AsianPlayer/TriDrive / benchmark /human_eval_299 /thresholds_frozen_v1.json
AsianPlayer's picture
download
raw
17.3 kB
{
"version": "v1",
"generated_utc": "2026-09-12T20:11:12Z",
"systems": {
"A": {
"runs": [
"W_I1_all_minus_road2drv_s0_final_merged",
"W_I1_all_minus_road2drv_s1_final_merged",
"W_I1_all_minus_road2drv_s2_final_merged"
],
"col": "W_learned_bothhgb_t15_w10_n979",
"rule": "mean over seeds"
},
"B": {
"run": "W_I1_all_minus_road2drv_s0_final_dwfc",
"col": "W_learned_curhgb_t15_w10_n979dwfc"
},
"C": {
"test": "/home/USER/cwm2/baselines/legacy_cockpitwm/results/marginals_<regime>_s0.npz -> compose.legacy_compose(pA, None, 15)['att_only']",
"val": "/home/USER/cwm2/baselines/legacy_cockpitwm/results/marginals_<regime>_val_s0.npz (score_val_marginals.py: frozen s0 chain checkpoints on the val pack) -> same compose"
}
},
"cooldown_s": 60.0,
"bisection": "operating_points.thr_for_rate (24 iterations) on alerts/h of train_warning_head.alerts_per_hour",
"points": {
"val10": [
"val",
10.0
],
"val20": [
"val",
20.0
],
"test10": [
"test",
10.0
],
"test20": [
"test",
20.0
]
},
"hours_test": {
"manual": 28.496333333333332,
"engaged": 25.102222222222224
},
"hours_val": {
"manual": 3.9072222222222224,
"engaged": 6.163777777777779
},
"thresholds": {
"A": {
"manual": {
"val10": {
"thr": 0.7779947716188786,
"target_alerts_per_hour": 10.0,
"fit_split": "val",
"reachable": true,
"floor_alerts_per_hour_fit": 0.2559363002985923,
"achieved_fit": 10.237452011943693,
"achieved_test": 4.316344792897332,
"achieved_val": 10.237452011943693,
"n_alerts_test": 123,
"n_alerts_val": 40,
"hours_test": 28.496333333333332,
"hours_val": 3.9072222222222224
},
"val20": {
"thr": 0.6757812696855249,
"target_alerts_per_hour": 20.0,
"fit_split": "val",
"reachable": true,
"floor_alerts_per_hour_fit": 0.2559363002985923,
"achieved_fit": 19.963031423290204,
"achieved_test": 9.40471873574378,
"achieved_val": 19.963031423290204,
"n_alerts_test": 268,
"n_alerts_val": 78,
"hours_test": 28.496333333333332,
"hours_val": 3.9072222222222224
},
"test10": {
"thr": 0.6661783776429763,
"target_alerts_per_hour": 10.0,
"fit_split": "test",
"reachable": true,
"floor_alerts_per_hour_fit": 0.03509223408859619,
"achieved_fit": 10.001286715249915,
"achieved_test": 10.001286715249915,
"achieved_val": 21.242712924783163,
"n_alerts_test": 285,
"n_alerts_val": 83,
"hours_test": 28.496333333333332,
"hours_val": 3.9072222222222224
},
"test20": {
"thr": 0.5337727990604886,
"target_alerts_per_hour": 20.0,
"fit_split": "test",
"reachable": true,
"floor_alerts_per_hour_fit": 0.03509223408859619,
"achieved_fit": 19.932388962322637,
"achieved_test": 19.932388962322637,
"achieved_val": 35.575145741504336,
"n_alerts_test": 568,
"n_alerts_val": 139,
"hours_test": 28.496333333333332,
"hours_val": 3.9072222222222224
},
"frame": {
"thr": 0.5337727990604886,
"rule": "min(thr_val20, thr_test20)",
"n_alerts_test": 568,
"achieved_test": 19.932388962322637,
"hours_test": 28.496333333333332
}
},
"engaged": {
"val10": {
"thr": 0.8142903619510188,
"target_alerts_per_hour": 10.0,
"fit_split": "val",
"reachable": true,
