe_med": 8.05
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 2.95,
"eac_mpe_med": -0.38,
"finish_err_med": 2.63,
"finish_ape_med": 26.31,
"finish_mpe_med": -4.43
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 10.25,
"eac_mpe_med": -4.78,
"finish_err_med": 8.54,
"finish_ape_med": 60.97,
"finish_mpe_med": 60.97
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 41.88,
"eac_mpe_med": -2.49,
"finish_err_med": 30.32,
"finish_ape_med": 79.88,
"finish_mpe_med": 79.88
}
}
},
"linear": {
"family": "naive",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 12.44,
"eac_mpe_med": -5.07,
"finish_err_med": 5.09,
"finish_ape_med": 46.78,
"finish_mpe_med": 3.03
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 8.77,
"eac_mpe_med": -2.21,
"finish_err_med": 3.67,
"finish_ape_med": 35.22,
"finish_mpe_med": 1.24
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.05,
"eac_mpe_med": -1.51,
"finish_err_med": 2.18,
"finish_ape_med": 23.85,
"finish_mpe_med": -0.37
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.1,
"eac_mpe_med": -0.81,
"finish_err_med": 1.6,
"finish_ape_med": 18.11,
"finish_mpe_med": -8.98
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 3.56,
"eac_mpe_med": -0.81,
"finish_err_med": 0.75,
"finish_ape_med": 18.16,
"finish_mpe_med": 0.83
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 24.1,
"eac_mpe_med": -3.34,
"finish_err_med": 4.22,
"finish_ape_med": 45.92,
"finish_mpe_med": -17.2
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 17.08,
"eac_mpe_med": -8.75,
"finish_err_med": 6.34,
"finish_ape_med": 48.79,
"finish_mpe_med": 17.16
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 15.02,
"eac_mpe_med": -5.33,
"finish_err_med": 40.13,
"finish_ape_med": 103.58,
"finish_mpe_med": 85.44
}
}
},
"logistic": {
"family": "classical",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 24.2,
"eac_mpe_med": -11.66,
"finish_err_med": 6.36,
"finish_ape_med": 51.73,
"finish_mpe_med": 5.24
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 21.3,
"eac_mpe_med": -17.39,
"finish_err_med": 14.0,
"finish_ape_med": 173.17,
"finish_mpe_med": 173.17
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 13.32,
"eac_mpe_med": -10.53,
"finish_err_med": 11.0,
"finish_ape_med": 166.67,
"finish_mpe_med": 166.67
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.1,
"eac_mpe_med": -2.1,
"finish_err_med": 5.62,
"finish_ape_med": 28.03,
"finish_mpe_med": 19.23
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 3.56,
"eac_mpe_med": -0.81,
"finish_err_med": 0.75,
"finish_ape_med": 18.16,
"finish_mpe_med": 0.83
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 43.86,
"eac_mpe_med": -38.12,
"finish_err_med": 23.0,
"finish_ape_med": 255.56,
"finish_mpe_med": 255.56
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 57.06,
"eac_mpe_med": -57.06,
"finish_err_med": 44.0,
"finish_ape_med": 263.64,
"finish_mpe_med": 263.64
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 50.28,
"eac_mpe_med": -50.28,
"finish_err_med": 69.0,
"finish_ape_med": 170.48,
"finish_mpe_med": 170.48
}
}
},
"growth_curve": {
"family": "classical",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.23,
"eac_mpe_med": 0.0,
"finish_err_med": 1.91,
"finish_ape_med": 22.0,
"finish_mpe_med": 0.62
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.37,
"eac_mpe_med": 0.0,
"finish_err_med": 1.55,
"finish_ape_med": 18.65,
"finish_mpe_med": 0.0
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.54,
"eac_mpe_med": -0.0,
"finish_err_med": 1.11,
"finish_ape_med": 15.09,
"finish_mpe_med": 2.0
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.28,
"eac_mpe_med": 0.0,
"finish_err_med": 1.2,
"finish_ape_med": 13.95,
"finish_mpe_med": 1.24
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 1.54,
"eac_mpe_med": -0.0,
"finish_err_med": 1.0,
"finish_ape_med": 21.13,
"finish_mpe_med": 11.05
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 3.41,
"eac_mpe_med": 0.0,
"finish_err_med": 1.61,
"finish_ape_med": 14.67,
"finish_mpe_med": 0.0
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 2.02,
"eac_mpe_med": -0.1,
"finish_err_med": 3.39,
"finish_ape_med": 17.96,
"finish_mpe_med": 0.0
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 6.04,
"eac_mpe_med": 0.32,
"finish_err_med": 10.35,
"finish_ape_med": 20.36,
"finish_mpe_med": -6.07
}
}
},
"exp_smoothing": {
"family": "classical",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 11.66,
"eac_mpe_med": -3.06,
"finish_err_med": 4.69,
"finish_ape_med": 46.89,
"finish_mpe_med": 2.19
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 7.59,
"eac_mpe_med": -1.41,
"finish_err_med": 3.69,
"finish_ape_med": 36.85,
"finish_mpe_med": 0.84
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.9,
"eac_mpe_med": -1.23,
"finish_err_med": 2.17,
"finish_ape_med": 20.5,
"finish_mpe_med": -2.22
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.24,
"eac_mpe_med": -0.7,
"finish_err_med": 1.6,
"finish_ape_med": 18.09,
"finish_mpe_med": -2.28
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 3.56,
"eac_mpe_med": -0.81,
"finish_err_med": 0.75,
"finish_ape_med": 16.8,
"finish_mpe_med": 0.84
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 23.67,
"eac_mpe_med": -2.18,
"finish_err_med": 4.43,
"finish_ape_med": 45.9,
"finish_mpe_med": -25.25
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 11.69,
"eac_mpe_med": -2.09,
"finish_err_med": 6.44,
"finish_ape_med": 44.72,
"finish_mpe_med": 12.31
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 52.79,
"eac_mpe_med": -1.95,
"finish_err_med": 69.0,
"finish_ape_med": 170.48,
"finish_mpe_med": 170.48
}
}
},
"earned_schedule": {
"family": "classical",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.23,
"eac_mpe_med": 0.0,
"finish_err_med": 0.98,
"finish_ape_med": 11.11,
"finish_mpe_med": 0.0
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.37,
"eac_mpe_med": 0.0,
"finish_err_med": 1.0,
"finish_ape_med": 10.71,
"finish_mpe_med": 0.0
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.54,
"eac_mpe_med": -0.0,
"finish_err_med": 0.75,
"finish_ape_med": 7.71,
"finish_mpe_med": 0.71
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.28,
"eac_mpe_med": 0.0,
"finish_err_med": 0.69,
"finish_ape_med": 7.1,
"finish_mpe_med": 0.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 1.54,
"eac_mpe_med": -0.0,
"finish_err_med": 0.35,
