armiger / calibration.json
spencernorton's picture
Publish Armiger v3.0.0 (Rule-3 Gold mit3): weights, calibration, cards and receipts-synced docs
25cbd40 verified
Raw History Blame Contribute Delete
5.04 kB
{
"temperature_scaling_stop_fit": {
"category": {
"temperature_T": 0.65,
"cal_temp_scaled": {
"n": 995,
"fitted_on": "snap_wave13_r5_20261021T115351Z_bfb9dfb67b41_val_guarded"
}
},
"lang": {
"temperature_T": 0.7,
"cal_temp_scaled": {
"n": 368,
"fitted_on": "snap_wave13_r5_20261021T115351Z_bfb9dfb67b41_val_guarded"
}
},
"owner_scope": {
"temperature_T": 0.55,
"cal_temp_scaled": {
"n": 995,
"fitted_on": "snap_wave13_r5_20261021T115351Z_bfb9dfb67b41_val_guarded"
}
},
"title_language": {
"temperature_T": 0.95,
"cal_temp_scaled": {
"n": 566,
"fitted_on": "snap_wave13_r5_20261021T115351Z_bfb9dfb67b41_val_guarded"
}
},
"english_subs": {
"temperature_T": 0.5,
"cal_temp_scaled": {
"n": 137,
"fitted_on": "snap_wave13_r5_20261021T115351Z_bfb9dfb67b41_val_guarded"
}
},
"anime": {
"temperature_T": 0.9,
"cal_temp_scaled": {
"n": 243,
"fitted_on": "snap_wave13_r5_20261021T115351Z_bfb9dfb67b41_val_guarded"
}
},
"adult": {
"temperature_T": 0.65,
"cal_temp_scaled": {
"n": 864,
"fitted_on": "snapshot_wave5a_val"
}
},
"junk": {
"temperature_T": 0.65,
"cal_temp_scaled": {
"n": 864,
"fitted_on": "snapshot_wave5a_val"
}
}
},
"menon_logit_adjustment_stop_fit": {
"D80000": {
"tau": 0.0
},
"D100000": {
"tau": 0.0
},
"E100000_TC_v3": {
"tau": 0.0
},
"E100000_TC_v4": {
"tau": 0.0
},
"G250000_Unified": {
"tau": 0.0
},
"G500000_Unified": {
"tau": 0.0
},
"H350000_Curated_Wave2": {
"tau": 0.0
},
"I350000_Distilled": {
"tau": 0.0
}
},
"mondrian_conformal_thresholds": {
"owner_scope": {
"alpha": 0.02,
"threshold_r5clean": 0.52486
}
},
"calibration_version": "v3.0-gold-mit3-final-guarded",
"temperature_audit": {
"category": {
"n": 995,
"nll_at_T1": 0.284156,
"nll_at_best_T": 0.250881,
"best_T_unclamped": 0.65,
"shipped_T_guarded": 0.65,
"ece5_at_T1_pct": 6.6104,
"ece5_guarded_pct": 2.1656,
"acc_pct": 91.4573
},
"lang": {
"n": 368,
"nll_at_T1": 0.308272,
"nll_at_best_T": 0.289053,
"best_T_unclamped": 0.7,
"shipped_T_guarded": 0.7,
"ece5_at_T1_pct": 6.9697,
"ece5_guarded_pct": 3.2334,
"acc_pct": 89.9457
},
"owner_scope": {
"n": 995,
"nll_at_T1": 0.042003,
"nll_at_best_T": 0.027084,
"best_T_unclamped": 0.55,
"shipped_T_guarded": 0.55,
"ece5_at_T1_pct": 2.1499,
"ece5_guarded_pct": 0.202,
"acc_pct": 98.995
},
"title_language": {
"n": 566,
"nll_at_T1": 0.137678,
"nll_at_best_T": 0.13748,
"best_T_unclamped": 0.95,
"shipped_T_guarded": 0.95,
"ece5_at_T1_pct": 1.0472,
"ece5_guarded_pct": 0.7014,
"acc_pct": 95.4064
},
"english_subs": {
"n": 137,
"nll_at_T1": 0.189409,
"nll_at_best_T": 0.132055,
"best_T_unclamped": 0.5,
"shipped_T_guarded": 0.5,
"ece5_at_T1_pct": 9.9213,
"ece5_guarded_pct": 2.5349,
"acc_pct": 96.3504
},
"anime": {
"n": 243,
"nll_at_T1": 0.391146,
"nll_at_best_T": 0.389958,
"best_T_unclamped": 0.9,
"shipped_T_guarded": 0.9,
"ece5_at_T1_pct": 3.8909,
"ece5_guarded_pct": 2.9506,
"acc_pct": 84.7737
},
"adult": {
"inherited": true,
"reason": "no Gold-val label support; retained wave5a fit"
},
"junk": {
"inherited": true,
"reason": "no Gold-val label support; retained wave5a fit"
}
},
"mondrian_thresholds": {
"adult": 0.5451,
"junk": 0.101,
"owner_scope": 0.477
},
"mondrian_audit": {
"owner_scope": {
"alpha": 0.02,
"n_neg": 256,
"n_pos": 739,
"val_fpr_at_thr": 0.015625,
"val_recall_at_thr": 0.994587,
"method": "split-conformal FPR quantile ceil((n+1)(1-alpha)) on val negatives, temperature-scaled probs"
}
},
"fitted_snapshot_id": "snap_wave13_r5_20261021T115351Z_bfb9dfb67b41",
"calibrated_onnx_fp32_sha256": "6459a20d7bf45d46d59efbcb50ffb8a519bacda14ae36403dcc510eceaa38f44",
"mondrian_fitted_calibration_split": {
"adult": 0.799935,
"junk": 0.259358,
"owner_scope": 0.944382,
"method": "split-conformal FPR quantile on packed calibration split (512), temperature-scaled; NOT shipped as gates (recall cost on confirmation) - see mondrian_refit_report"
},
"mondrian_provenance": "Inherited production gates retained for v3.0.0 (higher adult/owner recall on confirmation splits than calibration-fitted FPR gates; fitted alternates recorded for operators).",
"calibrated_onnx_int8_sha256": "a0dab886be6252739d4c89ce01d65d8d2135204beaec6b00159d038cf420f329"
}