"floor_alerts_per_hour_fit": 0.1622381656271406,
"achieved_fit": 10.22100443450986,
"achieved_test": 6.533286118980169,
"achieved_val": 10.22100443450986,
"n_alerts_test": 164,
"n_alerts_val": 63,
"hours_test": 25.102222222222224,
"hours_val": 6.163777777777779
},
"val20": {
"thr": 0.7177734325808937,
"target_alerts_per_hour": 20.0,
"fit_split": "val",
"reachable": true,
"floor_alerts_per_hour_fit": 0.1622381656271406,
"achieved_fit": 20.117532537765438,
"achieved_test": 14.102337110481585,
"achieved_val": 20.117532537765438,
"n_alerts_test": 354,
"n_alerts_val": 124,
"hours_test": 25.102222222222224,
"hours_val": 6.163777777777779
},
"test10": {
"thr": 0.7592773478999344,
"target_alerts_per_hour": 10.0,
"fit_split": "test",
"reachable": true,
"floor_alerts_per_hour_fit": 0.0398371104815864,
"achieved_fit": 9.999114730878187,
"achieved_test": 9.999114730878187,
"achieved_val": 16.386054728341204,
"n_alerts_test": 251,
"n_alerts_val": 101,
"hours_test": 25.102222222222224,
"hours_val": 6.163777777777779
},
"test20": {
"thr": 0.6411132910617379,
"target_alerts_per_hour": 20.0,
"fit_split": "test",
"reachable": true,
"floor_alerts_per_hour_fit": 0.0398371104815864,
"achieved_fit": 19.998229461756374,
"achieved_test": 19.998229461756374,
"achieved_val": 27.580488156613907,
"n_alerts_test": 502,
"n_alerts_val": 170,
"hours_test": 25.102222222222224,
"hours_val": 6.163777777777779
},
"frame": {
"thr": 0.6411132910617379,
"rule": "min(thr_val20, thr_test20)",
"n_alerts_test": 502,
"achieved_test": 19.998229461756374,
"hours_test": 25.102222222222224
}
}
},
"B": {
"manual": {
"val10": {
"thr": 0.6235351405898655,
"target_alerts_per_hour": 10.0,
"fit_split": "val",
"reachable": true,
"floor_alerts_per_hour_fit": 0.2559363002985923,
"achieved_fit": 10.237452011943693,
"achieved_test": 3.825053515656985,
"achieved_val": 10.237452011943693,
"n_alerts_test": 109,
"n_alerts_val": 40,
"hours_test": 28.496333333333332,
"hours_val": 3.9072222222222224
},
"val20": {
"thr": 0.4931640862364475,
"target_alerts_per_hour": 20.0,
"fit_split": "val",
"reachable": true,
"floor_alerts_per_hour_fit": 0.2559363002985923,
"achieved_fit": 19.963031423290204,
"achieved_test": 13.685971294552516,
"achieved_val": 19.963031423290204,
"n_alerts_test": 390,
"n_alerts_val": 78,
"hours_test": 28.496333333333332,
"hours_val": 3.9072222222222224
},
"test10": {
"thr": 0.5327148377250523,
"target_alerts_per_hour": 10.0,
"fit_split": "test",
"reachable": true,
"floor_alerts_per_hour_fit": 0.03509223408859619,
"achieved_fit": 10.001286715249915,
"achieved_test": 10.001286715249915,
"achieved_val": 16.891795819707095,
"n_alerts_test": 285,
"n_alerts_val": 66,
"hours_test": 28.496333333333332,
"hours_val": 3.9072222222222224
},
"test20": {
"thr": 0.434814477969212,
"target_alerts_per_hour": 20.0,
"fit_split": "test",
"reachable": true,
"floor_alerts_per_hour_fit": 0.03509223408859619,
"achieved_fit": 19.967481196411235,
"achieved_test": 19.967481196411235,
"achieved_val": 26.105502630456417,
"n_alerts_test": 569,
"n_alerts_val": 102,
"hours_test": 28.496333333333332,
"hours_val": 3.9072222222222224