"finish_ape_med": 8.32,
"finish_mpe_med": 0.0
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 3.41,
"eac_mpe_med": 0.0,
"finish_err_med": 1.0,
"finish_ape_med": 11.11,
"finish_mpe_med": 0.34
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 2.02,
"eac_mpe_med": -0.1,
"finish_err_med": 2.67,
"finish_ape_med": 15.33,
"finish_mpe_med": 0.0
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 6.04,
"eac_mpe_med": 0.32,
"finish_err_med": 5.37,
"finish_ape_med": 10.39,
"finish_mpe_med": 1.5
}
}
},
"evm_cpi_spi": {
"family": "classical",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 10.0,
"eac_mpe_med": 4.67,
"finish_err_med": 0.98,
"finish_ape_med": 11.11,
"finish_mpe_med": 0.0
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 9.65,
"eac_mpe_med": 4.61,
"finish_err_med": 1.0,
"finish_ape_med": 10.71,
"finish_mpe_med": 0.0
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.29,
"eac_mpe_med": 2.61,
"finish_err_med": 0.75,
"finish_ape_med": 7.71,
"finish_mpe_med": 0.71
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.23,
"eac_mpe_med": 1.28,
"finish_err_med": 0.69,
"finish_ape_med": 7.1,
"finish_mpe_med": 0.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 3.7,
"eac_mpe_med": 3.23,
"finish_err_med": 0.35,
"finish_ape_med": 8.32,
"finish_mpe_med": 0.0
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 12.71,
"eac_mpe_med": 11.65,
"finish_err_med": 1.0,
"finish_ape_med": 11.11,
"finish_mpe_med": 0.34
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 15.12,
"eac_mpe_med": 4.51,
"finish_err_med": 2.67,
"finish_ape_med": 15.33,
"finish_mpe_med": 0.0
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 22.86,
"eac_mpe_med": 15.25,
"finish_err_med": 5.37,
"finish_ape_med": 10.39,
"finish_mpe_med": 1.5
}
}
},
"xsm": {
"family": "classical",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.91,
"eac_mpe_med": 0.0,
"finish_err_med": 1.01,
"finish_ape_med": 13.88,
"finish_mpe_med": 3.36
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.8,
"eac_mpe_med": 0.0,
"finish_err_med": 0.9,
"finish_ape_med": 12.44,
"finish_mpe_med": 3.81
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.87,
"eac_mpe_med": 0.0,
"finish_err_med": 0.87,
"finish_ape_med": 10.02,
"finish_mpe_med": 1.12
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.48,
"eac_mpe_med": -0.0,
"finish_err_med": 0.7,
"finish_ape_med": 6.9,
"finish_mpe_med": 0.18
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 1.56,
"eac_mpe_med": 0.44,
"finish_err_med": 0.34,
"finish_ape_med": 6.9,
"finish_mpe_med": 0.0
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 3.91,
"eac_mpe_med": 0.31,
"finish_err_med": 1.26,
"finish_ape_med": 12.68,
"finish_mpe_med": 5.41
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 4.16,
"eac_mpe_med": -0.23,
"finish_err_med": 4.24,
"finish_ape_med": 23.45,
"finish_mpe_med": 12.29
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 14.87,
"eac_mpe_med": 0.32,
"finish_err_med": 7.64,
"finish_ape_med": 17.33,
"finish_mpe_med": 10.07
}
}
},
"timesfm_2.5": {
"family": "foundation",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.39,
"eac_mpe_med": -0.1,
"finish_err_med": 2.45,
"finish_ape_med": 27.2,
"finish_mpe_med": 11.03,
"coverage_med": 1.0
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.04,
"eac_mpe_med": -0.39,
"finish_err_med": 2.19,
"finish_ape_med": 24.15,
"finish_mpe_med": 11.6,
"coverage_med": 0.923
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.29,
"eac_mpe_med": -0.1,
"finish_err_med": 1.47,
"finish_ape_med": 18.3,
"finish_mpe_med": 4.93,
"coverage_med": 1.0
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.24,
"eac_mpe_med": 0.06,
"finish_err_med": 1.21,
"finish_ape_med": 14.44,
"finish_mpe_med": -3.11,
"coverage_med": 1.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 2.99,
"eac_mpe_med": 0.14,
"finish_err_med": 0.59,
"finish_ape_med": 13.51,
"finish_mpe_med": 9.12,
"coverage_med": 0.667
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 2.52,
"eac_mpe_med": -0.1,
"finish_err_med": 2.79,
"finish_ape_med": 27.95,
"finish_mpe_med": 2.11,
"coverage_med": 1.0
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 4.29,
"eac_mpe_med": -2.55,
"finish_err_med": 6.65,
"finish_ape_med": 41.24,
"finish_mpe_med": 41.24,
"coverage_med": 0.909
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 22.45,
"eac_mpe_med": -3.93,
"finish_err_med": 12.45,
"finish_ape_med": 41.97,
"finish_mpe_med": 39.78,
"coverage_med": 0.921
}
}
},
"chronos_2": {
"family": "foundation",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.76,
"eac_mpe_med": -0.1,
"finish_err_med": 3.22,
"finish_ape_med": 33.9,
"finish_mpe_med": 10.09,
"coverage_med": 1.0
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.93,
"eac_mpe_med": -0.12,
"finish_err_med": 2.13,
"finish_ape_med": 22.38,
"finish_mpe_med": 7.26,
"coverage_med": 1.0
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.18,
"eac_mpe_med": -0.1,
"finish_err_med": 1.61,
"finish_ape_med": 18.51,
"finish_mpe_med": 7.03,
"coverage_med": 1.0
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.24,
"eac_mpe_med": -0.1,
"finish_err_med": 1.28,
"finish_ape_med": 13.55,
"finish_mpe_med": -0.18,
"coverage_med": 1.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 3.74,
"eac_mpe_med": 0.61,
"finish_err_med": 0.71,
"finish_ape_med": 15.43,
"finish_mpe_med": 8.55,
"coverage_med": 1.0
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 2.93,
"eac_mpe_med": -0.18,
"finish_err_med": 2.35,
"finish_ape_med": 20.41,
"finish_mpe_med": -2.33,
"coverage_med": 1.0
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 3.52,
"eac_mpe_med": -1.17,
"finish_err_med": 5.43,
"finish_ape_med": 38.5,
"finish_mpe_med": 32.68,
"coverage_med": 1.0
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 14.55,
"eac_mpe_med": -0.51,
"finish_err_med": 19.78,
"finish_ape_med": 46.02,
"finish_mpe_med": 22.7,
"coverage_med": 0.98
}
}
},
"chronos_2_cov": {
"family": "foundation",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 5.34,
"eac_mpe_med": -0.22,
"finish_err_med": 3.05,
"finish_ape_med": 33.9,
"finish_mpe_med": 10.7,
"coverage_med": 1.0
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.43,
"eac_mpe_med": -0.1,
"finish_err_med": 2.29,
"finish_ape_med": 22.11,
"finish_mpe_med": 9.01,
"coverage_med": 1.0
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.82,