},
"frame": {
"thr": 0.434814477969212,
"rule": "min(thr_val20, thr_test20)",
"n_alerts_test": 569,
"achieved_test": 19.967481196411235,
"hours_test": 28.496333333333332
}
},
"engaged": {
"val10": {
"thr": 0.7558593759940777,
"target_alerts_per_hour": 10.0,
"fit_split": "val",
"reachable": true,
"floor_alerts_per_hour_fit": 0.1622381656271406,
"achieved_fit": 9.896528103255578,
"achieved_test": 2.98778328611898,
"achieved_val": 9.896528103255578,
"n_alerts_test": 75,
"n_alerts_val": 61,
"hours_test": 25.102222222222224,
"hours_val": 6.163777777777779
},
"val20": {
"thr": 0.6269531452517185,
"target_alerts_per_hour": 20.0,
"fit_split": "val",
"reachable": true,
"floor_alerts_per_hour_fit": 0.1622381656271406,
"achieved_fit": 19.955294372138297,
"achieved_test": 12.907223796033993,
"achieved_val": 19.955294372138297,
"n_alerts_test": 324,
"n_alerts_val": 123,
"hours_test": 25.102222222222224,
"hours_val": 6.163777777777779
},
"test10": {
"thr": 0.6591797029807367,
"target_alerts_per_hour": 10.0,
"fit_split": "test",
"reachable": true,
"floor_alerts_per_hour_fit": 0.0398371104815864,
"achieved_fit": 9.999114730878187,
"achieved_test": 9.999114730878187,
"achieved_val": 18.17067455023975,
"n_alerts_test": 251,
"n_alerts_val": 112,
"hours_test": 25.102222222222224,
"hours_val": 6.163777777777779
},
"test20": {
"thr": 0.5478515491297458,
"target_alerts_per_hour": 20.0,
"fit_split": "test",
"reachable": true,
"floor_alerts_per_hour_fit": 0.0398371104815864,
"achieved_fit": 20.03806657223796,
"achieved_test": 20.03806657223796,
"achieved_val": 26.28258283159678,
"n_alerts_test": 503,
"n_alerts_val": 162,
"hours_test": 25.102222222222224,
"hours_val": 6.163777777777779
},
"frame": {
"thr": 0.5478515491297458,
"rule": "min(thr_val20, thr_test20)",
"n_alerts_test": 503,
"achieved_test": 20.03806657223796,
"hours_test": 25.102222222222224
}
}
},
"C": {
"manual": {
"val10": {
"thr": 1.0,
"target_alerts_per_hour": 10.0,
"fit_split": "val",
"reachable": false,
"floor_alerts_per_hour_fit": 17.243666268735904,
"achieved_fit": 17.243666268735904,
"achieved_test": 15.096262185861951,
"achieved_val": 17.243666268735904,
"n_alerts_test": 428,
"n_alerts_val": 65,
"hours_test": 28.351388888888888,
"hours_val": 3.7695000000000003
},
"val20": {
"thr": 0.9999999283402339,
"target_alerts_per_hour": 20.0,
"fit_split": "val",
"reachable": true,
"floor_alerts_per_hour_fit": 17.243666268735904,
"achieved_fit": 20.42711234911792,
"achieved_test": 17.671091951207565,
"achieved_val": 20.42711234911792,
"n_alerts_test": 501,
"n_alerts_val": 77,
"hours_test": 28.351388888888888,
"hours_val": 3.7695000000000003
},
"test10": {
"thr": 1.0,
"target_alerts_per_hour": 10.0,
"fit_split": "test",
"reachable": false,
"floor_alerts_per_hour_fit": 15.096262185861951,
"achieved_fit": 15.096262185861951,
"achieved_test": 15.096262185861951,
"achieved_val": 17.243666268735904,
"n_alerts_test": 428,
"n_alerts_val": 65,
"hours_test": 28.351388888888888,
"hours_val": 3.7695000000000003
},
"test20": {
"thr": 0.9999997846683915,
"target_alerts_per_hour": 20.0,
"fit_split": "test",