"eac_mpe_med": -0.26,
"finish_err_med": 1.4,
"finish_ape_med": 18.53,
"finish_mpe_med": 7.16,
"coverage_med": 1.0
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.08,
"eac_mpe_med": -0.1,
"finish_err_med": 1.26,
"finish_ape_med": 14.64,
"finish_mpe_med": 0.17,
"coverage_med": 1.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 4.04,
"eac_mpe_med": 0.63,
"finish_err_med": 0.66,
"finish_ape_med": 13.57,
"finish_mpe_med": 8.97,
"coverage_med": 1.0
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 4.03,
"eac_mpe_med": -0.1,
"finish_err_med": 2.32,
"finish_ape_med": 24.07,
"finish_mpe_med": -0.08,
"coverage_med": 1.0
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 5.26,
"eac_mpe_med": -1.72,
"finish_err_med": 5.58,
"finish_ape_med": 39.06,
"finish_mpe_med": 37.9,
"coverage_med": 1.0
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 13.75,
"eac_mpe_med": -1.18,
"finish_err_med": 9.18,
"finish_ape_med": 31.2,
"finish_mpe_med": 21.12,
"coverage_med": 1.0
}
}
},
"naive_dist": {
"family": "control",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.32,
"eac_mpe_med": 0.05,
"finish_err_med": 0.71,
"finish_ape_med": 14.29,
"finish_mpe_med": 5.49
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.32,
"eac_mpe_med": 0.05,
"finish_err_med": 0.71,
"finish_ape_med": 14.29,
"finish_mpe_med": 5.49
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.32,
"eac_mpe_med": 0.05,
"finish_err_med": 0.71,
"finish_ape_med": 14.29,
"finish_mpe_med": 5.49
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.32,
"eac_mpe_med": 0.05,
"finish_err_med": 0.71,
"finish_ape_med": 14.29,
"finish_mpe_med": 5.49
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 2.53,
"eac_mpe_med": -0.53,
"finish_err_med": 0.57,
"finish_ape_med": 14.29,
"finish_mpe_med": 14.29
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 5.18,
"eac_mpe_med": 1.32,
"finish_err_med": 0.86,
"finish_ape_med": 8.57,
"finish_mpe_med": 1.59
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 3.6,
"eac_mpe_med": -0.77,
"finish_err_med": 1.43,
"finish_ape_med": 7.94,
"finish_mpe_med": 5.49
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 3.97,
"eac_mpe_med": -3.97,
"finish_err_med": 3.93,
"finish_ape_med": 12.9,
"finish_mpe_med": -2.71
}
}
},
"ml_ridge": {
"family": "ml",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 0.9906542056074766,
"eac_ape_med": 4.39,
"eac_mpe_med": 1.61,
"finish_err_med": 0.98,
"finish_ape_med": 12.31,
"finish_mpe_med": 8.94
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.67,
"eac_mpe_med": 0.97,
"finish_err_med": 1.12,
"finish_ape_med": 11.15,
"finish_mpe_med": 9.1
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.42,
"eac_mpe_med": 1.08,
"finish_err_med": 0.52,
"finish_ape_med": 5.3,
"finish_mpe_med": 2.91
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.02,
"eac_mpe_med": 1.17,
"finish_err_med": 0.3,
"finish_ape_med": 3.8,
"finish_mpe_med": 3.37
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 2.74,
"eac_mpe_med": 1.34,
"finish_err_med": 1.12,
"finish_ape_med": 27.73,
"finish_mpe_med": 27.73
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 5.09,
"eac_mpe_med": 1.63,
"finish_err_med": 0.46,
"finish_ape_med": 4.34,
"finish_mpe_med": -2.51
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 4.32,
"eac_mpe_med": -0.88,
"finish_err_med": 1.47,
"finish_ape_med": 7.98,
"finish_mpe_med": 2.97
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 7.02,
"eac_mpe_med": 1.05,
"finish_err_med": 3.79,
"finish_ape_med": 8.97,
"finish_mpe_med": 3.18
}
}
},
"ml_svr": {
"family": "ml",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 5.05,
"eac_mpe_med": 2.0,
"finish_err_med": 1.3,
"finish_ape_med": 16.21,
"finish_mpe_med": 13.89
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.61,
"eac_mpe_med": 1.0,
"finish_err_med": 1.25,
"finish_ape_med": 14.04,
"finish_mpe_med": 9.1
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.45,
"eac_mpe_med": 0.7,
"finish_err_med": 0.93,
"finish_ape_med": 8.66,
"finish_mpe_med": 6.01
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.27,
"eac_mpe_med": 0.58,
"finish_err_med": 0.89,
"finish_ape_med": 9.89,
"finish_mpe_med": 8.61
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 2.23,
"eac_mpe_med": 1.66,
"finish_err_med": 1.23,
"finish_ape_med": 30.61,
"finish_mpe_med": 25.3
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 4.17,
"eac_mpe_med": 1.33,
"finish_err_med": 0.91,
"finish_ape_med": 9.08,
"finish_mpe_med": 1.15
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 4.16,
"eac_mpe_med": -0.21,
"finish_err_med": 1.28,
"finish_ape_med": 6.38,
"finish_mpe_med": -1.4
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 8.58,
"eac_mpe_med": 2.05,
"finish_err_med": 1.5,
"finish_ape_med": 4.06,
"finish_mpe_med": 2.06
}
}
},
"ml_rf": {
"family": "ml",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.84,
"eac_mpe_med": 0.57,
"finish_err_med": 0.97,
"finish_ape_med": 10.99,
"finish_mpe_med": 8.23
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.26,
"eac_mpe_med": -0.03,
"finish_err_med": 0.83,
"finish_ape_med": 6.09,
"finish_mpe_med": 3.78
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.53,
"eac_mpe_med": -0.08,
"finish_err_med": 0.36,
"finish_ape_med": 3.61,
"finish_mpe_med": 2.47
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.49,
"eac_mpe_med": 0.05,
"finish_err_med": 0.03,
"finish_ape_med": 0.24,
"finish_mpe_med": 0.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 1.64,
"eac_mpe_med": 0.4,
"finish_err_med": 0.89,
"finish_ape_med": 21.06,
"finish_mpe_med": 21.06
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 3.8,
"eac_mpe_med": 0.98,
"finish_err_med": 0.37,
"finish_ape_med": 3.69,
"finish_mpe_med": 0.0
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 2.6,
"eac_mpe_med": -0.55,
"finish_err_med": 0.73,
"finish_ape_med": 4.29,
"finish_mpe_med": 0.46
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 6.29,
"eac_mpe_med": -0.19,
"finish_err_med": 0.89,
"finish_ape_med": 2.83,
"finish_mpe_med": -1.19
}
}
},
"ml_histgbm": {
"family": "ml",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.7,
"eac_mpe_med": 0.47,
"finish_err_med": 0.98,
"finish_ape_med": 11.14,
"finish_mpe_med": 8.13
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.9,
"eac_mpe_med": 0.02,
"finish_err_med": 0.94,