"reachable": true,
"floor_alerts_per_hour_fit": 15.096262185861951,
"achieved_fit": 19.78739038847793,
"achieved_test": 19.78739038847793,
"achieved_val": 24.14113277623027,
"n_alerts_test": 561,
"n_alerts_val": 91,
"hours_test": 28.351388888888888,
"hours_val": 3.7695000000000003
},
"frame": {
"thr": 0.9999997846683915,
"rule": "min(thr_val20, thr_test20)",
"n_alerts_test": 561,
"achieved_test": 19.78739038847793,
"hours_test": 28.351388888888888
}
},
"engaged": {
"val10": {
"thr": 1.0,
"target_alerts_per_hour": 10.0,
"fit_split": "val",
"reachable": false,
"floor_alerts_per_hour_fit": 12.854734475976397,
"achieved_fit": 12.854734475976397,
"achieved_test": 15.66329536307096,
"achieved_val": 12.854734475976397,
"n_alerts_test": 387,
"n_alerts_val": 61,
"hours_test": 24.707444444444445,
"hours_val": 4.745333333333334
},
"val20": {
"thr": 0.9999968930776646,
"target_alerts_per_hour": 20.0,
"fit_split": "val",
"reachable": true,
"floor_alerts_per_hour_fit": 12.854734475976397,
"achieved_fit": 20.01966844619275,
"achieved_test": 24.810336066052965,
"achieved_val": 20.01966844619275,
"n_alerts_test": 613,
"n_alerts_val": 95,
"hours_test": 24.707444444444445,
"hours_val": 4.745333333333334
},
"test10": {
"thr": 1.0,
"target_alerts_per_hour": 10.0,
"fit_split": "test",
"reachable": false,
"floor_alerts_per_hour_fit": 15.66329536307096,
"achieved_fit": 15.66329536307096,
"achieved_test": 15.66329536307096,
"achieved_val": 12.854734475976397,
"n_alerts_test": 387,
"n_alerts_val": 61,
"hours_test": 24.707444444444445,
"hours_val": 4.745333333333334
},
"test20": {
"thr": 0.9999996899530572,
"target_alerts_per_hour": 20.0,
"fit_split": "test",
"reachable": true,
"floor_alerts_per_hour_fit": 15.66329536307096,
"achieved_fit": 20.19634208313284,
"achieved_test": 20.19634208313284,
"achieved_val": 16.0157347569542,
"n_alerts_test": 499,
"n_alerts_val": 76,
"hours_test": 24.707444444444445,
"hours_val": 4.745333333333334
},
"frame": {
"thr": 0.9999968930776646,
"rule": "min(thr_val20, thr_test20)",
"n_alerts_test": 613,
"achieved_test": 24.810336066052965,
"hours_test": 24.707444444444445
}
}
}
},
"frame_rule": "min(thr_val20, thr_test20)",
"not_reachable": [
"C/manual/val10",
"C/manual/test10",
"C/engaged/val10",
"C/engaged/test10"
],
"layout_sha256": {
"/home/USER/s12_wm/results/targets_manual_test.npz": "f15d98ac5724d4d06d729450db396d45e00c135c6feac412a2c79519ce61ef3a",
"/home/USER/s12_wm/results/targets_manual_val.npz": "343347136f97a41436e7ff8a1dd15e86c90e04671b3dd8023888a5508d25f4ae",
"/home/USER/s12_wm/results/targets_engaged_test.npz": "ee5824c8ddd0db24964873ea0d6efe1d106d4390ff71b2328d112b6684368107",