"finish_ape_med": 6.96,
"finish_mpe_med": 5.13
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.81,
"eac_mpe_med": -0.02,
"finish_err_med": 0.35,
"finish_ape_med": 3.7,
"finish_mpe_med": 2.3
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.19,
"eac_mpe_med": 0.17,
"finish_err_med": 0.13,
"finish_ape_med": 1.67,
"finish_mpe_med": 0.88
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 1.72,
"eac_mpe_med": 0.63,
"finish_err_med": 0.99,
"finish_ape_med": 24.18,
"finish_mpe_med": 23.59
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 3.0,
"eac_mpe_med": 0.46,
"finish_err_med": 0.29,
"finish_ape_med": 4.2,
"finish_mpe_med": -0.02
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 2.9,
"eac_mpe_med": -1.15,
"finish_err_med": 0.84,
"finish_ape_med": 5.3,
"finish_mpe_med": 1.51
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 7.0,
"eac_mpe_med": 0.66,
"finish_err_med": 1.22,
"finish_ape_med": 3.26,
"finish_mpe_med": -1.6
}
}
},
"ml_xgboost": {
"family": "ml",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.6,
"eac_mpe_med": 0.26,
"finish_err_med": 0.98,
"finish_ape_med": 9.83,
"finish_mpe_med": 6.91
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.31,
"eac_mpe_med": 0.19,
"finish_err_med": 0.93,
"finish_ape_med": 7.67,
"finish_mpe_med": 5.53
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.69,
"eac_mpe_med": -0.21,
"finish_err_med": 0.45,
"finish_ape_med": 3.87,
"finish_mpe_med": 2.92
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.38,
"eac_mpe_med": 0.16,
"finish_err_med": 0.2,
"finish_ape_med": 2.65,
"finish_mpe_med": 1.67
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 1.63,
"eac_mpe_med": 0.53,
"finish_err_med": 0.97,
"finish_ape_med": 23.64,
"finish_mpe_med": 23.63
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 4.05,
"eac_mpe_med": 0.43,
"finish_err_med": 0.41,
"finish_ape_med": 4.13,
"finish_mpe_med": 1.3
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 3.04,
"eac_mpe_med": -1.05,
"finish_err_med": 0.82,
"finish_ape_med": 4.04,
"finish_mpe_med": 0.43
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 9.22,
"eac_mpe_med": -0.07,
"finish_err_med": 0.94,
"finish_ape_med": 2.71,
"finish_mpe_med": -1.04
}
}
},
"ml_lightgbm": {
"family": "ml",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.38,
"eac_mpe_med": 0.55,
"finish_err_med": 0.99,
"finish_ape_med": 10.34,
"finish_mpe_med": 8.41
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.92,
"eac_mpe_med": 0.2,
"finish_err_med": 0.92,
"finish_ape_med": 6.41,
"finish_mpe_med": 3.98
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.9,
"eac_mpe_med": -0.1,
"finish_err_med": 0.4,
"finish_ape_med": 3.87,
"finish_mpe_med": 2.36
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.19,
"eac_mpe_med": 0.16,
"finish_err_med": 0.16,
"finish_ape_med": 1.68,
"finish_mpe_med": 1.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 2.16,
"eac_mpe_med": 0.46,
"finish_err_med": 0.98,
"finish_ape_med": 23.92,
"finish_mpe_med": 23.38
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 4.05,
"eac_mpe_med": 0.44,
"finish_err_med": 0.23,
"finish_ape_med": 2.92,
"finish_mpe_med": 0.53
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 2.84,
"eac_mpe_med": -0.9,
"finish_err_med": 0.66,
"finish_ape_med": 3.82,
"finish_mpe_med": 0.74
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 6.42,
"eac_mpe_med": 0.07,
"finish_err_med": 1.34,
"finish_ape_med": 3.15,
"finish_mpe_med": 0.18
}
}
},
"ml_catboost": {
"family": "ml",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.63,
"eac_mpe_med": 0.82,
"finish_err_med": 0.97,
"finish_ape_med": 10.03,
"finish_mpe_med": 6.64
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.07,
"eac_mpe_med": 0.6,
"finish_err_med": 0.91,
"finish_ape_med": 7.39,
"finish_mpe_med": 4.34
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.0,
"eac_mpe_med": -0.09,
"finish_err_med": 0.41,
"finish_ape_med": 4.1,
"finish_mpe_med": 2.86
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.37,
"eac_mpe_med": -0.0,
"finish_err_med": 0.18,
"finish_ape_med": 2.1,
"finish_mpe_med": 1.57
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 1.92,
"eac_mpe_med": 0.88,
"finish_err_med": 0.95,
"finish_ape_med": 23.27,
"finish_mpe_med": 23.22
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 3.94,
"eac_mpe_med": 0.6,
"finish_err_med": 0.29,
"finish_ape_med": 3.21,
"finish_mpe_med": 0.77
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 2.85,
"eac_mpe_med": -0.24,
"finish_err_med": 0.61,
"finish_ape_med": 4.25,
"finish_mpe_med": -0.38
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 9.53,
"eac_mpe_med": 0.97,
"finish_err_med": 1.31,
"finish_ape_med": 3.22,
"finish_mpe_med": -2.04
}
}
},
"ml_mlp": {
"family": "ml",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 0.9906542056074766,
"eac_ape_med": 5.8,
"eac_mpe_med": 2.35,
"finish_err_med": 1.31,
"finish_ape_med": 13.59,
"finish_mpe_med": 11.09
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 5.85,
"eac_mpe_med": 2.65,
"finish_err_med": 1.04,
"finish_ape_med": 12.16,
"finish_mpe_med": 8.06
},
"0.60": {
"n": 107,
"valid_rate": 0.9906542056074766,
"eac_ape_med": 3.89,
"eac_mpe_med": 1.09,
"finish_err_med": 0.69,
"finish_ape_med": 8.32,
"finish_mpe_med": 5.21
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.49,
"eac_mpe_med": 1.69,
"finish_err_med": 0.81,
"finish_ape_med": 7.67,
"finish_mpe_med": 7.31
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 5.85,
"eac_mpe_med": 3.88,
"finish_err_med": 1.07,
"finish_ape_med": 26.08,
"finish_mpe_med": 26.08
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 5.65,
"eac_mpe_med": 4.21,
"finish_err_med": 0.7,
"finish_ape_med": 7.4,
"finish_mpe_med": 3.23
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 5.97,
"eac_mpe_med": -0.77,
"finish_err_med": 1.05,
"finish_ape_med": 5.55,
"finish_mpe_med": 1.46
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 8.93,
"eac_mpe_med": 0.02,
"finish_err_med": 1.5,
"finish_ape_med": 4.24,
"finish_mpe_med": -2.72
}
}
},
"ml_tabpfn": {
"family": "ml",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.73,
"eac_mpe_med": 0.6,
"finish_err_med": 0.97,
"finish_ape_med": 8.28,
"finish_mpe_med": 5.88
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.0,
"eac_mpe_med": 0.07,
"finish_err_med": 0.93,
"finish_ape_med": 5.77,
"finish_mpe_med": 3.55
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.77,
"eac_mpe_med": 0.07,
"finish_err_med": 0.41,
"finish_ape_med": 2.43,
"finish_mpe_med": 0.57
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.54,
"eac_mpe_med": 0.02,
"finish_err_med": 0.04,
"finish_ape_med": 0.19,
"finish_mpe_med": 0.01
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 1.68,
"eac_mpe_med": 0.17,
"finish_err_med": 0.98,
"finish_ape_med": 24.2,
"finish_mpe_med": 24.2
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 3.86,
"eac_mpe_med": 0.4,
"finish_err_med": 0.46,
"finish_ape_med": 4.6,
"finish_mpe_med": -0.01
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 3.48,
"eac_mpe_med": -0.39,
"finish_err_med": 0.72,
"finish_ape_med": 4.62,
"finish_mpe_med": 0.17
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 6.75,
"eac_mpe_med": 0.52,
"finish_err_med": 0.89,
"finish_ape_med": 2.98,
"finish_mpe_med": -1.0
}
}
},
"ml_lightgbm_quantile": {
"family": "ml",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.99,
"eac_mpe_med": 0.39,
"finish_err_med": 1.0,
"finish_ape_med": 9.15,
"finish_mpe_med": 4.78,
"coverage_med": 0.411,
"finish_cov_med": 0.299
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.6,
"eac_mpe_med": 0.38,
"finish_err_med": 0.98,
"finish_ape_med": 7.14,
"finish_mpe_med": 1.91,
"coverage_med": 0.374,
"finish_cov_med": 0.336
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.61,
"eac_mpe_med": -0.14,
"finish_err_med": 0.58,
"finish_ape_med": 3.37,
"finish_mpe_med": 1.59,
"coverage_med": 0.439,
"finish_cov_med": 0.439
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.26,
"eac_mpe_med": 0.02,
"finish_err_med": 0.27,
"finish_ape_med": 1.68,
"finish_mpe_med": 0.75,
"coverage_med": 0.467,
"finish_cov_med": 0.327
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 1.94,
"eac_mpe_med": 0.38,
"finish_err_med": 0.99,
"finish_ape_med": 24.57,
"finish_mpe_med": 23.96,
"coverage_med": 0.372,
"finish_cov_med": 0.186
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 3.84,
"eac_mpe_med": 0.59,
"finish_err_med": 0.61,
"finish_ape_med": 7.14,
"finish_mpe_med": 0.18,
"coverage_med": 0.407,
"finish_cov_med": 0.556
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 2.49,
"eac_mpe_med": -0.07,
"finish_err_med": 0.68,
"finish_ape_med": 2.97,
"finish_mpe_med": 0.4,
"coverage_med": 0.4,
"finish_cov_med": 0.4
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 6.24,
"eac_mpe_med": 1.08,
"finish_err_med": 1.05,
"finish_ape_med": 2.97,
"finish_mpe_med": -2.1,
"coverage_med": 0.25,
"finish_cov_med": 0.25
}
}
},
"ml_xgboost_realcv": {
"family": "ml",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 4.2,
"eac_mpe_med": 0.37,
"finish_err_med": 0.79,
"finish_ape_med": 7.82,
"finish_mpe_med": 0.96
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.76,
"eac_mpe_med": -0.11,
"finish_err_med": 0.61,
"finish_ape_med": 5.8,
"finish_mpe_med": 0.67
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.66,
"eac_mpe_med": -0.32,
"finish_err_med": 0.39,
"finish_ape_med": 4.49,
"finish_mpe_med": 0.33
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.22,
"eac_mpe_med": 0.09,
"finish_err_med": 0.23,
"finish_ape_med": 2.81,
"finish_mpe_med": 0.04
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 2.33,
"eac_mpe_med": -0.16,
"finish_err_med": 0.3,
"finish_ape_med": 6.58,
"finish_mpe_med": 1.22
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 6.38,
"eac_mpe_med": -0.7,
"finish_err_med": 0.42,
"finish_ape_med": 5.21,
"finish_mpe_med": -2.02
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 5.4,
"eac_mpe_med": 0.78,
"finish_err_med": 0.85,
"finish_ape_med": 4.89,
"finish_mpe_med": 3.58
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 7.88,
"eac_mpe_med": -3.33,
"finish_err_med": 3.47,
"finish_ape_med": 9.13,
"finish_mpe_med": -3.73
}
}
},
"ml_tabpfn_realcv": {
"family": "ml",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.72,
"eac_mpe_med": 0.06,
"finish_err_med": 0.66,
"finish_ape_med": 6.25,
"finish_mpe_med": 1.01
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 2.82,
"eac_mpe_med": 0.24,
"finish_err_med": 0.58,
"finish_ape_med": 4.54,
"finish_mpe_med": 0.64
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.68,
"eac_mpe_med": -0.03,
"finish_err_med": 0.24,
"finish_ape_med": 1.95,
"finish_mpe_med": 0.39
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 1.4,
"eac_mpe_med": -0.04,
"finish_err_med": 0.15,
"finish_ape_med": 1.1,
"finish_mpe_med": 0.05
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 1.4,
"eac_mpe_med": -0.27,
"finish_err_med": 0.25,
"finish_ape_med": 5.82,
"finish_mpe_med": 1.06
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 5.06,
"eac_mpe_med": 0.87,
"finish_err_med": 0.59,
"finish_ape_med": 5.53,
"finish_mpe_med": -0.51
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 4.33,
"eac_mpe_med": 1.42,
"finish_err_med": 0.64,
"finish_ape_med": 4.32,
"finish_mpe_med": 1.93
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 4.65,
"eac_mpe_med": -1.59,
"finish_err_med": 1.25,
"finish_ape_med": 3.31,
"finish_mpe_med": -0.63
}
}
},
"naive_dist_realcv": {
"family": "control",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.55,
"eac_mpe_med": -0.13,
"finish_err_med": 0.71,
"finish_ape_med": 10.0,
"finish_mpe_med": -1.0
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.55,
"eac_mpe_med": -0.13,
"finish_err_med": 0.71,
"finish_ape_med": 10.0,
"finish_mpe_med": -1.0
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.55,
"eac_mpe_med": -0.13,
"finish_err_med": 0.71,
"finish_ape_med": 10.0,
"finish_mpe_med": -1.0
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"eac_ape_med": 3.55,
"eac_mpe_med": -0.13,
"finish_err_med": 0.71,
"finish_ape_med": 10.0,
"finish_mpe_med": -1.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"eac_ape_med": 2.74,
"eac_mpe_med": -0.13,
"finish_err_med": 0.44,
"finish_ape_med": 10.0,
"finish_mpe_med": 6.79
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"eac_ape_med": 5.0,
"eac_mpe_med": 1.46,
"finish_err_med": 0.71,
"finish_ape_med": 7.79,
"finish_mpe_med": -4.18
},
"long": {
"n": 25,
"valid_rate": 1.0,
"eac_ape_med": 3.91,
"eac_mpe_med": -1.22,
"finish_err_med": 1.25,
"finish_ape_med": 7.93,
"finish_mpe_med": -2.26
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"eac_ape_med": 4.02,
"eac_mpe_med": -4.02,