"/home/USER/s12_wm/results/targets_engaged_val.npz": "371a22bbee81282bc20c854e34756d0f041bf9be70878c4cefdb29b0d3736ed2",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s0_final_merged/pred_layout_manual_test.npz": "673da3cb505b7512abe528714ec814913749c1d0e36b50f665c669b6cb686f31",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s1_final_merged/pred_layout_manual_test.npz": "04208cdd39db7de743ee2bb772c25153e04fe026ae03543637ce1d1eb144f602",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s2_final_merged/pred_layout_manual_test.npz": "73a73401002728a9d9fe6e39c28911727ebfd233c8ff0976c758a0b6754b8ad1",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s0_final_dwfc/pred_layout_manual_test.npz": "b3b3df8e9826537b0d81dedd8fdf400ea7a51cdeeb75dde33ddd32ee68f23994",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s0_final_merged/pred_layout_manual_val.npz": "0b1c518b7b4de2b1451c5078239fa0f47420096ebc01c22aef521d5c4951a8be",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s1_final_merged/pred_layout_manual_val.npz": "51d71e8fdb189080bf8ac40d446203b2fc0c5259377eb1349bf1793b6391736e",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s2_final_merged/pred_layout_manual_val.npz": "796f2932a6ee35f34c92ec8d3787440fd827ddbb115055546ecc5edb415086f1",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s0_final_dwfc/pred_layout_manual_val.npz": "3d1f445fa497174412314b0c9921857588f29f21d3ca990ad01264608caf5ac1",
"/home/USER/cwm2/baselines/legacy_cockpitwm/results/marginals_manual_s0.npz": "400f452c70368fe12d7aa8e99db0e5928c5f44b44f4f2e3e3b47b663ec825472",
"/home/USER/cwm2/baselines/legacy_cockpitwm/results/marginals_manual_val_s0.npz": "a9c2747e12b3aa6c1f97ece7ac9228048b90c7e879cca0667524e78c449fd647",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s0_final_merged/pred_layout_engaged_test.npz": "c484c6777b16cce2e802d2d590b39a258d76eaf6a1c16429453be685e27fc17d",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s1_final_merged/pred_layout_engaged_test.npz": "49e68c5c7c9745eeca6d227656afbcc8272c2173eafa64ed1a8b8788a73086b8",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s2_final_merged/pred_layout_engaged_test.npz": "50f924d0ba73a748586db028e16b04f715ac8d71f254375792484275b937aa70",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s0_final_dwfc/pred_layout_engaged_test.npz": "3c41018f28727c18c56087426a4c6e7a9900985606c5cdd2953923036650c6ad",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s0_final_merged/pred_layout_engaged_val.npz": "1238ccb49bed7185c1c1667d360ad2ec37815ff90543b43e01f8ddcd81b8a1fe",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s1_final_merged/pred_layout_engaged_val.npz": "ce171870fb603af544381939f596562d4ed53c9441a0802bea80b2938b32e42f",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s2_final_merged/pred_layout_engaged_val.npz": "474840fb11630c0ebd9f5bb69380a2ce64468dd6056b4c0621a3348b8e9a3839",
"/home/USER/cwm3/results/runs/W_I1_all_minus_road2drv_s0_final_dwfc/pred_layout_engaged_val.npz": "1e967a21d86891bf83a35c7c113ee39514cd42a466e867556bd88bb40ba2c6fa",
"/home/USER/cwm2/baselines/legacy_cockpitwm/results/marginals_engaged_s0.npz": "f7d0f7244415934b0b7b50e289f4e8082c3e52bbcce4891ed9f0fb76019a1bfb",
"/home/USER/cwm2/baselines/legacy_cockpitwm/results/marginals_engaged_val_s0.npz": "5300066a6e76a1d4d8b84ddf923b739a82bc6f4cb4d0ce2a98a48e87c7cb85e0"
},
"dms_fields_used": []
}

Xet Storage Details

Size:
17.3 kB
·
Xet hash:
7468532ab2007d80471c50fbbdc08d1c5950581393477c5e99ed1923e915785b

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.