"finish_err_med": 4.0,
"finish_ape_med": 10.81,
"finish_mpe_med": -8.65
}
}
},
"agent_deepseek_v4_flash": {
"family": "agent",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 3,
"cost_total": 0.0,
"tokens_total": 1685971,
"eac_ape_med": 3.15,
"eac_mpe_med": 0.0,
"finish_err_med": 0.67,
"finish_mpe_med": 0.0
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 4.0,
"err_total": 7,
"cost_total": 0.0,
"tokens_total": 1848021,
"eac_ape_med": 2.4,
"eac_mpe_med": 0.0,
"finish_err_med": 0.6,
"finish_mpe_med": 0.0
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 4.0,
"err_total": 5,
"cost_total": 0.0,
"tokens_total": 1974062,
"eac_ape_med": 1.61,
"eac_mpe_med": -0.0,
"finish_err_med": 0.35,
"finish_mpe_med": 0.0
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 4.0,
"err_total": 7,
"cost_total": 0.0,
"tokens_total": 1978877,
"eac_ape_med": 1.26,
"eac_mpe_med": 0.0,
"finish_err_med": 0.4,
"finish_mpe_med": 0.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"turns_med": 4.0,
"err_total": 2,
"cost_total": 0.0,
"tokens_total": 646885,
"eac_ape_med": 1.54,
"eac_mpe_med": -0.0,
"finish_err_med": 0.35,
"finish_mpe_med": 0.0
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 2,
"cost_total": 0.0,
"tokens_total": 448128,
"eac_ape_med": 3.31,
"eac_mpe_med": 0.92,
"finish_err_med": 0.5,
"finish_mpe_med": 0.0
},
"long": {
"n": 25,
"valid_rate": 1.0,
"turns_med": 4.0,
"err_total": 3,
"cost_total": 0.0,
"tokens_total": 491823,
"eac_ape_med": 2.11,
"eac_mpe_med": 0.0,
"finish_err_med": 0.84,
"finish_mpe_med": 0.0
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"turns_med": 4.0,
"err_total": 0,
"cost_total": 0.0,
"tokens_total": 261185,
"eac_ape_med": 7.09,
"eac_mpe_med": 0.32,
"finish_err_med": 1.3,
"finish_mpe_med": -2.04
}
}
},
"student_MiniCPM5-1B_base": {
"family": "agent",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 0.009,
"turns_med": 6.0,
"err_total": 289,
"cost_total": 0.0,
"tokens_total": 1209134,
"eac_ape_med": 3.36,
"eac_mpe_med": -3.36,
"finish_err_med": 1797870.0,
"finish_mpe_med": 44946750.0
},
"0.40": {
"n": 107,
"valid_rate": 0.019,
"turns_med": 6.0,
"err_total": 167,
"cost_total": 0.0,
"tokens_total": 1228476,
"eac_ape_med": 50.54,
"eac_mpe_med": -50.54,
"finish_err_med": 1.27,
"finish_mpe_med": -14.11
},
"0.60": {
"n": 107,
"valid_rate": 0.009,
"turns_med": 6.0,
"err_total": 232,
"cost_total": 0.0,
"tokens_total": 1224221,
"eac_ape_med": 14.34,
"eac_mpe_med": 14.34,
"finish_err_med": 30.0,
"finish_mpe_med": -96.77
},
"0.75": {
"n": 107,
"valid_rate": 0.019,
"turns_med": 6.0,
"err_total": 316,
"cost_total": 0.0,
"tokens_total": 1186720,
"eac_ape_med": 1.25,
"eac_mpe_med": -0.48,
"finish_err_med": 32308.0,
"finish_mpe_med": 538440.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 0.0,
"turns_med": 6.0,
"err_total": 75,
"cost_total": 0.0,
"tokens_total": 505928
},
"medium": {
"n": 27,
"valid_rate": 0.037,
"turns_med": 6.0,
"err_total": 64,
"cost_total": 0.0,
"tokens_total": 278177,
"eac_ape_med": 100.0,
"eac_mpe_med": -100.0,
"finish_err_med": 2.54,
"finish_mpe_med": -28.22
},
"long": {
"n": 25,
"valid_rate": 0.04,
"turns_med": 6.0,
"err_total": 16,
"cost_total": 0.0,
"tokens_total": 296800,
"eac_ape_med": 1.08,
"eac_mpe_med": -1.08,
"finish_err_med": 0.0,
"finish_mpe_med": 0.0
},
"very_long": {
"n": 12,
"valid_rate": 0.0,
"turns_med": 6.0,
"err_total": 12,
"cost_total": 0.0,
"tokens_total": 147571
}
}
},
"student_MiniCPM5-1B_sft": {
"family": "agent",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 0.991,
"turns_med": 3.0,
"err_total": 66,
"cost_total": 0.0,
"tokens_total": 346514,
"eac_ape_med": 3.28,
"eac_mpe_med": -0.05,
"finish_err_med": 0.96,
"finish_mpe_med": 0.0
},
"0.40": {
"n": 107,
"valid_rate": 0.991,
"turns_med": 3.0,
"err_total": 93,
"cost_total": 0.0,
"tokens_total": 411124,
"eac_ape_med": 2.69,
"eac_mpe_med": 0.0,
"finish_err_med": 0.76,
"finish_mpe_med": 0.0
},
"0.60": {
"n": 107,
"valid_rate": 0.991,
"turns_med": 3.0,
"err_total": 98,
"cost_total": 0.0,
"tokens_total": 462523,
"eac_ape_med": 1.92,
"eac_mpe_med": -0.0,
"finish_err_med": 0.44,
"finish_mpe_med": 0.0
},
"0.75": {
"n": 107,
"valid_rate": 0.981,
"turns_med": 3.0,
"err_total": 136,
"cost_total": 0.0,
"tokens_total": 548791,
"eac_ape_med": 1.28,
"eac_mpe_med": 0.04,
"finish_err_med": 0.39,
"finish_mpe_med": 0.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 0.977,
"turns_med": 3.0,
"err_total": 37,
"cost_total": 0.0,
"tokens_total": 174178,
"eac_ape_med": 1.58,
"eac_mpe_med": 0.02,
"finish_err_med": 0.34,
"finish_mpe_med": 0.0
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"turns_med": 4.0,
"err_total": 28,
"cost_total": 0.0,
"tokens_total": 91391,
"eac_ape_med": 3.41,
"eac_mpe_med": 0.0,
"finish_err_med": 0.77,
"finish_mpe_med": 0.0
},
"long": {
"n": 25,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 20,
"cost_total": 0.0,
"tokens_total": 94454,
"eac_ape_med": 2.24,
"eac_mpe_med": -0.1,
"finish_err_med": 1.0,
"finish_mpe_med": -0.42
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"turns_med": 4.0,
"err_total": 8,
"cost_total": 0.0,
"tokens_total": 51101,
"eac_ape_med": 6.84,
"eac_mpe_med": 0.32,
"finish_err_med": 1.63,
"finish_mpe_med": -0.15
}
}
},
"student_Nemotron-4B_base": {
"family": "agent",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 0.991,
"turns_med": 10.0,
"err_total": 123,
"cost_total": 0.0,
"tokens_total": 235039,
"eac_ape_med": 3.32,
"eac_mpe_med": 0.0,
"finish_err_med": 1.14,
"finish_mpe_med": 0.0
},
"0.40": {
"n": 107,
"valid_rate": 0.972,
"turns_med": 9.0,
"err_total": 126,
"cost_total": 0.0,
"tokens_total": 240451,
"eac_ape_med": 2.69,
"eac_mpe_med": 0.02,
"finish_err_med": 1.0,
"finish_mpe_med": 0.05
},
"0.60": {
"n": 107,
"valid_rate": 0.953,
"turns_med": 10.0,
"err_total": 142,
"cost_total": 0.0,
"tokens_total": 368215,
"eac_ape_med": 1.84,
"eac_mpe_med": -0.0,
"finish_err_med": 0.51,
"finish_mpe_med": 0.0
},
"0.75": {
"n": 107,
"valid_rate": 0.972,
"turns_med": 10.0,
"err_total": 119,
"cost_total": 0.0,
"tokens_total": 268546,
"eac_ape_med": 1.47,
"eac_mpe_med": 0.0,
"finish_err_med": 0.47,
"finish_mpe_med": 0.15
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"turns_med": 9.0,
"err_total": 50,
"cost_total": 0.0,
"tokens_total": 106166,
"eac_ape_med": 1.34,
"eac_mpe_med": 0.69,
"finish_err_med": 1.0,
"finish_mpe_med": 5.49
},
"medium": {
"n": 27,
"valid_rate": 0.963,
"turns_med": 9.0,
"err_total": 35,
"cost_total": 0.0,
"tokens_total": 54595,
"eac_ape_med": 3.79,
"eac_mpe_med": 0.0,
"finish_err_med": 0.94,
"finish_mpe_med": 0.0
},
"long": {
"n": 25,
"valid_rate": 0.92,
"turns_med": 10.0,
"err_total": 26,
"cost_total": 0.0,
"tokens_total": 50844,
"eac_ape_med": 2.48,
"eac_mpe_med": -0.1,
"finish_err_med": 0.61,
"finish_mpe_med": -0.42
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"turns_med": 12.0,
"err_total": 15,
"cost_total": 0.0,
"tokens_total": 28846,
"eac_ape_med": 6.32,
"eac_mpe_med": 0.74,
"finish_err_med": 1.63,
"finish_mpe_med": -2.04
}
}
},
"student_Qwen3.5-4B_base": {
"family": "agent",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 0.981,
"turns_med": 3.0,
"err_total": 200,
"cost_total": 0.0,
"tokens_total": 396281,
"eac_ape_med": 3.41,
"eac_mpe_med": 0.0,
"finish_err_med": 0.92,
"finish_mpe_med": 0.0
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 134,
"cost_total": 0.0,
"tokens_total": 384125,
"eac_ape_med": 2.78,
"eac_mpe_med": 0.0,
"finish_err_med": 0.61,
"finish_mpe_med": 0.0
},
"0.60": {
"n": 107,
"valid_rate": 0.981,
"turns_med": 3.0,
"err_total": 155,
"cost_total": 0.0,
"tokens_total": 376693,
"eac_ape_med": 1.61,
"eac_mpe_med": 0.0,
"finish_err_med": 0.36,
"finish_mpe_med": 0.0
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 133,
"cost_total": 0.0,
"tokens_total": 381914,
"eac_ape_med": 1.31,
"eac_mpe_med": 0.0,
"finish_err_med": 0.39,
"finish_mpe_med": 0.23
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 39,
"cost_total": 0.0,
"tokens_total": 136558,
"eac_ape_med": 1.54,
"eac_mpe_med": -0.0,
"finish_err_med": 0.51,
"finish_mpe_med": 0.0
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"turns_med": 4.0,
"err_total": 46,
"cost_total": 0.0,
"tokens_total": 112634,
"eac_ape_med": 4.17,
"eac_mpe_med": 0.92,
"finish_err_med": 0.29,
"finish_mpe_med": 0.0
},
"long": {
"n": 25,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 33,
"cost_total": 0.0,
"tokens_total": 88064,
"eac_ape_med": 2.02,
"eac_mpe_med": -0.1,
"finish_err_med": 0.9,
"finish_mpe_med": 0.0
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"turns_med": 4.0,
"err_total": 16,
"cost_total": 0.0,
"tokens_total": 46869,
"eac_ape_med": 7.24,
"eac_mpe_med": 0.32,
"finish_err_med": 1.31,
"finish_mpe_med": -2.04
}
}
},
"student_gemma-4-E2B_base": {
"family": "agent",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 0.673,
"turns_med": 6.0,
"err_total": 991,
"cost_total": 0.0,
"tokens_total": 929091,
"eac_ape_med": 3.6,
"eac_mpe_med": 0.86,
"finish_err_med": 0.91,
"finish_mpe_med": 0.56
},
"0.40": {
"n": 107,
"valid_rate": 0.664,
"turns_med": 6.0,
"err_total": 986,
"cost_total": 0.0,
"tokens_total": 922957,
"eac_ape_med": 3.21,
"eac_mpe_med": -0.0,
"finish_err_med": 0.75,
"finish_mpe_med": 0.0
},
"0.60": {
"n": 107,
"valid_rate": 0.729,
"turns_med": 8.0,
"err_total": 919,
"cost_total": 0.0,
"tokens_total": 946829,
"eac_ape_med": 1.79,
"eac_mpe_med": -0.06,
"finish_err_med": 0.38,
"finish_mpe_med": 1.1
},
"0.75": {
"n": 107,
"valid_rate": 0.682,
"turns_med": 6.0,
"err_total": 949,
"cost_total": 0.0,
"tokens_total": 940851,
"eac_ape_med": 1.51,
"eac_mpe_med": 0.13,
"finish_err_med": 0.27,
"finish_mpe_med": 1.16
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 0.674,
"turns_med": 5.0,
"err_total": 376,
"cost_total": 0.0,
"tokens_total": 350372,
"eac_ape_med": 2.37,
"eac_mpe_med": 0.44,
"finish_err_med": 0.66,
"finish_mpe_med": 11.05
},
"medium": {
"n": 27,
"valid_rate": 0.667,
"turns_med": 7.0,
"err_total": 270,
"cost_total": 0.0,
"tokens_total": 232948,
"eac_ape_med": 4.17,
"eac_mpe_med": 0.11,
"finish_err_med": 0.23,
"finish_mpe_med": 0.0
},
"long": {
"n": 25,
"valid_rate": 0.72,
"turns_med": 5.0,
"err_total": 203,
"cost_total": 0.0,
"tokens_total": 200387,
"eac_ape_med": 2.96,
"eac_mpe_med": -0.2,
"finish_err_med": 0.71,
"finish_mpe_med": -0.67
},
"very_long": {
"n": 12,
"valid_rate": 0.5,
"turns_med": 23.5,
"err_total": 137,
"cost_total": 0.0,
"tokens_total": 139250,
"eac_ape_med": 23.22,
"eac_mpe_med": -9.25,
"finish_err_med": 2.18,
"finish_mpe_med": -2.9
}
}
},
"student_Qwen3.5-2B_base": {
"family": "agent",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 0.243,
"turns_med": 24.0,
"err_total": 1743,
"cost_total": 0.0,
"tokens_total": 1164878,
"eac_ape_med": 3.3,
"eac_mpe_med": 0.24,
"finish_err_med": 0.74,
"finish_mpe_med": 0.0
},
"0.40": {
"n": 107,
"valid_rate": 0.159,
"turns_med": 24.0,
"err_total": 1798,
"cost_total": 0.0,
"tokens_total": 1214780,
"eac_ape_med": 1.2,
"eac_mpe_med": 0.57,
"finish_err_med": 0.9,
"finish_mpe_med": 0.0
},
"0.60": {
"n": 107,
"valid_rate": 0.187,
"turns_med": 24.0,
"err_total": 1703,
"cost_total": 0.0,
"tokens_total": 1049668,
"eac_ape_med": 2.14,
"eac_mpe_med": 1.42,
"finish_err_med": 0.47,
"finish_mpe_med": 2.28
},
"0.75": {
"n": 107,
"valid_rate": 0.196,
"turns_med": 24.0,
"err_total": 1698,
"cost_total": 0.0,
"tokens_total": 1539312,
"eac_ape_med": 2.42,
"eac_mpe_med": 0.11,
"finish_err_med": 0.09,
"finish_mpe_med": 0.32
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 0.209,
"turns_med": 24.0,
"err_total": 704,
"cost_total": 0.0,
"tokens_total": 499581,
"eac_ape_med": 1.2,
"eac_mpe_med": 0.58,
"finish_err_med": 0.9,
"finish_mpe_med": 0.0
},
"medium": {
"n": 27,
"valid_rate": 0.185,
"turns_med": 24.0,
"err_total": 435,
"cost_total": 0.0,
"tokens_total": 422007,
"eac_ape_med": 4.17,
"eac_mpe_med": 0.92,
"finish_err_med": 0.77,
"finish_mpe_med": 3.86
},
"long": {
"n": 25,
"valid_rate": 0.12,
"turns_med": 24.0,
"err_total": 424,
"cost_total": 0.0,
"tokens_total": 203585,
"eac_ape_med": 0.57,
"eac_mpe_med": 0.34,
"finish_err_med": 3.39,
"finish_mpe_med": -19.96
},
"very_long": {
"n": 12,
"valid_rate": 0.0,
"turns_med": 24.0,
"err_total": 235,
"cost_total": 0.0,
"tokens_total": 89607
}
}
},
"student_Qwen3.5-4B_sft": {
"family": "agent",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 0.981,
"turns_med": 3.0,
"err_total": 143,
"cost_total": 0.0,
"tokens_total": 367727,
"eac_ape_med": 3.32,
"eac_mpe_med": 0.0,
"finish_err_med": 0.89,
"finish_mpe_med": 0.0
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 129,
"cost_total": 0.0,
"tokens_total": 361918,
"eac_ape_med": 2.91,
"eac_mpe_med": 0.0,
"finish_err_med": 0.55,
"finish_mpe_med": 0.0
},
"0.60": {
"n": 107,
"valid_rate": 0.991,
"turns_med": 3.0,
"err_total": 122,
"cost_total": 0.0,
"tokens_total": 398920,
"eac_ape_med": 1.84,
"eac_mpe_med": -0.0,
"finish_err_med": 0.39,
"finish_mpe_med": 0.13
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 131,
"cost_total": 0.0,
"tokens_total": 386452,
"eac_ape_med": 1.26,
"eac_mpe_med": -0.0,
"finish_err_med": 0.32,
"finish_mpe_med": 0.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 49,
"cost_total": 0.0,
"tokens_total": 133298,
"eac_ape_med": 1.54,
"eac_mpe_med": -0.0,
"finish_err_med": 0.35,
"finish_mpe_med": 0.0
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"turns_med": 4.0,
"err_total": 48,
"cost_total": 0.0,
"tokens_total": 101768,
"eac_ape_med": 4.17,
"eac_mpe_med": 0.22,
"finish_err_med": 0.52,
"finish_mpe_med": 0.0
},
"long": {
"n": 25,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 26,
"cost_total": 0.0,
"tokens_total": 88527,
"eac_ape_med": 2.25,
"eac_mpe_med": -0.3,
"finish_err_med": 0.9,
"finish_mpe_med": -0.42
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"turns_med": 2.0,
"err_total": 6,
"cost_total": 0.0,
"tokens_total": 38325,
"eac_ape_med": 6.05,
"eac_mpe_med": 0.32,
"finish_err_med": 1.31,
"finish_mpe_med": -2.04
}
}
},
"student_gemma-4-E2B_sft": {
"family": "agent",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 29,
"cost_total": 0.0,
"tokens_total": 494640,
"eac_ape_med": 3.43,
"eac_mpe_med": 0.0,
"finish_err_med": 0.79,
"finish_mpe_med": 0.0
},
"0.40": {
"n": 107,
"valid_rate": 0.991,
"turns_med": 3.0,
"err_total": 31,
"cost_total": 0.0,
"tokens_total": 541123,
"eac_ape_med": 2.31,
"eac_mpe_med": -0.0,
"finish_err_med": 0.63,
"finish_mpe_med": 0.0
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 23,
"cost_total": 0.0,
"tokens_total": 548672,
"eac_ape_med": 1.76,
"eac_mpe_med": -0.0,
"finish_err_med": 0.38,
"finish_mpe_med": 0.0
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 37,
"cost_total": 0.0,
"tokens_total": 558859,
"eac_ape_med": 1.28,
"eac_mpe_med": 0.0,
"finish_err_med": 0.39,
"finish_mpe_med": 0.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 6,
"cost_total": 0.0,
"tokens_total": 202140,
"eac_ape_med": 1.54,
"eac_mpe_med": -0.0,
"finish_err_med": 0.35,
"finish_mpe_med": 0.0
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 11,
"cost_total": 0.0,
"tokens_total": 126962,
"eac_ape_med": 3.41,
"eac_mpe_med": 0.0,
"finish_err_med": 0.52,
"finish_mpe_med": 0.0
},
"long": {
"n": 25,
"valid_rate": 0.96,
"turns_med": 3.0,
"err_total": 3,
"cost_total": 0.0,
"tokens_total": 128406,
"eac_ape_med": 2.07,
"eac_mpe_med": -0.2,
"finish_err_med": 1.05,
"finish_mpe_med": -0.21
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 11,
"cost_total": 0.0,
"tokens_total": 83615,
"eac_ape_med": 6.84,
"eac_mpe_med": -1.43,
"finish_err_med": 1.63,
"finish_mpe_med": -2.04
}
}
},
"student_Qwen3.5-2B_sft": {
"family": "agent",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 0.271,
"turns_med": 24.0,
"err_total": 1653,
"cost_total": 0.0,
"tokens_total": 888476,
"eac_ape_med": 3.15,
"eac_mpe_med": 0.47,
"finish_err_med": 0.57,
"finish_mpe_med": 0.0
},
"0.40": {
"n": 107,
"valid_rate": 0.131,
"turns_med": 24.0,
"err_total": 1763,
"cost_total": 0.0,
"tokens_total": 1048427,
"eac_ape_med": 3.94,
"eac_mpe_med": 1.42,
"finish_err_med": 0.97,
"finish_mpe_med": 0.0
},
"0.60": {
"n": 107,
"valid_rate": 0.224,
"turns_med": 24.0,
"err_total": 1819,
"cost_total": 0.0,
"tokens_total": 1084626,
"eac_ape_med": 2.1,
"eac_mpe_med": 0.54,
"finish_err_med": 0.53,
"finish_mpe_med": -0.17
},
"0.75": {
"n": 107,
"valid_rate": 0.121,
"turns_med": 24.0,
"err_total": 1794,
"cost_total": 0.0,
"tokens_total": 1210331,
"eac_ape_med": 2.93,
"eac_mpe_med": 0.13,
"finish_err_med": 0.21,
"finish_mpe_med": 0.8
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 0.07,
"turns_med": 24.0,
"err_total": 787,
"cost_total": 0.0,
"tokens_total": 494830,
"eac_ape_med": 1.96,
"eac_mpe_med": 0.88,
"finish_err_med": 0.98,
"finish_mpe_med": 0.0
},
"medium": {
"n": 27,
"valid_rate": 0.185,
"turns_med": 24.0,
"err_total": 418,
"cost_total": 0.0,
"tokens_total": 188645,
"eac_ape_med": 8.91,
"eac_mpe_med": 8.91,
"finish_err_med": 0.29,
"finish_mpe_med": 0.0
},
"long": {
"n": 25,
"valid_rate": 0.12,
"turns_med": 24.0,
"err_total": 383,
"cost_total": 0.0,
"tokens_total": 224868,
"eac_ape_med": 2.59,
"eac_mpe_med": 2.48,
"finish_err_med": 0.96,
"finish_mpe_med": 1.96
},
"very_long": {
"n": 12,
"valid_rate": 0.25,
"turns_med": 24.0,
"err_total": 175,
"cost_total": 0.0,
"tokens_total": 140084,
"eac_ape_med": 16.16,
"eac_mpe_med": 0.83,
"finish_err_med": 2.8,
"finish_mpe_med": -2.6
}
}
},
"student_Nemotron-4B_sft": {
"family": "agent",
"stages": {
"0.25": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 35,
"cost_total": 0.0,
"tokens_total": 392676,
"eac_ape_med": 3.37,
"eac_mpe_med": 0.0,
"finish_err_med": 0.93,
"finish_mpe_med": 0.0
},
"0.40": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 50,
"cost_total": 0.0,
"tokens_total": 395269,
"eac_ape_med": 2.37,
"eac_mpe_med": 0.0,
"finish_err_med": 0.61,
"finish_mpe_med": 0.0
},
"0.60": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 30,
"cost_total": 0.0,
"tokens_total": 430285,
"eac_ape_med": 1.61,
"eac_mpe_med": 0.0,
"finish_err_med": 0.37,
"finish_mpe_med": 0.0
},
"0.75": {
"n": 107,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 41,
"cost_total": 0.0,
"tokens_total": 407593,
"eac_ape_med": 1.28,
"eac_mpe_med": 0.0,
"finish_err_med": 0.29,
"finish_mpe_med": 0.0
}
},
"by_strata": {
"short": {
"n": 43,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 10,
"cost_total": 0.0,
"tokens_total": 134419,
"eac_ape_med": 1.54,
"eac_mpe_med": -0.0,
"finish_err_med": 0.36,
"finish_mpe_med": 0.0
},
"medium": {
"n": 27,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 13,
"cost_total": 0.0,
"tokens_total": 101902,
"eac_ape_med": 3.41,
"eac_mpe_med": 0.0,
"finish_err_med": 0.77,
"finish_mpe_med": 0.0
},
"long": {
"n": 25,
"valid_rate": 1.0,
"turns_med": 3.0,
"err_total": 6,
"cost_total": 0.0,
"tokens_total": 97588,
"eac_ape_med": 2.02,
"eac_mpe_med": -0.1,
"finish_err_med": 0.88,
"finish_mpe_med": -0.43
},
"very_long": {
"n": 12,
"valid_rate": 1.0,
"turns_med": 4.0,
"err_total": 21,
"cost_total": 0.0,
"tokens_total": 61360,
"eac_ape_med": 7.23,
"eac_mpe_med": 0.45,
"finish_err_med": 1.63,
"finish_mpe_med": -2.04
}
}
}
}
}